{"id":"https://openalex.org/W4312224334","doi":"https://doi.org/10.3389/fbinf.2022.1083292","title":"On the choice of negative examples for prediction of host-pathogen protein interactions","display_name":"On the choice of negative examples for prediction of host-pathogen protein interactions","publication_year":2022,"publication_date":"2022-12-15","ids":{"openalex":"https://openalex.org/W4312224334","doi":"https://doi.org/10.3389/fbinf.2022.1083292","pmid":"https://pubmed.ncbi.nlm.nih.gov/36591335"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2022.1083292","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1083292","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2022.1083292/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://www.frontiersin.org/articles/10.3389/fbinf.2022.1083292/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012951296","display_name":"Don Neumann","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Don Neumann","raw_affiliation_strings":["Department Computer Science, Colorado State University, Fort Collins, CO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science, Colorado State University, Fort Collins, CO, United States","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042403987","display_name":"Soumyadip Roy","orcid":"https://orcid.org/0000-0003-1932-4315"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumyadip Roy","raw_affiliation_strings":["Department Computer Science, Colorado State University, Fort Collins, CO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science, Colorado State University, Fort Collins, CO, United States","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086173090","display_name":"Fayyaz Minhas","orcid":"https://orcid.org/0000-0001-9129-1189"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fayyaz Ul Amir Afsar Minhas","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005013902","display_name":"Asa Ben\u2010Hur","orcid":"https://orcid.org/0000-0001-8269-6942"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Asa Ben-Hur","raw_affiliation_strings":["Department Computer Science, Colorado State University, Fort Collins, CO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science, Colorado State University, Fort Collins, CO, United States","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005013902","https://openalex.org/A5012951296"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":0.1732,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49548145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"1083292","last_page":"1083292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9976999759674072,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9976999759674072,"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":0.9957000017166138,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.991599977016449,"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/task","display_name":"Task (project management)","score":0.6485987305641174},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6143341064453125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.592190146446228},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5810839533805847},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5716400146484375},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5246884226799011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4563884735107422},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41377532482147217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40222448110580444},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3552435040473938},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3508074879646301},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30781644582748413},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14467614889144897},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.12040233612060547}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6485987305641174},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6143341064453125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.592190146446228},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5810839533805847},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5716400146484375},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5246884226799011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4563884735107422},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41377532482147217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40222448110580444},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3552435040473938},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3508074879646301},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30781644582748413},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14467614889144897},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.12040233612060547},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2022.1083292","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1083292","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2022.1083292/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:36591335","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36591335","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:11d563147da840a9870289946b9bc8f5","is_oa":true,"landing_page_url":"https://doaj.org/article/11d563147da840a9870289946b9bc8f5","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":"Frontiers in Bioinformatics, Vol 2 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9798088","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9798088","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.2022.1083292","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1083292","pdf_url":"https://www.frontiersin.org/articles/10.3389/fbinf.2022.1083292/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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312224334.pdf","grobid_xml":"https://content.openalex.org/works/W4312224334.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1982267716","https://openalex.org/W2008840001","https://openalex.org/W2074231493","https://openalex.org/W2101234009","https://openalex.org/W2116988471","https://openalex.org/W2131562240","https://openalex.org/W2136957665","https://openalex.org/W2150452800","https://openalex.org/W2161922860","https://openalex.org/W2272509401","https://openalex.org/W2465613542","https://openalex.org/W2537623931","https://openalex.org/W2618265628","https://openalex.org/W2768528779","https://openalex.org/W2791848964","https://openalex.org/W2885821429","https://openalex.org/W2957436444","https://openalex.org/W2998220730","https://openalex.org/W3081689004","https://openalex.org/W3098119651","https://openalex.org/W3133705589","https://openalex.org/W3134084134","https://openalex.org/W3168531047","https://openalex.org/W3174714560","https://openalex.org/W3185942550","https://openalex.org/W3194722675","https://openalex.org/W3209369100","https://openalex.org/W4200461926","https://openalex.org/W4282927263","https://openalex.org/W4284691226","https://openalex.org/W4288950918","https://openalex.org/W4289704564","https://openalex.org/W4295312788","https://openalex.org/W4296774836","https://openalex.org/W6675354045","https://openalex.org/W6766978945","https://openalex.org/W6787414469"],"related_works":["https://openalex.org/W2117112636","https://openalex.org/W2001981265","https://openalex.org/W2317560666","https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2898732673","https://openalex.org/W2014134454","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2389015757"],"abstract_inverted_index":{"As":[0],"practitioners":[1],"of":[2,8,15,23,37,55,62,69,100,108,121,130,144,169,209,212,217,223,235],"machine":[3],"learning":[4],"in":[5,84,90],"the":[6,13,16,21,35,40,53,60,85,97,101,106,128,175,184,192,207,233],"area":[7],"bioinformatics":[9],"we":[10,51],"know":[11],"that":[12,81],"quality":[14,22,36],"results":[17],"crucially":[18],"depends":[19],"on":[20,34,110],"our":[24],"labeled":[25],"data.":[26],"While":[27],"there":[28],"is":[29,96,116,148,178],"a":[30,70,140,215],"tendency":[31],"to":[32,117,139,163,174,201,229,232],"focus":[33],"positive":[38,176],"examples,":[39],"negative":[41,57,125,165],"examples":[42,58,166,177],"are":[43,82,133],"equally":[44],"as":[45,124,167],"important.":[46],"In":[47],"this":[48,94,137,156,210],"opinion":[49],"paper":[50],"revisit":[52],"problem":[54,193],"choosing":[56],"for":[59,74,93,151,186,239],"task":[61,95],"predicting":[63],"protein-protein":[64],"interactions,":[65],"either":[66],"among":[67],"proteins":[68,123,170],"given":[71],"species":[72,132],"or":[73],"host-pathogen":[75,152],"interactions":[76,104],"and":[77,105,226],"describe":[78],"important":[79],"issues":[80],"prevalent":[83],"current":[86],"literature.":[87],"The":[88],"challenge":[89],"creating":[91],"datasets":[92,238],"noisy":[98],"nature":[99],"experimentally":[102],"derived":[103],"lack":[107],"information":[109],"non-interacting":[111,122],"proteins.":[112],"A":[113],"standard":[114],"approach":[115],"choose":[118],"random":[119],"pairs":[120,168],"examples.":[126],"Since":[127],"interactomes":[129],"all":[131],"only":[134],"partially":[135],"known,":[136],"leads":[138],"very":[141],"small":[142],"percentage":[143],"false":[145,187],"negatives.":[146],"This":[147,181],"especially":[149],"true":[150],"interactions.":[153],"To":[154],"address":[155],"perceived":[157],"issue,":[158],"some":[159],"researchers":[160,228],"have":[161],"chosen":[162],"select":[164],"whose":[171],"sequence":[172],"similarity":[173],"sufficiently":[179],"low.":[180],"clearly":[182],"reduces":[183],"chance":[185],"negatives,":[188],"but":[189],"also":[190],"makes":[191],"much":[194],"easier":[195],"than":[196],"it":[197],"really":[198],"is,":[199],"leading":[200],"over-optimistic":[202],"accuracy":[203],"estimates.":[204],"We":[205],"demonstrate":[206],"effect":[208],"form":[211],"bias":[213],"using":[214],"selection":[216],"recent":[218],"protein":[219],"interaction":[220],"prediction":[221],"methods":[222],"varying":[224],"complexity,":[225],"urge":[227],"pay":[230],"attention":[231],"details":[234],"generating":[236],"their":[237],"potential":[240],"biases":[241],"like":[242],"this.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
