{"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","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/12237507"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf206","doi":"https://doi.org/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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","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":null,"display_name":"Tamsin James","orcid":"https://orcid.org/0009-0009-3498-8567","observed_orcids":["https://orcid.org/0009-0009-3498-8567"]},"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,"],"raw_orcid":"https://orcid.org/0009-0009-3498-8567","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":null,"display_name":"Ben Williamson","orcid":null,"observed_orcids":[]},"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,"],"raw_orcid":null,"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 B","orcid":"https://orcid.org/0000-0003-2330-128X","observed_orcids":["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,"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0003-4599-9164"]},"institutions":[{"id":"https://openalex.org/I4405262244","display_name":"Advanced Research + Invention Agency","ror":"https://ror.org/028y4g372","country_code":"GB","type":"government","lineage":["https://openalex.org/I4405262244"]}],"countries":["GB"],"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,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research and Invention Agency , 210 Euston Road , London, NW1 2DA,","institution_ids":["https://openalex.org/I4405262244"]},{"raw_affiliation_string":"Advanced Research and Invention Agency (ARIA) , London, NW1 2DA,","institution_ids":["https://openalex.org/I4405262244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":5.6717,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97408979,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"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":0.33230000734329224,"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":0.33230000734329224,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.13570000231266022,"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"}},{"id":"https://openalex.org/T10195","display_name":"Antimicrobial Resistance in Staphylococcus","score":0.12620000541210175,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phenotype-prediction","display_name":"phenotype prediction","score":0.5979999899864197},{"id":"https://openalex.org/keywords/bacterial-genomics","display_name":"bacterial genomics","score":0.8550000190734863},{"id":"https://openalex.org/keywords/genotype-phenotype-map","display_name":"genotype-phenotype mapping","score":0.8080000281333923},{"id":"https://openalex.org/keywords/causal-inference","display_name":"causal inference","score":0.7400000095367432},{"id":"https://openalex.org/keywords/linkage-disequilibrium","display_name":"linkage disequilibrium","score":0.7509999871253967},{"id":"https://openalex.org/keywords/confounding","display_name":"confounding","score":0.699999988079071},{"id":"https://openalex.org/keywords/staphylococcus-aureus","display_name":"Staphylococcus aureus","score":0.8740000128746033},{"id":"https://openalex.org/keywords/whole-genome-sequencing","display_name":"whole genome sequencing","score":0.6769999861717224},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.5600000023841858},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.6610000133514404},{"id":"https://openalex.org/keywords/genetic-variants","display_name":"genetic variants","score":0.3930000066757202}],"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":"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":"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":"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}],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btaf206","doi":"https://doi.org/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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"pmh:oai:pubmedcentral.nih.gov:12237507","doi":null,"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":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmid:40581074","doi":null,"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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:pure.atira.dk:openaire/ba0449b6-77fc-44f7-9b15-ba48a3af04d6","doi":null,"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,"listed_in":[],"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:arXiv.org:2502.07749","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07749","pdf_url":"https://arxiv.org/pdf/2502.07749","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.07749","doi":"https://doi.org/10.48550/arxiv.2502.07749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.07749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf206","doi":"https://doi.org/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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":[{"score":0.6240000128746033,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"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":36,"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"],"related_works":["https://openalex.org/W4411114967","https://openalex.org/W7120578044","https://openalex.org/W2991470468","https://openalex.org/W3039127888","https://openalex.org/W2991289247","https://openalex.org/W4200051255","https://openalex.org/W4413612456","https://openalex.org/W7167277744","https://openalex.org/W2950419643","https://openalex.org/W4385799726"],"abstract_inverted_index":{"MOTIVATION:":[0],"How":[1],"can":[2,81],"we":[3,80,101,180],"identify":[4,141],"causal":[5,119],"genetic":[6,95],"mechanisms":[7],"governing":[8],"bacterial":[9,62,94,110,219],"traits?":[10],"Initial":[11],"efforts":[12,86],"entrusting":[13],"machine":[14,169],"learning":[15,118,170],"models":[16,39],"to":[17,32,42,117],"handle":[18],"the":[19,37,71,126,147,150,184,197,217],"task":[20],"of":[21,99,128,136,144,149,175],"predicting":[22],"phenotype":[23,107],"from":[24,36,109,196],"genotype":[25],"yield":[26],"high":[27],"accuracy":[28],"scores.":[29],"However,":[30],"attempts":[31],"extract":[33],"meaningful":[34],"interpretations":[35],"predictive":[38],"are":[40,70,87,194],"found":[41],"be":[43],"corrupted":[44],"by":[45],"falsely":[46],"identified":[47],"'causal'":[48],"features.":[49],"Relying":[50],"solely":[51],"on":[52],"pattern":[53],"recognition":[54],"and":[55,67,113,121,162,209,212,222],"correlations":[56],"is":[57,75],"unreliable,":[58],"significantly":[59],"so":[60],"in":[61,146,158],"genomics":[63],"settings":[64],"where":[65],"high-dimensionality":[66],"spurious":[68],"associations":[69],"norm.":[72],"Though":[73],"it":[74],"not":[76],"yet":[77],"clear":[78],"whether":[79],"overcome":[82],"this":[83,137],"hurdle,":[84],"significant":[85],"being":[88],"made":[89],"towards":[90],"discovering":[91],"potential":[92],"high-risk":[93],"variants.":[96],"In":[97],"view":[98],"this,":[100],"set":[102],"up":[103],"open":[104,186],"problems":[105],"surrounding":[106,183],"prediction":[108],"whole-genome":[111],"datasets":[112,135],"extending":[114],"those":[115],"approaches":[116],"effects,":[120],"discuss":[122],"challenges":[123,182],"that":[124],"impact":[125],"reliability":[127],"a":[129,173],"machine's":[130],"decision-making":[131],"when":[132],"faced":[133],"with":[134,216],"nature.":[138],"RESULTS:":[139],"We":[140],"major":[142],"sources":[143],"non-injectivity":[145],"formulation":[148],"genotype-to-phenotype":[151],"mapping":[152],"function-linkage-disequilibrium,":[153],"limited":[154],"sampling,":[155],"information":[156],"loss":[157],"representations,":[159],"unmeasured":[160],"confounders":[161],"observational":[163],"noise-and":[164],"analyse":[165],"their":[166],"implications":[167],"for":[168],"applications.":[171],"Using":[172],"collection":[174],"4,140":[176],"Staphylococcus":[177],"aureus":[178],"isolates,":[179],"illustrate":[181],"defined":[185],"problems.":[187],"AVAILABILITY":[188],"AND":[189],"IMPLEMENTATION:":[190],"Raw":[191],"sequencing":[192],"data":[193],"available":[195],"European":[198],"Nucleotide":[199],"Archive":[200],"(ENA)":[201],"under":[202],"project":[203],"accessions":[204],"ERP001012,":[205],"PRJEB3174,":[206],"PRJEB2655,":[207],"PRJEB2756,":[208],"PRJEB2944.":[210],"Assemblies":[211],"annotations":[213],"were":[214],"generated":[215],"Sanger":[218],"pipeline":[220],"(https://github.com/sanger-pathogens/vr-codebase)":[221],"unitigs":[223],"extracted":[224],"using":[225],"DBGWAS":[226],"(https://gitlab.com/leoisl/dbgwas).":[227]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":4}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2025-10-10T00:00:00"}