Merge pull request #193 from togoid/main

release 2023-10-16

Rakefile

@@ -334,6 +334,8 @@ module TogoID
         return "prepare:ncbigene"
       when /#{OUTPUT_TSV_DIR}oma_protein/
         return "prepare:oma_protein"
+      when /#{OUTPUT_TSV_DIR}prosite/
+        return "prepare:prosite"
       when /#{OUTPUT_TSV_DIR}reactome/
         return "prepare:reactome"
       when /#{OUTPUT_TSV_DIR}refseq_protein/
@@ -473,7 +475,7 @@ end
 
 namespace :prepare do
   desc "Prepare all"
-  task :all => [ :bioproject, :cellosaurus, :ensembl, :hmdb, :homologene, :hp_phenotype, :cog, :interpro, :ncbigene, :oma_protein, :reactome, :refseq_protein, :refseq_rna, :rhea, :sra, :swisslipids, :uniprot, :taxonomy ]
+  task :all => [ :bioproject, :cellosaurus, :ensembl, :hmdb, :homologene, :hp_phenotype, :cog, :interpro, :ncbigene, :oma_protein, :prosite, :reactome, :refseq_protein, :refseq_rna, :rhea, :sra, :swisslipids, :uniprot, :taxonomy ]
 
   directory INPUT_DRUGBANK_DIR    = "input/drugbank"
   directory INPUT_BIOPROJECT_DIR  = "input/bioproject"
@@ -486,6 +488,7 @@ namespace :prepare do
   directory INPUT_INTERPRO_DIR    = "input/interpro"
   directory INPUT_NCBIGENE_DIR    = "input/ncbigene"
   directory INPUT_OMA_PROTEIN_DIR = "input/oma_protein"
+  directory INPUT_PROSITE_DIR     = "input/prosite"
   directory INPUT_REACTOME_DIR    = "input/reactome"
   directory INPUT_REFSEQ_PROTEIN_DIR  = "input/refseq_protein"
   directory INPUT_REFSEQ_RNA_DIR  = "input/refseq_rna"
@@ -724,6 +727,21 @@ namespace :prepare do
     end
   end
 
+  desc "Prepare required files for PROSITE"
+  task :prosite => INPUT_PROSITE_DIR do
+    $stderr.puts "## Prepare input files for PROSITE"
+    download_lock(INPUT_PROSITE_DIR) do
+      updated = false
+      input_file = "#{INPUT_PROSITE_DIR}/prosite.dat"
+      input_url  = "https://ftp.expasy.org/databases/prosite/prosite.dat"
+      if update_input_file?(input_file, input_url)
+        download_file(INPUT_PROSITE_DIR, input_url)
+        updated = true
+      end
+      updated
+    end
+  end
+
   desc "Prepare required files for Reactome"
   task :reactome => INPUT_REACTOME_DIR do
     $stderr.puts "## Prepare input files for Reactome"

bin/prosite_prorule.awk

@@ -0,0 +1,28 @@
+BEGIN { 
+    RS="//\n"; 
+    FS="\n"; 
+    ac = ""; 
+    pr = ""; 
+    OFS="\t"; 
+}
+
+{
+    for (i=1; i<=NF; i++) {
+        if ($i ~ /^AC/) {
+            split($i, ac_arr, "   ");
+            ac = ac_arr[2];
+            gsub(/;$/, "", ac);  # 行末のセミコロンを削除
+        }
+        if ($i ~ /^PR/) {
+            split($i, pr_arr, "   ");
+            split(pr_arr[2], pr_ids, ";");  # セミコロンで複数のIDを区切る
+            for (j=1; j<=length(pr_ids); j++) {
+                gsub(/^ +| +$/, "", pr_ids[j]);  # 余分な空白を削除
+                if (ac && pr_ids[j]) {
+                    print ac, pr_ids[j];
+                }
+            }
+            ac = ""; 
+        }
+    }
+}

config/dataset.yaml

@@ -652,6 +652,22 @@ pfam:
   examples:
     - ["PF03719","PF03726","PF02809","PF00105","PF00250","PF00412","PF01412","PF00459","PF02532","PF01226"]
   method: awk -F "\t" 'FNR==NR&&$2=="name"{a[$1]=$3}FNR!=NR&&$2=="PFAM"{print $3 "\t" a[$1]}' $TOGOID_ROOT/input/interpro/interpro.tsv $TOGOID_ROOT/input/interpro/interpro.tsv
+prosite:
+  label: PROSITE
+  catalog: nbdc00241
+  category: Domain
+  regex: '^(?<id>PS\d{5})$'
+  prefix: 'http://identifiers.org/prosite/'
+  examples:
+    - ["PS01177","PS00516","PS01065","PS00418","PS01085","PS01086","PS01293","PS00355","PS01253","PS00992"]
+prosite_prorule:
+  label: PROSITE ProRule
+  catalog: nbdc00241
+  category: AnnotationRule
+  regex: '^(?<id>PRU\d{5})$'
+  prefix: 'https://prosite.expasy.org/rule/'
+  examples:
+    - ["PRU00498","PRU00672","PRU00673","PRU00293","PRU00499","PRU10142","PRU10001","PRU10002","PRU10004","PRU10005"]
 pubchem_compound:
   label: PubChem compound
   catalog: nbdc00641
@@ -768,6 +784,14 @@ sgd:
   prefix: 'http://identifiers.org/sgd/'
   examples:
     - ["S000003096","S000003789","S000005770","S000028467","S000006377","S000001180","S000003769","S000001459","S000004428","S000006021"]
+smart:
+  label: SMART
+  catalog: nbdc00682
+  category: Domain
+  regex: '^(?<id>SM\d{5})$'
+  prefix: 'http://identifiers.org/smart/'
+  examples:
+    - ["SM00130","SM00239","SM00043","SM00091","SM00104","SM01001","SM00135","SM00281","SM00996","SM00015"]
 sra_accession:
   label: SRA accession
   catalog: nbdc00687

config/interpro-prosite/config.yaml

@@ -0,0 +1,7 @@
+link:
+  forward: TIO_000001
+  reverse: TIO_000001
+  file: sample.tsv
+update:
+  frequency: Bimonthly
+  method: awk -F '\t' -v db=PROSITE '$2 == db {print $1 "\t" $3}' $TOGOID_ROOT/input/interpro/interpro.tsv

config/interpro-prosite/sample.tsv

@@ -0,0 +1,10 @@
+IPR000020	PS01177
+IPR000035	PS00516
+IPR000049	PS01065
+IPR000052	PS00418
+IPR000056	PS01085
+IPR000056	PS01086
+IPR000059	PS01293
+IPR000079	PS00355
+IPR000083	PS01253
+IPR000096	PS00992

config/interpro-smart/config.yaml

@@ -0,0 +1,7 @@
+link:
+  forward: TIO_000001
+  reverse: TIO_000001
+  file: sample.tsv
+update:
+  frequency: Bimonthly
+  method: awk -F '\t' -v db=SMART '$2 == db {print $1 "\t" $3}' $TOGOID_ROOT/input/interpro/interpro.tsv

config/interpro-smart/sample.tsv

@@ -0,0 +1,10 @@
+IPR000001	SM00130
+IPR000008	SM00239
+IPR000010	SM00043
+IPR000014	SM00091
+IPR000020	SM00104
+IPR000031	SM01001
+IPR000033	SM00135
+IPR000034	SM00281
+IPR000043	SM00996
+IPR000048	SM00015

config/prosite-prosite_prorule/config.yaml

@@ -0,0 +1,7 @@
+link:
+  forward: TIO_000114
+  reverse: TIO_000115
+  file: sample.tsv
+update:
+  frequency: Bimonthly
+  method: awk -f $TOGOID_ROOT/bin/prosite_prorule.awk $TOGOID_ROOT/input/prosite/prosite.dat

config/prosite-prosite_prorule/sample.tsv

@@ -0,0 +1,10 @@
+PS00001 PRU00498
+PS00005 PRU00672
+PS00006 PRU00673
+PS00016 PRU00293
+PS00017 PRU00499
+PS00018 PRU10142
+PS00061 PRU10001
+PS00064 PRU10002
+PS00068 PRU10004
+PS00069 PRU10005

docs/help.md

@@ -1,5 +1,5 @@
 # TogoID ver. 1.1
-Datasets last updated: 2023/10/10
+Datasets last updated: 2023/10/16
 
 ## 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 currently supports 89 datasets covering various biological categories. 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.
@@ -22,9 +22,9 @@ Shuya Ikeda, Hiromasa Ono, Tazro Ohta, Hirokazu Chiba, Yuki Naito, Yuki Moriya,
 
 - [API Documentation (Swagger)](https://togoid.dbcls.jp/apidoc/)
 
-## Statistics (as of 2023/10/10)
+## Statistics (as of 2023/10/16)
 - Number of target datasets 
-    - 96 (from 69 databases)
+    - 99 (from 71 databases)
 - For details on the target DBs and ID examples, please refer to the "DATASETS" tab. 
 
 ## Web user interface

docs/help_ja.md

@@ -1,5 +1,5 @@
 # TogoID ver. 1.1
-Datasets last updated: 2023/10/10
+Datasets last updated: 2023/10/16
 
 ## 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。
@@ -26,9 +26,9 @@ Datasets last updated: 2023/10/10
 
 - [API Documentation (Swagger)](https://togoid.dbcls.jp/apidoc/)
 
-## 統計 (2023/10/10)
+## 統計 (2023/10/16)
 - 対象データセット数 
-    - 96 (69のデータベースに由来)
+    - 99 (71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。 
 
 ## Web user interface