Merge pull request #281 from togoid/main

release 2024-12-09

config/dataset.yaml

@@ -948,7 +948,7 @@ uniprot_proteome:
   examples:
     - ["UP000005640","UP000002311","UP000000589","UP000000803","UP000000437","UP000001819","UP000008028","UP000008143","UP000079169"]
   method: zcat $TOGOID_ROOT/input/uniprot/uniprot_proteome.tab.gz | awk -F "\t" 'FNR>=2&&$1&&$4{print $1 "\t" $4}'
-  description: 'This is a proteome dataset defined by UniProt. UniProt assigns IDs to the set of proteins expressed by a single organism. Since multiple genomes are often sequenced for the same organism, and a proteome is defined for each genome, proteome IDs to distinguish individual proteomes from the same taxonomy identifier were introduced. [More info](https://www.uniprot.org/help/proteome_id)'
+  description: 'This is a proteome dataset defined by UniProt. UniProt assigns IDs to the set of proteins expressed by a single organism. Since multiple genomes are often sequenced for the same organism, and a proteome is defined for each genome, proteome IDs to distinguish individual proteomes from the same taxonomy identifier were introduced. More info: https://www.uniprot.org/help/proteome_id'
 vgnc:
   label: VGNC
   catalog: nbdc02624

docs/help.md

@@ -1,5 +1,5 @@
 # TogoID ver. 2.0
-Datasets last updated: 2024-12-05
+Datasets last updated: 2024-12-09
 
 ## 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: 2024-12-05
 ## Video tutorial
 - [How to use TogoID: an exploratory ID converter to bridge biological datasets](https://youtu.be/gXnvm6Fn4R8)
 
-## Statistics (as of 2024-12-05)
+## Statistics (as of 2024-12-09)
 - 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: 2024-12-05
+Datasets last updated: 2024-12-09
 
 ## 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: 2024-12-05
 ## 動画マニュアル
 - [TogoID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/gXnvm6Fn4R8)
 
-## 統計 (2024-12-05)
+## 統計 (2024-12-09)
 - 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

@@ -1,3 +1,6 @@
+# 2024-12-09
+- Weekly update has been completed.
+
 # 2024-12-05
 - Weekly update has been completed.
 - The dataset `uniprot_reference_proteome` has been renamed to `uniprot_proteome`, because this dataset includes proteomes other than the reference proteomes. We apologize for any inconvenience caused.

lib/togoid-config.rb

@@ -101,7 +101,7 @@ def initialize(name, hash)
     end
 
     def setup_files
-      @ttl_dir = "output/id-label/"
+      @ttl_dir = "output/ttl/label"
       @ttl_file = "#{@ttl_dir}/#{@name}.ttl"
       FileUtils.mkdir_p(@ttl_dir)
     end
@@ -205,7 +205,7 @@ def load_dataset
 
     def setup_files
       @tsv_dir = "output/tsv"
-      @ttl_dir = "output/ttl"
+      @ttl_dir = "output/ttl/relation"
       @tsv_file = "#{@tsv_dir}/#{@source_ns}-#{@target_ns}.tsv"
       @ttl_file = "#{@ttl_dir}/#{@source_ns}-#{@target_ns}.ttl"
       FileUtils.mkdir_p(@tsv_dir)

log/config-summary.tsv

@@ -248,10 +248,10 @@ uniprot-omim_gene	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbd
 uniprot-omim_phenotype	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00154	Phenotype	OMIM phenotype	http://identifiers.org/mim/	tio:TIO_000010	has related phenotype	has related phenotype	tio:TIO_000011	phenotype is related with	is related with	Monthly	"sparql_thread.pl -t 10"
 uniprot-orphanet_phenotype	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc01422	Phenotype	Orphanet phenotype	http://identifiers.org/orphanet.ordo/Orphanet_	tio:TIO_000010	has related phenotype	has related phenotype	tio:TIO_000011	phenotype is related with	is related with	Monthly	"uniprot_idmapping2tsv.rb ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz Orphanet"
 uniprot-pdb	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00156	Structure	PDB	http://rdf.wwpdb.org/pdb/	tio:TIO_000026	protein has 3D structure	has 3D structure	tio:TIO_000027	is 3D structure of protein	is 3D structure of	Monthly	"uniprot_idmapping2tsv.rb ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz PDB"
+uniprot_proteome-assembly_insdc	nbdc00221	Proteome	UniProt proteome	http://purl.uniprot.org/proteomes/	FIXME	Genome	Assembly INSDC	http://identifiers.org/insdc.gca/	tio:TIO_000092	proteome is coded by genome	is coded by	tio:TIO_000093	genome codes proteome	codes	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_proteome.tab.gz | sed -e '1d' | cut -f1,3 | grep GCA |cut -f1 -d '.'"
+uniprot_proteome-assembly_refseq	nbdc00221	Proteome	UniProt proteome	http://purl.uniprot.org/proteomes/	FIXME	Genome	Assembly RefSeq	http://identifiers.org/insdc.gca/	tio:TIO_000092	proteome is coded by genome	is coded by	tio:TIO_000093	genome codes proteome	codes	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_proteome.tab.gz | sed -e '1d' | cut -f1,3 | grep GCF |cut -f1 -d '.'"
+uniprot_proteome-taxonomy	nbdc00221	Proteome	UniProt proteome	http://purl.uniprot.org/proteomes/	nbdc00700	Organism	Taxonomy	http://identifiers.org/taxonomy/	tio:TIO_000090	is proteome of organism	is proteome of	tio:TIO_000091	organism has proteome	has proteome	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_proteome.tab.gz | sed -e '1d' | cut -f 1,2"
 uniprot-reactome_pathway	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00185	Pathway	Reactome pathway	http://identifiers.org/reactome/	tio:TIO_000069	molecule participates in pathway	participates in pathway	tio:TIO_000068	pathway has participant molecule	has participant molecule	Monthly	"uniprot_idmapping2tsv.rb ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz Reactome"
-uniprot_reference_proteome-assembly_insdc	nbdc00221	Proteome	UniProt reference proteome	http://purl.uniprot.org/proteomes/	FIXME	Genome	Assembly INSDC	http://identifiers.org/insdc.gca/	tio:TIO_000092	proteome is coded by genome	is coded by	tio:TIO_000093	genome codes proteome	codes	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_reference_proteome.tab.gz | sed -e '1d' | cut -f1,3 | grep GCA |cut -f1 -d '.'"
-uniprot_reference_proteome-assembly_refseq	nbdc00221	Proteome	UniProt reference proteome	http://purl.uniprot.org/proteomes/	FIXME	Genome	Assembly RefSeq	http://identifiers.org/insdc.gca/	tio:TIO_000092	proteome is coded by genome	is coded by	tio:TIO_000093	genome codes proteome	codes	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_reference_proteome.tab.gz | sed -e '1d' | cut -f1,3 | grep GCF |cut -f1 -d '.'"
-uniprot_reference_proteome-taxonomy	nbdc00221	Proteome	UniProt reference proteome	http://purl.uniprot.org/proteomes/	nbdc00700	Organism	Taxonomy	http://identifiers.org/taxonomy/	tio:TIO_000090	is proteome of organism	is proteome of	tio:TIO_000091	organism has proteome	has proteome	Monthly	"gzip -dc ${TOGOID_ROOT}/input/uniprot/uniprot_reference_proteome.tab.gz | sed -e '1d' | cut -f 1,2"
 uniprot-refseq_protein	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00187	Protein	RefSeq protein	http://identifiers.org/refseq/	tio:TIO_000002	is equivalent to	is equivalent to	tio:TIO_000002	is equivalent to	is equivalent to	Monthly	"uniprot_idmapping2tsv.rb ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz RefSeq | perl -pe 's/\\.\\d+$//;s/-\\d+\\t/\\t/'"
 uniprot-taxonomy	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00700	Organism	Taxonomy	http://identifiers.org/taxonomy/	tio:TIO_000124	is protein of organism	is protein of organism	tio:TIO_000125	organism has protein	has protein	Monthly	"zcat ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz | awk -F \"\\t\" '$2==\"NCBI_TaxID\"{print $1 \"\\t\" $3}'"
 uniprot-uniprot_mnemonic	nbdc00221	Protein	UniProt	http://purl.uniprot.org/uniprot/	nbdc00221	Protein	UniProt mnemonic	http://purl.uniprot.org/uniprot/	tio:TIO_000022	has synonym	has synonym	tio:TIO_000023	is synonym of	is synonym of	Monthly	"uniprot_idmapping2tsv.rb ${TOGOID_ROOT}/input/uniprot/idmapping.dat.gz UniProtKB-ID"

log/error.log

@@ -3,7 +3,7 @@ Error: check_remote_file_time(input/homologene/homologene.data, https://ftp.ncbi
 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%2C10%2C9%2F%5Ba2122h-1b_1-5%5D%5Ba2112h-1b_1-5%5D%5BAad21122h-2a_2-6_5%2ANCC%2F3%3DO%5D%5Ba2112h-1b_1-5_2%2ANCC%2F3%3DO%5D%2F1-2-3-3-3-4-2-3-3-3%2Fa4-b1_b3-c2_b4-f1_c8-d2_d8-e2_f3-g1_f6-j2_g3-h2_h8-i2&rootnode=true G14091MR
+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
 # Error: output/tsv/glycomotif-glytoucan.tsv new file size per old 0 / 2804382 = 0.0 < 0.5
 # Error: Failed to create output/tsv/glycomotif-glytoucan.tsv or created file was empty
 # Error: output/tsv/glytoucan-doid.tsv new file size per old 1538 / 4376 = 0.35146252285191953 < 0.5
@@ -63,4 +63,46 @@ 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/ncit_disease-ncit_tissue.tsv new file size per old 291 / 385314 = 0.0007552282034911786 < 0.5
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <html><head>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <title>408 Request Timeout</title>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML </head><body>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <h1>Request Timeout</h1>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <p>Server timeout waiting for the HTTP request from the client.</p>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <p>Additionally	 a 502 Bad Gateway
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML error was encountered while trying to use an ErrorDocument to handle the request.</p>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML </body></html>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <html><head>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <title>408 Request Timeout</title>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML </head><body>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <h1>Request Timeout</h1>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <p>Server timeout waiting for the HTTP request from the client.</p>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML <p>Additionally	 a 502 Bad Gateway
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML error was encountered while trying to use an ErrorDocument to handle the request.</p>
+# Error: output/tsv/ncit_disease-ncit_tissue.tsv seems to contain HTML </body></html>
+# Error: output/tsv/togovar-ensembl_transcript.tsv new file size per old 0 / 8069270901 = 0.0 < 0.5
+# Error: Failed to create output/tsv/togovar-ensembl_transcript.tsv or created file was empty
+# Error: output/tsv/togovar-ncbigene.tsv new file size per old 0 / 1097267175 = 0.0 < 0.5
+# Error: Failed to create output/tsv/togovar-ncbigene.tsv or created file was empty
+# Error: output/tsv/togovar-pubmed.tsv new file size per old 0 / 14408635 = 0.0 < 0.5
+# Error: Failed to create output/tsv/togovar-pubmed.tsv or created file was empty
+# Error: output/tsv/togovar-refseq_rna.tsv new file size per old 0 / 4180808277 = 0.0 < 0.5
+# Error: Failed to create output/tsv/togovar-refseq_rna.tsv or created file was empty
+# Error: output/tsv/uberon-ncit_tissue.tsv new file size per old 288 / 38722 = 0.007437632353700738 < 0.5
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <html><head>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <title>502 Proxy Error</title>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML </head><body>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <h1>Proxy Error</h1>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <p>The proxy server received an invalid
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML response from an upstream server.<br />
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML The proxy server could not handle the request<p>Reason: <strong>Error reading from remote server</strong></p></p>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML </body></html>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <html><head>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <title>502 Proxy Error</title>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML </head><body>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <h1>Proxy Error</h1>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML <p>The proxy server received an invalid
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML response from an upstream server.<br />
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML The proxy server could not handle the request<p>Reason: <strong>Error reading from remote server</strong></p></p>
+# Error: output/tsv/uberon-ncit_tissue.tsv seems to contain HTML </body></html>
 # Error: output/tsv/wikipathways-uniprot.tsv new file size per old 60240 / 470542 = 0.12802257821830995 < 0.5