{"id":"https://openalex.org/W3097323088","doi":"https://doi.org/10.1186/s12859-020-03835-5","title":"Improved cytokine\u2013receptor interaction prediction by exploiting the negative sample space","display_name":"Improved cytokine\u2013receptor interaction prediction by exploiting the negative sample space","publication_year":2020,"publication_date":"2020-10-31","ids":{"openalex":"https://openalex.org/W3097323088","doi":"https://doi.org/10.1186/s12859-020-03835-5","mag":"3097323088","pmid":"https://pubmed.ncbi.nlm.nih.gov/33129275"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-020-03835-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03835-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03835-5","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","license_id":"https://openalex.org/licenses/cc-by","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://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03835-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004453727","display_name":"Abhigyan Nath","orcid":"https://orcid.org/0000-0003-1253-7115"},"institutions":[{"id":"https://openalex.org/I2799791569","display_name":"Pt. Jawahar Lal Nehru Memorial Medical College","ror":"https://ror.org/04h4g6162","country_code":"IN","type":"education","lineage":["https://openalex.org/I2799791569"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhigyan Nath","raw_affiliation_strings":["Department of Biochemistry, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, 492001, India. abhigyannath01@gmail.com","Department of Biochemistry, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, 492001, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, 492001, India. abhigyannath01@gmail.com","institution_ids":["https://openalex.org/I2799791569"]},{"raw_affiliation_string":"Department of Biochemistry, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, 492001, India","institution_ids":["https://openalex.org/I2799791569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042438246","display_name":"Andr\u00e9 Leier","orcid":"https://orcid.org/0000-0002-2647-2693"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andr\u00e9 Leier","raw_affiliation_strings":["Department of Genetics, Department of Cell Developmental and Integrative Biology, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA. leier.andre@gmail.com","Department of Genetics, Department of Cell Developmental and Integrative Biology, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":"https://orcid.org/0000-0002-2647-2693","affiliations":[{"raw_affiliation_string":"Department of Genetics, Department of Cell Developmental and Integrative Biology, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA. leier.andre@gmail.com","institution_ids":["https://openalex.org/I32389192"]},{"raw_affiliation_string":"Department of Genetics, Department of Cell Developmental and Integrative Biology, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004453727","https://openalex.org/A5042438246"],"corresponding_institution_ids":["https://openalex.org/I2799791569","https://openalex.org/I32389192"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.5005,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.82670953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"493","last_page":"493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.6783000230789185,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.6783000230789185,"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":0.11919999867677689,"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":0.06679999828338623,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6893417239189148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6562003493309021},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6206211447715759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.602825403213501},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.591090202331543},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5085412263870239},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47996068000793457},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4589915871620178},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4458746910095215},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4399031400680542},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42020130157470703},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.41922739148139954},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4104800224304199},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3804224133491516},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17993363738059998},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15610653162002563}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6893417239189148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6562003493309021},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6206211447715759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.602825403213501},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.591090202331543},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5085412263870239},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47996068000793457},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4589915871620178},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4458746910095215},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4399031400680542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42020130157470703},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.41922739148139954},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4104800224304199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3804224133491516},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17993363738059998},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15610653162002563},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018121","descriptor_name":"Receptors, Cytokine","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D018121","descriptor_name":"Receptors, Cytokine","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D018121","descriptor_name":"Receptors, Cytokine","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-020-03835-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03835-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03835-5","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33129275","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33129275","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":null},{"id":"pmh:oai:doaj.org/article:a9335017ce6f454cba550b9be239cd2e","is_oa":true,"landing_page_url":"https://doaj.org/article/a9335017ce6f454cba550b9be239cd2e","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 21, Iss 1, Pp 1-16 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7603689","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7603689","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-020-03835-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03835-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03835-5","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097323088.pdf","grobid_xml":"https://content.openalex.org/works/W3097323088.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1544435011","https://openalex.org/W1594736447","https://openalex.org/W1605695115","https://openalex.org/W1873256004","https://openalex.org/W1964421503","https://openalex.org/W1987582651","https://openalex.org/W1990212480","https://openalex.org/W2011376672","https://openalex.org/W2021025020","https://openalex.org/W2045747807","https://openalex.org/W2050721857","https://openalex.org/W2080922074","https://openalex.org/W2084619201","https://openalex.org/W2088187711","https://openalex.org/W2091710329","https://openalex.org/W2092927559","https://openalex.org/W2096451472","https://openalex.org/W2099862356","https://openalex.org/W2119583098","https://openalex.org/W2122646361","https://openalex.org/W2127637605","https://openalex.org/W2127979711","https://openalex.org/W2133990480","https://openalex.org/W2136957665","https://openalex.org/W2149310258","https://openalex.org/W2150452800","https://openalex.org/W2152923973","https://openalex.org/W2155653793","https://openalex.org/W2166020074","https://openalex.org/W2167609307","https://openalex.org/W2167821759","https://openalex.org/W2171831844","https://openalex.org/W2195660088","https://openalex.org/W2287383879","https://openalex.org/W2295240344","https://openalex.org/W2340589369","https://openalex.org/W2378867027","https://openalex.org/W2473684010","https://openalex.org/W2578695285","https://openalex.org/W2618265628","https://openalex.org/W2731397609","https://openalex.org/W2794055206","https://openalex.org/W2950403332","https://openalex.org/W3016364455","https://openalex.org/W3021414116","https://openalex.org/W3023430131"],"related_works":["https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W4224941037","https://openalex.org/W2004826645","https://openalex.org/W3135818052","https://openalex.org/W4388745254","https://openalex.org/W2980082554","https://openalex.org/W1517228774","https://openalex.org/W2767419625","https://openalex.org/W2389704471"],"abstract_inverted_index":{"BACKGROUND:":[0],"Cytokines":[1],"act":[2],"by":[3],"binding":[4],"to":[5,47,103,165,177,272,309,333],"specific":[6],"receptors":[7],"in":[8,60,81,156,238,319,340],"the":[9,25,66,76,82,105,115,118,126,135,144,179,189,233,263,274,287,326],"plasma":[10],"membrane":[11],"of":[12,16,27,68,107,120,130,137,140,146,161,172,181,193,201,240,276,289,336],"target":[13],"cells.":[14],"Knowledge":[15],"cytokine-receptor":[17],"interaction":[18],"(CRI)":[19],"is":[20,175],"very":[21],"important":[22],"for":[23,93,111,151],"understanding":[24],"pathogenesis":[26],"various":[28],"human":[29],"diseases-notably":[30],"autoimmune,":[31],"inflammatory":[32],"and":[33,57,71,78,117,197,250,259,283,331],"infectious":[34],"diseases-and":[35],"identifying":[36],"potential":[37],"therapeutic":[38],"targets.":[39],"Recently,":[40],"machine":[41,121],"learning":[42,69,122,147,290,338],"algorithms":[43,70,291],"have":[44],"been":[45],"used":[46,100],"predict":[48],"CRIs.":[49],"\"Gold":[50],"Standard\"":[51],"negative":[52,61,83,95,141,173,218],"datasets":[53,62,174,301],"are":[54,328],"still":[55],"lacking":[56],"strong":[58],"biases":[59],"can":[63],"significantly":[64,231,305],"affect":[65],"training":[67,116,145,288],"their":[72],"evaluation.":[73],"To":[74],"mitigate":[75,178],"unrepresentativeness":[77],"bias":[79],"inherent":[80],"sample":[84,96,219],"selection":[85],"(non-interacting":[86],"proteins),":[87],"we":[88,133],"propose":[89],"a":[90,304],"clustering-based":[91],"approach":[92],"representative":[94],"selection.":[97],"RESULTS:":[98],"We":[99],"deep":[101,131],"autoencoders":[102,132],"investigate":[104],"effect":[106,275],"different":[108,138,199,217,278,293],"sampling":[109,150,171,279,327],"approaches":[110,339],"non-interacting":[112,153],"pairs":[113,154],"on":[114,143,210,286,298,312,325],"performance":[119,307],"classifiers.":[123],"By":[124],"using":[125,256,292],"anomaly":[127],"detection":[128],"capabilities":[129],"deduced":[134],"effects":[136],"categories":[139],"samples":[142],"algorithms.":[148],"Random":[149],"selecting":[152],"results":[155],"either":[157],"over-":[158],"or":[159,163],"under-representation":[160],"hard":[162],"easy":[164],"classify":[166],"instances.":[167],"When":[168],"K-means":[169,282,299],"based":[170,209],"applied":[176],"inadequacies":[180],"random":[182,184,313],"sampling,":[183],"forest":[185],"(RF)":[186],"together":[187],"with":[188],"combined":[190],"feature":[191],"set":[192],"atomic":[194],"composition,":[195],"physicochemical-2grams":[196],"two":[198],"representations":[200],"evolutionary":[202],"information":[203],"performs":[204],"best.":[205],"Average":[206],"model":[207,223],"performances":[208],"leave-one-out":[211],"cross":[212],"validation":[213],"(loocv)":[214],"over":[215],"ten":[216],"sets":[220],"that":[221,228],"each":[222],"was":[224,270],"trained":[225,297,311],"with,":[226],"show":[227,303],"RF":[229,315],"models":[230],"outperform":[232],"previous":[234],"best":[235],"CRI":[236],"predictor":[237],"terms":[239],"accuracy":[241],"(+":[242,245,248,253],"5.1%),":[243],"specificity":[244],"13%),":[246],"mcc":[247],"0.1)":[249],"g-means":[251],"value":[252],"5.1).":[254],"Evaluations":[255],"tenfold":[257],"cv":[258],"training/testing":[260],"splits":[261],"confirm":[262],"competitive":[264],"performance.":[265],"CONCLUSIONS:":[266],"A":[267],"comparative":[268],"analysis":[269],"performed":[271],"assess":[273],"three":[277],"methods":[280],"(random,":[281],"uniform":[284],"sampling)":[285],"evaluation":[294],"methods.":[295],"Models":[296],"sampled":[300],"generally":[302],"improved":[306],"compared":[308],"those":[310],"selections-with":[314],"seemingly":[316],"benefiting":[317],"most":[318],"our":[320],"particular":[321],"setting.":[322],"Our":[323],"findings":[324],"highly":[329],"relevant":[330],"apply":[332],"many":[334],"applications":[335],"supervised":[337],"bioinformatics.":[341]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}