{"id":"https://openalex.org/W4396661765","doi":"https://doi.org/10.1021/acs.jcim.4c00137","title":"Leveraging Language Model Multitasking To Predict C\u2013H Borylation Selectivity","display_name":"Leveraging Language Model Multitasking To Predict C\u2013H Borylation Selectivity","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W4396661765","doi":"https://doi.org/10.1021/acs.jcim.4c00137","pmid":"https://pubmed.ncbi.nlm.nih.gov/38708520"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00137","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00137","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00137","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096468547","display_name":"Ruslan Kotlyarov","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruslan Kotlyarov","raw_affiliation_strings":["Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000853150","display_name":"Konstantinos Papachristos","orcid":"https://orcid.org/0000-0002-4777-9088"},"institutions":[{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantinos Papachristos","raw_affiliation_strings":["Exscientia Plc, The Schr\u00f6dinger Building, Oxford Science Park, Oxford OX4 4GE, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Exscientia Plc, The Schr\u00f6dinger Building, Oxford Science Park, Oxford OX4 4GE, U.K","institution_ids":["https://openalex.org/I4210146410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090389147","display_name":"Geoffrey P. F. Wood","orcid":"https://orcid.org/0000-0003-1248-0542"},"institutions":[{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geoffrey P. F. Wood","raw_affiliation_strings":["Exscientia Plc, The Schr\u00f6dinger Building, Oxford Science Park, Oxford OX4 4GE, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Exscientia Plc, The Schr\u00f6dinger Building, Oxford Science Park, Oxford OX4 4GE, U.K","institution_ids":["https://openalex.org/I4210146410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086984299","display_name":"Jonathan M. Goodman","orcid":"https://orcid.org/0000-0002-8693-9136"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jonathan M. Goodman","raw_affiliation_strings":["Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8693-9136","affiliations":[{"raw_affiliation_string":"Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086984299"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65641317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"64","issue":"10","first_page":"4286","last_page":"4297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11281","display_name":"Asymmetric Hydrogenation and Catalysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11281","display_name":"Asymmetric Hydrogenation and Catalysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9891999959945679,"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/T11441","display_name":"Organoboron and organosilicon chemistry","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/borylation","display_name":"Borylation","score":0.9286280870437622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6717894077301025},{"id":"https://openalex.org/keywords/regioselectivity","display_name":"Regioselectivity","score":0.5188137888908386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4430139362812042},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4185223877429962},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.33003854751586914},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2676105499267578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09943905472755432},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.09318041801452637}],"concepts":[{"id":"https://openalex.org/C2776413204","wikidata":"https://www.wikidata.org/wiki/Q17113001","display_name":"Borylation","level":4,"score":0.9286280870437622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717894077301025},{"id":"https://openalex.org/C59759590","wikidata":"https://www.wikidata.org/wiki/Q2275927","display_name":"Regioselectivity","level":3,"score":0.5188137888908386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4430139362812042},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4185223877429962},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.33003854751586914},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2676105499267578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09943905472755432},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.09318041801452637},{"id":"https://openalex.org/C2781076698","wikidata":"https://www.wikidata.org/wiki/Q718074","display_name":"Aryl","level":3,"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/C2780263894","wikidata":"https://www.wikidata.org/wiki/Q335268","display_name":"Alkyl","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006859","descriptor_name":"Hydrogen","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1021/acs.jcim.4c00137","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00137","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00137","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:38708520","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38708520","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":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11134489","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11134489","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11134489/pdf/ci4c00137.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":"J Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/367527","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/367527","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/4e8795eb-9ad8-4747-9e4b-3bb62e84aa84/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/368949","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/368949","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/19453b18-688c-4e20-baf5-2afac434278b/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"},{"id":"doi:10.17863/cam.108085","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.108085","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.4c00137","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00137","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00137","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396661765.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1926827464","https://openalex.org/W1974001124","https://openalex.org/W1975147762","https://openalex.org/W1976825482","https://openalex.org/W1978890358","https://openalex.org/W1979276942","https://openalex.org/W1985580893","https://openalex.org/W2054953645","https://openalex.org/W2151882027","https://openalex.org/W2769423117","https://openalex.org/W2771169143","https://openalex.org/W2895677720","https://openalex.org/W2947423323","https://openalex.org/W2949618004","https://openalex.org/W2967187060","https://openalex.org/W2970764640","https://openalex.org/W2989615256","https://openalex.org/W3009321976","https://openalex.org/W3045705195","https://openalex.org/W3045928028","https://openalex.org/W3103092523","https://openalex.org/W3117879109","https://openalex.org/W3118349318","https://openalex.org/W3123901912","https://openalex.org/W3138781613","https://openalex.org/W4220902634","https://openalex.org/W4224950134","https://openalex.org/W4226145240","https://openalex.org/W4226159083","https://openalex.org/W4283317658","https://openalex.org/W4286224767","https://openalex.org/W4296393188","https://openalex.org/W4310510565","https://openalex.org/W4313335143","https://openalex.org/W4318952054","https://openalex.org/W4319041725","https://openalex.org/W4320727261","https://openalex.org/W4321123672","https://openalex.org/W4321214126","https://openalex.org/W4360608424","https://openalex.org/W4366602447","https://openalex.org/W4383217278","https://openalex.org/W4385245566","https://openalex.org/W4385408944","https://openalex.org/W4385661017","https://openalex.org/W4388939056","https://openalex.org/W4396508870"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W4353034857","https://openalex.org/W2509455402","https://openalex.org/W2965408345"],"abstract_inverted_index":{"C-H":[0,75,110],"borylation":[1,49,76],"is":[2,24,39],"a":[3,17,41,45,56,63],"high-value":[4],"transformation":[5],"in":[6,31,79,99],"the":[7,13,74,96,107],"synthesis":[8],"of":[9,20,48,66,101],"lead":[10],"candidates":[11],"for":[12],"pharmaceutical":[14],"industry":[15],"because":[16],"wide":[18],"array":[19],"downstream":[21],"coupling":[22],"reactions":[23,50],"available.":[25],"However,":[26],"predicting":[27],"its":[28],"regioselectivity,":[29],"especially":[30],"drug-like":[32],"molecules":[33],"that":[34],"may":[35],"contain":[36],"multiple":[37],"heterocycles,":[38],"not":[40],"trivial":[42],"task.":[43],"Using":[44],"data":[46],"set":[47,65],"from":[51],"Reaxys,":[52],"we":[53],"explored":[54],"how":[55],"language":[57,92],"model":[58,93],"originally":[59],"trained":[60],"on":[61],"USPTO_500_MT,":[62],"broad-scope":[64],"patent":[67],"data,":[68],"can":[69,94,104],"be":[70],"used":[71],"to":[72],"predict":[73],"reaction":[77],"product":[78,82,98],"different":[80],"modes:":[81],"generation":[83],"and":[84,115],"site":[85],"reactivity":[86],"classification.":[87],"Our":[88],"fine-tuned":[89],"T5Chem":[90],"multitask":[91],"generate":[95],"correct":[97],"79%":[100],"cases.":[102],"It":[103],"also":[105],"classify":[106],"reactive":[108],"aromatic":[109],"bonds":[111],"with":[112],"95%":[113],"accuracy":[114],"88%":[116],"positive":[117],"predictive":[118],"value,":[119],"exceeding":[120],"purpose-developed":[121],"graph-based":[122],"neural":[123],"networks.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
