Addition of the revised files

disease_module_obtention/2_disease_module_identification/.ipynb_checkpoints/Implementation-checkpoint.ipynb

 {
- "cells": [],
- "metadata": {},
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f62b61bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python src/main.py --thresholds"
+   ]
+  }
+ ],
+ "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": "3.11.6"
+  }
+ },
  "nbformat": 4,
  "nbformat_minor": 5
 }

disease_module_obtention/2_disease_module_identification/Implementation.ipynb

 {
  "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "233d5348",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "  0%|                                                     | 0/1 [00:00<?, ?it/s]DIAMOnD(): ignoring 1 of 14 seed genes that are not in the network\n",
-      "\n",
-      " results have been saved to 'first_1000_added_nodes_weight_1.txt' \n",
-      "\n",
-      "start running DOMINO...\n",
-      "generating graph from /tmp/tmpctgip1np\n",
-      "network' pkl is saved: /tmp/tmpctgip1np.pkl\n",
-      "done building network\n",
-      "generating subgraphs...\n",
-      "Before slicing: n of cc:7, n of nodes: 16920, n of edges, 238362\n",
-      "# of modules after extraction: 69\n",
-      "After slicing: n of cc:107, n of nodes: 7055, n of edges, 56982\n",
-      "subgraphs' pkl is saved\n",
-      "number of slices: 107\n",
-      "# of slices after perturbation TH: 4/107\n",
-      "4 relevant slices were retained with threshold 0.3\n",
-      "n of putative modules: 1\n",
-      "n of final modules: 1 (n=[13])\n",
-      "1 final modules are reported at /tmp/tmpqptdxutp/tmpq4jr44k8/modules.out\n",
-      "False\n",
-      "Setting the graph_diameter to the precomputed value of 8. Directly specify meta to overwrite this.\n",
-      "100%|█████████████████████████████████████████████| 1/1 [00:59<00:00, 59.06s/it]\n",
-      "100%|███████████████████████████████████████████| 1/1 [00:00<00:00, 1175.53it/s]\n",
-      "Saving weighted DIAMOnD: 0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "100%|█████████████████████████████████████████████| 1/1 [00:00<00:00, 15.60it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "100%|███████████████████████████████████████████| 1/1 [00:00<00:00, 8405.42it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n",
-      "PPI Network: 16918 nodes, 238361 edges\n",
-      "0it [00:00, ?it/s]\n"
-     ]
-    }
-   ],
-   "source": [
-    "!python src/main.py --thresholds"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "01e63699",
+   "id": "f62b61bc",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "!python src/main.py --thresholds"
+   ]
   }
  ],
  "metadata": {

disease_module_obtention/2_disease_module_identification/src/classical_methods/diamond_algorithm.py

@@ -3,11 +3,10 @@ import sys
 import tempfile
 import shutil
 
-# Add the folder containing DIAMOnD and DIAMOnD_mod to the path
 sys.path.append(os.path.abspath('./state_of_art_repos/DIAMOnD'))
 
-from DIAMOnD import run_diamond_from_args
-from DIAMOnD_mod import run_diamond_mod_from_args
+from DIAMOnD import run_diamond_from_args as run_diamond_from_args
+from DIAMOnD_weighted import run_diamond_weighted_from_args
 
 class DIAMOND:
     """
@@ -17,59 +16,22 @@ class DIAMOND:
         self.alpha = alpha
 
     def run_diamond(self, ppi_path: str, seed_file: str, n: int):
-        # Execute the standard DIAMOnD with network file, seed file, and number of additions
+        # standard DIAMOnD (all seeds weight = self.alpha)
         seed_genes, added_nodes = run_diamond_from_args([
             ppi_path,
             seed_file,
-            str(n)
+            str(n),
+            str(self.alpha)
         ])
-        # Collect unique added genes
-        added_genes = set(gene[0] for gene in added_nodes)
-        return {
-            'seed_nodes': list(seed_genes),
-            'module_nodes': list(added_genes)
-        }
-
-class DIAMOND_MOD:
-    """
-    Wrapper for the modified DIAMOnD algorithm used in thresholded runs.
-    This wrapper creates a temporary directory structure that DIAMOnD_mod expects,
-    invokes the algorithm, then cleans up.
-    """
-    def __init__(self, alpha=1):
-        self.alpha = alpha
-
-    def run_diamond(self, ppi_path: str, seed_file: str, n: int):
-        # 1) Create a temporary directory for seeds, with a subfolder 'score_default'
-        tmpdir = tempfile.mkdtemp(prefix="diamondmod_")
-        score_dir = os.path.join(tmpdir, "score_default")
-        os.makedirs(score_dir, exist_ok=True)
-
-        # 2) Extract the disease name from the seed_file basename
-        basename = os.path.basename(seed_file)  # e.g. 'seed_nodes_Disease.txt'
-        # Remove prefix 'seed_nodes_' and suffix '.txt'
-        disease = basename.replace("seed_nodes_", "").rsplit('.txt', 1)[0]
+        added = set(g[0] for g in added_nodes)
+        return {'seed_nodes': list(seed_genes), 'module_nodes': list(added)}
 
-        # 3) Copy and rename the seed file into the expected location
-        #    DIAMOnD_mod looks for 'seed_genes_<disease>.txt' in subfolders
-        dest_file = os.path.join(score_dir, f"seed_genes_{disease}.txt")
-        shutil.copy(seed_file, dest_file)
-
-        # 4) Call the modified DIAMOnD with the directory containing score_* subfolders
-        seed_genes, added_nodes = run_diamond_mod_from_args([
+    def run_diamond_weighted(self, ppi_path: str, seed_file: str, n: int):
+        # weighted DIAMOnD: seed_file has "gene<TAB>weight"
+        seed_genes, added_nodes = run_diamond_weighted_from_args([
             ppi_path,
-            tmpdir,
-            disease,
+            seed_file,
             str(n)
         ])
-
-        # 5) Clean up the temporary directory
-        shutil.rmtree(tmpdir)
-
-        # 6) Format and return results like the original DIAMOND wrapper
-        added_genes = set(gene[0] for gene in added_nodes)
-        return {
-            'seed_nodes': list(seed_genes),
-            'module_nodes': list(added_genes)
-        }
-
+        added = set(g[0] for g in added_nodes)
+        return {'seed_nodes': list(seed_genes), 'module_nodes': list(added)}

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Acanthosis Nigricans.txt

-P22607
-P06213

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Achromatopsia 1.txt

-Q9NQW8
-O75051
-Q9GZU5
-O60840
-P19087
-P26441
-Q6ZUT3
-Q6P4Q7
-Q9Y3T9
-Q16281
-P26367
-Q13956
-Q13057
-P08100
-Q9P2K1
-P51160
-Q8TC44
-Q9Y5X4
-P08842
-P18850

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Acoustic Neuroma.txt

-Q04609
-P80723
-Q14524
-Q15046
-P49815
-Q9NS23
-P01112
-P16070
-Q92508
-P14210
-P13473
-P12004
-P42345
-P35240
-Q13520
-Q14240
-P15056
-P61073
-Q6ZMJ4
-P01116
-Q96P20
-P01375
-Q9UNQ0
-P00403
-Q9NZQ7
-P10451
-Q99748
-Q15303
-P04626
-P04637
-P10644
-P42336
-Q9HBA0
-P30281
-Q8N653
-P10176
-P23560
-Q9BXM9
-P29323
-Q04637
-P05181
-P09211
-P17813
-Q9Y3B3
-P04040
-P15692
-P29474
-Q03135
-P00533
-P21860
-Q14790
-Q9BZC7
-P06400
-P39905
-O14786
-Q86XR7
-P55011
-P08253
-Q02297
-P10415
-Q8ND04
-Q92574
-P38936
-P32119
-Q86VB7
-Q99758
-P60842
-Q14533
-P01133
-P29972
-P08581
-P24385
-P07996
-P06730
-P19235
-P09603
-P04424
-P01588
-Q5T4W7
-P40305
-O97980
-P53667
-P41181
-O60232
-P55087
-P13612
-P35354
-P03372
-O43511
-Q86YT6
-Q96A00
-P52788
-P01135
-P46527
-P05231
-Q12824
-O14901
-Q13214
-Q9HC07
-P31749
-P10275
-P46013
-P04179
-P42771
-O00399
-Q12979
-P19544
-P09038
-P21359
-P51946
-Q86TG7
-P05230
-P01137
-Q9UBP5
-Q9BTV5
-Q86SH2
-O75462
-Q00987
-P42224
-P28482
-O43790
-P14780
-Q8N726
-P60484
-O00233

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Acute Promyelocytic Leukemia.txt

-O14733
-Q9P0V3
-P20930
-P20702
-P08700
-Q15464
-P06702
-P17676
-O95983
-Q6GMV2
-P11308
-Q96GD4
-Q9Y5W5
-P14210
-P40337
-Q9Y5K2
-O60260
-P13726
-P49841
-Q9H4L4
-P21980
-O76064
-O95059
-Q9UQ74
-P05161
-Q9UKV0
-P35573
-P41226
-P16442
-P42338
-P15391
-O94907
-Q9Y618
-P00395
-P32780
-P14635
-P04637
-Q96AH8
-Q9HBH0
-P17252
-P11362
-P28698
-P41134
-P50502
-Q9H3M7
-P29350
-P59666
-Q9NRI5
-Q5MNZ9
-Q9Y6K9
-Q9Y6Q9
-Q9H165
-Q9HC35
-P01215
-P11473
-Q969V5
-P05813
-Q92830
-P00740
-P13631
-Q9HBK9
-O60885
-P22004
-Q96J66
-P49736
-P10827
-P20585
-P07900
-O95352
-Q96QH2
-P10070
-O00220
-P01583
-P29590
-Q96BJ3
-O00470
-P31269
-P23219
-Q04206
-P33527
-P48023
-P01111
-O15067
-Q15910
-P40238
-Q96AD5
-P16220
-Q03112
-O14933
-P19526
-P05164
-P56159
-P23769
-Q12948
-Q14289
-Q99856
-Q13547
-Q9Y4H4
-Q9Y275
-P08138
-Q86UG4
-Q06124
-Q6ISU1
-Q13541
-P28340
-P37231
-Q9Y2Y4
-O75874
-P35354
-P16278
-P40933
-Q9UIK4
-P45983
-O43175
-Q7LBC6
-Q13948
-Q30201
-Q9H4A4
-Q07065
-Q86T82
-Q7LGC8
-P01584
-Q13427
-P20813
-P17861
-P14222
-P11465
-P31749
-O75956
-Q13162
-Q99835
-Q86YL7
-O60760
-P32248
-O14521
-Q9UJW0
-Q5T9L3
-P20248
-P04818
-P52630
-Q15004
-P07355
-O00144
-P10276
-Q02880
-P17948
-P11926
-P0DN86
-Q07812
-Q13794
-Q00532
-P28482
-Q9UIH9
-P17405
-P17931
-Q12778
-Q7RTS3
-P78396
-O43174
-P60484
-P46098
-P41222
-Q9Y4P8
-Q15125
-O14520
-O95936
-O15151
-P30044
-Q9H4X1
-Q14526
-O14727
-P35232
-Q96DB5
-Q9Y3B4
-P35659
-Q96AH0
-P01100
-O96019
-P52948
-O43663
-Q5JUW0
-Q12918
-P01375
-O96017
-Q16552
-P04626
-O15162
-Q8NFH3
-Q96HU1
-Q06546
-P27469
-P29323
-P05160
-P26358
-Q14469
-P47736
-Q9H2X6
-P02545
-P27361
-Q14790
-P06493
-Q15238
-P20393
-Q14764
-P08311
-P51397
-P55089
-P00742
-Q00978
-P21941
-P49639
-P63165
-P55073
-P10415
-P25445
-Q9Y222
-Q9P2Y5
-Q9Y2Q3
-Q9H9Z2
-Q8IZL9
-P40424
-Q9Y4J8
-Q13253
-Q15717
-P08238
-Q16649
-P49715
-P09917
-P20701
-P56945
-Q9H1Y0
-P13501
-P09683
-P13591
-P55273
-Q14683
-P48736
-Q96LZ7
-Q9P1W9
-Q09428
-P08670
-P00734
-Q96KQ7
-O00625
-O43524
-Q09472
-Q53EL6
-Q6UX65
-P16455
-Q15843
-Q92851
-P12724
-Q9Y6K1
-P46100
-P20138
-O60341
-P11215
-P39748
-Q8TC59
-P40763
-P49959
-Q8NB91
-P10912
-P50591
-Q6N021
-Q9UM07
-Q13478
-Q6W2J9
-P05231
-Q01196
-P50052
-P07204
-P10914
-P31358
-P54259
-P26651
-Q7Z5L9
-P00750
-P53999
-P10275
-P42771
-O14980
-P39880
-P78344
-Q7Z6L0
-Q8N264
-P55085
-P48735
-Q9Y4E5
-Q86TG7
-Q9BUK6
-P49711
-P05107
-P46531
-P19793
-P54253
-Q03111
-Q6UN15
-P25103
-P42224
-P15144
-Q9P2R6
-Q13501
-Q9UBB5
-P55854
-P25325
-Q9UL19
-Q8N726
-O14745
-Q14739
-P02786
-P11274
-P16871
-Q9H0R6
-Q9Y248
-Q13084
-Q9NS23
-P31249
-Q9BT92
-Q03252
-P30307
-P07333
-Q13564
-P06731
-Q5H9F3
-O60682
-P15056
-O75376
-Q02750
-P22083
-Q13323
-P54132
-P51828
-Q15303
-P22735
-Q86SQ9
-P42336
-O60503
-P37198
-P61956
-Q8N7E2
-P05362
-P46695
-Q9H2G9
-P24864
-Q16665
-P25791
-Q9UM73
-P09211
-P42773
-P10721
-P01911
-P08246
-Q9ULX5
-Q13526
-P27708
-Q02779
-Q8TDQ0
-Q16518
-P00533
-P63244
-P00441
-P10145
-Q92913
-P80370
-P18887
-P05204
-P04141
-Q16881
-P26718
-Q9HCS7
-Q9UBN6
-Q9GZP9
-P78395
-Q9BQQ3
-P14598
-P08151
-P78504
-O15350
-P30048
-Q14002
-Q16539
-P53355
-Q9H4A3
-P08571
-P20700
-P16473
-P19484
-Q8WXI8
-Q9H3D4
-O14497
-P98160
-P01133
-Q03164
-Q8IZQ1
-Q01094
-O15120
-O15205
-Q8WZ82
-P05109
-P58340
-O43918
-P16284
-Q9BVP2
-O00167
-O95361
-P41221
-P34810
-Q02556
-P41182
-P09382
-P10826
-Q9NX95
-Q9UBH6
-Q15672
-O14798
-P18440
-P12314
-P06748
-P15531
-Q9UKK6
-O15297
-Q03014
-P46527
-Q86U10
-P78317
-Q75NE6
-P22301
-P30203
-Q99612
-Q86V85
-P05112
-O60216
-Q8IXJ9
-P01137
-P00747
-P35227
-Q14116
-O75925
-Q08722
-Q9HD15
-P23458
-P36888
-P00492
-P63279
-P05114
-Q8WXS3
-Q96TC7
-Q13241
-P62333
-P78347
-Q8WUD6
-P10124
-P42684
-P60520
-P08631
-Q8N474
-Q06250
-P01106
-Q13342
-P23497
-P16070
-P07949
-P18146
-P09488
-Q969K3
-P28906
-Q9Y2Q5
-P60903
-Q53EP0
-Q9UMW8
-P61073
-P78357
-P01116
-P08758
-P08519
-Q96LR5
-Q16236
-Q9UIB8
-Q8IUI8
-Q8NFJ5
-P30711
-O00329
-P07741
-Q86UV5
-P10242
-P10644
-Q9NPF7
-P55081
-Q05516
-P51532
-P06401
-O75787
-Q5T5J6
-P42574
-P80098
-P15498
-P15692
-Q15744
-P16949
-P40198
-Q9Y5Y4
-Q76LX8
-P42229
-Q9UJU2
-P51580
-P05771
-P52790
-P39905
-P42772
-P02768
-Q9UER7
-P12643
-Q13671
-P04083
-P06729
-P50135
-P00488
-Q96DT0
-P17947
-P13928
-P00519
-P43004
-O15550
-O43315
-O75844
-P38936
-Q14980
-Q9NR12
-Q9UPP1
-P14652
-Q96Q27
-P61006
-Q9BZK7
-P01033
-O75592
-Q8NFD5
-O14746
-P51825
-P04049
-P07996
-Q96RU7
-Q07820
-P42566
-Q02363
-Q13950
-O15392
-Q7Z7K6
-P51692
-Q9UBX3
-Q15257
-P52798
-P11279
-P29762
-P49006
-P01579
-Q03169
-Q07666
-Q9UBW7
-P28907
-P08183
-Q01105
-P49913
-P51689
-P01135
-Q6ZT07
-Q15022
-P17936
-O14931
-Q5VT79
-P09619
-P12644
-P09919
-P38398
-P35610
-Q02548
-Q12829
-P21579
-P19544
-Q15466
-P08575
-Q68D85
-P16152
-Q06455
-P41212
-P07954
-P05451
-Q8N8S7
-Q92597
-P14780
-P12429
-P60709
-Q13485

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Acute gastroenteritis.txt

-P01584
-P12821
-Q9NP81
-Q2M385
-Q96JG9
-O15055
-P35555
-Q8N157
-P27352
-Q6UWY2
-Q9Y276
-Q12948
-Q15493
-O95832
-P12755
-P49591
-Q9BRG2
-O75298
-Q07654
-O75914
-P51606
-O95471
-Q92570
-Q9NZQ3
-Q5T5P2
-Q5M775
-P16442
-Q3V6T2
-O95255
-Q10981
-P22897
-O75815
-P15882
-Q9UPI3

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Acute leukemia.txt

-O14733
-P17181
-P08700
-P39019
-Q15596
-Q13761
-Q86VZ1
-Q9Y6D9
-Q9BXL5
-P0DJD1
-Q12866
-P11308
-Q92954
-O43324
-Q96GD4
-Q9NQS1
-Q14563
-Q15468
-Q16829
-P29375
-P25063
-O60675
-P35240
-Q9GZY0
-O75365
-P33151
-P14921
-Q9NX94
-Q13795
-Q9UKV0
-P18433
-P11226
-Q14C87
-P55075
-Q6P1Q0
-Q8TD46
-P16442
-Q9Y3D8
-P42338
-P15391
-O60353
-P04637
-P08842
-P11362
-P35237
-P62324
-Q9UPS8
-Q9H1B5
-P29350
-Q9UBP4
-Q9NR96
-P20815
-A8K2U0
-Q86X10
-P06881
-P51826
-P10599
-P62244
-Q99697
-P08865
-O95081
-Q8IUH3
-O60674
-Q6UW56
-P61254
-P00740
-Q14005
-O60885
-P13631
-O00548
-P42677
-P20585
-Q96QH2
-P50225
-P01583
-P35475
-P29590
-P55199
-P15976
-Q7L1I2
-Q86U70
-P31269
-O00470
-Q92574
-Q12884
-Q15154
-P33527
-P61964
-P01111
-Q15910
-P40238
-P47928
-Q15438
-Q96EB6
-P08473
-Q03112
-O14709
-P30679
-P05164
-P23769
-P06730
-Q9NZK5
-P31314
-Q14289
-P13051
-Q53HV7
-O43914
-P35251
-P35637
-O14627
-P56645
-P61313
-Q14994
-P08138
-Q86UG4
-Q06124
-P00540
-P62854
-Q8NBU5
-O00255
-P25800
-O75874
-Q13951
-Q13948
-Q2M3G0
-Q30201
-Q15306
-Q9UBK8
-P28908
-P49789
-P01584
-Q5XKL5
-Q9NZZ3
-P19525
-P20813
-P41586
-Q99873
-Q16667
-P19113
-Q14865
-Q8IWP9
-P31749
-O60760
-O60641
-P32248
-Q5T9L3
-P20248
-P04818
-P22681
-Q9UM11
-P55198
-P10276
-Q06945
-P17948
-Q07812
-P09601
-P40225
-Q00987
-Q9Y286
-P28482
-Q07020
-P20336
-P35453
-P12821
-P16104
-O15151
-Q9UP52
-Q9NWQ8
-Q9BR01
-O14727
-P54274
-P55017
-Q92835
-P52948
-P01375
-Q9UNQ0
-Q6J9G0
-Q92820
-P57679
-P02787
-P15516
-P59282
-O60936
-Q06609
-B0YJ81
-P08174
-P10398
-P03999
-P29323
-P30291
-P52823
-P98177
-P17813
-Q8N7R0
-Q92673
-Q92804
-Q9HD36
-Q06520
-Q92817
-P06400
-Q14764
-P08311
-Q9BSI4
-Q9NW38
-Q13625
-P51397
-P51878
-P00742
-Q01844
-O14786
-P01282
-P42568
-P08253
-P10415
-P25445
-P04629
-Q9Y222
-P17693
-P41217
-Q9Y2Q3
-Q9H9Z2
-P04798
-P40424
-P04440
-P50539
-Q6RUI8
-Q02083
-P18031
-P09683
-P46777
-P08620
-P13591
-Q8WUF5
-Q15554
-Q6IAA8
-Q9BXW9
-P55273
-O95456
-P48736
-Q9P1W9
-Q93052
-P27797
-Q9Y2B2
-P01258
-P00734
-P11586
-Q96KQ7
-P27487
-Q09472
-P16455
-Q9Y6K1
-Q8WWQ2
-Q96T37
-P46100
-P20138
-O60341
-P34925
-Q15773
-P47974
-P35318
-P40763
-Q9UIQ6
-P78415
-Q8NB91
-P50591
-Q6N021
-P0DP23
-P05231
-Q9UQ26
-Q01196
-Q99626
-P10914
-P54259
-O00501
-P53999
-P42771
-P39880
-P17542
-Q8N264
-O15438
-P78310
-P18065
-Q16270
-P48735
-Q9UGL1
-Q96BS2
-O00206
-O95453
-P46531
-P09429
-Q92794
-P04003
-Q9Y6Q2
-Q92945
-P15036
-Q9Y2S2
-Q03111
-Q7L266
-Q6UN15
-P25103
-P42224
-Q9UHD8
-Q9HD64
-Q14774
-Q13018
-Q14814
-Q8N726
-P57723
-P55157
-Q14739
-P02786
-Q5DJT8
-P11274
-P16871
-P14784
-Q92832
-Q13084
-Q9Y235
-P49815
-P17483
-Q9BT92
-P46783
-P62273
-P07333
-P23771
-P12004
-P15923
-P40189
-P04280
-P15056
-O75376
-P22083
-P13569
-P20809
-P54132
-P20366
-P51681
-Q16517
-P13942
-Q86SQ9
-P42336
-O95841
-Q16658
-P62913
-P62380
-P29017
-Q5VWP3
-P25791
-Q16665
-O43711
-P0DMV1
-Q9UM73
-P09211
-P42773
-P12259
-P10721
-P51587
-P01911
-O94915
-P14679
-Q15696
-P00533
-P20333
-Q08257
-Q07955
-Q9UQQ2
-P02751
-Q5ZPR3
-P18887
-P04141
-P21741
-P35579
-P78395
-P24468
-Q05923
-P01889
-Q8IZP0
-Q7Z7C8
-P08151
-Q96T68
-O15350
-P42898
-P53350
-Q13422
-P02788
-P08571
-Q07011
-P01563
-Q03164
-Q99732
-Q00597
-P09874
-O15527
-P04004
-Q13315
-P04439
-P58340
-Q9UH73
-Q99062
-P41221
-Q03701
-P42704
-Q02556
-P09382
-P16591
-P16035
-P32320
-Q92793
-O14508
-Q05932
-P04216
-O75533
-P06748
-P10321
-Q9UKK6
-P15559
-P0DP25
-P48551
-Q86U10
-P28072
-Q75NE6
-P22301
-O60264
-P21439
-P01374
-Q9NR09
-P30203
-Q99612
-Q969E8
-Q15375
-Q5T4F7
-O15516
-P05112
-Q8IXJ9
-P35226
-P61163
-P11912
-Q14116
-P25391
-P23458
-P36888
-P00492
-P63279
-P16581
-Q8WXS3
-P62081
-P12980
-Q9NP58
-P46087
-P42768
-P23528
-P20273
-O15164
-Q70J99
-Q06250
-P13747
-P01106
-Q13426
-P16234
-O14763
-P41180
-P04275
-P09488
-P43626
-Q9H0R1
-P28906
-P01562
-Q9BX66
-Q08050
-P08708
-Q13492
-P61073
-P78357
-P62847
-P01116
-P04000
-P05113
-Q13617
-O60934
-P11245
-P49917
-P30711
-O00329
-P10242
-P10644
-Q9NPF7
-P35222
-P09651
-P23560
-P10176
-P46937
-P18074
-Q9H0G5
-P11388
-P08684
-P16410
-Q86UK5
-Q12974
-Q12983
-P15692
-Q15744
-P16949
-Q05195
-Q01518
-Q07954
-Q96RU8
-P42229
-Q16186
-Q9NX02
-Q9UJU2
-P51580
-P42772
-P14317
-Q9HC29
-P55197
-P13928
-P00519
-Q9BYW2
-Q9UBN7
-P36575
-P43246
-Q8TCX1
-Q8IWZ3
-Q96P11
-P55265
-Q2M1K9
-P42766
-O15524
-O43490
-P18077
-P29965
-P01344
-Q8TF68
-P51825
-P28370
-P24385
-P13987
-Q07820
-P60568
-P51692
-P01241
-Q13505
-P00374
-O60858
-P25490
-P0DMV2
-P48357
-P61353
-Q9NZC2
-Q13015
-P41159
-P13612
-Q14542
-O75475
-P43652
-P49006
-P05067
-P28907
-P08183
-P11802
-P0DP24
-Q01105
-P06753
-Q6ZT07
-Q8NFT8
-O60603
-Q16625
-O43516
-Q12824
-Q5VT79
-Q9NZ71
-P09919
-O00481
-P38398
-Q02548
-P35610
-Q9UQ90
-Q02952
-Q9C000
-P19544
-Q9H3R0
-Q15466
-P08575
-P10635
-Q14457
-P17812
-P21359
-Q06455
-P01303
-P41212
-P35749
-Q9Y251
-P05451
-Q9ULB4
-P13611
-Q9C0K0
-P48061
-O14544
-P51816
-P62857
-P62979
-Q8TEK3
-P60709
-Q9UNN4

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Ataxias, Hereditary.txt

-O76024
-Q7Z333
-P49638
-P11166
-O14773
-Q9H173
-Q8N2K0
-Q16595

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Bronchiolitis, Viral.txt

-P02778

disease_module_obtention/2_disease_module_identification/src/inputs/seed_nodes_Hypertrophic Cardiomyopathy.txt

-Q9ULZ1
-O76041
-Q13427
-Q02750
-O75792
-O00483
-O75306
-P19429
-Q9H9J2
-Q14116
-O75112
-Q969Y2
-Q9NW38
-O95822
-O00329
-P31645
-Q9NPD8
-P18206
-Q9NX95
-Q9UBP5
-Q9NSU2
-P14854
-P01308
-O75489
-O15239
-Q9HD89
-P29323
-O00400
-P24844
-O00622
-Q06124
-Q14126
-Q02817
-P01889
-Q8N7E2
-P29475
-P06280
-P04406
-P26447
-Q9UI09
-Q9Y4P3
-Q96P66
-Q9Y6M9
-Q9BYV6
-Q9UQ13
-P56556
-Q53S33
-P30084
-P07951
-Q8NBP7
-Q969V5
-Q96G97
-Q9UDT6
-P17655
-O60936
-P19105
-Q92963
-Q12887
-P01100
-P20472
-Q92889
-O43451
-P10321
-Q86SK9
-P51532
-P20800
-O60706
-P39060
-O15287
-Q8TCY5
-Q13423
-P48736
-P16671
-P13987
-Q5JWF2
-Q8IY92
-P15531
-Q9BU61
-P10809
-Q99959
-P16615
-Q96I36
-P05305
-P51790
-Q05195
-O14958
-O76082
-Q06587
-Q9H8M7
-P49638
-P02545
-P24311
-P05362
-Q9UH92
-Q92736
-P01189
-P09493
-O75072
-P19099
-Q01094
-P48995
-P08590
-P17931
-O14521
-P50461
-Q13093
-P53667
-O95390
-P05976
-P17936
-P29460
-P03905
-P00403
-Q9Y6C7
-O43502
-Q01718
-P56381
-O75880
-Q8TB37
-Q6NXT6
-Q06413
-P25490
-Q96IL0
-P48735
-Q13118
-P56539
-P0DJ07
-P04049
-O43678
-P48029
-P52179
-Q8N653
-P03923
-P49675
-P02585
-Q00872
-P84996
-P13533
-Q96RL7
-P09601
-P04439
-Q92558
-Q9P232
-P10415
-Q9P032
-P10599
-P53597
-Q86WW8
-O00300
-Q9UKP3
-Q9H270
-Q14896
-Q9P0J0
-P35609
-Q30201
-Q86TC9
-Q9NQX0
-Q15831
-Q6P5Q4
-Q96DP5
-P45379
-O00767
-Q5JTJ3
-Q02078
-P31749
-P08588
-P28330
-P16035
-P00846
-P19404
-P08123
-P07741
-P35318
-Q9Y2Z2
-P51689
-Q15746
-P12883
-Q9NVI7
-P15056
-P02511
-P19634
-Q92905
-Q5ST30
-Q9BXW9
-Q5JTZ9
-O00206
-Q9H0R6
-O60313
-Q16665
-Q96AC1
-P09622
-P02766
-Q9UL12
-P04440
-Q9BSH4
-P10144
-Q6TFL4
-Q16584
-P41595
-Q8NB12
-Q14192
-Q9BQ52
-P37231
-P83436
-P12724
-P12821
-P04275
-P50052
-P62508
-Q92574
-P00797
-P38606
-Q92769
-P27361
-Q92570
-P49821
-Q2V2M9
-P08559
-P12829
-P30556
-Q14324
-Q13085
-Q9UBK2
-Q9BZQ4
-P63316
-P42338
-O15360
-P17661
-Q9BUP3
-Q9BXM9
-Q08289
-Q16891
-Q330K2
-Q06609
-P04637
-O95817
-Q15046
-P22301
-P40939
-Q53GG5
-Q8NB91
-P68363
-P17050
-Q14524
-Q9BT22
-P12955
-Q96HC4
-P00395
-P06753
-P55081
-P42345
-Q96FA3
-O43766
-Q9NPI8
-O00217
-Q9HB96
-P51787
-Q15526
-O00170
-P41180
-P31040
-Q14683
-P62753
-P60174
-P51884
-Q12926
-O14807
-P01116
-P42336
-Q53H12
-Q96TC7
-Q8IYD8
-Q92629
-P01185
-P05019
-Q9NSE4
-Q9BYX4
-P17302
-P28482
-P49748
-P62140
-Q7Z406
-P38398
-P53701
-Q9Y234
-P08833
-P51671
-Q9P0K1
-Q00325
-P62736
-P14410
-Q9UMX1
-O95319
-Q3T906
-Q6PCD5
-Q5TEU4
-P27797
-P01137
-P01375
-P98161
-O75251
-Q96H96
-P60709
-Q0ZGT2
-F8WCM5
-P24723
-P04216
-Q9BUB7
-O60260
-P09001
-O75052
-P08235
-Q8TDP1
-O95467
-Q86Y39
-P00156
-P21359
-Q9BTV5
-Q99731
-Q9NX14
-Q01105
-P23560
-O95299
-O95997
-P23946
-P30988
-P00414
-Q9UI95
-P41252
-O95169
-P01111
-P42658
-P16930
-P58546
-Q14164
-P16278
-Q03164
-P54652
-P08397
-Q8WXI7
-P40763
-P68133
-P15692
-P13866
-P50416
-Q13203
-Q96CU9
-Q53HV7
-Q5SZL2
-Q92879
-O75347
-P13473
-P49796
-Q8N5M1
-Q9Y3Q4
-P29474
-P35219
-P01160
-P10646
-Q5RI15
-Q8N183
-Q9UPT6
-Q8NEB9
-P47972
-P04792
-Q16795
-Q96LZ7
-P42166
-Q13315
-Q99797
-Q9Y5Y9
-P10176
-Q13467
-Q9NZJ5
-O96000
-Q10713
-Q13131
-P10253
-Q8TF45
-Q96AX1
-P43694
-Q9NPC6
-P02462
-P30626
-Q14692
-P49888
-Q9UHL9
-Q86SG6
-P53805
-P01344
-Q9Y375
-Q9NPL8
-P43405
-Q969Q1
-O95528
-Q9NNW7
-O15305
-Q9BZV2
-Q99684
-P02741
-Q9H1R3
-Q9BX63
-O60941
-P08069
-Q9UP38
-Q13936
-Q9UGJ0
-Q99572
-Q5VST9
-P01130
-O43181
-Q9Y5Y7
-Q9BYF1
-P14780
-Q13424
-P08253
-Q9H845
-Q99873
-Q9UI47
-O43676
-A6NFY7
-Q9NS23
-Q9BTV4
-P04150
-Q9HCF6
-P07900
-P26678
-Q9Y376
-P28331
-P36507
-Q16595
-Q99714
-P01106
-Q03135
-P50402
-Q9BR39
-Q15327
-O15431
-P06213
-Q9Y276
-P68032
-Q8WXH0
-Q6XR72
-P50221
-P35250
-O15120
-Q7KZN9
-P78347
-Q8WZ42
-P10916
-Q96DB5
-Q09013
-O43819
-O75164
-Q702N8
-Q16836
-O75380
-Q6UUV9
-Q00597
-Q99996
-P42167
-Q6NZI2
-Q9NYY8
-P15924
-Q8IZQ8
-Q13642
-Q96A33
-O60783
-P16066
-O14950
-P03897
-Q86WJ1
-P15502
-O15273
-Q96L96
-O43543
-P03372
-P16442
-Q9UIG0
-Q16635
-Q8IVG9
-P51504
-P21912
-P49327
-P03891
-P12235
-P02810
-P55265
-Q9Y3Z3
-Q8IUX1
-Q99988
-Q14315
-P03886
-Q86YQ2
-P49006
-P01112
-Q96L12
-P03915
-P51587
-A4UGR9
-P16860
-Q9NVI1
-P51449
-Q86VF7
-P42574
-O14793
-P04280
-P82650
-Q9C0B1
-Q01449
-Q15842
-Q5TBB1
-P63092
-Q8NF91
-P10275
-P01019
-Q86YC2
-Q13164
-Q07889
-P02452
-Q9H7Z6

disease_module_obtention/2_disease_module_identification/state_of_art_repos/DIAMOnD/DIAMOnD_mod.py

@@ -263,38 +263,3 @@ def run_diamond_mod_from_args(args=None):
 #
 # ===========================================================================
 
-
-if __name__ == '__main__':
-
-
-    # -----------------------------------------------------
-    # Checking for input from the command line:
-    # -----------------------------------------------------
-    #
-    # [1] file providing the network in the form of an edgelist
-    #     (tab-separated table, columns 1 & 2 will be used)
-    #
-    # [2] file with the seed genes (if table contains more than one
-    #     column they must be tab-separated; the first column will be
-    #     used only)
-    #
-    # [3] number of desired iterations
-    #
-    # [4] (optional) seeds weight (integer), default value is 1 
-    # [5] (optional) name for the results file 
-
-    #check if input style is correct
-    input_list = sys.argv
-    network_edgelist_file,seeds_file,max_number_of_added_nodes,alpha,outfile_name= check_input_style(input_list)
-    
-    # read the network and the seed genes:
-    G_original,seed_genes = read_input(network_edgelist_file,seeds_file)
-    
-    # run DIAMOnD
-    added_nodes = DIAMOnD(G_original,
-                          seed_genes,
-                          max_number_of_added_nodes,alpha,
-                          outfile=outfile_name)
-    
-    print("\n results have been saved to '%s' \n" %outfile_name)
-

disease_module_obtention/2_disease_module_identification/state_of_art_repos/DIAMOnD/DIAMOnD_weighted.py

+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+A DIAMOnD implementation with individual seed weights per gene.
+Seeds file must have two columns: gene_id and weight (integer).
+"""
+import copy
+import csv
+import pickle
+import sys
+import time
+from collections import defaultdict
+
+import networkx as nx
+import numpy as np
+import scipy.stats
+
+# =============================================================================
+def print_usage():
+    print(' ')
+    print('        usage: ./DIAMOnD_weighted network_file seed_file n outfile_name')
+    print('        -----------------------------------------------------------------')
+    print('        network_file : path to PPI edgelist (any delimiter)')
+    print('        seed_file    : table with gene_id and weight columns')
+    print('        n            : number of DIAMOnD genes to add')
+    print('        outfile_name : destination for results')
+    print(' ')
+
+# =============================================================================
+def check_input_style(input_list):
+    try:
+        network_file = input_list[1]
+        seed_file = input_list[2]
+        max_added = int(input_list[3])
+    except:
+        print_usage()
+        sys.exit(0)
+
+    outfile = None
+    if len(input_list) >= 5:
+        outfile = input_list[4]
+    else:
+        outfile = f'first_{max_added}_weighted_nodes.txt'
+    return network_file, seed_file, max_added, outfile
+
+# =============================================================================
+def read_input(network_file, seed_file):
+    """
+    Reads network and weighted seed genes.
+    Seeds file must have two columns: gene_id and weight.
+    """
+    # --- read network
+    G = nx.Graph()
+    sniffer = csv.Sniffer()
+    delim = None
+    # detect delimiter
+    for line in open(network_file, 'r'):
+        if line.startswith('#'): continue
+        delim = sniffer.sniff(line).delimiter
+        break
+    if delim is None:
+        print('Bad network file format'); sys.exit(1)
+    for line in open(network_file, 'r'):
+        if line.startswith('#'): continue
+        parts = line.strip().split(delim)
+        G.add_edge(parts[0], parts[1])
+
+    # --- read weighted seeds
+    seed_weights = {}
+    for line in open(seed_file, 'r'):
+        if line.startswith('#'): continue
+        parts = line.strip().split()  # whitespace or tab
+        gene = parts[0]
+        try:
+            wt = int(parts[1])
+        except:
+            wt = 1
+        seed_weights[gene] = wt
+
+    return G, seed_weights
+
+# =============================================================================
+def compute_all_gamma_ln(N):
+    gamma_ln = {}
+    for i in range(1, N+1):
+        gamma_ln[i] = scipy.special.gammaln(i)
+    return gamma_ln
+
+# =============================================================================
+def logchoose(n, k, gamma_ln):
+    if n-k+1 <= 0:
+        return np.inf
+    return gamma_ln[n+1] - (gamma_ln[k+1] + gamma_ln[n-k+1])
+
+# =============================================================================
+def gauss_hypergeom(x, r, b, n, gamma_ln):
+    return np.exp(
+        logchoose(r, x, gamma_ln) +
+        logchoose(b, n-x, gamma_ln) -
+        logchoose(r+b, n, gamma_ln)
+    )
+
+# =============================================================================
+def pvalue(kb, k, N, s, gamma_ln):
+    p = 0.0
+    for n in range(kb, k+1):
+        if n > s: break
+        p += gauss_hypergeom(n, s, N-s, k, gamma_ln)
+    return min(p, 1)
+
+# =============================================================================
+def get_neighbors_and_degrees(G):
+    neighbors = {}
+    degrees = {}
+    for node in G.nodes():
+        neighbors[node] = set(G.neighbors(node))
+        degrees[node] = G.degree(node)
+    return neighbors, degrees
+
+# =============================================================================
+def reduce_not_in_cluster_nodes(all_degrees, neighbors, not_in_cluster, cluster_weights):
+    """
+    Reduce candidates by weighted degree computations.
+    """
+    kb2k = defaultdict(dict)
+    for node in not_in_cluster:
+        k_base = all_degrees[node]
+        # weighted connections to cluster
+        kb = sum(cluster_weights.get(nei, 1) for nei in neighbors[node] if nei in cluster_weights)
+        weight = cluster_weights.get(node, 1)
+        # adjust k and kb by weight influence
+        k = k_base + (weight - 1) * kb
+        kb = kb + (weight - 1) * kb
+        kb2k[kb][k] = node
+    # select best per k
+    reduced = {}
+    for kb, k2node in kb2k.items():
+        min_k = min(k2node.keys())
+        node = k2node[min_k]
+        reduced[node] = (kb, min_k)
+    return reduced
+
+# =============================================================================
+def diamond_iteration_of_first_X_nodes(G, seed_weights, X):
+    """
+    Core DIAMOnD loop with weighted seeds.
+    seed_weights: dict gene->weight
+    """
+    N = G.number_of_nodes()
+    neighbors, degrees = get_neighbors_and_degrees(G)
+
+    # initial cluster weights
+    cluster_weights = seed_weights.copy()
+    s0 = sum(cluster_weights.values())
+    N_adj = N + sum((w-1) for w in seed_weights.values())
+
+    gamma_ln = compute_all_gamma_ln(N_adj + 1)
+
+    not_in_cluster = set()
+    for gene in cluster_weights:
+        not_in_cluster |= neighbors.get(gene, set())
+    not_in_cluster -= set(cluster_weights.keys())
+
+    added_nodes = []
+    all_p = {}
+
+    while len(added_nodes) < X:
+        reduced = reduce_not_in_cluster_nodes(degrees, neighbors, not_in_cluster, cluster_weights)
+        pmin = 1.1
+        next_node = None
+        info = {}
+        for node, (kb, k) in reduced.items():
+            key = (k, kb, s0)
+            p = all_p.get(key) or pvalue(kb, k, N_adj, s0, gamma_ln)
+            all_p[key] = p
+            if p < pmin:
+                pmin = p
+                next_node = node
+            info[node] = (k, kb, p)
+
+        if pmin > 0.05:
+            print(f"Stopping early at iteration {len(added_nodes)}: p-value = {pmin:.4f}")
+            break
+
+        # record addition
+        added_nodes.append((next_node, info[next_node][0], info[next_node][1], info[next_node][2]))
+        # update cluster
+        weight_next = seed_weights.get(next_node, 1)
+        cluster_weights[next_node] = weight_next
+        s0 += weight_next
+        not_in_cluster |= (neighbors[next_node] - set(cluster_weights.keys()))
+        not_in_cluster.discard(next_node)
+
+    return added_nodes
+
+# =============================================================================
+def DIAMOnD(G_original, seed_weights, max_nodes, outfile):
+    """
+    Runs weighted DIAMOnD and writes results to outfile.
+    """
+    all_genes = set(G_original.nodes())
+    seeds = {g: w for g, w in seed_weights.items() if g in all_genes}
+    if len(seeds) < len(seed_weights):
+        missing = set(seed_weights) - all_genes
+        print(f"Ignoring {len(missing)} seeds not in network: {missing}")
+
+    added = diamond_iteration_of_first_X_nodes(G_original, seeds, max_nodes)
+    # save output
+    with open(outfile, 'w') as fout:
+        fout.write('#rank\tDIAMOnD_node\n')
+        for rank, (node, k, kb, p) in enumerate(added, 1):
+            fout.write(f"{rank}\t{node}\n")
+    return list(seeds.keys()), added
+
+# =============================================================================
+def run_diamond_weighted_from_args(args=None):
+    if args is None:
+        args = sys.argv
+    else:
+        args = ['DIAMOnD_weighted.py'] + args
+    netf, seedf, n, outfile = check_input_style(list(args))
+    G, seed_weights = read_input(netf, seedf)
+    return DIAMOnD(G, seed_weights, n, outfile)
+
+if __name__ == '__main__':
+    run_diamond_weighted_from_args()

significance_analysis/significance_diamond.csv

-disease,score,n_input,n_used,zscore,pvalue,lcc_size,significance
-Acanthosis Nigricans,0.0,200,200,8.595609719180702,0.0,200,True
-"Bronchiolitis, Viral",0.0,200,200,5.550186398118612,0.0,199,True
-Acanthosis Nigricans,0.1,200,200,7.800835882837143,0.0,196,True

significance_analysis/significance_domino.csv

-disease,score,n_input,n_used,zscore,pvalue,lcc_size,significance
-Acanthosis Nigricans,0.0,70,70,12.232261486730968,0.0,70,True
-Acanthosis Nigricans,0.1,48,48,21.549552001770667,0.0,48,True
-"Bronchiolitis, Viral",0.0,13,13,8.036465189401895,0.0,13,True

significance_analysis/significance_lcc.csv

-disease,score,n_input,n_used,zscore,pvalue,lcc_size,significance
-Acanthosis Nigricans,0.0,63,63,3.7791431444824575,0.001,27,True
-Acanthosis Nigricans,0.0,27,27,7.301711700487385,0.0,27,True
-"Bronchiolitis, Viral",0.0,13,13,-0.8026240370093498,1.0,1,False
-"Bronchiolitis, Viral",0.0,1,1,,1.0,1,False
-Acanthosis Nigricans,0.1,37,37,5.233075002125382,0.0,11,True
-Acanthosis Nigricans,0.1,11,11,10.192777957538603,0.0,11,True

significance_analysis/significance_robust.csv

-disease,score,n_input,n_used,zscore,pvalue,lcc_size,significance
-Acanthosis Nigricans,0.0,76,76,3.1402920979607636,0.0,50,True
-"Bronchiolitis, Viral",0.0,22,22,5.0654874160779215,0.001,8,True
-Acanthosis Nigricans,0.1,47,47,5.365588705196455,0.0,29,True

significance_analysis/significance_topas.csv

-disease,score,n_input,n_used,zscore,pvalue,lcc_size,significance
-Acanthosis Nigricans,0.0,85,85,6.82410673243988,0.0,85,True
-"Bronchiolitis, Viral",0.0,23,23,11.312913145300755,0.0,23,True
-Acanthosis Nigricans,0.1,53,53,5.512634412249499,0.0,53,True