{"id":"https://openalex.org/W4411754635","doi":"https://doi.org/10.1093/bioinformatics/btaf206","title":"Whole-genome phenotype prediction with machine learning: open problems in bacterial genomics","display_name":"Whole-genome phenotype prediction with machine learning: open problems in bacterial genomics","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411754635","doi":"https://doi.org/10.1093/bioinformatics/btaf206","pmid":"https://pubmed.ncbi.nlm.nih.gov/40581074"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf206","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf206","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf206/63545785/btaf206.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/btaf206/63545785/btaf206.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107870751","display_name":"T. James","orcid":null},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tamsin James","raw_affiliation_strings":["University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086450084","display_name":"Ben Williamson","orcid":"https://orcid.org/0000-0001-9356-3213"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Williamson","raw_affiliation_strings":["University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051182859","display_name":"Peter Ti\u0148o","orcid":"https://orcid.org/0000-0003-2330-128X"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Tino","raw_affiliation_strings":["University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, School of Computer Science , University Road West, Edgbaston , Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"University of Birmingham School of Computer Science, , Edgbaston, Birmingham, B15 2TT,","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050019061","display_name":"Nicole E. Wheeler","orcid":"https://orcid.org/0000-0003-4599-9164"},"institutions":[{"id":"https://openalex.org/I1280581677","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08","country_code":"US","type":"government","lineage":["https://openalex.org/I1280581677","https://openalex.org/I1296703163","https://openalex.org/I1330347796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicole Wheeler","raw_affiliation_strings":["Advanced Research and Invention Agency , 210 Euston Road , London, NW1 2DA,","Advanced Research and Invention Agency (ARIA) , London, NW1 2DA,"],"affiliations":[{"raw_affiliation_string":"Advanced Research and Invention Agency , 210 Euston Road , London, NW1 2DA,","institution_ids":["https://openalex.org/I1280581677"]},{"raw_affiliation_string":"Advanced Research and Invention Agency (ARIA) , London, NW1 2DA,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107870751"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":5.8975,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.96449437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"41","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9948999881744385,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.6770913004875183},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5817221999168396},{"id":"https://openalex.org/keywords/phenotype","display_name":"Phenotype","score":0.5617788434028625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5342504382133484},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.525844156742096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38636159896850586},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3532612919807434},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2776644229888916},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1728624701499939}],"concepts":[{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.6770913004875183},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5817221999168396},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.5617788434028625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5342504382133484},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.525844156742096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38636159896850586},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3532612919807434},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2776644229888916},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1728624701499939}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D013211","descriptor_name":"Staphylococcus aureus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaf206","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf206","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf206/63545785/btaf206.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:40581074","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40581074","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:pure.atira.dk:openaire/ba0449b6-77fc-44f7-9b15-ba48a3af04d6","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/ba0449b6-77fc-44f7-9b15-ba48a3af04d6","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"James, T, Williamson, B, Tino, P & Wheeler, N 2025, 'Whole-genome phenotype prediction with machine learning : open problems in bacterial genomics', Bioinformatics, vol. 41, no. 7, btaf206. https://doi.org/10.1093/bioinformatics/btaf206","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:12237507","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12237507","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/btaf206","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf206","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf206/63545785/btaf206.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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411754635.pdf","grobid_xml":"https://content.openalex.org/works/W4411754635.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2098969718","https://openalex.org/W2113651812","https://openalex.org/W2171980229","https://openalex.org/W2204678061","https://openalex.org/W2237956683","https://openalex.org/W2561048320","https://openalex.org/W2752250603","https://openalex.org/W2758908936","https://openalex.org/W2765855012","https://openalex.org/W2901155787","https://openalex.org/W2943862789","https://openalex.org/W2950299756","https://openalex.org/W2950417030","https://openalex.org/W2952473089","https://openalex.org/W2971492877","https://openalex.org/W2997828579","https://openalex.org/W3004252453","https://openalex.org/W3007426492","https://openalex.org/W3026996309","https://openalex.org/W3029806744","https://openalex.org/W3039127888","https://openalex.org/W3080298860","https://openalex.org/W3093665745","https://openalex.org/W3118363245","https://openalex.org/W3190916927","https://openalex.org/W3195766468","https://openalex.org/W3215234080","https://openalex.org/W4200051255","https://openalex.org/W4207023259","https://openalex.org/W4214840814","https://openalex.org/W4385481089","https://openalex.org/W4387661870","https://openalex.org/W4389050550","https://openalex.org/W4390005441","https://openalex.org/W4393192460","https://openalex.org/W4396663706","https://openalex.org/W6684942582","https://openalex.org/W6774720665","https://openalex.org/W6857379791"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W3178279768","https://openalex.org/W1840542775","https://openalex.org/W2416830231","https://openalex.org/W2888097224","https://openalex.org/W2773861473","https://openalex.org/W2053972265"],"abstract_inverted_index":{"Raw":[0],"sequencing":[1],"data":[2],"are":[3],"available":[4],"from":[5],"the":[6,26],"European":[7],"Nucleotide":[8],"Archive":[9],"(ENA)":[10],"under":[11],"project":[12],"accessions":[13],"ERP001012,":[14],"PRJEB3174,":[15],"PRJEB2655,":[16],"PRJEB2756,":[17],"and":[18,21,31],"PRJEB2944.":[19],"Assemblies":[20],"annotations":[22],"were":[23],"generated":[24],"with":[25],"Sanger":[27],"bacterial":[28],"pipeline":[29],"(https://github.com/sanger-pathogens/vr-codebase)":[30],"unitigs":[32],"extracted":[33],"using":[34],"DBGWAS":[35],"(https://gitlab.com/leoisl/dbgwas).":[36]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
