{"id":"https://openalex.org/W4416503985","doi":"https://doi.org/10.1093/bioinformatics/btaf636","title":"Benchmarking methods for measuring biosynthetic gene cluster similarity and determination of gene cluster families","display_name":"Benchmarking methods for measuring biosynthetic gene cluster similarity and determination of gene cluster families","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416503985","doi":"https://doi.org/10.1093/bioinformatics/btaf636","pmid":"https://pubmed.ncbi.nlm.nih.gov/41269115"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf636","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf636","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf636/65450454/btaf636.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf636/65450454/btaf636.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042280286","display_name":"Abiodun S. Oyedele","orcid":"https://orcid.org/0000-0001-9528-5288"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abiodun S Oyedele","raw_affiliation_strings":["Department of Chemistry, Vanderbilt University , Nashville, TN 37240,","Department of Chemistry, Vanderbilt University, 1234 Stevenson Center Lane, Nashville, TN 37240, United States"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Vanderbilt University , Nashville, TN 37240,","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Department of Chemistry, Vanderbilt University, 1234 Stevenson Center Lane, Nashville, TN 37240, United States","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044272398","display_name":"Allison S. Walker","orcid":"https://orcid.org/0000-0001-5666-7232"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allison S Walker","raw_affiliation_strings":["Department of Biological Sciences, Vanderbilt University , Nashville, TN 37235,","Department of Chemistry, Vanderbilt University , Nashville, TN 37240,","Department of Pathology, Microbiology, and Immunology, Vanderbilt University Medical Center , Nashville, TN 37232,","Department of Chemistry, Vanderbilt University, 1234 Stevenson Center Lane, Nashville, TN 37240, United States","Department of Pathology, Microbiology, and Immunology, 1211 Medical Center Drive, Vanderbilt University Medical Center, Nashville, TN 37232, United States"],"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Vanderbilt University , Nashville, TN 37235,","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Department of Chemistry, Vanderbilt University , Nashville, TN 37240,","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Department of Pathology, Microbiology, and Immunology, Vanderbilt University Medical Center , Nashville, TN 37232,","institution_ids":["https://openalex.org/I901861585"]},{"raw_affiliation_string":"Department of Chemistry, Vanderbilt University, 1234 Stevenson Center Lane, Nashville, TN 37240, United States","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Department of Pathology, Microbiology, and Immunology, 1211 Medical Center Drive, Vanderbilt University Medical Center, Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I901861585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042280286"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.7625,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77749708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"41","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.34220001101493835,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.34220001101493835,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.24879999458789825,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.0617000013589859,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8629999756813049},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6751000285148621},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6596999764442444},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5378999710083008},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42410001158714294},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8629999756813049},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6751000285148621},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6596999764442444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402999758720398},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5917999744415283},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47130000591278076},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C36857842","wikidata":"https://www.wikidata.org/wiki/Q1501261","display_name":"Gene cluster","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3366999924182892},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.25589999556541443}],"mesh":[{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf636","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf636","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf636/65450454/btaf636.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41269115","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41269115","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12701797","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12701797/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf636","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf636","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf636/65450454/btaf636.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3262142318","display_name":null,"funder_award_id":"14698","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7294413678","display_name":null,"funder_award_id":"R35GM146987","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320309151","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416503985.pdf","grobid_xml":"https://content.openalex.org/works/W4416503985.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1961959471","https://openalex.org/W1984994707","https://openalex.org/W1996395911","https://openalex.org/W1998455136","https://openalex.org/W2005790390","https://openalex.org/W2013718446","https://openalex.org/W2046006818","https://openalex.org/W2060531713","https://openalex.org/W2087704167","https://openalex.org/W2090199399","https://openalex.org/W2126714764","https://openalex.org/W2127278475","https://openalex.org/W2145974700","https://openalex.org/W2151697120","https://openalex.org/W2171908015","https://openalex.org/W2318475905","https://openalex.org/W2340848047","https://openalex.org/W2587544700","https://openalex.org/W2692027428","https://openalex.org/W2781489468","https://openalex.org/W2893448478","https://openalex.org/W2900421900","https://openalex.org/W2961626135","https://openalex.org/W2970013364","https://openalex.org/W2984933828","https://openalex.org/W2990471452","https://openalex.org/W2990586204","https://openalex.org/W3011366455","https://openalex.org/W3119952098","https://openalex.org/W3121081543","https://openalex.org/W3141260513","https://openalex.org/W3176180864","https://openalex.org/W3207256498","https://openalex.org/W4225416490","https://openalex.org/W4283659942","https://openalex.org/W4300772404","https://openalex.org/W4309305948","https://openalex.org/W4367833791","https://openalex.org/W4368358469","https://openalex.org/W4377861946","https://openalex.org/W4396494616","https://openalex.org/W4399972112","https://openalex.org/W4401103147","https://openalex.org/W4404349982","https://openalex.org/W4405220977","https://openalex.org/W4406817136","https://openalex.org/W4408387458","https://openalex.org/W4409409776"],"related_works":[],"abstract_inverted_index":{"Scripts":[0],"and":[1,12,16],"data":[2],"required":[3],"to":[4],"reproduce":[5],"the":[6],"results":[7],"are":[8,18],"available":[9,20,26],"at":[10,21,27],"https://github.com/aswalker-lab/BGC-clustering-benchmark":[11],"processed":[13],"similarity,":[14],"clusters,":[15],"scaffolds":[17],"also":[19,25],"https://huggingface.co/datasets/allie-walker/BGC-clustering-benchmark.":[22],"Code":[23],"is":[24],"Zenodo:":[28],"10.5281/zenodo.17373546.":[29]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-23T00:00:00"}
