Merge pull request #290 from togoid/main

release 2024-02-14

Author: sh-ikeda

config/pubchem_compound-chembl_compound/query_01.rq

@@ -2,13 +2,14 @@ PREFIX sio: <http://semanticscience.org/resource/>
 PREFIX cheminf: <http://semanticscience.org/resource/>
 PREFIX source: <http://rdf.ncbi.nlm.nih.gov/pubchem/source/>
 PREFIX dcterms: <http://purl.org/dc/terms/>
-PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
-SELECT DISTINCT (substr(str(?cid), 49) as ?pubchem_id) ?chembl_id
+SELECT DISTINCT (STRAFTER(STR(?cid), "http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID") as ?pubchem_id) ?chembl_id
 FROM <http://rdf.ncbi.nlm.nih.gov/pubchem/substance>
 WHERE {
-    [] cheminf:CHEMINF_000477 ?cid ;
-        dcterms:source source:ChEMBL ;
-        skos:exactMatch ?chembl_b .
-        BIND (strafter(str(?chembl_b), "CHEMBL") AS ?chembl_id)
+  [] cheminf:CHEMINF_000477 ?cid ;
+     dcterms:source source:ChEMBL ;
+     rdfs:seeAlso ?chembl .
+  FILTER (STRSTARTS(STR(?chembl), "http://identifiers.org/chembl.compound:"))
+  BIND (STRAFTER(STR(?chembl), "CHEMBL") AS ?chembl_id)
 }

config/pubchem_compound-chembl_compound/query_01_count.rq

@@ -2,15 +2,15 @@ PREFIX sio: <http://semanticscience.org/resource/>
 PREFIX cheminf: <http://semanticscience.org/resource/>
 PREFIX source: <http://rdf.ncbi.nlm.nih.gov/pubchem/source/>
 PREFIX dcterms: <http://purl.org/dc/terms/>
-PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
-SELECT (count(*) as ?total) {
-SELECT DISTINCT ?cid ?chembl_id
+SELECT (COUNT(*) as ?total) {
+SELECT DISTINCT ?cid ?chembl
 FROM <http://rdf.ncbi.nlm.nih.gov/pubchem/substance>
 WHERE {
-    [] cheminf:CHEMINF_000477 ?cid ;
-        dcterms:source source:ChEMBL ; # has PubChem normalized counterpart
-        skos:exactMatch ?chembl_b .
-        BIND (strafter(str(?chembl_b), "CHEMBL") AS ?chembl_id)
+  [] cheminf:CHEMINF_000477 ?cid ;
+     dcterms:source source:ChEMBL ; # has PubChem normalized counterpart
+     rdfs:seeAlso ?chembl .
+  FILTER (STRSTARTS(STR(?chembl), "http://identifiers.org/chembl.compound:"))
 }
 }

config/pubchem_compound-glytoucan/query.rq

@@ -1,12 +1,13 @@
 PREFIX dcterms: <http://purl.org/dc/terms/>
 PREFIX source: <http://rdf.ncbi.nlm.nih.gov/pubchem/source/>
 PREFIX cheminf: <http://semanticscience.org/resource/>
-PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT DISTINCT ?pubchem_id ?glytoucan_id {
   [ dcterms:source source:ID11830 ;
-    skos:exactMatch ?glytoucan ;
+    rdfs:seeAlso ?glytoucan ;
     cheminf:CHEMINF_000477 ?pubchem ] .
   BIND(STRAFTER(STR(?pubchem), "compound/CID") AS ?pubchem_id)
-  BIND(STRAFTER(STR(?glytoucan), "glytoucan/") AS ?glytoucan_id)
+  FILTER (STRSTARTS(STR(?glytoucan), "http://identifiers.org/glytoucan:"))
+  BIND(STRAFTER(STR(?glytoucan), "http://identifiers.org/glytoucan:") AS ?glytoucan_id)
 }

config/pubchem_pathway-pathbank/query.rq

@@ -2,13 +2,13 @@
 
 PREFIX bp: <http://www.biopax.org/release/biopax-level3.owl#>
 PREFIX obo: <http://purl.obolibrary.org/obo/>
-PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT DISTINCT ?pathway_id ?pathbank_id
 FROM <http://rdf.ncbi.nlm.nih.gov/pubchem/pathway>
 WHERE {
   ?pathway a bp:Pathway;
-           owl:sameAs ?orig .
+           rdfs:seeAlso ?orig .
   FILTER(STRSTARTS(STR(?orig), "http://pathbank.org/view/"))
   BIND(STRAFTER(STR(?pathway), "http://rdf.ncbi.nlm.nih.gov/pubchem/pathway/PWID") AS ?pathway_id)
   BIND(STRAFTER(STR(?orig), "http://pathbank.org/view/") AS ?pathbank_id)

config/pubchem_pathway-reactome_pathway/query.rq

@@ -1,12 +1,12 @@
 PREFIX bp: <http://www.biopax.org/release/biopax-level3.owl#>
 PREFIX obo: <http://purl.obolibrary.org/obo/>
-PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT DISTINCT ?path_id ?reactome_id
 FROM <http://rdf.ncbi.nlm.nih.gov/pubchem/pathway>
 WHERE {
   ?pathway a bp:Pathway;
-           owl:sameAs ?orig .
+           rdfs:seeAlso ?orig .
   FILTER(STRSTARTS(STR(?orig), "http://identifiers.org/reactome/"))
   BIND(STRAFTER(STR(?pathway), "http://rdf.ncbi.nlm.nih.gov/pubchem/pathway/PWID") AS ?path_id)
   BIND(STRAFTER(STR(?orig), "http://identifiers.org/reactome/") AS ?reactome_id)

config/pubchem_pathway-uniprot/query_01.rq

@@ -2,14 +2,14 @@
 PREFIX bp: <http://www.biopax.org/release/biopax-level3.owl#>
 PREFIX obo: <http://purl.obolibrary.org/obo/>
 PREFIX sio: <http://semanticscience.org/resource/>
-PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT DISTINCT ?path_id ?uniprot
 WHERE {
   ?pathway a bp:Pathway;
            obo:RO_0000057 [
              a sio:SIO_010043 ;
-             skos:closeMatch ?protein
+             rdfs:seeAlso ?protein
            ] .
            #(obo:RO_0000057/owl:sameAs) ?participant .
   FILTER(CONTAINS(STR(?protein), "http://purl.uniprot.org/uniprot/"))

config/pubchem_pathway-uniprot/query_01_count.rq

@@ -2,7 +2,7 @@
 PREFIX bp: <http://www.biopax.org/release/biopax-level3.owl#>
 PREFIX obo: <http://purl.obolibrary.org/obo/>
 PREFIX sio: <http://semanticscience.org/resource/>
-PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT (COUNT(*) AS ?total)
 WHERE {
@@ -11,7 +11,7 @@ WHERE {
     ?pathway a bp:Pathway ;
              obo:RO_0000057 [
              a sio:SIO_010043 ;
-             skos:closeMatch ?protein
+             rdfs:seeAlso ?protein
            ] .
     FILTER(CONTAINS(STR(?protein), "http://purl.uniprot.org/uniprot/"))
   }

config/pubchem_pathway-wikipathways/query.rq

@@ -1,12 +1,12 @@
 PREFIX bp: <http://www.biopax.org/release/biopax-level3.owl#>
 PREFIX obo: <http://purl.obolibrary.org/obo/>
-PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 
 SELECT DISTINCT ?pathway_id ?wp_id
 FROM <http://rdf.ncbi.nlm.nih.gov/pubchem/pathway>
 WHERE {
   ?pathway a bp:Pathway;
-           owl:sameAs ?orig .
+           rdfs:seeAlso ?orig .
   FILTER(STRSTARTS(STR(?orig), "http://identifiers.org/wikipathways/"))
   BIND(STRAFTER(STR(?pathway), "http://rdf.ncbi.nlm.nih.gov/pubchem/pathway/PWID") AS ?pathway_id)
   BIND(STRAFTER(STR(?orig), "http://identifiers.org/wikipathways/") AS ?wp_id)

docs/help.md

@@ -1,5 +1,5 @@
 # TogoID ver. 2.0
-Datasets last updated: 2025-02-04
+Datasets last updated: 2025-02-12
 
 ## About
 - [TogoID](https://togoid.dbcls.jp/) is an ID conversion service implementing unique features with an intuitive web interface and an API for programmatic access. TogoID supports datasets from various biological categories such as gene, protein, chemical compound, pathway, disease, etc. TogoID users can perform exploratory multistep conversions to find a path among IDs. To guide the interpretation of biological meanings in the conversions, we crafted an [ontology](https://togoid.dbcls.jp/ontology) that defines the semantics of the dataset relations.
@@ -10,7 +10,7 @@ Datasets last updated: 2025-02-04
 ## Video tutorial
 - [How to use TogoID ver 2.0: an exploratory ID converter to bridge biological datasets](https://youtu.be/ORW1GGIaJsY)
 
-## Statistics (as of 2025-02-04)
+## Statistics (as of 2025-02-12)
 - Number of target datasets 
     - 105 (from 73 databases)
 - For details on the target DBs and ID examples, please refer to the "DATASETS" tab. 

docs/help_ja.md

@@ -1,5 +1,5 @@
 # TogoID ver. 2.0
-Datasets last updated: 2025-02-04
+Datasets last updated: 2025-02-12
 
 ## About
 - [TogoID](https://togoid.dbcls.jp/) は、直感的なインターフェースにより生命科学系データベース(DB)間のつながりを探索的に確認しながらID変換を行うことができるウェブアプリケーションです。同一の実体を指すID間の変換だけでなく、関連する別のカテゴリーのIDへの変換も可能です。また、直接リンクされていないDBのID間でも、他のDBを経由した変換を探索することができます。
@@ -10,7 +10,7 @@ Datasets last updated: 2025-02-04
 ## 動画マニュアル
 - [TogoID ver. 2.0を使って生命科学系データベースのさまざまなIDを探索的に変換する](https://youtu.be/ORW1GGIaJsY)
 
-## 統計 (2025-02-04)
+## 統計 (2025-02-12)
 - 対象データセット数 
     - 105 (73 のデータベースに由来)
 - 対象DBの詳細やID例については、"DATASETS" タブ からご覧いただけます。 

docs/news.md

@@ -1,6 +1,9 @@
 # 2025-01-13
 - [Our new publication](https://link.springer.com/article/10.1186/s13326-024-00322-1) has been published.
 
+# 2025-02-12
+- Weekly update has been completed.
+
 # 2025-02-04
 - Weekly update has been completed.
 

log/error.log

@@ -1,11 +1,5 @@
 Error: check_remote_file_time(input/homologene/homologene.data, https://ftp.ncbi.nlm.nih.gov/pub/HomoloGene/current/homologene.data): no time information in ""
 Error: Remote file is empty
-Error: check_remote_file_time(input/interpro/interpro2go, https://ftp.ebi.ac.uk/pub/databases/interpro/current_release/interpro2go): no time information in ""
-Error: Remote file is empty
-Error: check_remote_file_time(input/interpro/protein2ipr.dat.gz, https://ftp.ebi.ac.uk/pub/databases/interpro/current_release/protein2ipr.dat.gz): no time information in ""
-Error: Remote file is empty
-Error: check_remote_file_time(input/interpro/interpro.xml.gz, https://ftp.ebi.ac.uk/pub/databases/interpro/current_release/interpro.xml.gz): no time information in ""
-Error: Remote file is empty
 # Error: output/tsv/chembl_target-ensembl_gene.tsv new file size per old 0 / 61845 = 0.0 < 0.5
 # Error: Failed to create output/tsv/chembl_target-ensembl_gene.tsv or created file was empty
 Error: HTTP Error 500: Internal Server Error: https://api.alpha.glycosmos.org/partialmatch?wurcs=WURCS%3D2.0%2F4%2C11%2C10%2F%5Ba2122h-1b_1-5%5D%5Ba2112h-1b_1-5%5D%5Ba2122h-1b_1-5_2%2ANCC%2F3%3DO%5D%5Ba1221m-1a_1-5%5D%2F1-2-3-2-3-2-3-4-2-3-2%2Fa4-b1_b3-c1_c4-d1_d3-e1_e4-f1_f3-g1_g3-h1_g4-i1_i3-j1_j4-k1&rootnode=true G64227KZ
@@ -69,4 +63,16 @@ Error: HTTP Error 500: Internal Server Error: https://api.alpha.glycosmos.org/pa
 # Error: Failed to create output/tsv/mondo-omim_phenotype.tsv or created file was empty
 # Error: output/tsv/mondo-orphanet_phenotype.tsv new file size per old 0 / 146923 = 0.0 < 0.5
 # Error: Failed to create output/tsv/mondo-orphanet_phenotype.tsv or created file was empty
+# Error: output/tsv/pubchem_compound-chembl_compound.tsv new file size per old 0 / 53838777 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_compound-chembl_compound.tsv or created file was empty
+# Error: output/tsv/pubchem_compound-glytoucan.tsv new file size per old 0 / 1277768 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_compound-glytoucan.tsv or created file was empty
+# Error: output/tsv/pubchem_pathway-pathbank.tsv new file size per old 0 / 1318229 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_pathway-pathbank.tsv or created file was empty
+# Error: output/tsv/pubchem_pathway-reactome_pathway.tsv new file size per old 0 / 56888 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_pathway-reactome_pathway.tsv or created file was empty
+# Error: output/tsv/pubchem_pathway-uniprot.tsv new file size per old 0 / 9181412 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_pathway-uniprot.tsv or created file was empty
+# Error: output/tsv/pubchem_pathway-wikipathways.tsv new file size per old 0 / 16836 = 0.0 < 0.5
+# Error: Failed to create output/tsv/pubchem_pathway-wikipathways.tsv or created file was empty
 # Error: output/tsv/wikipathways-uniprot.tsv new file size per old 61682 / 470542 = 0.13108712931045474 < 0.5