{"id":"https://openalex.org/W7161625623","doi":"https://doi.org/10.1186/s12859-026-06473-5","title":"Machine learning framework for cost effective deep mutational scanning through targeted substitution profiling","display_name":"Machine learning framework for cost effective deep mutational scanning through targeted substitution profiling","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161625623","doi":"https://doi.org/10.1186/s12859-026-06473-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/42157089"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06473-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06473-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06473-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Emily Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Emily Morgan","raw_affiliation_strings":["Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa","institution_ids":["https://openalex.org/I203238179"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaylyn Govender","orcid":null},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Shaylyn Govender","raw_affiliation_strings":["Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa","institution_ids":["https://openalex.org/I203238179"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Prashant Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I2800139495","display_name":"Science for Life Laboratory","ror":"https://ror.org/04ev03g22","country_code":"SE","type":"facility","lineage":["https://openalex.org/I2800139495"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Prashant Singh","raw_affiliation_strings":["Department of Information Technology, Science for Life Laboratory, Scientific Computing, Uppsala University, Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Science for Life Laboratory, Scientific Computing, Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I2800139495"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ian Goodfellow","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Goodfellow","raw_affiliation_strings":["Division of Virology, Department of Pathology, University of Cambridge, Cambridge, CB2 1QP, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Virology, Department of Pathology, University of Cambridge, Cambridge, CB2 1QP, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stephen C. Graham","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stephen C. Graham","raw_affiliation_strings":["Division of Virology, Department of Pathology, University of Cambridge, Cambridge, CB2 1QP, UK. scg34@cam.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Virology, Department of Pathology, University of Cambridge, Cambridge, CB2 1QP, UK. scg34@cam.ac.uk","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nigel T. Bishop","orcid":null},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]},{"id":"https://openalex.org/I4210106521","display_name":"National Institute for Theoretical Physics","ror":"https://ror.org/01jgv6w72","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I4210106521"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Nigel T. Bishop","raw_affiliation_strings":["Department of Pure and Applied Mathematics, Rhodes University, Makhanda, 6139, South Africa. n.bishop@ru.ac.za","National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch, South Africa. n.bishop@ru.ac.za"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Mathematics, Rhodes University, Makhanda, 6139, South Africa. n.bishop@ru.ac.za","institution_ids":["https://openalex.org/I203238179"]},{"raw_affiliation_string":"National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch, South Africa. n.bishop@ru.ac.za","institution_ids":["https://openalex.org/I4210106521"]}]},{"author_position":"last","author":{"id":null,"display_name":"\u00d6zlem Tastan Bishop","orcid":null},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]},{"id":"https://openalex.org/I4210106521","display_name":"National Institute for Theoretical Physics","ror":"https://ror.org/01jgv6w72","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I4210106521"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"\u00d6zlem Tastan Bishop","raw_affiliation_strings":["National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch, South Africa. o.tastanbishop@ru.ac.za","Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa. o.tastanbishop@ru.ac.za"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch, South Africa. o.tastanbishop@ru.ac.za","institution_ids":["https://openalex.org/I4210106521"]},{"raw_affiliation_string":"Research Unit in Bioinformatics (RUBi), Department of Biochemistry, Microbiology and Bioinformatics, Rhodes University, Makhanda, 6139, South Africa. o.tastanbishop@ru.ac.za","institution_ids":["https://openalex.org/I203238179"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203238179","https://openalex.org/I241749","https://openalex.org/I4210106521"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46435999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.3334999978542328,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.3334999978542328,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.09549999982118607,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.08560000360012054,"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/support-vector-machine","display_name":"Support vector machine","score":0.6238999962806702},{"id":"https://openalex.org/keywords/amino-acid-substitution","display_name":"Amino acid substitution","score":0.5813000202178955},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5752999782562256},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.515999972820282},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3675999939441681},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.3580999970436096},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.32269999384880066},{"id":"https://openalex.org/keywords/deep-sequencing","display_name":"Deep sequencing","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7493000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.728600025177002},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5943999886512756},{"id":"https://openalex.org/C2993683473","wikidata":"https://www.wikidata.org/wiki/Q30693176","display_name":"Amino acid substitution","level":4,"score":0.5813000202178955},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.3190000057220459},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3084999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.25529998540878296}],"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":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086782","descriptor_name":"Coronavirus 3C Proteases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000093743","descriptor_name":"Random Forest","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098412","descriptor_name":"Predictive Learning Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098412","descriptor_name":"Predictive Learning Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098412","descriptor_name":"Predictive Learning Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098429","descriptor_name":"Classification Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098429","descriptor_name":"Classification Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098429","descriptor_name":"Classification Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003362","descriptor_name":"Cost-Benefit Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003362","descriptor_name":"Cost-Benefit Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003362","descriptor_name":"Cost-Benefit Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000191","qualifier_name":"economics","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000191","qualifier_name":"economics","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000191","qualifier_name":"economics","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/s12859-026-06473-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06473-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42157089","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42157089","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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/404946","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/404946","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/f9e1dd52-fbad-44c7-994e-eac190bc0179/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:DiVA.org:uu-593077","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-593077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400653","display_name":"Diva portal (Dalarna University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:73dae6ffefb54976a16abb9356cbc8d0","is_oa":false,"landing_page_url":"https://doaj.org/article/73dae6ffefb54976a16abb9356cbc8d0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13274108","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13274108/","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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06473-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06473-5","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G837346312","display_name":null,"funder_award_id":"NNF23SA0084504","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320324119","display_name":"Uppsala Universitet","ror":"https://ror.org/048a87296"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2060588922","https://openalex.org/W2068638854","https://openalex.org/W2139365100","https://openalex.org/W2144893575","https://openalex.org/W2339766289","https://openalex.org/W2999290641","https://openalex.org/W3012384638","https://openalex.org/W3038248848","https://openalex.org/W3048714202","https://openalex.org/W3098471978","https://openalex.org/W3112879688","https://openalex.org/W3186934009","https://openalex.org/W3202411178","https://openalex.org/W3215514970","https://openalex.org/W4283161447","https://openalex.org/W4283364403","https://openalex.org/W4315641072","https://openalex.org/W4378530277","https://openalex.org/W4380422659","https://openalex.org/W4386818197","https://openalex.org/W4400906358","https://openalex.org/W4402836611","https://openalex.org/W4403627687","https://openalex.org/W4409564264","https://openalex.org/W4409657019","https://openalex.org/W4411865423","https://openalex.org/W4412707732","https://openalex.org/W4413139494"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Deep":[1],"mutational":[2],"scanning":[3],"(DMS)":[4],"provides":[5],"comprehensive":[6],"maps":[7],"of":[8,27,34,73,83,122],"protein":[9,140],"variant":[10,171],"effects":[11],"but":[12],"remains":[13],"experimentally":[14],"intensive.":[15],"Machine":[16],"learning":[17],"(ML)":[18],"approaches":[19],"have":[20],"the":[21,31,84,123],"potential":[22],"to":[23,55,135,169],"reduce":[24,156],"experimental":[25],"burden":[26],"DMS":[28,48,136,151],"by":[29],"predicting":[30],"functional":[32,61],"impact":[33],"substitutions":[35,59],"from":[36,50],"limited":[37],"data.":[38],"RESULTS:":[39],"We":[40],"introduced":[41],"a":[42,166],"ML":[43,154],"classifier":[44],"trained":[45],"on":[46],"normalised":[47],"scores":[49,76,91],"SARS-CoV-2":[51,112],"main":[52],"protease":[53],"(Mpro)":[54],"categorise":[56],"amino":[57],"acid":[58],"as":[60],"(wild-type-like)":[62],"or":[63],"non-functional.":[64],"Using":[65],"brute-force":[66],"feature":[67],"selection,":[68],"we":[69],"identified":[70],"minimal":[71],"subsets":[72],"six":[74],"substitution":[75],"per":[77],"residue":[78],"that":[79,138,149],"enable":[80],"accurate":[81],"classification":[82,163],"remaining":[85],"substitutions,":[86],"achieving":[87],"minimum":[88],"(worst":[89],"accuracy)":[90],"exceeding":[92],"90%.":[93],"Models":[94],"including":[95],"support":[96],"vector":[97],"machines,":[98],"random":[99],"forests,":[100],"and":[101,115,130,158],"logistic":[102],"regression":[103],"were":[104],"evaluated":[105],"without":[106],"retraining":[107],"(zero-shot":[108],"prediction)":[109],"against":[110,116],"additional":[111],"Mpro":[113],"datasets":[114],"unrelated":[117],"datasets.":[118],"The":[119,146],"zero-shot":[120],"performance":[121],"models":[124],"was":[125],"strongest":[126],"for":[127],"other":[128],"enzymes":[129],"more":[131],"modest":[132],"when":[133],"applied":[134],"systems":[137],"assess":[139],"folding":[141],"and/or":[142],"protein-protein":[143],"interactions.":[144],"CONCLUSION:":[145],"results":[147],"show":[148],"targeted":[150],"combined":[152],"with":[153],"can":[155],"sequencing":[157],"reagent":[159],"costs":[160],"while":[161],"preserving":[162],"accuracy,":[164],"offering":[165],"practical":[167],"route":[168],"accelerate":[170],"effect":[172],"prediction.":[173]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2026-05-19T00:00:00"}
