{"id":"https://openalex.org/W4385237444","doi":"https://doi.org/10.1093/bioinformatics/btad456","title":"CSI: Contrastive data Stratification for Interaction prediction and its application to compound\u2013protein interaction prediction","display_name":"CSI: Contrastive data Stratification for Interaction prediction and its application to compound\u2013protein interaction prediction","publication_year":2023,"publication_date":"2023-07-25","ids":{"openalex":"https://openalex.org/W4385237444","doi":"https://doi.org/10.1093/bioinformatics/btad456","pmid":"https://pubmed.ncbi.nlm.nih.gov/37490457"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad456/50959384/btad456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad456/50959384/btad456.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002724808","display_name":"Apurva Kalia","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apurva Kalia","raw_affiliation_strings":["Department of Computer Science, Tufts University , Medford, MA 02155, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103083233","display_name":"Dilip Krishnan","orcid":"https://orcid.org/0000-0002-9183-2886"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilip Krishnan","raw_affiliation_strings":["Google Research , Cambridge, MA 02142, Unites States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Cambridge, MA 02142, Unites States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048817284","display_name":"Soha Hassoun","orcid":"https://orcid.org/0000-0001-9477-2199"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soha Hassoun","raw_affiliation_strings":["Department of Chemical and Biological Engineering, Tufts University , Medford, MA 02155, United States","Department of Computer Science, Tufts University , Medford, MA 02155, United States"],"raw_orcid":"https://orcid.org/0000-0001-9477-2199","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Tufts University , Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048817284"],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.9963,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78132678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.7336000204086304,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.7336000204086304,"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":0.12559999525547028,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.04650000110268593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668922543525696},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5759570002555847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5572338700294495},{"id":"https://openalex.org/keywords/interaction-information","display_name":"Interaction information","score":0.5440979599952698},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5159531235694885},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.5073923468589783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48030513525009155},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4725116193294525},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4366241693496704},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4140751361846924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12311860918998718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668922543525696},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5759570002555847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572338700294495},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.5440979599952698},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5159531235694885},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.5073923468589783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48030513525009155},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4725116193294525},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4366241693496704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4140751361846924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12311860918998718},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016503","descriptor_name":"Drug Delivery Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016503","descriptor_name":"Drug Delivery Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016503","descriptor_name":"Drug Delivery Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016503","descriptor_name":"Drug Delivery Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058615","descriptor_name":"Synthetic Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058615","descriptor_name":"Synthetic Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058615","descriptor_name":"Synthetic Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058615","descriptor_name":"Synthetic Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060847","descriptor_name":"Metabolic Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060847","descriptor_name":"Metabolic Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060847","descriptor_name":"Metabolic Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060847","descriptor_name":"Metabolic Engineering","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad456/50959384/btad456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37490457","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37490457","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10423023","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10423023","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10423023/pdf/btad456.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad456/50959384/btad456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1928829289","display_name":null,"funder_award_id":"W911NF-22-1-0239","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G362080672","display_name":null,"funder_award_id":"R35GM148219","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3748230582","display_name":"FET: Small: Tools and Experimental Validation for Predicting Enzymatic Promiscuity and its Products","funder_award_id":"1909536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3803196217","display_name":null,"funder_award_id":"R35GM148219","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5172521839","display_name":null,"funder_award_id":"R01GM132391","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G574536544","display_name":null,"funder_award_id":"W911NF2210239","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5775615792","display_name":null,"funder_award_id":"R01 GM132391","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385237444.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1976308333","https://openalex.org/W2029195137","https://openalex.org/W2163922914","https://openalex.org/W2204695023","https://openalex.org/W2259538443","https://openalex.org/W2744129621","https://openalex.org/W2785947426","https://openalex.org/W2860192827","https://openalex.org/W2883535080","https://openalex.org/W2892816441","https://openalex.org/W2899788782","https://openalex.org/W2937307539","https://openalex.org/W2942559242","https://openalex.org/W3000043291","https://openalex.org/W3018980093","https://openalex.org/W3026092005","https://openalex.org/W3084084616","https://openalex.org/W3090513030","https://openalex.org/W3096561213","https://openalex.org/W3096828292","https://openalex.org/W3096831136","https://openalex.org/W3105895642","https://openalex.org/W3121826386","https://openalex.org/W3122451732","https://openalex.org/W3197123494","https://openalex.org/W4206174637","https://openalex.org/W6752830377","https://openalex.org/W6777179611"],"related_works":["https://openalex.org/W4384112194","https://openalex.org/W2783354812","https://openalex.org/W2103009189","https://openalex.org/W4312958259","https://openalex.org/W2349383066","https://openalex.org/W1969901537","https://openalex.org/W4328132048","https://openalex.org/W4308259661","https://openalex.org/W2376202349","https://openalex.org/W2969318460"],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurately":[1],"predicting":[2],"the":[3,31,37,43,50,56,78,113,142,146,154],"likelihood":[4],"of":[5,30,42,55,77,141,148],"interaction":[6,157,171,179],"between":[7,36],"two":[8],"objects":[9],"(compound-protein":[10],"sequence,":[11],"user-item,":[12],"author-paper,":[13],"etc.)":[14],"is":[15],"a":[16,83,95,98,122,135,160,185],"fundamental":[17],"problem":[18,162],"in":[19,97,200],"Computer":[20],"Science.":[21],"Current":[22],"deep-learning":[23],"models":[24],"rely":[25],"on":[26],"learning":[27,71],"accurate":[28],"representations":[29,76],"interacting":[32,38,57],"objects.":[33,58,79],"Importantly,":[34],"relationships":[35],"objects,":[39],"or":[40],"features":[41,229],"interaction,":[44],"offer":[45],"an":[46],"opportunity":[47],"to":[48,52,73,92,108,127,153,166,206,225],"partition":[49],"data":[51,118,129,132,192],"create":[53],"multi-views":[54],"The":[59],"resulting":[60],"congruent":[61,117,139],"and":[62,124,175,194,197,210,217,220,239],"non-congruent":[63],"views":[64,126,140],"can":[65,101],"then":[66],"be":[67,102],"exploited":[68,103],"via":[69,104],"contrastive":[70,195],"techniques":[72],"learn":[74,109],"enhanced":[75],"RESULTS:":[80],"We":[81,144],"present":[82],"novel":[84],"method,":[85],"Contrastive":[86,105],"Stratification":[87],"for":[88],"Interaction":[89],"Prediction":[90],"(CSI),":[91],"stratify":[93],"(partition)":[94],"dataset":[96,240],"manner":[99],"that":[100,111,188],"Multiview":[106],"Coding":[107],"embeddings":[110],"maximize":[112],"mutual":[114],"information":[115],"across":[116,214,232],"views.":[119],"CSI":[120,149,183],"assigns":[121],"key":[123,137],"multiple":[125,215],"each":[128],"point,":[130],"where":[131],"partitions":[133],"under":[134],"particular":[136],"form":[138],"data.":[143],"showcase":[145],"effectiveness":[147],"by":[150],"applying":[151],"it":[152],"compound-protein":[155],"sequence":[156],"prediction":[158],"problem,":[159],"pressing":[161],"whose":[163],"solution":[164],"promises":[165],"expedite":[167],"drug":[168],"delivery":[169],"(drug-protein":[170],"prediction),":[172],"metabolic":[173],"engineering,":[174],"synthetic":[176],"biology":[177],"(compound-enzyme":[178],"prediction)":[180],"applications.":[181],"Comparing":[182],"with":[184],"baseline":[186],"model":[187],"does":[189],"not":[190],"utilize":[191],"stratification":[193],"learning,":[196],"show":[198],"gains":[199,221],"average":[201],"precision":[202],"ranging":[203,222],"from":[204,223],"13.7%":[205],"39%":[207],"using":[208,227],"compounds":[209],"sequences":[211],"as":[212,230],"keys":[213,231],"drug-target":[216],"enzymatic":[218,233],"datasets,":[219],"16.9%":[224],"63%":[226],"reaction":[228],"datasets.":[234],"AVAILABILITY":[235],"AND":[236],"IMPLEMENTATION:":[237],"Code":[238],"available":[241],"at":[242],"https://github.com/HassounLab/CSI.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}