initial commit

936a9ff9 · Gerardo Lagunes García · 936a9ff9 · 936a9ff9 · 936a9ff9 · 936a9ff9
Commit 936a9ff9 authored Oct 24, 2018 by Gerardo Lagunes García
18 changed files
--- a/DKE_RetrievedInTheSnapshotOf_2018-04-15.csv
+++ b/DKE_RetrievedInTheSnapshotOf_2018-04-15.csv
--- a/DKE_RetrievedInTheSnapshotOf_2018-08-15.csv
+++ b/DKE_RetrievedInTheSnapshotOf_2018-08-15.csv
--- a/Diseases_and_their_number_of_disease_findings.csv
+++ b/Diseases_and_their_number_of_disease_findings.csv
--- a/External_Vocabulary_Found.csv
+++ b/External_Vocabulary_Found.csv
+Code;Name
+78;ALFRED
+103;Aliases
+80;AO
+105;AO Foundation
+108;BRENDA
+76;CAS Number
+81;CAS number
+89;ChEBI
+97;ChEMBL
+94;ChemSpider
+77;Code
+122;CSP
+83;dbSNP
+92;DiseasesDB
+59;Dorlands /Elsevier
+95;DrugBank
+57;EC number
+70;ECHA InfoCard
+62;eMedicine
+113;Ensembl
+114;Entrez
+107;ExPASy
+61;External IDs
+98;FMA
+79;GARD
+69;Gene Ontology
+90;GeneReviews
+52;HapMap
+63;HgenetInfoDB
+65;HUGO
+53;ICD-10
+124;ICD-10-CM
+118;ICD-9
+60;ICD-9-CM
+54;ICD-O
+110;IntEnz
+55;InterPro
+88;IUPHAR/BPS
+67;KEGG
+58;MedlinePlus
+75;MeSH
+101;MetaCyc
+82;NCI
+74;NeuroLex ID
+66;NORD
+72;OMIM
+99;Orphanet
+96;Orthobullets
+116;OrthoInfo
+87;Patient UK
+112;PDB structures
+102;Pfam
+84;Pfam clan
+115;PRIAM
+56;PROSITE
+93;PubChem CID
+73;Radiopaedia
+109;Radiopedia
+85;RefSeq
+71;Rfam
+64;SCOP
+120;SNOMED_CT
+68;SNPedia
+111;SUPERFAMILY
+104;TA
+119;TE
+106;TH
+121;UMLS
+100;UNII
+86;UniProt
+91;Wheeless Online
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-02-01.csv
+++ b/Information_per_metric_for_each_snapshot/2018-02-01.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;8,161
Articles that contained diagnostic knowledge elements (from EMF process);3,881
Diagnostic knowledge elements (DKE) found (no duplicates);9,937
UMLS semantic types found (no duplicates);11
Disease codes found (no duplicates);19,229
External vocabularies found (no duplicates);64
Number of texts (no duplicates);31,126
Number of links found in the texts;149,368
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-02-15.csv
+++ b/Information_per_metric_for_each_snapshot/2018-02-15.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;8,161
Articles that contained diagnostic knowledge elements (from EMF process);3,889
Diagnostic knowledge elements (DKE) found (no duplicates);9,953
UMLS semantic types found (no duplicates);11
Disease codes found (no duplicates);19,187
External vocabularies found (no duplicates);63
Number of texts (no duplicates);31,203
Number of links found in the texts;149,802
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-03-01.csv
+++ b/Information_per_metric_for_each_snapshot/2018-03-01.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;8,161
Articles that contained diagnostic knowledge elements (from EMF process);3,907
Diagnostic knowledge elements (DKE) found (no duplicates);11,697
UMLS semantic types found (no duplicates);15
Disease codes found (no duplicates);19,141
External vocabularies found (no duplicates);62
Number of texts (no duplicates);31,393
Number of links found in the texts;150,528
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-03-15.csv
+++ b/Information_per_metric_for_each_snapshot/2018-03-15.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;8,161
Articles that contained diagnostic knowledge elements (from EMF process);3,917
Diagnostic knowledge elements (DKE) found (no duplicates);11,731
UMLS semantic types found (no duplicates);15
Disease codes found (no duplicates);19,127
External vocabularies found (no duplicates);63
Number of texts (no duplicates);31,657
Number of links found in the texts;151,794
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-04-01.csv
+++ b/Information_per_metric_for_each_snapshot/2018-04-01.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;9,857
Articles that contained diagnostic knowledge elements (from EMF process);4,155
Diagnostic knowledge elements (DKE) found (no duplicates);11,889
UMLS semantic types found (no duplicates);15
Disease codes found (no duplicates);19,327
External vocabularies found (no duplicates);65
Number of texts (no duplicates);158,574
Number of links found in the texts;159,097
\ No newline at end of file
--- a/Information_per_metric_for_each_snapshot/2018-04-15.csv
+++ b/Information_per_metric_for_each_snapshot/2018-04-15.csv
+Metric;Count
Articles categorized as disease in DBpedia (DDLE process) ;9,858
Articles that contained diagnostic knowledge elements (from EMF process);4,163
Diagnostic knowledge elements (DKE) found (no duplicates);12,571
UMLS semantic types found (no duplicates);16
Disease codes found (no duplicates);19,314
External vocabularies found (no duplicates);65
Number of texts (no duplicates);33,263
Number of links found in the texts;159,097
\ No newline at end of file
--- a/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/AllArticlesDBPedia.csv
+++ b/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/AllArticlesDBPedia.csv
--- a/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/DBpediaArticlesNotBeenConsidereDiseases(withoutCodes).csv
+++ b/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/DBpediaArticlesNotBeenConsidereDiseases(withoutCodes).csv
--- a/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/WikipediaArticlesBeenConsideredAsDiseases(withOneCodesOrOneTexts).csv
+++ b/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/WikipediaArticlesBeenConsideredAsDiseases(withOneCodesOrOneTexts).csv
--- a/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/WikipediaArticlesNotBeenConsideredAsDiseases(withoutCodesOrTexts).csv
+++ b/articles_that_have_been_retrieved_as_diseases_in_DBpedia_but_have_not_been_considered_as_diseases/WikipediaArticlesNotBeenConsideredAsDiseases(withoutCodesOrTexts).csv
--- a/enfermedadesOMIMEnWikipedia.xlsx
+++ b/enfermedadesOMIMEnWikipedia.xlsx
--- a/getDiseases.sparql
+++ b/getDiseases.sparql
+PREFIX dcterms: <http://purl.org/dc/terms/>
+PREFIX category: <http://dbpedia.org/resource/Category:>
+PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> 
+SELECT DISTINCT ?d ?dn ?wikiPage ?icd9 ?icd10 ?disDB ?meshID ?mlp ?omim ?emed ?frbase 
+WHERE {
+	?d a <http://dbpedia.org/ontology/Disease>.
+	?d foaf:isPrimaryTopicOf ?wikiPage.
+	OPTIONAL { ?d <http://dbpedia.org/ontology/icd9> ?icd9. }
+	OPTIONAL { ?d <http://dbpedia.org/ontology/icd10> ?icd10. }
+	OPTIONAL { ?d <http://dbpedia.org/ontology/diseasesDb> ?disDB. }
+	OPTIONAL { ?d <http://dbpedia.org/ontology/meshId> ?meshID. }
+	OPTIONAL { ?d <http://dbpedia.org/property/medlineplus> ?mlp. }
+	OPTIONAL { ?d <http://dbpedia.org/ontology/omim> ?omim. }
+	OPTIONAL { ?d <http://dbpedia.org/property/emedicinetopic> ?emed. }
+	OPTIONAL {
+  		?d owl:sameAs ?frbase.
+  		FILTER(regex(str(?frbase), "freebase", "i")).
+	}
+        OPTIONAL {
+                ?d rdfs:label ?dn.
+                FILTER (lang(?dn) = 'en')
+        }
+}
\ No newline at end of file
--- a/getDiseasesDisGeNET.sparql
+++ b/getDiseasesDisGeNET.sparql
+SELECT DISTINCT str(?umlsID) as ?umlsID, 
+                        str(?diseasename) as ?diseasename
+        WHERE { 
+            ?disease a ncit:C7057, sio:SIO_010299;
+                      sio:SIO_000008 <http://purl.bioontology.org/ontology/STY/T047>;
+                      dcterms:identifier ?umlsID;
+                      dcterms:title ?diseasename}
+        ORDER BY (?umlsID)
\ No newline at end of file
--- a/getDiseasesMesh.sparql
+++ b/getDiseasesMesh.sparql
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX meshv: <http://id.nlm.nih.gov/mesh/vocab#>
+PREFIX mesh: <http://id.nlm.nih.gov/mesh/>
+PREFIX mesh2015: <http://id.nlm.nih.gov/mesh/2015/>
+PREFIX mesh2016: <http://id.nlm.nih.gov/mesh/2016/>
+PREFIX mesh2017: <http://id.nlm.nih.gov/mesh/2017/>
+ SELECT DISTINCT count(?d)
+ FROM <http://id.nlm.nih.gov/mesh>
+ WHERE {
+ ?d a meshv:Descriptor .
+ ?d meshv:treeNumber ?tn .     
+ FILTER(REGEX(?tn,".*C01.*|.*C02.*|.*C03.*|.*C04.*|.*C05.*|.*C06.*|.*C07.*|.*C08.*|.*C09.*|.*C010.*|.*C011.*|.*C012.*|.*C013.*|.*C014.*|.*C015.*|.*C016.*|.*C017.*|.*C018.*|.*C019.*|.*C020.*|.*C021.*|.*C023.*|.*C024.*|.*C025.*|.*C026.*|.*F03.*"))
+ }
\ No newline at end of file