From 40f48ac24c7b046ef9d442a0c5f4f7a18625e419 Mon Sep 17 00:00:00 2001 From: Laura Masa Date: Mon, 8 Jul 2024 15:39:05 +0200 Subject: [PATCH] Reorganizing files and directories --- ..._neuro_diseases_final_disease_selected.tsv | 177 + data/raw/top10_genecount_disease.tsv | 11 + results/disease_gds.csv | 215 + results/gds_gpl.csv | 74 + results/prefilt_disease_gds.csv | 363 ++ scripts/download_files.ipynb | 3859 +++++++++++++++++ .../download_files.py | 0 scripts/gpl_main.ipynb | 247 ++ scripts/insert_tables.py | 380 ++ scripts/preprocess_functions.py | 242 ++ scripts/preprocess_upload_data.ipynb | 2724 ++++++++++++ 11 files changed, 8292 insertions(+) create mode 100644 data/raw/data_01_neuro_diseases_final_disease_selected.tsv create mode 100644 data/raw/top10_genecount_disease.tsv create mode 100644 results/disease_gds.csv create mode 100644 results/gds_gpl.csv create mode 100644 results/prefilt_disease_gds.csv create mode 100644 scripts/download_files.ipynb rename download_files.py => scripts/download_files.py (100%) create mode 100644 scripts/gpl_main.ipynb create mode 100644 scripts/insert_tables.py create mode 100644 scripts/preprocess_functions.py create mode 100644 scripts/preprocess_upload_data.ipynb diff --git a/data/raw/data_01_neuro_diseases_final_disease_selected.tsv b/data/raw/data_01_neuro_diseases_final_disease_selected.tsv new file mode 100644 index 0000000..a22196a --- /dev/null +++ b/data/raw/data_01_neuro_diseases_final_disease_selected.tsv @@ -0,0 +1,177 @@ +cui disease_name gene_id drug_id symptom_id Genes in LCC +C0001206 Acromegaly 178.0 3.0 18.0 38.0 +C0001973 Alcoholic Intoxication, Chronic 1008.0 22.0 34.0 249.0 +C0002395 Alzheimer's Disease 5736.0 38.0 7.0 2697.0 +C0002622 Amnesia 200.0 41.0 14.0 74.0 +C0002736 Amyotrophic Lateral Sclerosis 1791.0 11.0 23.0 847.0 +C0003467 Anxiety 1335.0 0.0 16.0 684.0 +C0003537 Aphasia 94.0 3.0 8.0 27.0 +C0004135 Ataxia Telangiectasia 481.0 0.0 24.0 235.0 +C0004352 Autistic Disorder 1710.0 35.0 5.0 706.0 +C0005586 Bipolar Disorder 2040.0 78.0 12.0 727.0 +C0007282 Carotid Stenosis 163.0 2.0 3.0 23.0 +C0007766 Intracranial Aneurysm 399.0 5.0 13.0 124.0 +C0007785 Cerebral Infarction 891.0 15.0 32.0 444.0 +C0007786 Brain Ischemia 449.0 48.0 4.0 236.0 +C0007787 Transient Ischemic Attack 410.0 17.0 14.0 233.0 +C0007789 Cerebral Palsy 284.0 5.0 31.0 81.0 +C0007959 Charcot-Marie-Tooth Disease 349.0 1.0 19.0 96.0 +C0009171 Cocaine Abuse 182.0 97.0 16.0 57.0 +C0009207 Cockayne Syndrome 133.0 0.0 7.0 46.0 +C0009952 Febrile Convulsions 267.0 8.0 9.0 30.0 +C0010964 Dandy-Walker Syndrome 155.0 0.0 9.0 53.0 +C0011195 Dejerine-Sottas Disease (disorder) 235.0 0.0 22.0 60.0 +C0011206 Delirium 152.0 23.0 18.0 15.0 +C0011265 Presenile dementia 944.0 38.0 23.0 467.0 +C0011269 Dementia, Vascular 268.0 2.0 26.0 103.0 +C0011570 Mental Depression 2208.0 0.0 7.0 1047.0 +C0011581 Depressive disorder 2544.0 112.0 5.0 1266.0 +C0011633 Dermatomyositis 296.0 8.0 18.0 80.0 +C0013080 Down Syndrome 1066.0 1.0 3.0 511.0 +C0013264 Muscular Dystrophy, Duchenne 467.0 3.0 10.0 196.0 +C0013362 Dysarthria 531.0 7.0 10.0 260.0 +C0013384 Dyskinetic syndrome 400.0 31.0 26.0 145.0 +C0014038 Encephalitis 406.0 8.0 37.0 148.0 +C0014057 Japanese Encephalitis 142.0 0.0 21.0 50.0 +C0014060 Encephalitis, St. Louis 330.0 0.0 13.0 124.0 +C0014065 Congenital cerebral hernia 101.0 0.0 4.0 43.0 +C0014070 Encephalomyelitis 1062.0 0.0 32.0 578.0 +C0014544 Epilepsy 1727.0 48.0 19.0 828.0 +C0014553 Absence Epilepsy 131.0 15.0 11.0 28.0 +C0014556 Epilepsy, Temporal Lobe 470.0 11.0 14.0 181.0 +C0015469 Facial paralysis 186.0 1.0 12.0 25.0 +C0016667 Fragile X Syndrome 255.0 1.0 6.0 86.0 +C0016719 Friedreich Ataxia 111.0 4.0 12.0 22.0 +C0017205 Gaucher Disease 183.0 2.0 17.0 35.0 +C0017921 Glycogen storage disease type II 243.0 0.0 12.0 44.0 +C0018378 Guillain-Barre Syndrome 194.0 0.0 44.0 58.0 +C0018524 Hallucinations 192.0 30.0 10.0 83.0 +C0018784 Sensorineural Hearing Loss (disorder) 989.0 6.0 5.0 432.0 +C0019202 Hepatolenticular Degeneration 200.0 9.0 21.0 43.0 +C0019562 Von Hippel-Lindau Syndrome 240.0 0.0 4.0 91.0 +C0020179 Huntington Disease 1345.0 11.0 16.0 677.0 +C0020255 Hydrocephalus 555.0 3.0 15.0 267.0 +C0022336 Creutzfeldt-Jakob disease 180.0 0.0 24.0 53.0 +C0023264 Leigh Disease 285.0 0.0 18.0 70.0 +C0023524 Leukoencephalopathy, Progressive Multifocal 263.0 1.0 6.0 152.0 +C0024266 Lymphocytic Choriomeningitis 159.0 0.0 22.0 47.0 +C0024408 Machado-Joseph Disease 171.0 0.0 14.0 66.0 +C0024809 Marijuana Abuse 209.0 0.0 13.0 52.0 +C0024814 Marinesco-Sjogren syndrome 167.0 1.0 15.0 62.0 +C0025286 Meningioma 929.0 2.0 14.0 460.0 +C0025289 Meningitis 225.0 20.0 42.0 79.0 +C0025958 Microcephaly 1360.0 0.0 10.0 824.0 +C0026106 Mild Mental Retardation 374.0 0.0 2.0 120.0 +C0026654 Moyamoya Disease 151.0 2.0 13.0 16.0 +C0026769 Multiple Sclerosis 2878.0 21.0 28.0 1284.0 +C0026847 Spinal Muscular Atrophy 440.0 0.0 17.0 194.0 +C0026850 Muscular Dystrophy 453.0 1.0 33.0 124.0 +C0026896 Myasthenia Gravis 447.0 17.0 11.0 133.0 +C0027121 Myositis 301.0 4.0 24.0 109.0 +C0027126 Myotonic Dystrophy 204.0 3.0 8.0 72.0 +C0027809 Neurilemmoma 259.0 2.0 13.0 120.0 +C0027830 neurofibroma 157.0 0.0 12.0 65.0 +C0027831 Neurofibromatosis 1 433.0 0.0 15.0 183.0 +C0027832 Neurofibromatosis 2 160.0 0.0 12.0 82.0 +C0027859 Acoustic Neuroma 159.0 0.0 11.0 74.0 +C0027873 Neuromyelitis Optica 214.0 1.0 25.0 30.0 +C0028043 Nicotine Dependence 227.0 13.0 8.0 38.0 +C0028077 Night Blindness 201.0 1.0 15.0 16.0 +C0028738 Nystagmus 923.0 10.0 12.0 551.0 +C0029124 Optic Atrophy 648.0 0.0 15.0 335.0 +C0030567 Parkinson Disease 3240.0 47.0 32.0 1582.0 +C0032000 Pituitary Adenoma 211.0 7.0 15.0 88.0 +C0033375 Prolactinoma 243.0 5.0 11.0 87.0 +C0035258 Restless Legs Syndrome 174.0 17.0 28.0 28.0 +C0035372 Rett Syndrome 299.0 0.0 25.0 105.0 +C0036341 Schizophrenia 5398.0 71.0 18.0 2171.0 +C0037773 Spastic Paraplegia, Hereditary 209.0 0.0 7.0 41.0 +C0038220 Status Epilepticus 664.0 41.0 23.0 294.0 +C0038379 Strabismus 771.0 1.0 4.0 501.0 +C0038436 Post-Traumatic Stress Disorder 528.0 23.0 8.0 200.0 +C0038525 Subarachnoid Hemorrhage 659.0 14.0 14.0 342.0 +C0038868 Progressive supranuclear palsy 237.0 1.0 19.0 92.0 +C0039483 Giant Cell Arteritis 327.0 5.0 15.0 123.0 +C0040517 Gilles de la Tourette syndrome 232.0 17.0 11.0 37.0 +C0041341 Tuberous Sclerosis 378.0 4.0 18.0 159.0 +C0042170 Uveomeningoencephalitic Syndrome 124.0 5.0 14.0 15.0 +C0043124 West Nile Fever 89.0 1.0 25.0 18.0 +C0043459 Zellweger Syndrome 81.0 0.0 5.0 22.0 +C0080178 Spina Bifida 233.0 1.0 12.0 59.0 +C0085084 Motor Neuron Disease 270.0 3.0 35.0 118.0 +C0085655 Polymyositis 226.0 7.0 10.0 41.0 +C0085762 Alcohol abuse 226.0 22.0 29.0 47.0 +C0086769 Panic Attacks 63.0 27.0 23.0 20.0 +C0149940 Sciatic Neuropathy 121.0 2.0 7.0 44.0 +C0151311 Cranial nerve palsies 81.0 2.0 29.0 26.0 +C0151740 Intracranial Hypertension 72.0 12.0 14.0 27.0 +C0152020 Gastroparesis 102.0 4.0 24.0 17.0 +C0152025 Polyneuropathy 192.0 6.0 14.0 45.0 +C0153633 Malignant neoplasm of brain 330.0 22.0 36.0 161.0 +C0162309 Adrenoleukodystrophy 368.0 0.0 12.0 119.0 +C0162635 Angelman Syndrome 149.0 0.0 17.0 44.0 +C0162666 Mitochondrial Encephalomyopathies 60.0 1.0 15.0 19.0 +C0175754 Agenesis of corpus callosum 767.0 0.0 3.0 417.0 +C0206728 Plexiform Neurofibroma 56.0 1.0 13.0 20.0 +C0220756 Niemann-Pick Disease, Type C 230.0 1.0 19.0 119.0 +C0221056 Adult type dermatomyositis 256.0 8.0 18.0 67.0 +C0221406 Pituitary-dependent Cushing's disease 164.0 3.0 11.0 37.0 +C0234144 Dysgraphia 43.0 0.0 9.0 22.0 +C0236642 Pick Disease of the Brain 289.0 1.0 9.0 137.0 +C0238190 Inclusion Body Myositis (disorder) 101.0 1.0 11.0 35.0 +C0238288 Muscular Dystrophy, Facioscapulohumeral 187.0 0.0 14.0 48.0 +C0242350 Erectile dysfunction 322.0 35.0 2.0 72.0 +C0265219 Miller Dieker syndrome 221.0 0.0 20.0 99.0 +C0266463 Lissencephaly 98.0 0.0 15.0 30.0 +C0266464 Polymicrogyria 239.0 0.0 2.0 109.0 +C0266483 Pachygyria 156.0 0.0 15.0 39.0 +C0270824 Visual seizure 235.0 216.0 25.0 53.0 +C0270972 Cornelia De Lange Syndrome 78.0 0.0 10.0 22.0 +C0271270 Oculovestibuloauditory syndrome 95.0 0.0 13.0 33.0 +C0276226 Herpes encephalitis 68.0 2.0 2.0 16.0 +C0276496 Familial Alzheimer Disease (FAD) 336.0 38.0 7.0 165.0 +C0282527 Infantile Refsum Disease (disorder) 37.0 0.0 2.0 15.0 +C0338451 Frontotemporal dementia 464.0 4.0 9.0 203.0 +C0338508 Optic Atrophy, Autosomal Dominant 161.0 0.0 16.0 59.0 +C0349204 Nonorganic psychosis 528.0 0.0 9.0 184.0 +C0410189 Muscular Dystrophy, Emery-Dreifuss 76.0 0.0 7.0 15.0 +C0410207 Tubular Aggregate Myopathy 78.0 0.0 14.0 31.0 +C0431380 Cortical Dysplasia 139.0 2.0 6.0 31.0 +C0494463 Alzheimer Disease, Late Onset 529.0 38.0 7.0 241.0 +C0496899 Benign neoplasm of brain, unspecified 42.0 22.0 23.0 18.0 +C0497327 Dementia 1153.0 16.0 28.0 522.0 +C0520679 Sleep Apnea, Obstructive 610.0 4.0 26.0 249.0 +C0543859 Amyotrophic Lateral Sclerosis, Guam Form 40.0 11.0 26.0 19.0 +C0546126 Acute Confusional Senile Dementia 100.0 38.0 7.0 48.0 +C0577631 Carotid Atherosclerosis 263.0 2.0 9.0 75.0 +C0600427 Cocaine Dependence 300.0 97.0 16.0 65.0 +C0740391 Middle Cerebral Artery Occlusion 766.0 15.0 7.0 404.0 +C0740392 Infarction, Middle Cerebral Artery 160.0 15.0 7.0 62.0 +C0750900 Alzheimer's Disease, Focal Onset 100.0 38.0 7.0 48.0 +C0750901 Alzheimer Disease, Early Onset 207.0 38.0 7.0 95.0 +C0750974 Brain Tumor, Primary 137.0 22.0 16.0 64.0 +C0750977 Recurrent Brain Neoplasm 39.0 22.0 16.0 18.0 +C0750979 Primary malignant neoplasm of brain 42.0 22.0 16.0 20.0 +C0751265 Learning Disabilities 114.0 38.0 7.0 25.0 +C0751587 CADASIL Syndrome 53.0 0.0 7.0 16.0 +C0751690 Malignant Peripheral Nerve Sheath Tumor 332.0 0.0 9.0 172.0 +C0751713 Inclusion Body Myopathy, Sporadic 93.0 1.0 11.0 38.0 +C0751772 REM Sleep Behavior Disorder 60.0 4.0 13.0 17.0 +C0751781 Dentatorubral-Pallidoluysian Atrophy 123.0 3.0 18.0 37.0 +C0751967 Multiple Sclerosis, Relapsing-Remitting 249.0 7.0 3.0 61.0 +C0752120 Spinocerebellar Ataxia Type 1 126.0 2.0 13.0 33.0 +C0752125 Spinocerebellar Ataxia Type 7 94.0 2.0 13.0 28.0 +C0752166 Bardet-Biedl Syndrome 176.0 0.0 10.0 27.0 +C0752304 Hypoxic-Ischemic Encephalopathy 197.0 2.0 1.0 62.0 +C0752347 Lewy Body Disease 335.0 3.0 32.0 145.0 +C0917798 Cerebral Ischemia 121.0 48.0 4.0 49.0 +C0917816 Mental deficiency 150.0 2.0 1.0 27.0 +C1263846 Attention deficit hyperactivity disorder 1084.0 30.0 14.0 484.0 +C1269683 Major Depressive Disorder 1814.0 56.0 19.0 775.0 +C1306214 ACTH-Secreting Pituitary Adenoma 88.0 0.0 3.0 23.0 +C1510586 Autism Spectrum Disorders 1478.0 0.0 9.0 699.0 +C1839259 Bulbo-Spinal Atrophy, X-Linked 144.0 0.0 13.0 70.0 +C1868675 PARKINSON DISEASE 2, AUTOSOMAL RECESSIVE JUVENILE 89.0 37.0 2.0 27.0 +C1955869 Malformations of Cortical Development 80.0 2.0 6.0 26.0 +C2931689 Dystrophia myotonica 2 144.0 3.0 18.0 21.0 +C3658299 Zellweger Spectrum 35.0 0.0 5.0 17.0 diff --git a/data/raw/top10_genecount_disease.tsv b/data/raw/top10_genecount_disease.tsv new file mode 100644 index 0000000..ab330a1 --- /dev/null +++ b/data/raw/top10_genecount_disease.tsv @@ -0,0 +1,11 @@ +cui disease_name gene_id drug_id symptom_id Genes in LCC +C0002395 Alzheimer's Disease 5736.0 38.0 7.0 2697.0 +C0036341 Schizophrenia 5398.0 71.0 18.0 2171.0 +C0030567 Parkinson Disease 3240.0 47.0 32.0 1582.0 +C0026769 Multiple Sclerosis 2878.0 21.0 28.0 1284.0 +C0011581 Depressive disorder 2544.0 112.0 5.0 1266.0 +C0011570 Mental Depression 2208.0 0.0 7.0 1047.0 +C0005586 Bipolar Disorder 2040.0 78.0 12.0 727.0 +C1269683 Major Depressive Disorder 1814.0 56.0 19.0 775.0 +C0002736 Amyotrophic Lateral Sclerosis 1791.0 11.0 23.0 847.0 +C0014544 Epilepsy 1727.0 48.0 19.0 828.0 diff --git a/results/disease_gds.csv b/results/disease_gds.csv new file mode 100644 index 0000000..f25a49b --- /dev/null +++ b/results/disease_gds.csv @@ -0,0 +1,215 @@ +disease_id,gds_id +C0221056,GDS3417 +C0221056,GDS2153 +C0221056,GDS2855 +C0221056,GDS1956 +C0038436,GDS1020 +C0032000,GDS2432 +C0032000,GDS1253 +C0013264,GDS2855 +C0013264,GDS1956 +C0013264,GDS612 +C0013264,GDS611 +C0013264,GDS610 +C0013264,GDS609 +C0013264,GDS563 +C0013264,GDS270 +C0013264,GDS265 +C0013264,GDS264 +C0013264,GDS262 +C0013264,GDS214 +C0035372,GDS2613 +C0080178,GDS2470 +C0027121,GDS2153 +C0037773,GDS1956 +C0033375,GDS1253 +C0410189,GDS2855 +C0410189,GDS1956 +C0496899,GDS4470 +C0496899,GDS5181 +C0496899,GDS3069 +C0496899,GDS2374 +C0496899,GDS2432 +C0496899,GDS1962 +C0496899,GDS1816 +C0496899,GDS1815 +C0496899,GDS1976 +C0496899,GDS1975 +C0496899,GDS2853 +C0496899,GDS1253 +C0496899,GDS232 +C1306214,GDS1253 +C0750979,GDS4470 +C0750979,GDS5181 +C0750979,GDS3069 +C0750979,GDS2374 +C0750979,GDS2432 +C0750979,GDS1962 +C0750979,GDS1816 +C0750979,GDS1815 +C0750979,GDS1976 +C0750979,GDS1975 +C0750979,GDS2853 +C0750979,GDS1253 +C0750979,GDS232 +C0085655,GDS2153 +C0085084,GDS4353 +C0085084,GDS3644 +C0085084,GDS2855 +C0085084,GDS1956 +C0085084,GDS412 +C0750974,GDS4470 +C0750974,GDS5181 +C0750974,GDS3069 +C0750974,GDS2374 +C0750974,GDS2432 +C0750974,GDS1962 +C0750974,GDS1816 +C0750974,GDS1815 +C0750974,GDS1976 +C0750974,GDS1975 +C0750974,GDS2853 +C0750974,GDS1253 +C0750974,GDS232 +C0497327,GDS2763 +C0497327,GDS2795 +C0238288,GDS2855 +C0238288,GDS1956 +C0014070,GDS4152 +C0028043,GDS2447 +C0221406,GDS2374 +C0038868,GDS2519 +C0026850,GDS2855 +C0026850,GDS1956 +C0026850,GDS612 +C0026850,GDS611 +C0026850,GDS610 +C0026850,GDS609 +C0026850,GDS563 +C0026850,GDS270 +C0026850,GDS265 +C0026850,GDS264 +C0026850,GDS262 +C0026850,GDS214 +C0013384,GDS4541 +C0013384,GDS2519 +C0013384,GDS1912 +C0013384,GDS1726 +C0013384,GDS1331 +C0151311,GDS2519 +C0151311,GDS1112 +C0751265,GDS1917 +C0020179,GDS4541 +C0020179,GDS1331 +C0011570,GDS2447 +C0002736,GDS1956 +C0002736,GDS412 +C0002395,GDS4136 +C0002395,GDS4135 +C0002395,GDS4128 +C0002395,GDS2519 +C0002395,GDS2795 +C0002395,GDS810 +C0014038,GDS4218 +C0014038,GDS1726 +C0001973,GDS5430 +C0001973,GDS2447 +C0001973,GDS2191 +C0001973,GDS2190 +C0750900,GDS4136 +C0750900,GDS4135 +C0750900,GDS4128 +C0750900,GDS2519 +C0750900,GDS2795 +C0750900,GDS810 +C0004352,GDS4431 +C0085762,GDS2191 +C0085762,GDS2190 +C0024809,GDS2447 +C0349204,GDS2779 +C1868675,GDS5646 +C1868675,GDS4154 +C1868675,GDS2821 +C1868675,GDS2519 +C1868675,GDS1912 +C0003467,GDS4152 +C0003467,GDS4012 +C0003467,GDS2978 +C0014544,GDS1962 +C0014544,GDS1051 +C0014544,GDS1050 +C0546126,GDS4136 +C0546126,GDS4135 +C0546126,GDS4128 +C0546126,GDS2519 +C0546126,GDS2795 +C0546126,GDS810 +C0025286,GDS2865 +C0007789,GDS4353 +C0007789,GDS3644 +C0011195,GDS1956 +C0543859,GDS1956 +C0543859,GDS412 +C0030567,GDS5646 +C0030567,GDS4154 +C0030567,GDS2821 +C0030567,GDS2519 +C0001206,GDS2432 +C0751967,GDS4150 +C0751967,GDS2419 +C0276496,GDS4136 +C0276496,GDS4135 +C0276496,GDS4128 +C0276496,GDS2519 +C0276496,GDS2795 +C0276496,GDS810 +C0162666,GDS1065 +C0026769,GDS4218 +C0026769,GDS3920 +C0026769,GDS4152 +C0026769,GDS4150 +C0026769,GDS2978 +C0026769,GDS2419 +C0270824,GDS4854 +C0270824,GDS3110 +C0270824,GDS968 +C0750901,GDS4136 +C0750901,GDS4135 +C0750901,GDS4128 +C0750901,GDS2519 +C0750901,GDS2795 +C0750901,GDS810 +C0002622,GDS2795 +C0011633,GDS3417 +C0011633,GDS2153 +C0011633,GDS2855 +C0011633,GDS1956 +C0011581,GDS2447 +C0041341,GDS3281 +C0036341,GDS4522 +C0036341,GDS4523 +C0036341,GDS1917 +C0751690,GDS2736 +C0005586,GDS2779 +C0005586,GDS2191 +C0005586,GDS2190 +C0917816,GDS2613 +C0750977,GDS4470 +C0750977,GDS5181 +C0750977,GDS3069 +C0750977,GDS2374 +C0750977,GDS2432 +C0750977,GDS1962 +C0750977,GDS1816 +C0750977,GDS1815 +C0750977,GDS1976 +C0750977,GDS1975 +C0750977,GDS2853 +C0750977,GDS1253 +C0750977,GDS232 +C0494463,GDS4136 +C0494463,GDS4135 +C0494463,GDS4128 +C0494463,GDS2519 +C0494463,GDS2795 +C0494463,GDS810 diff --git a/results/gds_gpl.csv b/results/gds_gpl.csv new file mode 100644 index 0000000..2733390 --- /dev/null +++ b/results/gds_gpl.csv @@ -0,0 +1,74 @@ +gds_id,gpl_id +GDS1050,GPL96 +GDS4136,GPL570 +GDS4150,GPL570 +GDS563,GPL8300 +GDS5430,GPL570 +GDS4541,GPL96 +GDS612,GPL95 +GDS2978,GPL96 +GDS2190,GPL96 +GDS1112,GPL8300 +GDS232,GPL74 +GDS2613,GPL8300 +GDS214,GPL246 +GDS2447,GPL1426 +GDS3281,GPL96 +GDS1962,GPL570 +GDS1816,GPL97 +GDS2519,GPL96 +GDS2763,GPL96 +GDS1815,GPL96 +GDS1975,GPL96 +GDS3920,GPL570 +GDS2432,GPL570 +GDS2795,GPL570 +GDS265,GPL95 +GDS2853,GPL8300 +GDS610,GPL93 +GDS264,GPL94 +GDS1912,GPL201 +GDS4353,GPL571 +GDS2855,GPL97 +GDS1253,GPL96 +GDS1956,GPL96 +GDS5646,GPL10558 +GDS3417,GPL96 +GDS3069,GPL96 +GDS1726,GPL8300 +GDS4523,GPL570 +GDS611,GPL94 +GDS270,GPL92 +GDS5181,GPL4133 +GDS2419,GPL4191 +GDS4128,GPL570 +GDS2191,GPL96 +GDS2470,GPL570 +GDS2374,GPL570 +GDS3644,GPL96 +GDS2821,GPL570 +GDS1051,GPL97 +GDS4012,GPL10526 +GDS968,GPL8300 +GDS2779,GPL570 +GDS2736,GPL96 +GDS1065,GPL96 +GDS3110,GPL96 +GDS1020,GPL91 +GDS2865,GPL96 +GDS810,GPL96 +GDS1976,GPL97 +GDS4135,GPL570 +GDS1331,GPL96 +GDS609,GPL92 +GDS4431,GPL570 +GDS4470,GPL570 +GDS2153,GPL96 +GDS4154,GPL571 +GDS1917,GPL570 +GDS4152,GPL570 +GDS4854,GPL570 +GDS4218,GPL570 +GDS412,GPL80 +GDS4522,GPL570 +GDS262,GPL91 diff --git a/results/prefilt_disease_gds.csv b/results/prefilt_disease_gds.csv new file mode 100644 index 0000000..a00eaa1 --- /dev/null +++ b/results/prefilt_disease_gds.csv @@ -0,0 +1,363 @@ +disease_id,gds_id +C0221056,GDS4841 +C0221056,GDS3417 +C0221056,GDS2153 +C0221056,GDS2855 +C0221056,GDS1956 +C0038436,GDS4879 +C0038436,GDS1020 +C0032000,GDS2432 +C0032000,GDS1253 +C0520679,GDS4857 +C0013080,GDS5211 +C0013080,GDS2941 +C0016667,GDS2824 +C0162309,GDS4559 +C0162309,GDS4451 +C0338451,GDS3459 +C0013264,GDS3027 +C0013264,GDS2855 +C0013264,GDS1956 +C0013264,GDS612 +C0013264,GDS611 +C0013264,GDS610 +C0013264,GDS609 +C0013264,GDS563 +C0013264,GDS270 +C0013264,GDS265 +C0013264,GDS264 +C0013264,GDS262 +C0013264,GDS214 +C0035372,GDS2613 +C0080178,GDS2470 +C0027121,GDS4841 +C0027121,GDS2153 +C0037773,GDS1956 +C0033375,GDS4859 +C0033375,GDS1253 +C0009171,GDS5047 +C0410189,GDS2855 +C0410189,GDS1956 +C0496899,GDS4838 +C0496899,GDS4464 +C0496899,GDS4469 +C0496899,GDS4470 +C0496899,GDS4471 +C0496899,GDS4473 +C0496899,GDS4859 +C0496899,GDS4477 +C0496899,GDS5181 +C0496899,GDS3952 +C0496899,GDS4275 +C0496899,GDS3069 +C0496899,GDS2374 +C0496899,GDS2432 +C0496899,GDS1962 +C0496899,GDS1816 +C0496899,GDS1815 +C0496899,GDS1976 +C0496899,GDS1975 +C0496899,GDS1813 +C0496899,GDS2853 +C0496899,GDS1253 +C0496899,GDS232 +C1306214,GDS1253 +C0750979,GDS4838 +C0750979,GDS4464 +C0750979,GDS4469 +C0750979,GDS4470 +C0750979,GDS4471 +C0750979,GDS4473 +C0750979,GDS4859 +C0750979,GDS4477 +C0750979,GDS5181 +C0750979,GDS3952 +C0750979,GDS4275 +C0750979,GDS3069 +C0750979,GDS2374 +C0750979,GDS2432 +C0750979,GDS1962 +C0750979,GDS1816 +C0750979,GDS1815 +C0750979,GDS1976 +C0750979,GDS1975 +C0750979,GDS1813 +C0750979,GDS2853 +C0750979,GDS1253 +C0750979,GDS232 +C0085655,GDS4841 +C0085655,GDS2153 +C0085084,GDS4353 +C0085084,GDS3644 +C0085084,GDS2855 +C0085084,GDS1956 +C0085084,GDS412 +C0750974,GDS4838 +C0750974,GDS4464 +C0750974,GDS4469 +C0750974,GDS4470 +C0750974,GDS4471 +C0750974,GDS4473 +C0750974,GDS4859 +C0750974,GDS4477 +C0750974,GDS5181 +C0750974,GDS3952 +C0750974,GDS4275 +C0750974,GDS3069 +C0750974,GDS2374 +C0750974,GDS2432 +C0750974,GDS1962 +C0750974,GDS1816 +C0750974,GDS1815 +C0750974,GDS1976 +C0750974,GDS1975 +C0750974,GDS1813 +C0750974,GDS2853 +C0750974,GDS1253 +C0750974,GDS232 +C0497327,GDS4758 +C0497327,GDS4358 +C0497327,GDS3459 +C0497327,GDS2763 +C0497327,GDS2795 +C0238288,GDS4404 +C0238288,GDS2855 +C0238288,GDS1956 +C0014070,GDS4152 +C0025289,GDS3540 +C0025289,GDS1563 +C0017921,GDS4410 +C0017921,GDS4409 +C0028043,GDS2447 +C0221406,GDS2374 +C0038868,GDS2519 +C0026850,GDS4843 +C0026850,GDS4404 +C0026850,GDS3475 +C0026850,GDS3474 +C0026850,GDS3027 +C0026850,GDS2855 +C0026850,GDS1956 +C0026850,GDS612 +C0026850,GDS611 +C0026850,GDS610 +C0026850,GDS609 +C0026850,GDS563 +C0026850,GDS270 +C0026850,GDS265 +C0026850,GDS264 +C0026850,GDS262 +C0026850,GDS214 +C0013384,GDS5242 +C0013384,GDS4314 +C0013384,GDS4541 +C0013384,GDS2887 +C0013384,GDS2519 +C0013384,GDS1912 +C0013384,GDS1726 +C0013384,GDS1331 +C0013384,GDS1330 +C0013384,GDS1332 +C0013384,GDS1235 +C0276226,GDS4540 +C0276226,GDS4539 +C0024266,GDS4161 +C0151311,GDS4224 +C0151311,GDS2519 +C0151311,GDS1112 +C0751265,GDS1917 +C0020179,GDS4541 +C0020179,GDS2887 +C0020179,GDS1331 +C0020179,GDS1332 +C0011570,GDS4879 +C0011570,GDS3345 +C0011570,GDS3268 +C0011570,GDS2447 +C0002736,GDS1956 +C0002736,GDS412 +C0002395,GDS4758 +C0002395,GDS4141 +C0002395,GDS4136 +C0002395,GDS4135 +C0002395,GDS4128 +C0002395,GDS2519 +C0002395,GDS2601 +C0002395,GDS2795 +C0002395,GDS810 +C0014038,GDS4358 +C0014038,GDS4218 +C0014038,GDS4540 +C0014038,GDS4539 +C0014038,GDS1726 +C0001973,GDS5430 +C0001973,GDS4879 +C0001973,GDS2447 +C0001973,GDS2191 +C0001973,GDS2190 +C0750900,GDS4758 +C0750900,GDS4141 +C0750900,GDS4136 +C0750900,GDS4135 +C0750900,GDS4128 +C0750900,GDS2519 +C0750900,GDS2601 +C0750900,GDS2795 +C0750900,GDS810 +C0004352,GDS4431 +C0004352,GDS2824 +C0085762,GDS2191 +C0085762,GDS2190 +C1510586,GDS2824 +C0024809,GDS2447 +C0349204,GDS2779 +C2931689,GDS5276 +C1868675,GDS5646 +C1868675,GDS4141 +C1868675,GDS4154 +C1868675,GDS3129 +C1868675,GDS3128 +C1868675,GDS2821 +C1868675,GDS2519 +C1868675,GDS1912 +C0003467,GDS4838 +C0003467,GDS4464 +C0003467,GDS4559 +C0003467,GDS4296 +C0003467,GDS4152 +C0003467,GDS3886 +C0003467,GDS4012 +C0003467,GDS2978 +C0003467,GDS1960 +C0014544,GDS3864 +C0014544,GDS1962 +C0014544,GDS1051 +C0014544,GDS1050 +C0546126,GDS4758 +C0546126,GDS4141 +C0546126,GDS4136 +C0546126,GDS4135 +C0546126,GDS4128 +C0546126,GDS2519 +C0546126,GDS2601 +C0546126,GDS2795 +C0546126,GDS810 +C0025286,GDS2865 +C0238190,GDS4841 +C0007789,GDS4353 +C0007789,GDS3644 +C0011195,GDS1956 +C0543859,GDS1956 +C0543859,GDS412 +C0030567,GDS5646 +C0030567,GDS4141 +C0030567,GDS4154 +C0030567,GDS3129 +C0030567,GDS3128 +C0030567,GDS2821 +C0030567,GDS2519 +C0001206,GDS2432 +C0751967,GDS4150 +C0751967,GDS4147 +C0751967,GDS2419 +C0007766,GDS3903 +C0276496,GDS4758 +C0276496,GDS4141 +C0276496,GDS4136 +C0276496,GDS4135 +C0276496,GDS4128 +C0276496,GDS2519 +C0276496,GDS2601 +C0276496,GDS2795 +C0276496,GDS810 +C0162666,GDS1065 +C0026769,GDS4218 +C0026769,GDS3920 +C0026769,GDS4152 +C0026769,GDS3886 +C0026769,GDS4150 +C0026769,GDS4147 +C0026769,GDS2978 +C0026769,GDS2419 +C0270824,GDS4854 +C0270824,GDS4279 +C0270824,GDS3085 +C0270824,GDS3110 +C0270824,GDS1563 +C0270824,GDS913 +C0270824,GDS968 +C0750901,GDS4758 +C0750901,GDS4141 +C0750901,GDS4136 +C0750901,GDS4135 +C0750901,GDS4128 +C0750901,GDS2519 +C0750901,GDS2601 +C0750901,GDS2795 +C0750901,GDS810 +C0002622,GDS2795 +C0011269,GDS4758 +C0011633,GDS4841 +C0011633,GDS3417 +C0011633,GDS2153 +C0011633,GDS2855 +C0011633,GDS1956 +C0011581,GDS4879 +C0011581,GDS3345 +C0011581,GDS3268 +C0011581,GDS2447 +C0041341,GDS3281 +C0036341,GDS4522 +C0036341,GDS3938 +C0036341,GDS4523 +C0036341,GDS3502 +C0036341,GDS3345 +C0036341,GDS1917 +C0027126,GDS5276 +C0751690,GDS2736 +C0751713,GDS4841 +C0005586,GDS4837 +C0005586,GDS3502 +C0005586,GDS3345 +C0005586,GDS2779 +C0005586,GDS2191 +C0005586,GDS2190 +C0917816,GDS5211 +C0917816,GDS4559 +C0917816,GDS4451 +C0917816,GDS3830 +C0917816,GDS2941 +C0917816,GDS2824 +C0917816,GDS2613 +C0750977,GDS4838 +C0750977,GDS4464 +C0750977,GDS4469 +C0750977,GDS4470 +C0750977,GDS4471 +C0750977,GDS4473 +C0750977,GDS4859 +C0750977,GDS4477 +C0750977,GDS5181 +C0750977,GDS3952 +C0750977,GDS4275 +C0750977,GDS3069 +C0750977,GDS2374 +C0750977,GDS2432 +C0750977,GDS1962 +C0750977,GDS1816 +C0750977,GDS1815 +C0750977,GDS1976 +C0750977,GDS1975 +C0750977,GDS1813 +C0750977,GDS2853 +C0750977,GDS1253 +C0750977,GDS232 +C0494463,GDS4758 +C0494463,GDS4141 +C0494463,GDS4136 +C0494463,GDS4135 +C0494463,GDS4128 +C0494463,GDS2519 +C0494463,GDS2601 +C0494463,GDS2795 +C0494463,GDS810 diff --git a/scripts/download_files.ipynb b/scripts/download_files.ipynb new file mode 100644 index 0000000..c8c456c --- /dev/null +++ b/scripts/download_files.ipynb @@ -0,0 +1,3859 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "28a48d50", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: biopython in /home/lmasa/miniconda3/lib/python3.12/site-packages (1.83)\n", + "Requirement already satisfied: numpy in /home/lmasa/miniconda3/lib/python3.12/site-packages (from biopython) (1.26.4)\n" + ] + } + ], + "source": [ + "!pip install biopython" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "322cad3f", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: geoparse in /home/lmasa/miniconda3/lib/python3.12/site-packages (2.0.4)\n", + "Requirement already satisfied: numpy>=1.7 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geoparse) (1.26.4)\n", + "Requirement already satisfied: pandas>=0.17 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geoparse) (2.2.2)\n", + "Requirement already satisfied: requests>=2.21.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geoparse) (2.31.0)\n", + "Requirement already satisfied: tqdm>=4.31.1 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geoparse) (4.65.0)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=0.17->geoparse) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=0.17->geoparse) (2023.3.post1)\n", + "Requirement already satisfied: tzdata>=2022.7 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=0.17->geoparse) (2024.1)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from requests>=2.21.0->geoparse) (2.0.4)\n", + "Requirement already satisfied: idna<4,>=2.5 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from requests>=2.21.0->geoparse) (3.4)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from requests>=2.21.0->geoparse) (2.1.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from requests>=2.21.0->geoparse) (2024.2.2)\n", + "Requirement already satisfied: six>=1.5 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas>=0.17->geoparse) (1.16.0)\n" + ] + } + ], + "source": [ + "!pip install geoparse" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "a84213b2", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: geopandas in /home/lmasa/miniconda3/lib/python3.12/site-packages (0.14.4)\n", + "Requirement already satisfied: fiona>=1.8.21 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (1.9.6)\n", + "Requirement already satisfied: numpy>=1.22 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (1.26.4)\n", + "Requirement already satisfied: packaging in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (23.1)\n", + "Requirement already satisfied: pandas>=1.4.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (2.2.2)\n", + "Requirement already satisfied: pyproj>=3.3.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (3.6.1)\n", + "Requirement already satisfied: shapely>=1.8.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from geopandas) (2.0.4)\n", + "Requirement already satisfied: attrs>=19.2.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (23.1.0)\n", + "Requirement already satisfied: certifi in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (2024.2.2)\n", + "Requirement already satisfied: click~=8.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (8.1.7)\n", + "Requirement already satisfied: click-plugins>=1.0 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (1.1.1)\n", + "Requirement already satisfied: cligj>=0.5 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (0.7.2)\n", + "Requirement already satisfied: six in /home/lmasa/miniconda3/lib/python3.12/site-packages (from fiona>=1.8.21->geopandas) (1.16.0)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=1.4.0->geopandas) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=1.4.0->geopandas) (2023.3.post1)\n", + "Requirement already satisfied: tzdata>=2022.7 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pandas>=1.4.0->geopandas) (2024.1)\n" + ] + } + ], + "source": [ + "!pip install geopandas" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "b0ac0c04-168b-4183-abb4-412383f9db05", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pyspark in /home/lmasa/miniconda3/lib/python3.12/site-packages (3.5.1)\n", + "Requirement already satisfied: py4j==0.10.9.7 in /home/lmasa/miniconda3/lib/python3.12/site-packages (from pyspark) (0.10.9.7)\n" + ] + } + ], + "source": [ + "!pip install pyspark" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "8e7956d3", + "metadata": {}, + "outputs": [], + "source": [ + "import requests\n", + "from Bio import Entrez\n", + "import GEOparse\n", + "import os\n", + "import gzip\n", + "import shutil\n", + "import pandas as pd\n", + "from os.path import join\n", + "from collections import defaultdict\n", + "import numpy as np\n", + "import csv\n", + "import download_files\n", + "import polars as pl\n", + "import mysql.connector\n", + "from mysql.connector import errorcode" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "11c53552", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "#disease names and ids \n", + "diseases_tsv_file='../data/raw/data_01_neuro_diseases_final_disease_selected.tsv'\n", + "disease_names=download_files.extract_tsv(diseases_tsv_file)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "0af72d99-57be-48ae-bef7-a6692cc53ff2", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "#email and path to store the GDS files\n", + "email_request='l.masa@alumnos.upm.es'\n", + "gds_path=\"../data/gds\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b6361761-21a1-412a-b342-6f5b0e0af402", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "29-May-2024 10:08:57 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:08:57 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3864/soft/GDS3864.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3864.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 3.26M/3.26M [00:01<00:00, 1.71MB/s]\n", + "29-May-2024 10:09:00 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:09:00 DEBUG downloader - Moving /tmp/tmp1n5w3mdb to /home/lmasa/GEO_Laura/Data/gds/GDS3864.soft.gz\n", + "29-May-2024 10:09:00 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3864/soft/GDS3864.soft.gz\n", + "29-May-2024 10:09:00 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3864.soft.gz: \n", + "29-May-2024 10:09:00 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:09:00 DEBUG GEOparse - DATASET: GDS3864\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_1\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_2\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_3\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_4\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_5\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_6\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_7\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_8\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_9\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_10\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_11\n", + "29-May-2024 10:09:00 DEBUG GEOparse - SUBSET: GDS3864_12\n", + "29-May-2024 10:09:00 DEBUG GEOparse - DATASET: GDS3864\n", + "29-May-2024 10:09:03 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:09:03 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1962/soft/GDS1962.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS1962.soft.gz\n", + " 28%|█████████████████████████▏ | 5.85M/20.9M [00:02<00:02, 6.26MB/s]29-May-2024 10:13:31 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:13:31 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4879/soft/GDS4879.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS4879.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 3.91M/3.91M [00:02<00:00, 1.93MB/s]\n", + "29-May-2024 10:13:34 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:13:34 DEBUG downloader - Moving /tmp/tmpboa6aqc5 to /home/lmasa/GEO_Laura/Data/gds/GDS4879.soft.gz\n", + "29-May-2024 10:13:34 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4879/soft/GDS4879.soft.gz\n", + "29-May-2024 10:13:34 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS4879.soft.gz: \n", + "29-May-2024 10:13:34 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:13:34 DEBUG GEOparse - DATASET: GDS4879\n", + "29-May-2024 10:13:34 DEBUG GEOparse - SUBSET: GDS4879_1\n", + "29-May-2024 10:13:34 DEBUG GEOparse - SUBSET: GDS4879_2\n", + "29-May-2024 10:13:34 DEBUG GEOparse - SUBSET: GDS4879_3\n", + "29-May-2024 10:13:34 DEBUG GEOparse - SUBSET: GDS4879_4\n", + "29-May-2024 10:13:34 DEBUG GEOparse - DATASET: GDS4879\n", + "29-May-2024 10:13:37 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:13:37 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3345/soft/GDS3345.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3345.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 2.11M/2.11M [00:01<00:00, 1.33MB/s]\n", + "29-May-2024 10:13:39 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:13:39 DEBUG downloader - Moving /tmp/tmpvp5786ab to /home/lmasa/GEO_Laura/Data/gds/GDS3345.soft.gz\n", + "29-May-2024 10:13:39 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3345/soft/GDS3345.soft.gz\n", + "29-May-2024 10:13:39 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3345.soft.gz: \n", + "29-May-2024 10:13:39 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:13:39 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:13:39 DEBUG GEOparse - SUBSET: GDS3345_1\n", + "29-May-2024 10:13:39 DEBUG GEOparse - SUBSET: GDS3345_2\n", + "29-May-2024 10:13:39 DEBUG GEOparse - SUBSET: GDS3345_3\n", + "29-May-2024 10:13:39 DEBUG GEOparse - SUBSET: GDS3345_4\n", + "29-May-2024 10:13:39 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:13:40 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:13:40 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3268/soft/GDS3268.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3268.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 25.5M/25.5M [00:03<00:00, 7.57MB/s]\n", + "29-May-2024 10:13:45 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:13:45 DEBUG downloader - Moving /tmp/tmpldvkp0et to /home/lmasa/GEO_Laura/Data/gds/GDS3268.soft.gz\n", + "29-May-2024 10:13:45 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3268/soft/GDS3268.soft.gz\n", + "29-May-2024 10:13:45 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3268.soft.gz: \n", + "29-May-2024 10:13:45 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:13:45 DEBUG GEOparse - DATASET: GDS3268\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_1\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_2\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_3\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_4\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_5\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_6\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_7\n", + "29-May-2024 10:13:45 DEBUG GEOparse - SUBSET: GDS3268_8\n", + "29-May-2024 10:13:45 DEBUG GEOparse - DATASET: GDS3268\n", + "29-May-2024 10:13:46 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:13:46 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS2nnn/GDS2447/soft/GDS2447.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS2447.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 2.06M/2.06M [00:01<00:00, 1.27MB/s]\n", + "29-May-2024 10:13:49 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:13:49 DEBUG downloader - Moving /tmp/tmp5fkb1opz to /home/lmasa/GEO_Laura/Data/gds/GDS2447.soft.gz\n", + "29-May-2024 10:13:49 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS2nnn/GDS2447/soft/GDS2447.soft.gz\n", + "29-May-2024 10:13:49 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS2447.soft.gz: \n", + "29-May-2024 10:13:49 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:13:49 DEBUG GEOparse - DATASET: GDS2447\n", + "29-May-2024 10:13:49 DEBUG GEOparse - SUBSET: GDS2447_1\n", + "29-May-2024 10:13:49 DEBUG GEOparse - SUBSET: GDS2447_2\n", + "29-May-2024 10:13:49 DEBUG GEOparse - DATASET: GDS2447\n", + "29-May-2024 10:15:57 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:15:57 INFO GEOparse - File already exist: using local version.\n", + "29-May-2024 10:15:57 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS4879.soft.gz: \n", + "29-May-2024 10:15:57 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:15:57 DEBUG GEOparse - DATASET: GDS4879\n", + "29-May-2024 10:15:57 DEBUG GEOparse - SUBSET: GDS4879_1\n", + "29-May-2024 10:15:57 DEBUG GEOparse - SUBSET: GDS4879_2\n", + "29-May-2024 10:15:57 DEBUG GEOparse - SUBSET: GDS4879_3\n", + "29-May-2024 10:15:57 DEBUG GEOparse - SUBSET: GDS4879_4\n", + "29-May-2024 10:15:57 DEBUG GEOparse - DATASET: GDS4879\n", + "29-May-2024 10:16:00 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:00 INFO GEOparse - File already exist: using local version.\n", + "29-May-2024 10:16:00 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3345.soft.gz: \n", + "29-May-2024 10:16:00 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:00 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:16:00 DEBUG GEOparse - SUBSET: GDS3345_1\n", + "29-May-2024 10:16:00 DEBUG GEOparse - SUBSET: GDS3345_2\n", + "29-May-2024 10:16:00 DEBUG GEOparse - SUBSET: GDS3345_3\n", + "29-May-2024 10:16:00 DEBUG GEOparse - SUBSET: GDS3345_4\n", + "29-May-2024 10:16:00 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:16:01 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:01 INFO GEOparse - File already exist: using local version.\n", + "29-May-2024 10:16:01 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3268.soft.gz: \n", + "29-May-2024 10:16:01 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:01 DEBUG GEOparse - DATASET: GDS3268\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_1\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_2\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_3\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_4\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_5\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_6\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_7\n", + "29-May-2024 10:16:01 DEBUG GEOparse - SUBSET: GDS3268_8\n", + "29-May-2024 10:16:01 DEBUG GEOparse - DATASET: GDS3268\n", + "29-May-2024 10:16:03 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:03 INFO GEOparse - File already exist: using local version.\n", + "29-May-2024 10:16:03 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS2447.soft.gz: \n", + "29-May-2024 10:16:03 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:03 DEBUG GEOparse - DATASET: GDS2447\n", + "29-May-2024 10:16:03 DEBUG GEOparse - SUBSET: GDS2447_1\n", + "29-May-2024 10:16:03 DEBUG GEOparse - SUBSET: GDS2447_2\n", + "29-May-2024 10:16:03 DEBUG GEOparse - DATASET: GDS2447\n", + "29-May-2024 10:16:39 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:39 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4522/soft/GDS4522.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS4522.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 7.04M/7.04M [00:02<00:00, 2.55MB/s]\n", + "29-May-2024 10:16:42 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:16:42 DEBUG downloader - Moving /tmp/tmpvykmsiq8 to /home/lmasa/GEO_Laura/Data/gds/GDS4522.soft.gz\n", + "29-May-2024 10:16:42 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4522/soft/GDS4522.soft.gz\n", + "29-May-2024 10:16:42 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS4522.soft.gz: \n", + "29-May-2024 10:16:42 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:42 DEBUG GEOparse - DATASET: GDS4522\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_1\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_2\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_3\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_4\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_5\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_6\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_7\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_8\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_9\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_10\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_11\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_12\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_13\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_14\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_15\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_16\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_17\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_18\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_19\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_20\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_21\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_22\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_23\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_24\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_25\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_26\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_27\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_28\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_29\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_30\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_31\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_32\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_33\n", + "29-May-2024 10:16:42 DEBUG GEOparse - SUBSET: GDS4522_34\n", + "29-May-2024 10:16:42 DEBUG GEOparse - DATASET: GDS4522\n", + "29-May-2024 10:16:44 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:44 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3938/soft/GDS3938.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3938.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 2.88M/2.88M [00:02<00:00, 1.50MB/s]\n", + "29-May-2024 10:16:47 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:16:47 DEBUG downloader - Moving /tmp/tmpl_rfhlfc to /home/lmasa/GEO_Laura/Data/gds/GDS3938.soft.gz\n", + "29-May-2024 10:16:47 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3938/soft/GDS3938.soft.gz\n", + "29-May-2024 10:16:47 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3938.soft.gz: \n", + "29-May-2024 10:16:47 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:47 DEBUG GEOparse - DATASET: GDS3938\n", + "29-May-2024 10:16:47 DEBUG GEOparse - SUBSET: GDS3938_1\n", + "29-May-2024 10:16:47 DEBUG GEOparse - SUBSET: GDS3938_2\n", + "29-May-2024 10:16:47 DEBUG GEOparse - SUBSET: GDS3938_3\n", + "29-May-2024 10:16:47 DEBUG GEOparse - SUBSET: GDS3938_4\n", + "29-May-2024 10:16:47 DEBUG GEOparse - DATASET: GDS3938\n", + "29-May-2024 10:16:51 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:51 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4523/soft/GDS4523.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS4523.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 7.09M/7.09M [00:02<00:00, 2.80MB/s]\n", + "29-May-2024 10:16:54 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:16:54 DEBUG downloader - Moving /tmp/tmphrrn826s to /home/lmasa/GEO_Laura/Data/gds/GDS4523.soft.gz\n", + "29-May-2024 10:16:54 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4523/soft/GDS4523.soft.gz\n", + "29-May-2024 10:16:54 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS4523.soft.gz: \n", + "29-May-2024 10:16:54 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:54 DEBUG GEOparse - DATASET: GDS4523\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_1\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_2\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_3\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_4\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_5\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_6\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_7\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_8\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_9\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_10\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_11\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_12\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_13\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_14\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_15\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_16\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_17\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_18\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_19\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_20\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_21\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_22\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_23\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_24\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_25\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_26\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_27\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_28\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_29\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_30\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_31\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_32\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_33\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_34\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_35\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_36\n", + "29-May-2024 10:16:54 DEBUG GEOparse - SUBSET: GDS4523_37\n", + "29-May-2024 10:16:54 DEBUG GEOparse - DATASET: GDS4523\n", + "29-May-2024 10:16:56 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:16:56 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3502/soft/GDS3502.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3502.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 6.98M/6.98M [00:03<00:00, 2.22MB/s]\n", + "29-May-2024 10:16:59 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:16:59 DEBUG downloader - Moving /tmp/tmpjbt967em to /home/lmasa/GEO_Laura/Data/gds/GDS3502.soft.gz\n", + "29-May-2024 10:16:59 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3502/soft/GDS3502.soft.gz\n", + "29-May-2024 10:16:59 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3502.soft.gz: \n", + "29-May-2024 10:16:59 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:16:59 DEBUG GEOparse - DATASET: GDS3502\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_1\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_2\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_3\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_4\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_5\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_6\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_7\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_8\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_9\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_10\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_11\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_12\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_13\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_14\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_15\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_16\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_17\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_18\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_19\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_20\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_21\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_22\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_23\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_24\n", + "29-May-2024 10:16:59 DEBUG GEOparse - SUBSET: GDS3502_25\n", + "29-May-2024 10:16:59 DEBUG GEOparse - DATASET: GDS3502\n", + "29-May-2024 10:17:01 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:17:01 INFO GEOparse - File already exist: using local version.\n", + "29-May-2024 10:17:01 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3345.soft.gz: \n", + "29-May-2024 10:17:01 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:17:01 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:17:01 DEBUG GEOparse - SUBSET: GDS3345_1\n", + "29-May-2024 10:17:01 DEBUG GEOparse - SUBSET: GDS3345_2\n", + "29-May-2024 10:17:01 DEBUG GEOparse - SUBSET: GDS3345_3\n", + "29-May-2024 10:17:01 DEBUG GEOparse - SUBSET: GDS3345_4\n", + "29-May-2024 10:17:01 DEBUG GEOparse - DATASET: GDS3345\n", + "29-May-2024 10:17:03 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:17:03 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1917/soft/GDS1917.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS1917.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 5.75M/5.75M [00:02<00:00, 2.51MB/s]\n", + "29-May-2024 10:17:06 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:17:06 DEBUG downloader - Moving /tmp/tmpd2_2fbex to /home/lmasa/GEO_Laura/Data/gds/GDS1917.soft.gz\n", + "29-May-2024 10:17:06 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1917/soft/GDS1917.soft.gz\n", + "29-May-2024 10:17:06 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS1917.soft.gz: \n", + "29-May-2024 10:17:06 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:17:06 DEBUG GEOparse - DATASET: GDS1917\n", + "29-May-2024 10:17:06 DEBUG GEOparse - SUBSET: GDS1917_1\n", + "29-May-2024 10:17:06 DEBUG GEOparse - SUBSET: GDS1917_2\n", + "29-May-2024 10:17:06 DEBUG GEOparse - DATASET: GDS1917\n", + "29-May-2024 10:23:40 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:23:40 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1956/soft/GDS1956.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS1956.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 9.39M/9.39M [00:03<00:00, 3.26MB/s]\n", + "29-May-2024 10:23:44 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:23:44 DEBUG downloader - Moving /tmp/tmpmcy5md5j to /home/lmasa/GEO_Laura/Data/gds/GDS1956.soft.gz\n", + "29-May-2024 10:23:44 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1956/soft/GDS1956.soft.gz\n", + "29-May-2024 10:23:44 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS1956.soft.gz: \n", + "29-May-2024 10:23:44 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:23:44 DEBUG GEOparse - DATASET: GDS1956\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_1\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_2\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_3\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_4\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_5\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_6\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_7\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_8\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_9\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_10\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_11\n", + "29-May-2024 10:23:44 DEBUG GEOparse - SUBSET: GDS1956_12\n", + "29-May-2024 10:23:44 DEBUG GEOparse - DATASET: GDS1956\n", + "29-May-2024 10:23:45 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:23:45 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDSnnn/GDS412/soft/GDS412.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS412.soft.gz\n", + "100%|█████████████████████████████████████████████████████████████████████████████████████████████| 184k/184k [00:00<00:00, 204kB/s]\n", + "29-May-2024 10:23:47 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:23:47 DEBUG downloader - Moving /tmp/tmp6jbesoyo to /home/lmasa/GEO_Laura/Data/gds/GDS412.soft.gz\n", + "29-May-2024 10:23:47 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDSnnn/GDS412/soft/GDS412.soft.gz\n", + "29-May-2024 10:23:47 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS412.soft.gz: \n", + "29-May-2024 10:23:47 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:23:47 DEBUG GEOparse - DATASET: GDS412\n", + "29-May-2024 10:23:47 DEBUG GEOparse - SUBSET: GDS412_1\n", + "29-May-2024 10:23:47 DEBUG GEOparse - SUBSET: GDS412_2\n", + "29-May-2024 10:23:47 DEBUG GEOparse - SUBSET: GDS412_3\n", + "29-May-2024 10:23:47 DEBUG GEOparse - DATASET: GDS412\n", + "29-May-2024 10:25:01 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:25:01 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4218/soft/GDS4218.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS4218.soft.gz\n", + "100%|███████████████████████████████████████████████████████████████████████████████████████████| 1.28M/1.28M [00:01<00:00, 875kB/s]\n", + "29-May-2024 10:25:04 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:25:04 DEBUG downloader - Moving /tmp/tmpwxisu6m2 to /home/lmasa/GEO_Laura/Data/gds/GDS4218.soft.gz\n", + "29-May-2024 10:25:04 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4218/soft/GDS4218.soft.gz\n", + "29-May-2024 10:25:04 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS4218.soft.gz: \n", + "29-May-2024 10:25:04 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:25:04 DEBUG GEOparse - DATASET: GDS4218\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_1\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_2\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_3\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_4\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_5\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_6\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_7\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_8\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_9\n", + "29-May-2024 10:25:04 DEBUG GEOparse - SUBSET: GDS4218_10\n", + "29-May-2024 10:25:04 DEBUG GEOparse - DATASET: GDS4218\n", + "29-May-2024 10:25:07 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:25:07 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3920/soft/GDS3920.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS3920.soft.gz\n", + "100%|██████████████████████████████████████████████████████████████████████████████████████████| 2.84M/2.84M [00:02<00:00, 1.47MB/s]\n", + "29-May-2024 10:25:10 DEBUG downloader - Size validation passed\n", + "29-May-2024 10:25:10 DEBUG downloader - Moving /tmp/tmpk0rzde4u to /home/lmasa/GEO_Laura/Data/gds/GDS3920.soft.gz\n", + "29-May-2024 10:25:10 DEBUG downloader - Successfully downloaded ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS3nnn/GDS3920/soft/GDS3920.soft.gz\n", + "29-May-2024 10:25:10 INFO GEOparse - Parsing /home/lmasa/GEO_Laura/Data/gds/GDS3920.soft.gz: \n", + "29-May-2024 10:25:10 DEBUG GEOparse - DATABASE: Geo\n", + "29-May-2024 10:25:10 DEBUG GEOparse - DATASET: GDS3920\n", + "29-May-2024 10:25:10 DEBUG GEOparse - SUBSET: GDS3920_1\n", + "29-May-2024 10:25:10 DEBUG GEOparse - SUBSET: GDS3920_2\n", + "29-May-2024 10:25:10 DEBUG GEOparse - DATASET: GDS3920\n", + "29-May-2024 10:25:12 DEBUG utils - Directory /home/lmasa/GEO_Laura/Data/gds already exists. Skipping.\n", + "29-May-2024 10:25:12 INFO GEOparse - Downloading ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS4nnn/GDS4152/soft/GDS4152.soft.gz to /home/lmasa/GEO_Laura/Data/gds/GDS4152.soft.gz\n", + " 0%| | 0.00/2.36M [00:00\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
gpl_idgpl_title
0GPL94[HG_U95D] Affymetrix Human Genome U95D Array
1GPL571[HG-U133A_2] Affymetrix Human Genome U133A 2.0...
2GPL570[HG-U133_Plus_2] Affymetrix Human Genome U133 ...
3GPL93[HG_U95C] Affymetrix Human Genome U95C Array
4GPL96[HG-U133A] Affymetrix Human Genome U133A Array
\n", + "" + ], + "text/plain": [ + " gpl_id gpl_title\n", + "0 GPL94 [HG_U95D] Affymetrix Human Genome U95D Array\n", + "1 GPL571 [HG-U133A_2] Affymetrix Human Genome U133A 2.0...\n", + "2 GPL570 [HG-U133_Plus_2] Affymetrix Human Genome U133 ...\n", + "3 GPL93 [HG_U95C] Affymetrix Human Genome U95C Array\n", + "4 GPL96 [HG-U133A] Affymetrix Human Genome U133A Array" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gpl_data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6389c1a1-c443-4774-bd9d-0fb65af45bee", + "metadata": {}, + "outputs": [], + "source": [ + "##Insert GPL data into database" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "d5785dba-71d0-4269-9ae7-b1968b8e9a19", + "metadata": {}, + "outputs": [], + "source": [ + "#The connection details needed to insert data into the database\n", + "host = \"{host}\" # Host where the MySQL server is located. Example: 'localhost' or '127.0.0.1'\n", + "user = \"{user_name}\" # Username for accessing the MySQL database. Example: 'root' or 'my_user'\n", + "password = \"{password}\" # Password for the MySQL user. Ensure to use a secure password for database access.\n", + "database = \"{database}\" # Name of the database to connect to. Example: 'disnet_biolayer'\n", + "port = \"{port}\" # Port number for the MySQL server. Default is 3306, but it may vary depending on the setup." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "b823d154-7c31-4aee-80b1-89bb933edb58", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize the connection variable to None\n", + "conn = None\n", + "\n", + "try:\n", + " # Attempt to establish a connection to the MySQL database\n", + " conn = mysql.connector.connect(\n", + " host=host,\n", + " user=user,\n", + " password=password,\n", + " database=database,\n", + " port=port\n", + " )\n", + " # Insert GPL data into the database\n", + " insert_tables.insert_gpl_main(conn, df)\n", + "\n", + "# Handle any MySQL errors that occur during the connection or insertion process\n", + "except mysql.connector.Error as err:\n", + " print(f\"Error connecting to MySQL: {err}\")\n", + "\n", + "# Ensure the connection is closed properly even if an error occurs\n", + "finally:\n", + " if conn and conn.is_connected():\n", + " conn.close()" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.1" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/scripts/insert_tables.py b/scripts/insert_tables.py new file mode 100644 index 0000000..2181cf7 --- /dev/null +++ b/scripts/insert_tables.py @@ -0,0 +1,380 @@ + +def insert_disease_gds(conn, df): + """ + Inserts data from a DataFrame into the 'expr_disease_gds' table in the MySQL database. + + This function takes a DataFrame with 'disease_id' and 'gds_id' columns and inserts the data into + the 'expr_disease_gds' table within the MySQL database specified by the provided connection. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + df (pandas.DataFrame): The DataFrame containing the data to be inserted. It should have columns 'disease_id' and 'gds_id'. + + Returns: + None + + Raises: + mysql.connector.Error: If there is a MySQL-specific error during the insert operation. + Exception: For any other exceptions that may occur. + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + for index, row in df.iterrows(): + # Define the SQL INSERT query + query = """ + INSERT INTO disnet_biolayer.expr_disease_gds (disease_id, gds_id) + VALUES (%s, %s) + """ + # Prepare the data to be inserted into the database + data = (row['disease_id'], row['gds_id']) + # Execute the SQL query with the data + cursor.execute(query, data) + # Commit the transaction to the database + conn.commit() + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + + + + + + + + + + + + + + + +def insert_gpl_main(conn, df): + """ + Inserts data from a DataFrame into the 'expr_gpl_main' table in the MySQL database. + + This function takes a DataFrame with 'gpl_id' and 'gpl_title' columns and inserts the data into + the 'expr_gpl_main' table within the MySQL database specified by the provided connection. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + df (pandas.DataFrame): The DataFrame containing the data to be inserted. It should have columns 'gpl_id' and 'gpl_title'. + + Returns: + None + + Raises: + mysql.connector.Error: If there is a MySQL-specific error during the insert operation. + Exception: For any other exceptions that may occur. + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + for index, row in df.iterrows(): + # Define the SQL INSERT query + query = """ + INSERT INTO disnet_biolayer.expr_gpl_main (gpl_id, gpl_title) + VALUES (%s, %s) + """ + # Prepare the data to be inserted into the database + data = (row['gpl_id'], row['gpl_title']) + # Execute the SQL query with the data + cursor.execute(query, data) + # Commit the transaction to the database + conn.commit() + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + + + +def insert_gds_metadata(conn, df): + """ + Inserts data from a DataFrame into the 'expr_gds_metadata' table in the MySQL database. + + This function processes each row of the DataFrame and inserts the `gds_id`, `gds_title`, `gds_type`, + `gpl_id`, `channel_count`, and `value_type` columns into the `expr_gds_metadata` table in the specified + MySQL database. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + df (pandas.DataFrame): The DataFrame containing the data to be inserted. It should have the following columns: 'gds_id','gds_title','gds_type','gpl_id','channel_count' and 'value_type' + + Returns: + None + + Raises: + mysql.connector.Error: If there is a MySQL-specific error during the insert operation. + Exception: For any other exceptions that may occur. + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + for index, row in df.iterrows(): + # Define the SQL INSERT query for inserting data into the table + query = """ + INSERT INTO disnet_biolayer.expr_gds_metadata (gds_id, gds_title, gds_type, gpl_id, channel_count, value_type) + VALUES (%s, %s, %s, %s, %s, %s) + """ + # Prepare the data to be inserted into the database + data = (row['gds_id'], row['gds_title'], row['gds_type'], row['gpl_id'], row['channel_count'], row['value_type']) + # Execute the SQL query with the data + cursor.execute(query, data) + # Commit the transaction to make the changes persistent + conn.commit() + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + + + + + + +def insert_raw_annot(conn, df): + """ + Inserts data from a DataFrame into the 'expr_raw_annot' table in the MySQL database. + + This function takes a DataFrame with various annotation fields and inserts the data into the + 'expr_raw_annot' table within the MySQL database specified by the provided connection. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + df (pandas.DataFrame): The DataFrame containing the data to be inserted. It should have the following columns: 'gds_id','gsm_id','disease_state','age','cell_type','genotype','individual','gender','infection','other','specimen' and 'development_stage'. + + Returns: + None + + Raises: + mysql.connector.Error: If there is a MySQL-specific error during the insert operation. + Exception: For any other exceptions that may occur. + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + for index, row in df.iterrows(): + # Define the SQL INSERT query for inserting data into the table + query = """ + INSERT INTO disnet_biolayer.expr_raw_annot (gds_id, gsm_id, disease_state, age, cell_type, genotype, individual, gender, infection, other, specimen, development_stage) + VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s) + """ + # Prepare the data to be inserted into the database + data = ( + row['gds_id'], + row['gsm_id'], + row['disease_state'], + row['age'], + row['cell_type'], + row['genotype'], + row['individual'], + row['gender'], + row['infection'], + row['other'], + row['specimen'], + row['development_stage'] + ) + # Execute the SQL query with the data + cursor.execute(query, data) + # Commit the transaction to make the changes persistent + conn.commit() + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + +def insert_processed_annot(conn, df): + """ + Inserts data from a DataFrame into the 'expr_processed_annot' table in the MySQL database. + + This function takes a DataFrame with various annotation fields and inserts the data into the + 'expr_processed_annot' table within the MySQL database specified by the provided connection. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + df (pandas.DataFrame): The DataFrame containing the data to be inserted. It should have the following columns: 'gds_id','gsm_id','disease_state','age','cell_type','genotype','individual','gender','infection','other','specimen' and 'development_stage'. + + Returns: + None + + Raises: + mysql.connector.Error: If there is a MySQL-specific error during the insert operation. + Exception: For any other exceptions that may occur. + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + for index, row in df.iterrows(): + # Define the SQL INSERT query for inserting data into the table + query = """ + INSERT INTO disnet_biolayer.expr_processed_annot ( + gds_id, gsm_id, disease_state, age, cell_type, genotype, individual, gender, infection, other, specimen, development_stage, flag + ) + VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s) + """ + # Prepare the data to be inserted into the database + data = ( + row['gds_id'], + row['gsm_id'], + row['disease_state'], + row['age'], + row['cell_type'], + row['genotype'], + row['individual'], + row['gender'], + row['infection'], + row['other'], + row['specimen'], + row['development_stage'], + row['flag'] + ) + # Execute the SQL query with the data + cursor.execute(query, data) + # Commit the transaction to make the changes persistent + conn.commit() + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + + + +def insert_values(conn, df): + """ + Inserts data from a DataFrame into the 'expr_values' table in the MySQL database. + + This function takes a DataFrame with gene expression data and inserts it into the + 'expr_values' table within the MySQL database specified by the provided connection. + + Input Parameters: + conn (mysql.connector.connection_cext.CMySQLConnection): The MySQL database connection object. + It should be established using the `mysql-connector-python` library, and it contains + the necessary details for connecting to the MySQL server. + + df (pandas.DataFrame): The DataFrame containing the data to be inserted into the database. + It must have the following columns: 'gds_id', 'gsm_id', 'id_ref', 'gene_symbol' and 'value' + + Returns: + None + """ + try: + # Create a cursor object to execute SQL commands + with conn.cursor() as cursor: + # Define the SQL INSERT query for inserting data into the table + for index, row in df.iterrows(): + query = """ + INSERT INTO disnet_biolayer.expr_values (gds_id, gsm_id, id_ref, gene_symbol, value) + VALUES (%s, %s, %s, %s,%s) + """ + # Prepare the data to be inserted into the database + data = ( + row['gds_id'], + row['gsm_id'], + row['id_ref'], + row['gene_symbol'], + row['value'] + ) + # Execute the SQL query with the data + cursor.execute(query, data) + + # Commit the transaction to make the changes persistent + conn.commit() + + except mysql.connector.Error as err: + # Handle MySQL-specific errors + if err.errno == errorcode.ER_ACCESS_DENIED_ERROR: + print("Something is wrong with your user or password") + elif err.errno == errorcode.ER_BAD_DB_ERROR: + print("The database does not exist") + else: + print(f"Error from MySQL: {err}") + except Exception as e: + # Handle any other exceptions that might occur + print(f"Error: {e}") + finally: + # Ensure the cursor is closed if it was opened + cursor.close() + + + + + + + + + + + diff --git a/scripts/preprocess_functions.py b/scripts/preprocess_functions.py new file mode 100644 index 0000000..9a3f5a2 --- /dev/null +++ b/scripts/preprocess_functions.py @@ -0,0 +1,242 @@ +import requests +from Bio import Entrez +import GEOparse +import os +import gzip +import shutil +import pandas as pd +from os.path import join +from collections import defaultdict +import numpy as np + + + +def fetch_gds_data(gds_path): + """ + Fetches and processes Gene Expression Omnibus (GEO) GDS data files from the specified directory. + + This function iterates through GDS files in the given directory, extracts gene expression data, annotations, + and metadata for each file, and consolidates this information into three dataframes. + + Input Parameters: + gds_path (str): The path to the directory containing GDS files. + + Returns: + tuple: A tuple containing three pandas DataFrames: + - expression_df: DataFrame with gene expression data. + - annotation_df: DataFrame with annotation data. + - metadata_df: DataFrame with metadata about the GDS files. + """ + expression_dfs = [] + annotation_dfs = [] + metadata_rows = [] + + for filename in os.listdir(gds_path): + if not filename.startswith("GDS") or not filename.endswith(".soft"): + continue + + filepath = os.path.join(gds_path, filename) + gds = GEOparse.get_GEO(filepath=filepath) + + value_types = gds.metadata.get('value_type', []) + if 'count' not in value_types: + continue + + #Collect metadata + metadata_rows.append({ + 'gds_id': gds.name, + 'gds_title': gds.metadata.get('title', [None])[0], + 'gds_type': gds.metadata.get('type', [None])[0], + 'gpl_id': gds.metadata.get('platform', [None])[0], + 'channel_count': gds.metadata.get('channel_count', [None])[0], + 'value_type': value_types[0] + }) + + #Extract gene expression data + gsm_columns = [col for col in gds.table.columns if col.startswith("GSM")] + non_gsm_columns = [col for col in gds.table.columns if not col.startswith("GSM")] + + melted_df = pd.melt( + gds.table, + id_vars=non_gsm_columns, + value_vars=gsm_columns, + var_name='gsm_id', + value_name='value' + ) + + melted_df.dropna(subset=['IDENTIFIER', 'value'], inplace=True) + melted_df.rename(columns={'ID_REF': 'id_ref', 'IDENTIFIER': 'gene_symbol'}, inplace=True) + melted_df['gds_id'] = gds.name + + #Extract annotation data + gds_annot = gds.columns.reset_index().drop(columns=['description']) + gds_annot['gds_id'] = gds.name + + #Collect expression data for expression_df + expression_dfs.append(melted_df) + + #Collect annotation data for annotation_df + annotation_dfs.append(gds_annot) + + #Combine all expression and annotation dataframes + expression_df = pd.concat(expression_dfs, ignore_index=True) + annotation_df = pd.concat(annotation_dfs, ignore_index=True) + + rename_dict = { + 'index': 'gsm_id', + 'disease state': 'disease_state', + 'cell type': 'cell_type', + 'development stage': 'development_stage', + 'genotype/variation': 'genotype' + } + annotation_df.rename(columns={k: v for k, v in rename_dict.items() if k in annotation_df.columns}, inplace=True) + + metadata_df = pd.DataFrame(metadata_rows) + + return expression_df, annotation_df, metadata_df + + + + +# ================================================================================= + + + +def fetch_gpl_annot(gpl_path): + """ + Fetch GPL data from files in the specified directory. + + Input Parameters: + gpl_path (str): The directory path where the GPL annotation files are stored. + + Returns: + pd.DataFrame: A dataframe containing GPL annotation data. + Columns are 'gpl_id' and 'gpl_title'. + """ + data_rows = [] + for filename in os.listdir(gpl_path): + if filename.startswith("GPL") and filename.endswith(".annot"): + filepath = os.path.join(gpl_path, filename) + gpl = GEOparse.get_GEO(filepath=filepath) + + #Collect GPL (platform) data + data_rows.append({ + 'gpl_id': gpl.name, + 'gpl_title': gpl.metadata.get('platform_title', [None])[0] + }) + gpl_data = pd.DataFrame(data_rows) + + return gpl_data + +# ================================================================================= + +def process_disease_state(df, fill_value=''): + """ + Processes the 'disease_state' column in the given DataFrame. + + This function fills missing values in the DataFrame, then categorizes the 'disease_state' column into + two categories: 'c' for control/normal/healthy states and 'd' for diseased states. + + Input Parameters: + df (pandas.DataFrame): The input DataFrame containing a 'disease_state' column. + fill_value (str, optional): The value to use for filling missing values in the DataFrame. Default is an empty string. + + Returns: + pandas.DataFrame: A new DataFrame with the processed 'disease_state' column. + """ + #Fill missing values and create a copy of the DataFrame + new_dataframe = df.fillna(fill_value).copy() + + #Create a mask for control/normal/healthy states using case-insensitive matching + mask_control = new_dataframe['disease_state'].str.lower().str.contains('|'.join(['control', 'normal', 'healthy', 'not diseased', 'wild-type'])) + + #Assign 'c' to control/normal/healthy states + new_dataframe.loc[mask_control, 'disease_state'] = 'c' + + #Assign 'd' to diseased states + new_dataframe.loc[~mask_control, 'disease_state'] = 'd' + + return new_dataframe + + +# ================================================================================= + +def extract_cuis(apikey,dataframe, column_name): + """ + Extracts CUIs (Concept Unique Identifiers) for terms in a specified column of a DataFrame. + + This function interacts with the UMLS API to fetch CUIs for unique terms found in the specified column of the input DataFrame. + + Input Parameters: + dataframe (pandas.DataFrame): The input DataFrame containing the terms. + column_name (str): The name of the column in the DataFrame containing the terms for which CUIs need to be extracted. + + Returns: + dict: A dictionary mapping terms to their respective CUIs. + """ + #UMLS API key and settings + apikey = apikey + version = 'current' + uri = "https://uts-ws.nlm.nih.gov" + content_endpoint = "/rest/search/" + version + full_url = uri + content_endpoint + search_type = 'exact' + + #Get the different terms from the specified column, removing NaNs and empty strings + list_different = set(dataframe[column_name].dropna()) + list_different = {item for item in list_different if item.strip()} + different_cuis = {} + + #Fetch CUIs for each different term + for item in list_different: + page = 0 + while True: + page += 1 + query = { + 'string': item, + 'apiKey': apikey, + 'pageNumber': page, + 'searchType': search_type + } + r = requests.get(full_url, params=query) + r.raise_for_status() + r.encoding = 'utf-8' + outputs = r.json() + + items = ((outputs.get('result', {})).get('results', [])) + + if len(items) == 0: + if page == 1: + break + else: + break + + for result in items: + cui = result['ui'] + different_cuis[item] = cui + + return different_cuis + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/scripts/preprocess_upload_data.ipynb b/scripts/preprocess_upload_data.ipynb new file mode 100644 index 0000000..d02dfce --- /dev/null +++ b/scripts/preprocess_upload_data.ipynb @@ -0,0 +1,2724 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "9d8f560a-2afd-4cd6-9db3-c3f417169e4f", + "metadata": {}, + "outputs": [], + "source": [ + "from Bio import Entrez\n", + "import GEOparse\n", + "import pandas as pd\n", + "import os\n", + "import polars as pl\n", + "import mysql.connector\n", + "import download_files\n", + "import preprocess_functions\n", + "import insert_tables\n", + "from mysql.connector import errorcode\n", + "import requests" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "83d9f5d3-71ee-4665-a5c3-feb0e786f2f1", + "metadata": {}, + "outputs": [], + "source": [ + "#Define the paths where GDS files and GPL files are stored\n", + "gds_path=\"../data/gds\"\n", + "gpl_path=\"../data/gpl\"" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "4bf31853-ead8-40a8-88a9-3567682e8a27", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "08-Jul-2024 11:22:11 INFO GEOparse - Parsing ../data/gds/GDS1050.soft: \n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS1050\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1050_1\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1050_2\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1050_3\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1050_4\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS1050\n", + "08-Jul-2024 11:22:11 INFO GEOparse - Parsing ../data/gds/GDS5211.soft: \n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS5211\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS5211_1\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS5211_2\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS5211_3\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS5211_4\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS5211\n", + "08-Jul-2024 11:22:11 INFO GEOparse - Parsing ../data/gds/GDS1563.soft: \n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS1563\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_1\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_2\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_3\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_4\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_5\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_6\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_7\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_8\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_9\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_10\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_11\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_12\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_13\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_14\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_15\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_16\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_17\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_18\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_19\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_20\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_21\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_22\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_23\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_24\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_25\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_26\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_27\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_28\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_29\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - SUBSET: GDS1563_30\n", + "08-Jul-2024 11:22:11 DEBUG GEOparse - DATASET: GDS1563\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS4136.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4136\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_3\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_4\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_5\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_6\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_7\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_8\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_9\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_10\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_11\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_12\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_13\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_14\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_15\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_16\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_17\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_18\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_19\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_20\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_21\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_22\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4136_23\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4136\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS4161.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4161\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_3\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_4\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_5\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_6\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_7\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_8\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_9\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_10\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_11\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_12\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_13\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_14\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_15\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_16\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_17\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4161_18\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4161\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS4150.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4150\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_3\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_4\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_5\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_6\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_7\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4150_8\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4150\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS563.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS563\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS563_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS563_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS563\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS4275.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4275\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4275_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4275_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4275_3\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4275_4\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS4275_5\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS4275\n", + "08-Jul-2024 11:22:12 INFO GEOparse - Parsing ../data/gds/GDS5430.soft: \n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS5430\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_1\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_2\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_3\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_4\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_5\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_6\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_7\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_8\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_9\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_10\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_11\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_12\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_13\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_14\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_15\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_16\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_17\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_18\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_19\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_20\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_21\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_22\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_23\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_24\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_25\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_26\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_27\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_28\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_29\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_30\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_31\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_32\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_33\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_34\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_35\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_36\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_37\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_38\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_39\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_40\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_41\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_42\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_43\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_44\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_45\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_46\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_47\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - SUBSET: GDS5430_48\n", + "08-Jul-2024 11:22:12 DEBUG GEOparse - DATASET: GDS5430\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS4541.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4541\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_3\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_4\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_5\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_6\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_7\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_8\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_9\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_10\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_11\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_12\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_13\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_14\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_15\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_16\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_17\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_18\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_19\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_20\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_21\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_22\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_23\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_24\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_25\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_26\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_27\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_28\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_29\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4541_30\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4541\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS612.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS612\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS612_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS612_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS612\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS2978.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2978\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2978_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2978_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2978\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS2190.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2190\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2190_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2190_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2190\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS4843.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4843\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_3\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_4\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_5\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_6\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4843_7\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4843\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS2887.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2887\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2887_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2887_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2887_3\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS2887_4\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS2887\n", + "08-Jul-2024 11:22:14 INFO GEOparse - Parsing ../data/gds/GDS4879.soft: \n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4879\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4879_1\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4879_2\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4879_3\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - SUBSET: GDS4879_4\n", + "08-Jul-2024 11:22:14 DEBUG GEOparse - DATASET: GDS4879\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS1112.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS1112\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS1112_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS1112_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS1112\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS232.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS232\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS232_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS232_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS232\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS2613.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS2613\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS2613_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS2613_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS2613\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS214.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS214\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_3\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_4\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_5\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS214_6\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS214\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS3459.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS3459\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_3\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_4\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_5\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3459_6\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS3459\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS1332.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS1332\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS1332_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS1332_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS1332_3\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS1332\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS2447.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS2447\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS2447_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS2447_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS2447\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS3281.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS3281\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_3\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_4\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_5\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_6\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_7\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_8\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS3281_9\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS3281\n", + "08-Jul-2024 11:22:15 INFO GEOparse - Parsing ../data/gds/GDS4837.soft: \n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS4837\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS4837_1\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS4837_2\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - SUBSET: GDS4837_3\n", + "08-Jul-2024 11:22:15 DEBUG GEOparse - DATASET: GDS4837\n", + "08-Jul-2024 11:22:16 INFO GEOparse - Parsing ../data/gds/GDS3475.soft: \n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATASET: GDS3475\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS3475_1\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS3475_2\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATASET: GDS3475\n", + "08-Jul-2024 11:22:16 INFO GEOparse - Parsing ../data/gds/GDS1962.soft: \n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATASET: GDS1962\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_1\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_2\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_3\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_4\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_5\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_6\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_7\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - SUBSET: GDS1962_8\n", + "08-Jul-2024 11:22:16 DEBUG GEOparse - DATASET: GDS1962\n", + "08-Jul-2024 11:22:18 INFO GEOparse - Parsing ../data/gds/GDS1816.soft: \n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS1816\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_1\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_2\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_3\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_4\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_5\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_6\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_7\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_8\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_9\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_10\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_11\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_12\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_13\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_14\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS1816_15\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS1816\n", + "08-Jul-2024 11:22:18 INFO GEOparse - Parsing ../data/gds/GDS4451.soft: \n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS4451\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS4451_1\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS4451_2\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS4451_3\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS4451_4\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS4451\n", + "08-Jul-2024 11:22:18 INFO GEOparse - Parsing ../data/gds/GDS2519.soft: \n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS2519\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS2519_1\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS2519_2\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - SUBSET: GDS2519_3\n", + "08-Jul-2024 11:22:18 DEBUG GEOparse - DATASET: GDS2519\n", + "08-Jul-2024 11:22:19 INFO GEOparse - Parsing ../data/gds/GDS2763.soft: \n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS2763\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS2763_1\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS2763_2\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS2763_3\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS2763_4\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS2763_5\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS2763\n", + "08-Jul-2024 11:22:19 INFO GEOparse - Parsing ../data/gds/GDS1815.soft: \n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1815\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_1\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_2\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_3\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_4\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_5\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_6\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_7\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_8\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_9\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_10\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_11\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_12\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_13\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_14\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1815_15\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1815\n", + "08-Jul-2024 11:22:19 INFO GEOparse - Parsing ../data/gds/GDS4147.soft: \n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS4147\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_1\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_2\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_3\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_4\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_5\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_6\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_7\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_8\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS4147_9\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS4147\n", + "08-Jul-2024 11:22:19 INFO GEOparse - Parsing ../data/gds/GDS1960.soft: \n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1960\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1960_1\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1960_2\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1960_3\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1960_4\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1960_5\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1960\n", + "08-Jul-2024 11:22:19 INFO GEOparse - Parsing ../data/gds/GDS1975.soft: \n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1975\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_1\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_2\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_3\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_4\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_5\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - SUBSET: GDS1975_6\n", + "08-Jul-2024 11:22:19 DEBUG GEOparse - DATASET: GDS1975\n", + "08-Jul-2024 11:22:20 INFO GEOparse - Parsing ../data/gds/GDS4314.soft: \n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS4314\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4314_1\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4314_2\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4314_3\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS4314\n", + "08-Jul-2024 11:22:20 INFO GEOparse - Parsing ../data/gds/GDS3920.soft: \n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS3920\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS3920_1\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS3920_2\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS3920\n", + "08-Jul-2024 11:22:20 INFO GEOparse - Parsing ../data/gds/GDS4841.soft: \n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS4841\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4841_1\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4841_2\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4841_3\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS4841_4\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS4841\n", + "08-Jul-2024 11:22:20 INFO GEOparse - Parsing ../data/gds/GDS2432.soft: \n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS2432\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS2432_1\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - SUBSET: GDS2432_2\n", + "08-Jul-2024 11:22:20 DEBUG GEOparse - DATASET: GDS2432\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS2795.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS2795\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_6\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_7\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_8\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_9\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_10\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_11\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2795_12\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS2795\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS265.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS265\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS265_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS265_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS265_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS265_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS265\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS3128.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS3128\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_6\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_7\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_8\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_9\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_10\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_11\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_12\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_13\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_14\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_15\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_16\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_17\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_18\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_19\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_20\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_21\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_22\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_23\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_24\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_25\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_26\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_27\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3128_28\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS3128\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS4404.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS4404\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_6\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_7\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_8\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_9\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_10\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_11\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_12\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_13\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_14\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_15\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_16\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_17\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_18\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_19\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_20\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_21\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_22\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_23\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_24\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_25\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_26\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_27\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_28\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_29\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_30\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_31\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_32\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_33\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_34\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_35\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_36\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_37\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_38\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_39\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4404_40\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS4404\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS2853.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS2853\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2853_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2853_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2853_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2853_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS2853_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS2853\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS4464.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS4464\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_6\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_7\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_8\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_9\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_10\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_11\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_12\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_13\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_14\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_15\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_16\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_17\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_18\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_19\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_20\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_21\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_22\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_23\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_24\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_25\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_26\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_27\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_28\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_29\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_30\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_31\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_32\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_33\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_34\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_35\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_36\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS4464_37\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS4464\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS610.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS610\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS610_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS610_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS610\n", + "08-Jul-2024 11:22:21 INFO GEOparse - Parsing ../data/gds/GDS3268.soft: \n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS3268\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_1\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_2\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_3\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_4\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_5\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_6\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_7\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - SUBSET: GDS3268_8\n", + "08-Jul-2024 11:22:21 DEBUG GEOparse - DATASET: GDS3268\n", + "08-Jul-2024 11:22:22 INFO GEOparse - Parsing ../data/gds/GDS264.soft: \n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - DATASET: GDS264\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - SUBSET: GDS264_1\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - SUBSET: GDS264_2\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - SUBSET: GDS264_3\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - SUBSET: GDS264_4\n", + "08-Jul-2024 11:22:22 DEBUG GEOparse - DATASET: GDS264\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS1912.soft: \n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS1912\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS1912_1\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS1912_2\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS1912_3\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS1912_4\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS1912\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS4353.soft: \n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS4353\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS4353_1\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS4353_2\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS4353_3\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS4353_4\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS4353\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS3502.soft: \n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS3502\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_1\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_2\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_3\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_4\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_5\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_6\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_7\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_8\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_9\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_10\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_11\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_12\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_13\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_14\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_15\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_16\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_17\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_18\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_19\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_20\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_21\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_22\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_23\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_24\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS3502_25\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS3502\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS2855.soft: \n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS2855\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_1\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_2\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_3\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_4\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_5\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_6\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_7\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_8\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_9\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_10\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS2855_11\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS2855\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS5242.soft: \n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS5242\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_1\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_2\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_3\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_4\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_5\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_6\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_7\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_8\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_9\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_10\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - SUBSET: GDS5242_11\n", + "08-Jul-2024 11:22:23 DEBUG GEOparse - DATASET: GDS5242\n", + "08-Jul-2024 11:22:23 INFO GEOparse - Parsing ../data/gds/GDS4473.soft: \n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS4473\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_1\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_2\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_3\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_4\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_5\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_6\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_7\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_8\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_9\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_10\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_11\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4473_12\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS4473\n", + "08-Jul-2024 11:22:24 INFO GEOparse - Parsing ../data/gds/GDS1253.soft: \n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS1253\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1253_1\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1253_2\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1253_3\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1253_4\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1253_5\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS1253\n", + "08-Jul-2024 11:22:24 INFO GEOparse - Parsing ../data/gds/GDS4838.soft: \n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS4838\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4838_1\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4838_2\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4838_3\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4838_4\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS4838_5\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS4838\n", + "08-Jul-2024 11:22:24 INFO GEOparse - Parsing ../data/gds/GDS1956.soft: \n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS1956\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_1\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_2\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_3\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_4\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_5\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_6\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_7\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_8\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_9\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_10\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_11\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - SUBSET: GDS1956_12\n", + "08-Jul-2024 11:22:24 DEBUG GEOparse - DATASET: GDS1956\n", + "08-Jul-2024 11:22:25 INFO GEOparse - Parsing ../data/gds/GDS1813.soft: \n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS1813\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_1\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_2\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_3\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_4\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_5\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS1813_6\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS1813\n", + "08-Jul-2024 11:22:25 INFO GEOparse - Parsing ../data/gds/GDS5646.soft: \n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS5646\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_1\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_2\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_3\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_4\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_5\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_6\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_7\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_8\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_9\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_10\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_11\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS5646_12\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS5646\n", + "08-Jul-2024 11:22:25 INFO GEOparse - Parsing ../data/gds/GDS3417.soft: \n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS3417\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS3417_1\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS3417_2\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS3417_3\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS3417\n", + "08-Jul-2024 11:22:25 INFO GEOparse - Parsing ../data/gds/GDS4477.soft: \n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS4477\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS4477_1\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS4477_2\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS4477_3\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - SUBSET: GDS4477_4\n", + "08-Jul-2024 11:22:25 DEBUG GEOparse - DATASET: GDS4477\n", + "08-Jul-2024 11:22:25 INFO GEOparse - Parsing ../data/gds/GDS3069.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS3069\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3069_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3069_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3069_3\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3069_4\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3069_5\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS3069\n", + "08-Jul-2024 11:22:26 INFO GEOparse - Parsing ../data/gds/GDS1726.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS1726\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS1726_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS1726_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS1726\n", + "08-Jul-2024 11:22:26 INFO GEOparse - Parsing ../data/gds/GDS4523.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS4523\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_3\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_4\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_5\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_6\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_7\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_8\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_9\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_10\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_11\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_12\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_13\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_14\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_15\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_16\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_17\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_18\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_19\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_20\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_21\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_22\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_23\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_24\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_25\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_26\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_27\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_28\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_29\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_30\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_31\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_32\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_33\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_34\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_35\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_36\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS4523_37\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS4523\n", + "08-Jul-2024 11:22:26 INFO GEOparse - Parsing ../data/gds/GDS611.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS611\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS611_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS611_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS611\n", + "08-Jul-2024 11:22:26 INFO GEOparse - Parsing ../data/gds/GDS2601.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS2601\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS2601_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS2601_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS2601_3\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS2601_4\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS2601\n", + "08-Jul-2024 11:22:26 INFO GEOparse - Parsing ../data/gds/GDS3085.soft: \n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS3085\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3085_1\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3085_2\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3085_3\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - SUBSET: GDS3085_4\n", + "08-Jul-2024 11:22:26 DEBUG GEOparse - DATASET: GDS3085\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS270.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS270\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS270_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS270_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS270_3\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS270_4\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS270\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS4469.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS4469\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_3\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_4\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_5\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_6\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_7\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4469_8\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS4469\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS5181.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS5181\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS5181_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS5181_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS5181\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS3903.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS3903\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3903_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3903_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS3903\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS2419.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS2419\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_3\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_4\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_5\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_6\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_7\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_8\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_9\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_10\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_11\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_12\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_13\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2419_14\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS2419\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS4128.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS4128\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_3\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_4\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_5\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS4128_6\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS4128\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS2191.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS2191\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2191_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS2191_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS2191\n", + "08-Jul-2024 11:22:27 INFO GEOparse - Parsing ../data/gds/GDS3952.soft: \n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS3952\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_1\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_2\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_3\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_4\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_5\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_6\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_7\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - SUBSET: GDS3952_8\n", + "08-Jul-2024 11:22:27 DEBUG GEOparse - DATASET: GDS3952\n", + "08-Jul-2024 11:22:28 INFO GEOparse - Parsing ../data/gds/GDS2470.soft: \n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS2470\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS2470_1\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS2470_2\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS2470\n", + "08-Jul-2024 11:22:28 INFO GEOparse - Parsing ../data/gds/GDS3540.soft: \n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS3540\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS3540_1\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS3540_2\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS3540_3\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS3540_4\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS3540_5\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS3540\n", + "08-Jul-2024 11:22:28 INFO GEOparse - Parsing ../data/gds/GDS5047.soft: \n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS5047\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_1\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_2\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_3\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_4\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_5\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_6\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_7\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_8\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_9\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_10\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_11\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_12\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_13\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_14\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_15\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_16\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_17\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_18\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_19\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_20\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_21\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - SUBSET: GDS5047_22\n", + "08-Jul-2024 11:22:28 DEBUG GEOparse - DATASET: GDS5047\n", + "08-Jul-2024 11:22:29 INFO GEOparse - Parsing ../data/gds/GDS5276.soft: \n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS5276\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS5276_1\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS5276_2\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS5276\n", + "08-Jul-2024 11:22:29 INFO GEOparse - Parsing ../data/gds/GDS2374.soft: \n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS2374\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS2374_1\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS2374_2\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS2374_3\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS2374_4\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS2374_5\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS2374\n", + "08-Jul-2024 11:22:29 INFO GEOparse - Parsing ../data/gds/GDS3474.soft: \n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS3474\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3474_1\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3474_2\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS3474\n", + "08-Jul-2024 11:22:29 INFO GEOparse - Parsing ../data/gds/GDS3644.soft: \n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS3644\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_1\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_2\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_3\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_4\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_5\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_6\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_7\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_8\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_9\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_10\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_11\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - SUBSET: GDS3644_12\n", + "08-Jul-2024 11:22:29 DEBUG GEOparse - DATASET: GDS3644\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS2821.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS2821\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS2821_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS2821_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS2821_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS2821_4\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS2821\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS3864.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3864\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_4\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_5\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_6\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_7\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_8\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_9\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_10\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_11\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3864_12\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3864\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS1051.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS1051\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS1051_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS1051_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS1051_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS1051_4\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS1051\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS4409.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS4409\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_4\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_5\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_6\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_7\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_8\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_9\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_10\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_11\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_12\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_13\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_14\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_15\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_16\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_17\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_18\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_19\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_20\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_21\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_22\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_23\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_24\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_25\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_26\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_27\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_28\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4409_29\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS4409\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS4141.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS4141\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4141_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4141_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS4141_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS4141\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS3886.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3886\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3886_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3886_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3886\n", + "08-Jul-2024 11:22:30 INFO GEOparse - Parsing ../data/gds/GDS3129.soft: \n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3129\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_1\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_2\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_3\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_4\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_5\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_6\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_7\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_8\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_9\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_10\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_11\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_12\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_13\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_14\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_15\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_16\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_17\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_18\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_19\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_20\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_21\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_22\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_23\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_24\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_25\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_26\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_27\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - SUBSET: GDS3129_28\n", + "08-Jul-2024 11:22:30 DEBUG GEOparse - DATASET: GDS3129\n", + "08-Jul-2024 11:22:31 INFO GEOparse - Parsing ../data/gds/GDS4012.soft: \n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS4012\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4012_1\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4012_2\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS4012\n", + "08-Jul-2024 11:22:31 INFO GEOparse - Parsing ../data/gds/GDS968.soft: \n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS968\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_1\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_2\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_3\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_4\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_5\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_6\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_7\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_8\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_9\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_10\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_11\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_12\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_13\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_14\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_15\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_16\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_17\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_18\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_19\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_20\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_21\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_22\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_23\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_24\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_25\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_26\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_27\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_28\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_29\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_30\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_31\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_32\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_33\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_34\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_35\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_36\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_37\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_38\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_39\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_40\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_41\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_42\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_43\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_44\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_45\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_46\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_47\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_48\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_49\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_50\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_51\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_52\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_53\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_54\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_55\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_56\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_57\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_58\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_59\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_60\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_61\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_62\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_63\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS968_64\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS968\n", + "08-Jul-2024 11:22:31 INFO GEOparse - Parsing ../data/gds/GDS3830.soft: \n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS3830\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_1\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_2\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_3\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_4\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_5\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_6\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS3830_7\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS3830\n", + "08-Jul-2024 11:22:31 INFO GEOparse - Parsing ../data/gds/GDS2779.soft: \n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS2779\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS2779_1\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS2779_2\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS2779_3\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS2779_4\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS2779_5\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS2779\n", + "08-Jul-2024 11:22:31 INFO GEOparse - Parsing ../data/gds/GDS4471.soft: \n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS4471\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_1\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_2\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_3\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_4\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_5\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_6\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_7\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_8\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_9\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_10\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_11\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - SUBSET: GDS4471_12\n", + "08-Jul-2024 11:22:31 DEBUG GEOparse - DATASET: GDS4471\n", + "08-Jul-2024 11:22:32 INFO GEOparse - Parsing ../data/gds/GDS2736.soft: \n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS2736\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_1\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_2\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_3\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_4\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_5\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_6\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_7\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_8\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_9\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS2736_10\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS2736\n", + "08-Jul-2024 11:22:32 INFO GEOparse - Parsing ../data/gds/GDS1065.soft: \n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS1065\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_1\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_2\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_3\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_4\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_5\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS1065_6\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS1065\n", + "08-Jul-2024 11:22:32 INFO GEOparse - Parsing ../data/gds/GDS4358.soft: \n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS4358\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_1\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_2\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_3\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_4\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_5\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_6\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - SUBSET: GDS4358_7\n", + "08-Jul-2024 11:22:32 DEBUG GEOparse - DATASET: GDS4358\n", + "08-Jul-2024 11:22:33 INFO GEOparse - Parsing ../data/gds/GDS3110.soft: \n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATASET: GDS3110\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_1\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_2\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_3\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_4\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_5\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS3110_6\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATASET: GDS3110\n", + "08-Jul-2024 11:22:33 INFO GEOparse - Parsing ../data/gds/GDS4296.soft: \n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATASET: GDS4296\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_1\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_2\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_3\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_4\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_5\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_6\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_7\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_8\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_9\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_10\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_11\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_12\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_13\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_14\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_15\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_16\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_17\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_18\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_19\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_20\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_21\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_22\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_23\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_24\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_25\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_26\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_27\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_28\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_29\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_30\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_31\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_32\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_33\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_34\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_35\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_36\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_37\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_38\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_39\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_40\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_41\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_42\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_43\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_44\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_45\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_46\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_47\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_48\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_49\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_50\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_51\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_52\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_53\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_54\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_55\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_56\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_57\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_58\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_59\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_60\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_61\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_62\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_63\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_64\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_65\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_66\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_67\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_68\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_69\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_70\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_71\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_72\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_73\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_74\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_75\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_76\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_77\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_78\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_79\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_80\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_81\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_82\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_83\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_84\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_85\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_86\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_87\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_88\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_89\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_90\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_91\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_92\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_93\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_94\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - SUBSET: GDS4296_95\n", + "08-Jul-2024 11:22:33 DEBUG GEOparse - DATASET: GDS4296\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS3027.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS3027\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_3\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_4\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_5\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_6\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_7\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_8\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_9\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_10\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_11\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_12\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_13\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_14\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_15\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_16\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_17\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_18\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_19\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_20\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_21\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_22\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_23\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_24\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_25\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3027_26\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS3027\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS1020.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS1020\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_3\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_4\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_5\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_6\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1020_7\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS1020\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS2865.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS2865\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS2865_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS2865_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS2865\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS3345.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS3345\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3345_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3345_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3345_3\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS3345_4\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS3345\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS810.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS810\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS810_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS810_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS810_3\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS810_4\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS810\n", + "08-Jul-2024 11:22:34 INFO GEOparse - Parsing ../data/gds/GDS1976.soft: \n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS1976\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_1\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_2\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_3\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_4\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_5\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - SUBSET: GDS1976_6\n", + "08-Jul-2024 11:22:34 DEBUG GEOparse - DATASET: GDS1976\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS4135.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS4135\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4135_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4135_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4135_3\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4135_4\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4135_5\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS4135\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS3938.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS3938\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS3938_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS3938_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS3938_3\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS3938_4\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS3938\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS4857.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS4857\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4857_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS4857_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS4857\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS1331.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS1331\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS1331_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS1331_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS1331_3\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS1331\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS2941.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS2941\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2941_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2941_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS2941\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS609.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS609\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS609_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS609_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS609\n", + "08-Jul-2024 11:22:35 INFO GEOparse - Parsing ../data/gds/GDS2824.soft: \n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS2824\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2824_1\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2824_2\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2824_3\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2824_4\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - SUBSET: GDS2824_5\n", + "08-Jul-2024 11:22:35 DEBUG GEOparse - DATASET: GDS2824\n", + "08-Jul-2024 11:22:36 INFO GEOparse - Parsing ../data/gds/GDS4410.soft: \n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATASET: GDS4410\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4410_1\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4410_2\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATASET: GDS4410\n", + "08-Jul-2024 11:22:36 INFO GEOparse - Parsing ../data/gds/GDS4431.soft: \n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATASET: GDS4431\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_1\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_2\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_3\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_4\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_5\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_6\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_7\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_8\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_9\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_10\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_11\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_12\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_13\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_14\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_15\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_16\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_17\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_18\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_19\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_20\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_21\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_22\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_23\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_24\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_25\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_26\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_27\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_28\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_29\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_30\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_31\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_32\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_33\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - SUBSET: GDS4431_34\n", + "08-Jul-2024 11:22:36 DEBUG GEOparse - DATASET: GDS4431\n", + "08-Jul-2024 11:22:37 INFO GEOparse - Parsing ../data/gds/GDS4224.soft: \n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - DATASET: GDS4224\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - SUBSET: GDS4224_1\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - SUBSET: GDS4224_2\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - SUBSET: GDS4224_3\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - SUBSET: GDS4224_4\n", + "08-Jul-2024 11:22:37 DEBUG GEOparse - DATASET: GDS4224\n", + "08-Jul-2024 11:22:37 INFO GEOparse - Parsing ../data/gds/GDS4470.soft: \n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS4470\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_1\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_2\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_3\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_4\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_5\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_6\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_7\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_8\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_9\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_10\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_11\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_12\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_13\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_14\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_15\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_16\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_17\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_18\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_19\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_20\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_21\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_22\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_23\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_24\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_25\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_26\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_27\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_28\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_29\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_30\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_31\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_32\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_33\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_34\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_35\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_36\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_37\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_38\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_39\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_40\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_41\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_42\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_43\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_44\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_45\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_46\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_47\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_48\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_49\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_50\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_51\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_52\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_53\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_54\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4470_55\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS4470\n", + "08-Jul-2024 11:22:38 INFO GEOparse - Parsing ../data/gds/GDS2153.soft: \n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS2153\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS2153_1\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS2153_2\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS2153\n", + "08-Jul-2024 11:22:38 INFO GEOparse - Parsing ../data/gds/GDS4154.soft: \n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS4154\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_1\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_2\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_3\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_4\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_5\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_6\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_7\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_8\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_9\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_10\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_11\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_12\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_13\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_14\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS4154_15\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS4154\n", + "08-Jul-2024 11:22:38 INFO GEOparse - Parsing ../data/gds/GDS1917.soft: \n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS1917\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS1917_1\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - SUBSET: GDS1917_2\n", + "08-Jul-2024 11:22:38 DEBUG GEOparse - DATASET: GDS1917\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS1235.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS1235\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS1235_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS1235_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS1235_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS1235\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS4152.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4152\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4152_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4152_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4152_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4152_4\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4152\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS4854.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4854\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_4\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_5\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_6\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_7\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_8\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_9\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_10\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_11\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_12\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_13\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_14\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_15\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_16\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_17\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_18\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_19\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_20\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_21\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4854_22\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4854\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS4218.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4218\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_4\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_5\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_6\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_7\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_8\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_9\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS4218_10\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS4218\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS412.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS412\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS412_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS412_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS412_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS412\n", + "08-Jul-2024 11:22:39 INFO GEOparse - Parsing ../data/gds/GDS913.soft: \n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS913\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_1\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_2\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_3\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_4\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_5\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_6\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_7\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_8\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_9\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_10\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_11\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_12\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_13\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_14\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_15\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_16\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_17\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - SUBSET: GDS913_18\n", + "08-Jul-2024 11:22:39 DEBUG GEOparse - DATASET: GDS913\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS4540.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4540\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_3\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_4\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_5\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_6\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_7\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4540_8\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4540\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS4559.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4559\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4559_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4559_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4559\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS4522.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4522\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_3\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_4\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_5\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_6\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_7\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_8\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_9\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_10\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_11\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_12\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_13\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_14\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_15\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_16\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_17\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_18\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_19\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_20\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_21\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_22\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_23\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_24\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_25\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_26\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_27\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_28\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_29\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_30\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_31\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_32\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_33\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4522_34\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4522\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS262.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS262\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_3\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_4\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_5\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS262_6\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS262\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS4539.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4539\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_3\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_4\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_5\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_6\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_7\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_8\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4539_9\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4539\n", + "08-Jul-2024 11:22:40 INFO GEOparse - Parsing ../data/gds/GDS4758.soft: \n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4758\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_1\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_2\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_3\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_4\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_5\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_6\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - SUBSET: GDS4758_7\n", + "08-Jul-2024 11:22:40 DEBUG GEOparse - DATASET: GDS4758\n", + "08-Jul-2024 11:22:41 INFO GEOparse - Parsing ../data/gds/GDS1330.soft: \n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS1330\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS1330_1\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS1330_2\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS1330_3\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS1330\n", + "08-Jul-2024 11:22:41 INFO GEOparse - Parsing ../data/gds/GDS4859.soft: \n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS4859\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4859_1\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4859_2\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS4859\n", + "08-Jul-2024 11:22:41 INFO GEOparse - Parsing ../data/gds/GDS4279.soft: \n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATABASE: Geo\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS4279\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_1\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_2\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_3\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_4\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_5\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_6\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_7\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_8\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_9\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_10\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_11\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - SUBSET: GDS4279_12\n", + "08-Jul-2024 11:22:41 DEBUG GEOparse - DATASET: GDS4279\n" + ] + } + ], + "source": [ + "#Parse GDS files and extract the expression values data, the samples annotation and the metadata\n", + "expression_df, annotation_df, metadata_df=preprocess_functions.fetch_gds_data(gds_path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "174442b8-7927-4c63-a7f2-f5b1593a5811", + "metadata": {}, + "outputs": [], + "source": [ + "#Define the UMLS API key needed to extract CUIs\n", + "apikey='{UMLS_API_pass}' #The API key required to use the UMLS API. " + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "b6153d75-f332-4fb0-91c7-d4bc2e6aba20", + "metadata": {}, + "outputs": [], + "source": [ + "#Replace null values with '' to avoid errors processing the data\n", + "annotation_df['tissue']=annotation_df['tissue'].fillna('')\n", + "annotation_df['cell_type']=annotation_df['cell_type'].fillna('')\n", + "for column in annotation_df.columns:\n", + " annotation_df[column] = annotation_df[column].fillna('')\n", + "\n", + "#Process disease state column\n", + "proc_dis_state=preprocess_functions.process_disease_state(annotation_df)\n", + "\n", + "#Extract tissue and cell type terms CUIs to standardize data\n", + "different_tissue_cuis=preprocess_functions.extract_cuis(apikey,proc_dis_state,'tissue')\n", + "different_cell_type_cuis=preprocess_functions.extract_cuis(apikey,proc_dis_state,'cell_type')\n", + "\n", + "# Replace the tissue and cell type terms with its corresponding CUI\n", + "processed_annotation = proc_dis_state.copy()\n", + "for tissue in processed_annotation['tissue']:\n", + " if tissue in different_tissue_cuis:\n", + " cui = different_tissue_cuis[tissue]\n", + " processed_annotation.loc[processed_annotation['tissue'] == tissue, \"tissue\"] = cui\n", + "for cell in processed_annotation['cell_type']:\n", + " if cell in different_cell_type_cuis:\n", + " cui = different_cell_type_cuis[cell]\n", + " processed_annotation.loc[processed_annotation['cell_type'] == cell, \"cell_type\"] = cui" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "0a58257d-0a4c-4d7d-ad5c-68a15842ed8f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
gsm_idagentdisease_stategds_idagecell_typeindividualgendertissuespecimenothergenotypetimecell linedevelopment_stageinfection
0GSM27536untreateddGDS1050
1GSM27537untreateddGDS1050
2GSM27538untreateddGDS1050
3GSM27540untreateddGDS1050
4GSM27541untreateddGDS1050
\n", + "
" + ], + "text/plain": [ + " gsm_id agent disease_state gds_id age cell_type individual gender \\\n", + "0 GSM27536 untreated d GDS1050 \n", + "1 GSM27537 untreated d GDS1050 \n", + "2 GSM27538 untreated d GDS1050 \n", + "3 GSM27540 untreated d GDS1050 \n", + "4 GSM27541 untreated d GDS1050 \n", + "\n", + " tissue specimen other genotype time cell line development_stage infection \n", + "0 \n", + "1 \n", + "2 \n", + "3 \n", + "4 " + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "processed_annotation.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "c31642ea-5c7d-410c-9f2f-87e9ad04f4fc", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
disease_idgds_id
105C0002395GDS4136
106C0002395GDS4135
107C0002395GDS4128
108C0002395GDS2519
109C0002395GDS2795
110C0002395GDS810
\n", + "
" + ], + "text/plain": [ + " disease_id gds_id\n", + "105 C0002395 GDS4136\n", + "106 C0002395 GDS4135\n", + "107 C0002395 GDS4128\n", + "108 C0002395 GDS2519\n", + "109 C0002395 GDS2795\n", + "110 C0002395 GDS810" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Extract the info about the top 10 diseases more related to genes\n", + "tsv_file='../data/raw/top10_genecount_disease.tsv'\n", + "top10_diseases=download_files.extract_tsv(tsv_file)\n", + "top1_disease=top10_diseases['disease_id'].head(1).tolist()\n", + "\n", + "#Select only the GDSs from the top 1 disease more related to genes\n", + "csv_file='../results/disease_gds.csv'\n", + "diseases_gds=pd.read_csv(csv_file)\n", + "filtered_gds=diseases_gds.loc[diseases_gds['disease_id'].isin(top1_disease)]\n", + "filtered_gds" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "7ad7a33e-0fce-4040-bf24-e182456ef0fa", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
gsm_idagentdisease_stategds_idagecell_typeindividualgendertissuespecimenothergenotypetimecell linedevelopment_stageinfectionflag
13GSM697332dGDS413665 years old1
14GSM697312cGDS413675 years old1
15GSM697327dGDS413679 years old1
16GSM697334dGDS413679 years old1
17GSM697336dGDS413679 years old1
......................................................
2261GSM735110dGDS4135ApoE ε4 -1
2262GSM735111dGDS4135ApoE ε4 -1
2263GSM735106dGDS4135ApoE ε4 +1
2264GSM735107dGDS4135ApoE ε4 +1
2265GSM735108dGDS4135ApoE ε4 +1
\n", + "

222 rows × 17 columns

\n", + "
" + ], + "text/plain": [ + " gsm_id agent disease_state gds_id age cell_type \\\n", + "13 GSM697332 d GDS4136 65 years old \n", + "14 GSM697312 c GDS4136 75 years old \n", + "15 GSM697327 d GDS4136 79 years old \n", + "16 GSM697334 d GDS4136 79 years old \n", + "17 GSM697336 d GDS4136 79 years old \n", + "... ... ... ... ... ... ... \n", + "2261 GSM735110 d GDS4135 \n", + "2262 GSM735111 d GDS4135 \n", + "2263 GSM735106 d GDS4135 \n", + "2264 GSM735107 d GDS4135 \n", + "2265 GSM735108 d GDS4135 \n", + "\n", + " individual gender tissue specimen other genotype time cell line \\\n", + "13 \n", + "14 \n", + "15 \n", + "16 \n", + "17 \n", + "... ... ... ... ... ... ... ... ... \n", + "2261 ApoE ε4 - \n", + "2262 ApoE ε4 - \n", + "2263 ApoE ε4 + \n", + "2264 ApoE ε4 + \n", + "2265 ApoE ε4 + \n", + "\n", + " development_stage infection flag \n", + "13 1 \n", + "14 1 \n", + "15 1 \n", + "16 1 \n", + "17 1 \n", + "... ... ... ... \n", + "2261 1 \n", + "2262 1 \n", + "2263 1 \n", + "2264 1 \n", + "2265 1 \n", + "\n", + "[222 rows x 17 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Mark the info from the selected GDSs with a flag\n", + "processed_annotation['flag']=processed_annotation['gds_id'].isin(filtered_gds['gds_id']).astype(int)\n", + "processed_annotation[processed_annotation['flag']==1]" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "10661ae3-f0a7-4fce-a469-4eba79806146", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "#Filter the expression dataframe to include only the entries for the selected GDSs\n", + "expression_filtered = expression_df[expression_df['gds_id'].isin(filtered_gds['gds_id'])]\n", + "\n", + "#Additional filter to remove expression measurements that do not correspond to actual genes\n", + "expression_filtered = expression_filtered[expression_filtered['gene_symbol'] != '--Control']" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "07fa4d85-c8a7-457b-8b52-0ff388f93786", + "metadata": {}, + "outputs": [], + "source": [ + "#The connection details needed to insert data into the database\n", + "host = \"{host}\" # Host where the MySQL server is located. Example: 'localhost' or '127.0.0.1'\n", + "user = \"{user_name}\" # Username for accessing the MySQL database. Example: 'root' or 'my_user'\n", + "password = \"{password}\" # Password for the MySQL user. Ensure to use a secure password for database access.\n", + "database = \"{database}\" # Name of the database to connect to. Example: 'disnet_biolayer'\n", + "port = \"{port}\" # Port number for the MySQL server. Default is 3306, but it may vary depending on the setup.\n", + "\n", + "#Get the different GDS IDs\n", + "different_gds_ids=annotation_df['gds_id'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "5e1254f4-00a6-4922-a91e-baf45f528522", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "# Initialize the connection variable to None\n", + "conn = None\n", + "\n", + "try:\n", + " # Attempt to establish a connection to the MySQL database\n", + " conn = mysql.connector.connect(\n", + " host=host,\n", + " user=user,\n", + " password=password,\n", + " database=database,\n", + " port=port\n", + " )\n", + "\n", + " # Insert GDS metadata into the database\n", + " insert_tables.insert_gds_metadata(conn, metadata_df)\n", + "\n", + " # Iterate over different GDS IDs to insert annotations\n", + " for gds_id in different_gds_ids:\n", + " # Filter annotation data for the current GDS ID\n", + " annotation_subset = annotation_df[annotation_df['gds_id'] == gds_id]\n", + " # Insert raw annotation data into the database\n", + " insert_tables.insert_raw_annot(conn, annotation_subset)\n", + "\n", + " # Filter processed annotation data for the current GDS ID\n", + " annot_subset = processed_annotation[processed_annotation['gds_id'] == gds_id]\n", + " # Insert processed annotation data into the database\n", + " insert_tables.insert_processed_annot(conn, annot_subset)\n", + "\n", + "# Handle any MySQL errors that occur during the connection or insertion process\n", + "except mysql.connector.Error as err:\n", + " print(f\"Error connecting to MySQL: {err}\")\n", + "\n", + "# Ensure the connection is closed properly even if an error occurs\n", + "finally:\n", + " if conn and conn.is_connected():\n", + " conn.close()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d858ee1f-b74c-4689-8ef1-cafd7aa49e83", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize the connection variable to None\n", + "conn = None\n", + "\n", + "try:\n", + " # Attempt to establish a connection to the MySQL database\n", + " conn = mysql.connector.connect(\n", + " host=host,\n", + " user=user,\n", + " password=password,\n", + " database=database,\n", + " port=port\n", + " )\n", + " # Iterate over different GDS IDs to insert expression values\n", + " for gds_id in different_gds_ids:\n", + " # Filter expression values data for the current GDS ID\n", + " values_subset = expression_filtered[expression_filtered['gds_id'] == gds_id]\n", + "\n", + " # Insert expression values data into the database\n", + " insert_tables.insert_values(conn, values_subset)\n", + " \n", + "# Handle any MySQL errors that occur during the connection or insertion process\n", + "except mysql.connector.Error as err:\n", + " print(f\"Error connecting to MySQL: {err}\")\n", + "\n", + "# Ensure the connection is closed properly even if an error occurs\n", + "finally:\n", + " if conn and conn.is_connected():\n", + " conn.close()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "606a9d64-e18b-4301-a8cd-5e5d28c65dab", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "491fe4f8-d8e9-4926-8601-8f3daf87287f", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.1" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} -- 2.24.1