Merge pull request #269 from togoid/main

release 2024-10-15

Rakefile

@@ -634,7 +634,7 @@ namespace :prepare do
     download_lock(INPUT_HGNC_DIR) do
       updated = false
       input_file = "#{INPUT_HGNC_DIR}/hgnc_complete_set.tsv"
-      input_url  = "https://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/tsv/hgnc_complete_set.tsv"
+      input_url  = "https://storage.googleapis.com/public-download-files/hgnc/tsv/tsv/hgnc_complete_set.txt"
       if update_input_file?(input_file, input_url)
         download_file(INPUT_HGNC_DIR, input_url)
         updated = true

docs/help.md

@@ -1,5 +1,5 @@
 # TogoID ver. 2.0
-Datasets last updated: 2024-10-10
+Datasets last updated: 2024-10-15
 
 ## 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.
@@ -22,7 +22,7 @@ Shuya Ikeda, Hiromasa Ono, Tazro Ohta, Hirokazu Chiba, Yuki Naito, Yuki Moriya,
 
 - [API Documentation (Swagger)](https://togoid.dbcls.jp/apidoc/)
 
-## Statistics (as of 2024-10-10)
+## Statistics (as of 2024-10-15)
 - 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: 2024-10-10
+Datasets last updated: 2024-10-15
 
 ## 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。
@@ -28,7 +28,7 @@ Datasets last updated: 2024-10-10
 
 - [API Documentation (Swagger)](https://togoid.dbcls.jp/apidoc/)
 
-## 統計 (2024-10-10)
+## 統計 (2024-10-15)
 - 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

@@ -1,15 +1,15 @@
-# *NOTICE*  
-The TogoID service will be temporarily unavailable due to a system update from 10:00 am to 00:00 pm (JST) on Tuesday, October 15, 2024. We apologize for any incovenience caused.
-
 # 2024-09-06
 *New features released!*  
 - You can now display labels for IDs by toggling the "Show labels" switch in the results table.  
 - In the LABEL2ID tab, you can convert labels into IDs (e.g., gene symbols to NCBI Gene IDs or disease names to MONDO IDs).  
 - TogoID now supports handling multiple semantic relations between the same dataset pair (e.g., try converting between GlyTouCan and UniProt).  
 A detailed document is currently being prepared.
 
+# 2024-10-15
+- Weekly update has been completed.
+
 # 2024-10-10
-- Weekly update has been completed.  
+- Weekly update has been completed.
 
 # 2024-09-30
 - Weekly update has been completed.  

log/error.log

@@ -1,4 +1,6 @@
 Error: download_file(input/glytoucan, https://glycosmos.org/download/glycosmos_ggdbs_pubmed.csv): Command failed with status (8): [wget --quiet --recursive --no-parent --no-...]
+Error: check_remote_file_time(input/hgnc/hgnc_complete_set.tsv, https://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/tsv/hgnc_complete_set.tsv): no time information in ""
+Error: Remote file is empty
 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: output/tsv/chembl_target-ensembl_gene.tsv new file size per old 0 / 61845 = 0.0 < 0.5

log/pair_count.tsv

@@ -3,11 +3,11 @@ assembly_insdc-bioproject.tsv	2283159
 assembly_insdc-biosample.tsv	2225812
 assembly_insdc-insdc_master.tsv	2150193
 bioproject-biosample.tsv	2546485
-bioproject-geo_series.tsv	217446
-bioproject-pubmed.tsv	278826
+bioproject-geo_series.tsv	217809
+bioproject-pubmed.tsv	279413
 bioproject_umbrella-bioproject.tsv	104586
-biosample-bioproject.tsv	19938580
-biosample-geo_sample.tsv	9431518
+biosample-bioproject.tsv	19988521
+biosample-geo_sample.tsv	9447146
 cellosaurus-ncit_disease.tsv	75821
 cellosaurus-orphanet_phenotype.tsv	41448
 chebi-glytoucan.tsv	10615
@@ -34,14 +34,14 @@ chembl_target-uniprot-TIO_000002.tsv	9094
 chembl_target-uniprot-TIO_000130.tsv	1533
 chembl_target-uniprot-TIO_000132.tsv	1434
 chembl_target-uniprot.tsv	9094
-clinvar-dbsnp.tsv	2937745
-clinvar-hgnc.tsv	3025875
-clinvar-medgen.tsv	4162525
-clinvar-mondo.tsv	1986846
-clinvar-ncbigene.tsv	3026191
-clinvar-omim_phenotype.tsv	1634429
-clinvar-orphanet_phenotype.tsv	1859346
-clinvar-uniprot.tsv	20797
+clinvar-dbsnp.tsv	2937791
+clinvar-hgnc.tsv	3044255
+clinvar-medgen.tsv	4171173
+clinvar-mondo.tsv	1988452
+clinvar-ncbigene.tsv	3044575
+clinvar-omim_phenotype.tsv	1635664
+clinvar-orphanet_phenotype.tsv	1860371
+clinvar-uniprot.tsv	20798
 cog-insdc.tsv	115826
 cog-refseq_protein.tsv	3340026
 doid-mesh.tsv	4019
@@ -117,37 +117,37 @@ medgen-mondo.tsv	21567
 medgen-ncbigene.tsv	7229
 medgen-omim_phenotype.tsv	11043
 medgen-orphanet_phenotype.tsv	9063
-mgi_gene-ensembl_gene.tsv	56428
+mgi_gene-ensembl_gene.tsv	56426
 mgi_gene-hgnc.tsv	24587
-mgi_gene-mgi_allele.tsv	110373
-mgi_gene-ncbigene.tsv	90619
+mgi_gene-mgi_allele.tsv	110437
+mgi_gene-ncbigene.tsv	90618
 mgi_gene-uniprot.tsv	79034
 mgi_genotype-doid.tsv	7837
-mgi_genotype-mgi_allele.tsv	124602
-mgi_genotype-mp.tsv	400771
+mgi_genotype-mgi_allele.tsv	124623
+mgi_genotype-mp.tsv	400910
 mondo-doid.tsv	10712
 mondo-hp_phenotype.tsv	574
 mondo-meddra.tsv	1486
 mondo-mesh.tsv	8352
 mondo-omim_phenotype.tsv	9693
 mondo-orphanet_phenotype.tsv	10380
 nando-mondo.tsv	2390
-ncbigene-ensembl_gene.tsv	11660930
-ncbigene-ensembl_protein.tsv	13459019
-ncbigene-ensembl_transcript.tsv	14189546
+ncbigene-ensembl_gene.tsv	11654277
+ncbigene-ensembl_protein.tsv	13449374
+ncbigene-ensembl_transcript.tsv	14177749
 ncbigene-flybase_gene.tsv	25078
-ncbigene-go.tsv	101043576
-ncbigene-hgnc.tsv	43829
+ncbigene-go.tsv	101041913
+ncbigene-hgnc.tsv	43827
 ncbigene-mgi_gene.tsv	71684
 ncbigene-mirbase.tsv	17541
-ncbigene-omim_gene.tsv	18526
-ncbigene-refseq_genomic.tsv	211759
-ncbigene-refseq_protein.tsv	68060620
-ncbigene-refseq_rna.tsv	66432148
+ncbigene-omim_gene.tsv	18527
+ncbigene-refseq_genomic.tsv	211762
+ncbigene-refseq_protein.tsv	68217911
+ncbigene-refseq_rna.tsv	66619410
 ncbigene-rgd.tsv	47288
 ncbigene-sgd.tsv	6471
 ncbigene-tair.tsv	32835
-ncbigene-taxonomy.tsv	56251350
+ncbigene-taxonomy.tsv	56353463
 ncbigene-vgnc.tsv	112162
 ncbigene-wormbase_gene.tsv	28779
 ncbigene-xenbase_gene.tsv	46842
@@ -170,7 +170,7 @@ pdb-interpro.tsv	726658
 pdb-pdb_ccd.tsv	530587
 pdb-pfam.tsv	339565
 pdb-uniprot.tsv	341431
-pmc-pubmed.tsv	9547208
+pmc-pubmed.tsv	9561234
 prosite-prosite_prorule.tsv	1455
 pubchem_compound-atc.tsv	4965
 pubchem_compound-chebi.tsv	174843
@@ -195,7 +195,7 @@ reactome_reaction-go.tsv	3318
 reactome_reaction-iuphar_ligand.tsv	14709
 reactome_reaction-mirbase.tsv	194
 reactome_reaction-uniprot.tsv	679876
-refseq_protein-uniprot.tsv	168636384
+refseq_protein-uniprot.tsv	154618594
 refseq_rna-dbsnp.tsv	267059416
 refseq_rna-hgnc.tsv	227230
 refseq_rna-ncbigene.tsv	65546825
@@ -209,28 +209,28 @@ rhea-go.tsv	4435
 rhea-pubmed.tsv	142680
 rhea-reactome_reaction.tsv	1511
 rhea-uniprot.tsv	41448659
-sra_accession-bioproject.tsv	529030
-sra_accession-biosample.tsv	31645689
-sra_accession-sra_analysis.tsv	329141
-sra_accession-sra_experiment.tsv	35486202
-sra_accession-sra_project.tsv	615018
-sra_accession-sra_run.tsv	40263951
-sra_accession-sra_sample.tsv	34290431
-sra_experiment-bioproject.tsv	30997361
-sra_experiment-biosample.tsv	31319829
-sra_experiment-sra_project.tsv	31341882
-sra_experiment-sra_sample.tsv	31341689
-sra_project-bioproject.tsv	532472
-sra_run-bioproject.tsv	32860319
-sra_run-biosample.tsv	33183885
-sra_run-sra_experiment.tsv	33225215
-sra_run-sra_project.tsv	33217614
-sra_run-sra_sample.tsv	33206609
-sra_sample-biosample.tsv	31666803
+sra_accession-bioproject.tsv	529462
+sra_accession-biosample.tsv	31680248
+sra_accession-sra_analysis.tsv	329243
+sra_accession-sra_experiment.tsv	35570093
+sra_accession-sra_project.tsv	616586
+sra_accession-sra_run.tsv	40350221
+sra_accession-sra_sample.tsv	34372201
+sra_experiment-bioproject.tsv	31035975
+sra_experiment-biosample.tsv	31352287
+sra_experiment-sra_project.tsv	31380496
+sra_experiment-sra_sample.tsv	31380303
+sra_project-bioproject.tsv	532904
+sra_run-bioproject.tsv	32903026
+sra_run-biosample.tsv	33216964
+sra_run-sra_experiment.tsv	33268661
+sra_run-sra_project.tsv	33260321
+sra_run-sra_sample.tsv	33246345
+sra_sample-biosample.tsv	31701362
 swisslipids-chebi.tsv	4276
 swisslipids-hmdb.tsv	26026
 swisslipids-inchi_key.tsv	593209
-taxonomy-pubmed.tsv	50523
+taxonomy-pubmed.tsv	50493
 togovar-clinvar.tsv	745335
 togovar-dbsnp.tsv	66877211
 togovar-ensembl_gene.tsv	72473309
@@ -270,4 +270,4 @@ wikipathways-hmdb.tsv	4119
 wikipathways-lipidmaps.tsv	1398
 wikipathways-ncbigene.tsv	30258
 wikipathways-uniprot.tsv	33518
-total	5194479012
+total	5181681751

log/pair_count_history.tsv

@@ -59,3 +59,4 @@ Date	affy_probeset-ncbigene	assembly_insdc-bioproject	assembly_insdc-biosample	a
 2024-09-21	19063	2283159	2225812	2150193		2546485	216421	277725	104586	19799048	9393416	75821		41448		175447	34347	3101919	3101919	4931	8211	11771	1915184	47707	14012	1878399	433145	1449263	2126	11847	10947	34588	3549	8047	8272				2937727	3025517	4145651	1986712	3025834	1635593	1859264	20797	115826	3340026	4019	4849	5671	54855	12969337	15910019	47792	14749031	5546630	12969340	224377	55211171	241612	40165483	141	5046	155799	290	1270	82906	82906	402	310	35510	2049	41234	43873	21166	1325		24071	1912	43815	17277	34911	13531	28774	18940	20379	13701	217899	522	104230	275237	8814	220065	137689		113135	59409158	193975949	1533582	1533178	30288	1615604	21171	1283	113855	473753	1274	759739513	199	305	130	12929	48152	12349	137319849	6318	16674	16849	21567	7229	11043		9063	56430	24587	110284	90619	79034	7831	124580	400502	10712	574	1486	8352	9693		10380	2390	11595819	13395290	14117908	25078	100092792	43815		71684	17541	18538	211760	67636019	65971928	47288	6471	32835	55892558	112161	19842	46840	27161	27199	2460780	2804840	4800754	18299774				4319	4337	4316	4298	1192	1798	7832	8040	1685211	726658	530587	339565	341431	9510159	1453	4965	174843	2372556	10789	69203	118598861	33861	69387	1253395	2877	623594	1267	268044	13144	40633	348	393545	868078	201371	3318	14387	194	672687	168635824	267059416	227230	65546825	190869	6191600	56922967	65576846	206037	7598	4447	138072	1480	41203851	519610	31337057	329141	35215516	611043	39977130	34070433	30555324	30863231	30899845	30899671	519629	32457464	32705393	32842308	32814759	32742149	31351325	4276	26026	593209	50493	745335	66877211	72473309	287277970	60732887	935843	60001809	692119	173346179	2578	10144	65716	39722925	9498084	9712712	9712712	604164314	81986	260978721	230595	12687882	7653121	16188	7077		8227	384047	281259	45015597	245896766	245896766	588007	190	656198	11471	1148	4119	1398	30258	33518	5236597486
 2024-09-28	19063	2283159	2225812	2150193		2546485	216801	278016	104586	19849642	9409388	75821		41448	10615	175447	34347	3101919	3101919	4931	8211	11771	1915184	47707	14012	1878399	433145	1449263	2126	11847	10947	34588	3549	8047	9094				2937727	3025517	4145651	1986712	3025834	1635593	1859264	20797	115826	3340026	4019	4849	5671	54855	12969337	15910019	47792	14749031	5546630	12969340	224377	55211171	241612	40165483	141	5046	155799	290	1270	82906	82906	402	310	35510	2049	41234	43873	21166	1325		24071	1912	43815	17277	34911	13531	28774	18940	20379	13701	217899	522	104230	275237	8814	220065	137689		113135	59409158	193975949	1533582	1533178	30288	1615604	21171	1283	113855	473753	1274	759739513	199	305	130	12929	48152	12349	137319849	6318	16674	16849	21567	7229	11043		9063	56430	24587	110329	90619	79034	7836	124600	400728	10712	574	1486	8352	9693		10380	2390	11640889	13437484	14165019	25078	100805649	43830		71684	17541	18530	211759	67906210	66278052	47288	6471	32835	56097873	112162	28779	46840	27162	27199	2533621	2925554	5849918	14432954				4319	4337	4316	4298	1192	1798	7832	8040	1685211	726658	530587	339565	341431	9522934	1453	4965	174843	2372556	10789	69203	118657562	33861	69387	1253395	2877	623594	1267	268044	13144	40633	348	393545	868078	201371	3318	14387	194	672687	168636138	267059416	227230	65546825	190869	6191600	56922967	65576846	206037	7598	4447	138072	1480	41203851	528400	31608624	329141	35358694	613078	40139217	34193817	30937045	31262333	31281566	31281373	531842	32784770	33125990	33149472	33142065	33145755	31629738	4276	26026	593209	50502	745335	66877211	72473309	287277970	60732887	935843	60001809	692119	173346179	2578	10144	65716	39722925	9498084	9712712	9712712	604164314	81986	260978721	230595	12687882	7653121	16188	7077		8227	384047	281259	45015597	245896766	245896766	588007	190	656198	11471	1148	4119	1398	30258	33518	5240093853
 2024-10-08	19063	2283159	2225812	2150193		2546485	217446	278826	104586	19938580	9431518	75821		41448	10615	175447	34347	3101919	3101919	4931	8211	11771	1915184	47707	14012	1878399	433145	1449263	2126	11847	10947	34588	3549	8047	9094	9094	1533	1434	2937745	3025875	4162525	1986846	3026191	1634429	1859346	20797	115826	3340026	4019	4849	5671	54855	12969337	15910019	47792	14749031	5546630	12969340	224377	55211171	241612	40165483	141	5046	155799	290	1270	82906	82906	402	310	35510	2049	41234	43873	21166	1325		24071	1912	43815	17277	34911	13531	28774	18940	20379	13701	217899	522	104230	275237	8814	220065	137689		113135	59409158	193975949	1533582	1533178	30282	1645155	21310	1282	114937	477238	1274	770832917	199	305	130	12929	48152	12349	137319849	6318	16674	16849	21567	7229	11043		9063	56428	24587	110373	90619	79034	7837	124602	400771	10712	574	1486	8352	9693		10380	2390	11660930	13459019	14189546	25078	101043576	43829		71684	17541	18526	211759	68060620	66432148	47288	6471	32835	56251350	112162	28779	46842	27163	27199	2533621	2925554	5849918	14432954				4319	4337	4316	4298	1192	1798	7832	8040	1685211	726658	530587	339565	341431	9547208	1455	4965	174843	2372556	10789	69203	118680448	33861	69387	1253395	2877	623594	1267	270070	13144	41304	348	393545	868219	203666	3318	14709	194	679876	168636384	267059416	227230	65546825	190869	6191600	56922967	65576846	216654	7719	4435	142680	1511	41448659	529030	31645689	329141	35486202	615018	40263951	34290431	30997361	31319829	31341882	31341689	532472	32860319	33183885	33225215	33217614	33206609	31666803	4276	26026	593209	50523	745335	66877211	72473309	287277970	60732887	935843	60001809	692119	173346179	2578	10336	66728	41313492	9613808	9834392	9834392	532822218	82524	264947440	237103	12855457	7617387	16357	7263		7981	390829	282944	45329880	248838887	248838887	641755	191	698680	11471	1148	4119	1398	30258	33518	5194479012
+2024-10-12	19063	2283159	2225812	2150193		2546485	217809	279413	104586	19988521	9447146	75821		41448	10615	175447	34347	3101919	3101919	4931	8211	11771	1915184	47707	14012	1878399	433145	1449263	2126	11847	10947	34588	3549	8047	9094	9094	1533	1434	2937791	3044255	4171173	1988452	3044575	1635664	1860371	20798	115826	3340026	4019	4849	5671	54855	12969337	15910019	47792	14749031	5546630	12969340	224377	55211171	241612	40165483	141	5046	155799	290	1270	82906	82906	402	310	35510	2049	41234	43873	21166	1325		24071	1912	43815	17277	34911	13531	28774	18940	20379	13701	217899	522	104230	275237	8814	220065	137689		113135	59409158	193975949	1533582	1533178	30282	1645155	21310	1282	114937	477238	1274	770832917	199	305	130	12929	48152	12349	137319849	6318	16674	16849	21567	7229	11043		9063	56426	24587	110437	90618	79034	7837	124623	400910	10712	574	1486	8352	9693		10380	2390	11654277	13449374	14177749	25078	101041913	43827		71684	17541	18527	211762	68217911	66619410	47288	6471	32835	56353463	112162	28779	46842	27163	27199	2533621	2925554	5849918	14432954				4319	4337	4316	4298	1192	1798	7832	8040	1685211	726658	530587	339565	341431	9561234	1455	4965	174843	2372556	10789	69203	118680448	33861	69387	1253395	2877	623594	1267	270070	13144	41304	348	393545	868219	203666	3318	14709	194	679876	154618594	267059416	227230	65546825	190869	6191600	56922967	65576846	216654	7719	4435	142680	1511	41448659	529462	31680248	329243	35570093	616586	40350221	34372201	31035975	31352287	31380496	31380303	532904	32903026	33216964	33268661	33260321	33246345	31701362	4276	26026	593209	50493	745335	66877211	72473309	287277970	60732887	935843	60001809	692119	173346179	2578	10336	66728	41313492	9613808	9834392	9834392	532822218	82524	264947440	237103	12855457	7617387	16357	7263		7981	390829	282944	45329880	248838887	248838887	641755	191	698680	11471	1148	4119	1398	30258	33518	5181681751