{"id":"https://openalex.org/W3109806123","doi":"https://doi.org/10.1142/9789811232701_0015","title":"Protein sequence models for prediction and comparative analysis of the SARS-CoV-2 \u2014human interactome","display_name":"Protein sequence models for prediction and comparative analysis of the SARS-CoV-2 \u2014human interactome","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3109806123","doi":"https://doi.org/10.1142/9789811232701_0015","mag":"3109806123","pmid":"https://pubmed.ncbi.nlm.nih.gov/33691013"},"language":"en","primary_location":{"id":"doi:10.1142/9789811232701_0015","is_oa":true,"landing_page_url":"https://doi.org/10.1142/9789811232701_0015","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biocomputing 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1142/9789811232701_0015","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030581161","display_name":"Meghana Kshirsagar","orcid":"https://orcid.org/0000-0002-4673-614X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Meghana Kshirsagar","raw_affiliation_strings":["Microsoft, AI for Good Research Lab, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, AI for Good Research Lab, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011812186","display_name":"Nure Tasnina","orcid":"https://orcid.org/0009-0000-2971-0987"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nure Tasnina","raw_affiliation_strings":["Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118899969","display_name":"Michael D. Ward","orcid":"https://orcid.org/0000-0002-2758-278X"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael D. Ward","raw_affiliation_strings":["Dept. of Biochemistry & Molecular Biophysics, Washington Univ., St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Biochemistry & Molecular Biophysics, Washington Univ., St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017369999","display_name":"Jeffrey Law","orcid":"https://orcid.org/0000-0003-2828-1273"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey N. Law","raw_affiliation_strings":["Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073142937","display_name":"T. M. Murali","orcid":"https://orcid.org/0000-0003-3688-4672"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. M. Murali","raw_affiliation_strings":["Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025368433","display_name":"Juan Lavista Ferres","orcid":"https://orcid.org/0000-0002-9654-3178"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan M. Lavista Ferres","raw_affiliation_strings":["Microsoft, AI for Good Research Lab, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, AI for Good Research Lab, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029297375","display_name":"Gregory R. Bowman","orcid":"https://orcid.org/0000-0002-2083-4892"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory R. Bowman","raw_affiliation_strings":["Dept. of Biochemistry & Molecular Biophysics, Washington Univ., St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Biochemistry & Molecular Biophysics, Washington Univ., St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065265042","display_name":"Judith Klein\u2010Seetharaman","orcid":"https://orcid.org/0000-0002-4892-6828"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judith Klein-Seetharaman","raw_affiliation_strings":["Colorado School of Mines, Initiative for AI in Bio and Health, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Colorado School of Mines, Initiative for AI in Bio and Health, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5030581161"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.4971,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63323545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"26","issue":null,"first_page":"154","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8533999919891357,"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":0.8533999919891357,"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":0.7307999730110168,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7027999758720398,"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/interactome","display_name":"Interactome","score":0.8339880704879761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6378916501998901},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6371324062347412},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.552244246006012},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4184646010398865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3371773362159729},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19724929332733154},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.19256219267845154},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1271946132183075},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07000204920768738}],"concepts":[{"id":"https://openalex.org/C9760119","wikidata":"https://www.wikidata.org/wiki/Q841382","display_name":"Interactome","level":3,"score":0.8339880704879761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378916501998901},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6371324062347412},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.552244246006012},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4184646010398865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3371773362159729},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19724929332733154},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.19256219267845154},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1271946132183075},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07000204920768738}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/9789811232701_0015","is_oa":true,"landing_page_url":"https://doi.org/10.1142/9789811232701_0015","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biocomputing 2021","raw_type":"proceedings-article"},{"id":"pmid:33691013","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33691013","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":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","raw_type":null}],"best_oa_location":{"id":"doi:10.1142/9789811232701_0015","is_oa":true,"landing_page_url":"https://doi.org/10.1142/9789811232701_0015","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biocomputing 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4292634579","https://openalex.org/W2964314049","https://openalex.org/W2022326234","https://openalex.org/W1531941329","https://openalex.org/W3005984791","https://openalex.org/W2169777166","https://openalex.org/W2007507741","https://openalex.org/W4377194874","https://openalex.org/W1980646002","https://openalex.org/W3090458178"],"abstract_inverted_index":{"Viruses":[0],"such":[1,33,63],"as":[2,34,64,221],"the":[3,12,24,45,53,56,80,86,101,141,155,172,175,184,188,228],"novel":[4,142],"coronavirus,":[5],"SARS-CoV-2,":[6],"that":[7,99,124],"is":[8,177],"wreaking":[9],"havoc":[10],"on":[11,15,119],"world,":[13],"depend":[14],"interactions":[16,117,236,242],"of":[17,23,44,52,82,88,100,132,137,140,157,169,187,230],"its":[18],"own":[19],"proteins":[20,91,94,202],"with":[21,129,179],"those":[22],"human":[25,93],"host":[26,176],"cells.":[27],"Relatively":[28],"small":[29],"changes":[30],"in":[31,71,85,134,162],"sequence":[32,84,120,160],"between":[35],"SARS-CoV":[36,218,245],"and":[37,50,67,95,122,165,174,193,215,246],"SARS-CoV-2":[38,89],"can":[39,226],"dramatically":[40],"change":[41],"clinical":[42],"phenotypes":[43],"virus,":[46],"including":[47],"transmission":[48],"rates":[49],"severity":[51],"disease.":[54],"On":[55],"other":[57,103],"hand,":[58],"highly":[59],"dissimilar":[60],"virus":[61,90,173],"families":[62],"Coronaviridae,":[65],"Ebola,":[66],"HIV":[68],"have":[69],"overlap":[70],"functions.":[72],"In":[73],"this":[74],"work":[75],"we":[76,197,225],"aim":[77],"to":[78,98,115],"analyze":[79],"role":[81],"protein":[83,209],"binding":[87,164],"towards":[92],"compare":[96],"it":[97],"above":[102],"viruses.":[104,205],"We":[105,152],"build":[106],"supervised":[107],"machine":[108],"learning":[109],"models,":[110],"using":[111,144],"Generalized":[112],"Additive":[113],"Models":[114],"predict":[116],"based":[118],"features":[121,161],"find":[123,198],"our":[125],"models":[126],"perform":[127],"well":[128],"an":[130,145,180],"AUC-PR":[131],"0.65":[133],"a":[135],"class-skew":[136],"1:10.":[138],"Analysis":[139],"predictions":[143],"independent":[146],"dataset":[147],"showed":[148],"statistically":[149],"significant":[150],"enrichment.":[151],"further":[153],"map":[154],"importance":[156],"specific":[158],"amino-acid":[159],"predicting":[163],"summarize":[166],"what":[167],"combinations":[168],"sequences":[170],"from":[171,190,203,210,213,217],"correlated":[178],"interaction.":[181],"By":[182],"analyzing":[183],"sequence-based":[185],"embeddings":[186],"interactomes":[189],"different":[191,204],"viruses":[192],"clustering":[194],"them":[195],"together":[196],"some":[199],"functionally":[200],"similar":[201,231],"For":[206],"example,":[207],"vif":[208],"HIV-1,":[211],"vp24":[212],"Ebola":[214],"orf3b":[216],"all":[219],"function":[220],"interferon":[222],"antagonists.":[223],"Furthermore,":[224],"differentiate":[227],"functions":[229],"viruses,":[232],"for":[233],"example":[234],"orf3a's":[235],"are":[237],"more":[238],"diverged":[239],"than":[240],"orf7b":[241],"when":[243],"comparing":[244],"SARS-CoV-2.":[247]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}