{"id":"https://openalex.org/W4416676737","doi":"https://doi.org/10.3389/fbinf.2025.1694009","title":"Bacteriocin prediction through cross-validation-based and hypergraph-based feature evaluation approaches","display_name":"Bacteriocin prediction through cross-validation-based and hypergraph-based feature evaluation approaches","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4416676737","doi":"https://doi.org/10.3389/fbinf.2025.1694009","pmid":"https://pubmed.ncbi.nlm.nih.gov/41377699"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1694009","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694009","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694009/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694009/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083442473","display_name":"Suraiya Akhter","orcid":"https://orcid.org/0000-0001-6577-2034"},"institutions":[{"id":"https://openalex.org/I16109614","display_name":"Washington State University Tri-Cities","ror":"https://ror.org/02sjef319","country_code":"US","type":"education","lineage":["https://openalex.org/I16109614","https://openalex.org/I72951846"]},{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]},{"id":"https://openalex.org/I93131583","display_name":"Emporia State University","ror":"https://ror.org/04e6r1478","country_code":"US","type":"education","lineage":["https://openalex.org/I93131583"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suraiya Akhter","raw_affiliation_strings":["School of Business and Technology, Emporia State University, Emporia, KS, United States","School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, United States","School of Engineering and Applied Sciences, Washington State University Tri-Cities, Richland, WA, United States"],"affiliations":[{"raw_affiliation_string":"School of Business and Technology, Emporia State University, Emporia, KS, United States","institution_ids":["https://openalex.org/I93131583"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, United States","institution_ids":["https://openalex.org/I72951846"]},{"raw_affiliation_string":"School of Engineering and Applied Sciences, Washington State University Tri-Cities, Richland, WA, United States","institution_ids":["https://openalex.org/I16109614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021738971","display_name":"John H. Miller","orcid":"https://orcid.org/0000-0001-6383-1037"},"institutions":[{"id":"https://openalex.org/I16109614","display_name":"Washington State University Tri-Cities","ror":"https://ror.org/02sjef319","country_code":"US","type":"education","lineage":["https://openalex.org/I16109614","https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. Miller","raw_affiliation_strings":["School of Engineering and Applied Sciences, Washington State University Tri-Cities, Richland, WA, United States"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Washington State University Tri-Cities, Richland, WA, United States","institution_ids":["https://openalex.org/I16109614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083442473"],"corresponding_institution_ids":["https://openalex.org/I16109614","https://openalex.org/I72951846","https://openalex.org/I93131583"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31170643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"1694009","last_page":"1694009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9345999956130981,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9345999956130981,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.016599999740719795,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.009800000116229057,"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/feature-selection","display_name":"Feature selection","score":0.7925999760627747},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7720000147819519},{"id":"https://openalex.org/keywords/bacteriocin","display_name":"Bacteriocin","score":0.6434000134468079},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4311999976634979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.37529999017715454},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7925999760627747},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7720000147819519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614999771118164},{"id":"https://openalex.org/C115574571","wikidata":"https://www.wikidata.org/wiki/Q183119","display_name":"Bacteriocin","level":3,"score":0.6434000134468079},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5497999787330627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5437999963760376},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2025.1694009","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694009","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694009/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41377699","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41377699","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:b481c47d1a6b4bcca01efc1235186017","is_oa":true,"landing_page_url":"https://doaj.org/article/b481c47d1a6b4bcca01efc1235186017","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12685867","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12685867/","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1694009","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694009","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694009/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416676737.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1544835748","https://openalex.org/W1908709110","https://openalex.org/W1985818354","https://openalex.org/W1989998611","https://openalex.org/W1992384972","https://openalex.org/W1992743450","https://openalex.org/W2047672715","https://openalex.org/W2054136420","https://openalex.org/W2058919317","https://openalex.org/W2067964678","https://openalex.org/W2072465905","https://openalex.org/W2078868070","https://openalex.org/W2084845164","https://openalex.org/W2097356092","https://openalex.org/W2105018887","https://openalex.org/W2107758049","https://openalex.org/W2113796404","https://openalex.org/W2121363497","https://openalex.org/W2122446900","https://openalex.org/W2157259034","https://openalex.org/W2159861471","https://openalex.org/W2170747616","https://openalex.org/W2171464043","https://openalex.org/W2172592212","https://openalex.org/W2295598076","https://openalex.org/W2317417725","https://openalex.org/W2500660203","https://openalex.org/W2791210395","https://openalex.org/W2803753687","https://openalex.org/W2884913705","https://openalex.org/W2887890204","https://openalex.org/W2888315807","https://openalex.org/W2894875598","https://openalex.org/W2951765074","https://openalex.org/W2971976902","https://openalex.org/W2999266361","https://openalex.org/W2999615587","https://openalex.org/W3124390867","https://openalex.org/W3153803914","https://openalex.org/W3192454714","https://openalex.org/W3210846046","https://openalex.org/W3217475918","https://openalex.org/W4220765486","https://openalex.org/W4289860739","https://openalex.org/W4312131391","https://openalex.org/W4313420307","https://openalex.org/W4385954015","https://openalex.org/W4390706033","https://openalex.org/W4403688447"],"related_works":[],"abstract_inverted_index":{"Bacteriocins":[0],"offer":[1],"a":[2,13,27],"promising":[3],"solution":[4],"to":[5,11,30,74,112,179,188],"antibiotic":[6],"resistance,":[7],"possessing":[8],"the":[9,48,55,82,96,127,140,145,165,170,196],"ability":[10],"target":[12],"wide":[14],"range":[15],"of":[16,63,162,198],"bacteria":[17],"with":[18,221],"precision.":[19],"Thus,":[20],"there":[21],"is":[22],"an":[23,160],"urgent":[24],"need":[25],"for":[26,191,225],"computational":[28],"model":[29,147],"predict":[31],"new":[32],"bacteriocins":[33],"and":[34,60,71,89,118,159,175,211,217],"aid":[35],"in":[36],"drug":[37],"development.":[38],"This":[39],"work":[40],"centers":[41],"on":[42,54,103,164],"constructing":[43],"web-based":[44],"predictive":[45],"models":[46,123],"using":[47,126,148,214],"XGBoost":[49,122],"machine":[50],"learning":[51],"algorithm,":[52],"based":[53],"physicochemical":[56],"properties,":[57],"structural":[58],"characteristics,":[59],"sequence":[61],"profiles":[62],"protein":[64],"sequences.":[65],"We":[66,137],"employed":[67],"correlation":[68],"analyses,":[69],"cross-validation,":[70],"hypergraph-based":[72,98,218],"techniques":[73],"select":[75],"features.":[76],"Cross-validated":[77],"feature":[78,99,117,134,141,172,226],"selection":[79],"(CVFS)":[80],"partitions":[81],"dataset,":[83],"selects":[84],"features":[85,129,185],"within":[86],"each":[87],"partition,":[88],"identifies":[90],"common":[91],"features,":[92],"ensuring":[93],"representativeness.":[94],"On":[95],"contrary,":[97],"evaluation":[100,135,173],"(HFE)":[101],"focuses":[102],"minimizing":[104],"hypergraph":[105],"cut":[106],"conductance,":[107],"leveraging":[108],"higher-order":[109],"data":[110],"relationships":[111],"precisely":[113],"utilize":[114],"information":[115],"regarding":[116],"sample":[119],"correlations.":[120],"The":[121,182],"were":[124],"built":[125],"selected":[128],"obtained":[130],"from":[131,144],"these":[132],"two":[133],"methods.":[136],"also":[138],"analyzed":[139],"contributions":[142],"directly":[143],"best":[146],"SHapley":[149],"Additive":[150],"exPlanations":[151],"(SHAP).":[152],"Our":[153,200],"HFE-based":[154],"approach":[155],"achieved":[156],"99.11%":[157],"accuracy":[158],"AUC":[161],"0.9974":[163],"test":[166],"data,":[167],"overall":[168],"outperforming":[169],"CVFS-based":[171],"method":[174],"yielding":[176],"results":[177],"comparable":[178],"existing":[180],"approaches.":[181],"most":[183],"influential":[184],"are":[186],"related":[187],"solvent":[189],"accessibility":[190],"buried":[192],"residues,":[193],"followed":[194],"by":[195],"composition":[197],"cysteine.":[199],"web":[201],"application,":[202],"accessible":[203],"at":[204],"https://shiny.tricities.wsu.edu/bacteriocin-prediction/,":[205],"offers":[206],"prediction":[207],"results,":[208],"probability":[209],"scores,":[210],"SHAP":[212],"plots":[213],"both":[215],"cross-validation-":[216],"methods,":[219],"along":[220],"previously":[222],"implemented":[223],"approaches":[224],"selection.":[227]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-25T00:00:00"}