{"id":"https://openalex.org/W3198646379","doi":"https://doi.org/10.1371/journal.pcbi.1009853","title":"Machine learning modeling of family wide enzyme-substrate specificity screens","display_name":"Machine learning modeling of family wide enzyme-substrate specificity screens","publication_year":2022,"publication_date":"2022-02-10","ids":{"openalex":"https://openalex.org/W3198646379","doi":"https://doi.org/10.1371/journal.pcbi.1009853","mag":"3198646379","pmid":"https://pubmed.ncbi.nlm.nih.gov/35143485"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009853","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009853","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1009853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045943967","display_name":"Samuel Goldman","orcid":"https://orcid.org/0000-0002-3928-6873"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Goldman","raw_affiliation_strings":["MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","MIT Computational and Systems Biology, Cambridge, Massachusetts, United States of America"],"affiliations":[{"raw_affiliation_string":"MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT Computational and Systems Biology, Cambridge, Massachusetts, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102422737","display_name":"Ria Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ria Das","raw_affiliation_strings":["MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","MIT Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States of America"],"affiliations":[{"raw_affiliation_string":"MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060834723","display_name":"Kevin Yang","orcid":"https://orcid.org/0000-0001-9045-6826"},"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"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin K. Yang","raw_affiliation_strings":["Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"affiliations":[{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076162644","display_name":"Connor W. Coley","orcid":"https://orcid.org/0000-0002-8271-8723"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Connor W. Coley","raw_affiliation_strings":["MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","MIT Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States of America"],"affiliations":[{"raw_affiliation_string":"MIT Chemical Engineering, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT Electrical Engineering and Computer Science, Cambridge, Massachusetts, United States of America","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076162644"],"corresponding_institution_ids":["https://openalex.org/I4210110987"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":15.3881,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.99352586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"2","first_page":"e1009853","last_page":"e1009853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"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":0.9984999895095825,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9926999807357788,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9922000169754028,"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/in-silico","display_name":"In silico","score":0.7663172483444214},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6692839860916138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5868646502494812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5804923176765442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5747852325439453},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.5311176776885986},{"id":"https://openalex.org/keywords/biocatalysis","display_name":"Biocatalysis","score":0.5206650495529175},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4721805155277252},{"id":"https://openalex.org/keywords/biochemical-engineering","display_name":"Biochemical engineering","score":0.44060301780700684},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2659761905670166},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2216866910457611},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.21174070239067078},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.14351502060890198},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12888604402542114}],"concepts":[{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.7663172483444214},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6692839860916138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5868646502494812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5804923176765442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747852325439453},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.5311176776885986},{"id":"https://openalex.org/C191503008","wikidata":"https://www.wikidata.org/wiki/Q16007026","display_name":"Biocatalysis","level":4,"score":0.5206650495529175},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4721805155277252},{"id":"https://openalex.org/C183696295","wikidata":"https://www.wikidata.org/wiki/Q2487696","display_name":"Biochemical engineering","level":1,"score":0.44060301780700684},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2659761905670166},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2216866910457611},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.21174070239067078},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.14351502060890198},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12888604402542114},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C161790260","wikidata":"https://www.wikidata.org/wiki/Q82264","display_name":"Catalysis","level":2,"score":0.0},{"id":"https://openalex.org/C154881586","wikidata":"https://www.wikidata.org/wiki/Q898579","display_name":"Ionic liquid","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D013379","descriptor_name":"Substrate Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013379","descriptor_name":"Substrate Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013379","descriptor_name":"Substrate Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1371/journal.pcbi.1009853","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009853","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:35143485","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35143485","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:arXiv.org:2109.03900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.03900","pdf_url":"https://arxiv.org/pdf/2109.03900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:278f0ea29de644f7b95660c87b1663e0","is_oa":true,"landing_page_url":"https://doaj.org/article/278f0ea29de644f7b95660c87b1663e0","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":"PLoS Computational Biology, Vol 18, Iss 2, p e1009853 (2022)","raw_type":"article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/141379","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/141379","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"625865","raw_type":"Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/141379.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/141379.2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"625865","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8865696","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8865696","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1009853","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009853","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.5099999904632568,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1969733451","https://openalex.org/W1970051672","https://openalex.org/W1974389826","https://openalex.org/W2044834685","https://openalex.org/W2062958450","https://openalex.org/W2086286404","https://openalex.org/W2101234009","https://openalex.org/W2113531097","https://openalex.org/W2114850508","https://openalex.org/W2118265845","https://openalex.org/W2128373944","https://openalex.org/W2132629607","https://openalex.org/W2134441341","https://openalex.org/W2144000913","https://openalex.org/W2148534902","https://openalex.org/W2156454061","https://openalex.org/W2177317049","https://openalex.org/W2210738511","https://openalex.org/W2767044445","https://openalex.org/W2769749548","https://openalex.org/W2799620402","https://openalex.org/W2805578306","https://openalex.org/W2899677526","https://openalex.org/W2917580301","https://openalex.org/W2920414590","https://openalex.org/W2938072319","https://openalex.org/W2949274932","https://openalex.org/W2949676527","https://openalex.org/W2950020917","https://openalex.org/W2963819570","https://openalex.org/W2971227267","https://openalex.org/W2979343028","https://openalex.org/W2980789587","https://openalex.org/W2981561997","https://openalex.org/W2984350850","https://openalex.org/W2991758999","https://openalex.org/W2995188634","https://openalex.org/W2995514860","https://openalex.org/W3002639525","https://openalex.org/W3013695388","https://openalex.org/W3019745511","https://openalex.org/W3022987161","https://openalex.org/W3031753718","https://openalex.org/W3035847987","https://openalex.org/W3092737886","https://openalex.org/W3095698385","https://openalex.org/W3108701030","https://openalex.org/W3111174583","https://openalex.org/W3111667196","https://openalex.org/W3115230674","https://openalex.org/W3120686965","https://openalex.org/W3127426316","https://openalex.org/W3144239152","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3165267435","https://openalex.org/W3166142427","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3200781945","https://openalex.org/W3204042087","https://openalex.org/W4212774754","https://openalex.org/W4235572996","https://openalex.org/W4296060337","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W4252713238","https://openalex.org/W91931185","https://openalex.org/W2125201894","https://openalex.org/W4233688127","https://openalex.org/W2373828514","https://openalex.org/W2751743037","https://openalex.org/W19842636","https://openalex.org/W4231088698","https://openalex.org/W4289884219","https://openalex.org/W2920570798"],"abstract_inverted_index":{"Biocatalysis":[0],"is":[1,22],"a":[2,65,194,203,210],"promising":[3],"approach":[4],"to":[5,27,56,61,71,177,216],"sustainably":[6],"synthesize":[7],"pharmaceuticals,":[8],"complex":[9],"natural":[10,34],"products,":[11],"and":[12,43,149,218,225],"commodity":[13],"chemicals":[14],"at":[15],"scale.":[16],"However,":[17],"the":[18,95,115,152,174,179,185],"adoption":[19],"of":[20,75,80,129,144,181,188],"biocatalysis":[21,224],"limited":[23],"by":[24,163],"our":[25,166],"ability":[26],"select":[28],"enzymes":[29,73,101],"that":[30,97,138,165],"will":[31],"catalyze":[32],"their":[33],"chemical":[35],"transformation":[36],"on":[37,77],"non-natural":[38],"substrates.":[39,104],"While":[40],"machine":[41,107],"learning":[42,145],"in":[44,151,214],"silico":[45],"directed":[46],"evolution":[47],"are":[48,142],"well-posed":[49],"for":[50,118,198,223],"this":[51,84,161,207],"predictive":[52,221],"modeling":[53,112],"challenge,":[54],"efforts":[55],"date":[57],"have":[58],"primarily":[59],"aimed":[60],"increase":[62],"activity":[63],"against":[64,102,127],"single":[66],"known":[67],"substrate,":[68],"rather":[69],"than":[70],"identify":[72],"capable":[74],"acting":[76],"new":[78,195],"substrates":[79],"interest.":[81],"To":[82],"address":[83],"need,":[85],"we":[86,192],"curate":[87],"6":[88],"different":[89],"high-quality":[90],"enzyme":[91],"family":[92,154],"screens":[93],"from":[94,114,173],"literature":[96,116,175],"each":[98],"measure":[99],"multiple":[100,103],"We":[105,158],"compare":[106],"learning-based":[108],"compound-protein":[109],"interaction":[110],"(CPI)":[111],"approaches":[113,141],"used":[117,176],"predicting":[119],"drug-target":[120],"interactions.":[121],"Surprisingly,":[122],"comparing":[123],"these":[124],"interaction-based":[125],"models":[126,136,172,222],"collections":[128],"independent":[130],"(single":[131],"task)":[132],"enzyme-only":[133],"or":[134],"substrate-only":[135],"reveals":[137],"current":[139,153],"CPI":[140],"incapable":[143],"interactions":[146],"between":[147],"compounds":[148],"proteins":[150],"level":[155],"data":[156],"regime.":[157],"further":[159],"validate":[160],"observation":[162],"demonstrating":[164],"no-interaction":[167],"baseline":[168],"can":[169],"outperform":[170],"CPI-based":[171],"guide":[178],"discovery":[180,228],"kinase":[182],"inhibitors.":[183],"Given":[184],"high":[186],"performance":[187],"non-interaction":[189],"based":[190],"models,":[191],"introduce":[193],"structure-based":[196],"strategy":[197],"pooling":[199],"residue":[200],"representations":[201],"across":[202],"protein":[204],"sequence.":[205],"Altogether,":[206],"work":[208],"motivates":[209],"principled":[211],"path":[212],"forward":[213],"order":[215],"build":[217],"evaluate":[219],"meaningful":[220],"other":[226],"drug":[227],"applications.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":10}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}