diff --git a/config.yaml b/config.yaml index 5365f712..c839ad5b 100644 --- a/config.yaml +++ b/config.yaml @@ -1,12 +1,12 @@ # Build information. Currently unstructured -- you can use this to write down any notes on what is going on with # this specific build of Babel. build: - branch: babel-1.14 + branch: babel-1.15 # Versions that need to be updated on every release. -biolink_version: "4.3.2" -umls_version: "2025AA" -rxnorm_version: "10062025" +biolink_version: "4.3.6" +umls_version: "2025AB" +rxnorm_version: "12012025" drugbank_version: "5-1-13" # Overall inputs and outputs. diff --git a/input_data/manual_concords/disease.txt b/input_data/manual_concords/disease.txt index a7765282..daa9cd51 100644 --- a/input_data/manual_concords/disease.txt +++ b/input_data/manual_concords/disease.txt @@ -123,4 +123,9 @@ EFO:1001390 oio:closeMatch UMLS:C2936258 HP:0040412 oio:closeMatch UMLS:C0587044 EFO:1001348 oio:closeMatch UMLS:C1136321 MONDO:0015517 oio:closeMatch DOID:12177 -EFO:1001863 oio:closeMatch UMLS:C0042135 \ No newline at end of file +EFO:1001863 oio:closeMatch UMLS:C0042135 + +# Diabetes (UMLS:C0011847) is mapped to ICD10CM:E11, which is specifically +# type 2 diabetes mellitus. So we should combine it with the MONDO term. +UMLS:C0011847 oio:exactMatch MONDO:0005148 + diff --git a/input_data/manual_concords/drugchemical.tsv b/input_data/manual_concords/drugchemical.tsv index 4139714e..bbe6fd1b 100644 --- a/input_data/manual_concords/drugchemical.tsv +++ b/input_data/manual_concords/drugchemical.tsv @@ -30,4 +30,4 @@ CHEBI:136034 skos:relatedMatch HMDB:HMDB0254418 "Not sure why these aren’t com CHEBI:59173 skos:relatedMatch PUBCHEM.COMPOUND:19797045 Conflating all the bivalirudin cliques into a single conflated clique https://github.com/TranslatorSRI/Babel/issues/346 CHEBI:59173 skos:relatedMatch PUBCHEM.COMPOUND:78357798 Conflating all the bivalirudin cliques into a single conflated clique https://github.com/TranslatorSRI/Babel/issues/346 MESH:D013668 skos:exactMatch CHEMBL.COMPOUND:CHEMBL1201522 Appears to be the same concept https://github.com/TranslatorSRI/NodeNormalization/issues/280 -UNII:2S9ZZM9Q9V skos:exactMatch UMLS:C0796392 "UNII:2S9ZZM9Q9V includes UMLS:C0796392 as an identifier, but is also generated as its own clique by the protein module." https://github.com/NCATSTranslator/Feedback/issues/970 \ No newline at end of file +UNII:2S9ZZM9Q9V skos:exactMatch UMLS:C0796392 "UNII:2S9ZZM9Q9V includes UMLS:C0796392 as an identifier, but is also generated as its own clique by the protein module." https://github.com/NCATSTranslator/Feedback/issues/970 diff --git a/src/snakefiles/publications.snakefile b/src/snakefiles/publications.snakefile index 8002cf4f..0f396e92 100644 --- a/src/snakefiles/publications.snakefile +++ b/src/snakefiles/publications.snakefile @@ -1,3 +1,5 @@ +import os + import src.createcompendia.publications as publications import src.assess_compendia as assessments from src.snakefiles import util @@ -65,10 +67,11 @@ rule generate_pubmed_compendia: publications.generate_compendium( [input.pmid_doi_concord_file], [input.metadata_yaml], [input.pmid_id_file], input.titles, output.publication_compendium, input.icrdf_filename ) - # generate_compendium() will generate an (empty) Publication.txt.gz file, but we need + # generate_compendium() will generate an (empty) Publication.txt file, but we need # to compress it. publication_synonyms = os.path.splitext(output.publication_synonyms_gz)[0] util.gzip_files([publication_synonyms]) + os.remove(publication_synonyms) rule check_publications_completeness: