{"id":"https://openalex.org/W4405720113","doi":"https://doi.org/10.1021/acs.jcim.4c01862","title":"Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow","display_name":"Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405720113","doi":"https://doi.org/10.1021/acs.jcim.4c01862","pmid":"https://pubmed.ncbi.nlm.nih.gov/39714952"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c01862","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01862","pdf_url":null,"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","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.4c01862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029069984","display_name":"Son Gyo Jung","orcid":"https://orcid.org/0000-0001-8464-2526"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"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"]},{"id":"https://openalex.org/I4210092957","display_name":"Research Complex at Harwell","ror":"https://ror.org/00gqx0331","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210092957"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Son Gyo Jung","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K"],"affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]},{"raw_affiliation_string":"Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K","institution_ids":["https://openalex.org/I4210092957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058969250","display_name":"Guwon Jung","orcid":"https://orcid.org/0000-0001-8624-8848"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"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"]},{"id":"https://openalex.org/I4210092957","display_name":"Research Complex at Harwell","ror":"https://ror.org/00gqx0331","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210092957"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guwon Jung","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K","Scientific Computing Department, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K"],"affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K","institution_ids":["https://openalex.org/I4210092957"]},{"raw_affiliation_string":"Scientific Computing Department, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068607578","display_name":"Jacqueline M. Cole","orcid":"https://orcid.org/0000-0002-1552-8743"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"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"]},{"id":"https://openalex.org/I4210092957","display_name":"Research Complex at Harwell","ror":"https://ror.org/00gqx0331","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210092957"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jacqueline M. Cole","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K"],"affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]},{"raw_affiliation_string":"Rutherford Appleton Laboratory, Research Complex at Harwell, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0FA, U.K","institution_ids":["https://openalex.org/I4210092957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068607578"],"corresponding_institution_ids":["https://openalex.org/I1286704778","https://openalex.org/I241749","https://openalex.org/I4210092957"],"apc_list":null,"apc_paid":null,"fwci":4.5816,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95557213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"65","issue":"1","first_page":"133","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9575999975204468,"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/interpretability","display_name":"Interpretability","score":0.7658489346504211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513701319694519},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.697106122970581},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.632957935333252},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6302223205566406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129931211471558},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.5204075574874878},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.45928123593330383},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4458782374858856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4282247722148895},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41815200448036194},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.11636313796043396}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7658489346504211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513701319694519},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.697106122970581},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.632957935333252},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6302223205566406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129931211471558},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.5204075574874878},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.45928123593330383},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4458782374858856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4282247722148895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41815200448036194},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11636313796043396},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.4c01862","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01862","pdf_url":null,"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:39714952","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39714952","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:11733926","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11733926","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11733926/pdf/ci4c01862.pdf","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":"J Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/378673","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/378673","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/5b143d3e-1802-460c-be74-b39df0b30099/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:purl.org/net/epubs:work/59545058","is_oa":true,"landing_page_url":"https://epubs.stfc.ac.uk/work/59545058","pdf_url":null,"source":{"id":"https://openalex.org/S4306400334","display_name":"Science and Technology Facilities Council","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.4c01862","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01862","pdf_url":null,"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":[{"id":"https://openalex.org/G1531024995","display_name":null,"funder_award_id":"RCSRF1819\\7\\10","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"},{"id":"https://openalex.org/F4320337816","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08"},{"id":"https://openalex.org/F4320338254","display_name":"ISIS Neutron and Muon Source","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1992099835","https://openalex.org/W1998056319","https://openalex.org/W2008056655","https://openalex.org/W2008505552","https://openalex.org/W2015197254","https://openalex.org/W2021748110","https://openalex.org/W2044834685","https://openalex.org/W2060531713","https://openalex.org/W2065854198","https://openalex.org/W2066273100","https://openalex.org/W2076498053","https://openalex.org/W2080635178","https://openalex.org/W2104489082","https://openalex.org/W2114704115","https://openalex.org/W2134164499","https://openalex.org/W2134473756","https://openalex.org/W2145578524","https://openalex.org/W2176516200","https://openalex.org/W2177317049","https://openalex.org/W2200017991","https://openalex.org/W2276859037","https://openalex.org/W2290847742","https://openalex.org/W2329258563","https://openalex.org/W2406943157","https://openalex.org/W2461470610","https://openalex.org/W2461620095","https://openalex.org/W2464725281","https://openalex.org/W2527189750","https://openalex.org/W2565684601","https://openalex.org/W2571816515","https://openalex.org/W2594183968","https://openalex.org/W2766856748","https://openalex.org/W2777416523","https://openalex.org/W2804431384","https://openalex.org/W2884430236","https://openalex.org/W2900090807","https://openalex.org/W2902452488","https://openalex.org/W2911293880","https://openalex.org/W2911964244","https://openalex.org/W2914757825","https://openalex.org/W2949095042","https://openalex.org/W2962810718","https://openalex.org/W2962876364","https://openalex.org/W2963784900","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W2968923792","https://openalex.org/W3009321976","https://openalex.org/W3045928028","https://openalex.org/W3093934881","https://openalex.org/W3100157108","https://openalex.org/W3100710928","https://openalex.org/W3208687975","https://openalex.org/W4213077304","https://openalex.org/W4214868967","https://openalex.org/W4225731953","https://openalex.org/W4313485929","https://openalex.org/W4321603581","https://openalex.org/W4388724267","https://openalex.org/W4391578539","https://openalex.org/W4392282307","https://openalex.org/W4401388215","https://openalex.org/W4402556597","https://openalex.org/W4403039705","https://openalex.org/W4405318654"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W1573015311","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344"],"abstract_inverted_index":{"Machine":[0],"learning":[1,57],"(ML)":[2],"methods":[3,58],"provide":[4],"a":[5,96,109,120,141,221,228],"pathway":[6],"to":[7,60,87,125,159,196],"accurately":[8],"predict":[9,126,197],"molecular":[10,128],"properties,":[11],"leveraging":[12],"patterns":[13],"derived":[14],"from":[15],"structure-property":[16],"relationships":[17],"within":[18],"materials":[19,30,48],"databases.":[20],"This":[21],"approach":[22,178],"holds":[23],"significant":[24],"importance":[25,213],"in":[26,117,167],"drug":[27,130],"discovery":[28],"and":[29,46,55,129,150,218],"design,":[31],"where":[32],"the":[33,41,88,134,198,204,212],"rapid,":[34],"efficient":[35],"screening":[36],"of":[37,43,99,136,144,169,200,206,214,231],"molecules":[38],"can":[39],"accelerate":[40],"development":[42],"new":[44],"pharmaceuticals":[45],"chemical":[47,101,201],"for":[49,90,188],"highly":[50],"specialized":[51],"target":[52],"application.":[53],"Unsupervised":[54],"self-supervised":[56],"applied":[59],"graph-based":[61],"or":[62],"geometric":[63],"models":[64,73],"have":[65,74],"garnered":[66],"considerable":[67,83],"traction.":[68],"More":[69],"recently,":[70],"transformer-based":[71],"language":[72],"emerged":[75],"as":[76],"powerful":[77],"tools.":[78],"Nevertheless,":[79],"their":[80],"application":[81],"entails":[82],"computational":[84,174],"resources,":[85],"owing":[86],"need":[89],"an":[91],"extensive":[92],"pretraining":[93],"process":[94],"on":[95,224],"vast":[97],"corpus":[98],"unlabeled":[100],"data":[102,145],"sets.":[103],"To":[104],"this":[105],"end,":[106],"we":[107],"present":[108],"semisupervised":[110],"strategy":[111],"that":[112,185],"harnesses":[113],"substructure":[114],"vector":[115],"embeddings":[116],"conjunction":[118],"with":[119,173,227],"ML-based":[121],"feature":[122,183,216],"selection":[123,219],"workflow":[124],"various":[127],"properties.":[131],"We":[132],"evaluate":[133],"efficacy":[135],"our":[137,177,207],"modeling":[138,226],"methodology":[139],"across":[140],"diverse":[142],"range":[143],"sets,":[146],"encompassing":[147],"both":[148],"regression":[149],"classification":[151],"tasks.":[152],"Our":[153],"findings":[154],"demonstrate":[155],"superior":[156],"performance":[157],"compared":[158],"most":[160],"existing":[161],"state-of-the-art":[162],"algorithms,":[163],"while":[164],"offering":[165],"advantages":[166],"terms":[168],"balancing":[170],"model":[171,189],"accuracy":[172],"requirements.":[175],"Moreover,":[176],"provides":[179],"deeper":[180],"insights":[181],"into":[182],"interactions":[184],"are":[186],"essential":[187],"interpretability.":[190],"A":[191],"case":[192],"study":[193],"is":[194],"conducted":[195],"lipophilicity":[199],"molecules,":[202],"exemplifying":[203],"robustness":[205],"strategy.":[208],"The":[209],"result":[210],"underscores":[211],"meticulous":[215],"analysis":[217],"over":[220],"mere":[222],"reliance":[223],"predictive":[225],"high":[229],"degree":[230],"algorithmic":[232],"complexity.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}