{"id":"https://openalex.org/W4415428530","doi":"https://doi.org/10.1021/acs.jcim.5c01844","title":"Improving Predictions of Molecular Properties with Graph Featurization and Heterogeneous Ensemble Models","display_name":"Improving Predictions of Molecular Properties with Graph Featurization and Heterogeneous Ensemble Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415428530","doi":"https://doi.org/10.1021/acs.jcim.5c01844","pmid":"https://pubmed.ncbi.nlm.nih.gov/41122934"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c01844","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01844","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":null,"license_id":null,"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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.23428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039862907","display_name":"M. L. Parker","orcid":"https://orcid.org/0000-0002-8466-7317"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Michael L. Parker","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8466-7317","affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062908223","display_name":"Samar Mahmoud","orcid":"https://orcid.org/0000-0002-8291-4417"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samar Mahmoud","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054672484","display_name":"Bailey C. Montefiore","orcid":"https://orcid.org/0000-0003-0217-7048"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bailey Montefiore","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084559638","display_name":"Mario \u00d6eren","orcid":"https://orcid.org/0000-0003-4292-5557"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mario \u00d6eren","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060681735","display_name":"Himani Tandon","orcid":"https://orcid.org/0000-0002-3469-8449"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Himani Tandon","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093267138","display_name":"Charlotte E. Wharrick","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Charlotte Wharrick","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044158268","display_name":"Matthew Segall","orcid":"https://orcid.org/0000-0002-2105-6535"},"institutions":[{"id":"https://openalex.org/I4210090988","display_name":"Optibrium (United Kingdom)","ror":"https://ror.org/00djq1r46","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090988"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew D. Segall","raw_affiliation_strings":["Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K"],"raw_orcid":"https://orcid.org/0000-0002-2105-6535","affiliations":[{"raw_affiliation_string":"Optibrium Ltd., F10-13 Blenheim House, Cambridge Innovation Park, Denny End Road, Cambridge CB25 9GL, U.K","institution_ids":["https://openalex.org/I4210090988"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5039862907"],"corresponding_institution_ids":["https://openalex.org/I4210090988"],"apc_list":null,"apc_paid":null,"fwci":1.3257,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86455067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"65","issue":"21","first_page":"11644","last_page":"11655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9614999890327454,"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/graph","display_name":"Graph","score":0.6037999987602234},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5746999979019165},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5733000040054321},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5722000002861023},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.492000013589859},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4269999861717224},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41929998993873596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41659998893737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268000245094299},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5153999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C86610423","wikidata":"https://www.wikidata.org/wiki/Q1925081","display_name":"Metamodeling","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2513999938964844}],"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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.5c01844","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01844","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:41122934","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41122934","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:arXiv.org:2510.23428","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.23428","pdf_url":"https://arxiv.org/pdf/2510.23428","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.23428","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.23428","pdf_url":"https://arxiv.org/pdf/2510.23428","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415428530.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1541765387","https://openalex.org/W2594183968","https://openalex.org/W2895884529","https://openalex.org/W2909063104","https://openalex.org/W2937307539","https://openalex.org/W2949676527","https://openalex.org/W2966357564","https://openalex.org/W2982188507","https://openalex.org/W3014594638","https://openalex.org/W3184680684","https://openalex.org/W3189831819","https://openalex.org/W3194368700","https://openalex.org/W4226159083","https://openalex.org/W4310014465","https://openalex.org/W4390221451"],"related_works":[],"abstract_inverted_index":{"We":[0,32,48,62,85,111],"explore":[1],"a":[2,15,24,34,41,50,119,138],"\"best-of-both\"":[3],"approach":[4],"to":[5,37,114,127,136,144],"modeling":[6],"molecular":[7,12,60],"properties":[8],"by":[9],"combining":[10,54],"learned":[11,133],"descriptors":[13,22,130],"from":[14,40,94],"graph":[16],"neural":[17],"network":[18],"(GNN)":[19],"with":[20,58,131],"general-purpose":[21,129],"and":[23,78,135],"mixed":[25],"ensemble":[26,98],"of":[27,44,80,122,141],"machine":[28],"learning":[29],"(ML)":[30],"models.":[31,47],"introduce":[33],"MetaModel":[35],"framework":[36,66],"aggregate":[38],"predictions":[39],"diverse":[42,139],"set":[43,121,140],"leading":[45],"ML":[46,142],"present":[49],"featurization":[51],"scheme":[52],"for":[53],"task-specific":[55,132],"GNN-derived":[56],"features":[57,92,134],"conventional":[59],"descriptors.":[61],"demonstrate":[63],"that":[64,88,113],"our":[65],"outperforms":[67],"the":[68,90,97,146],"cutting-edge":[69],"ChemProp":[70,95],"model":[71],"on":[72,101],"all":[73],"regression":[74],"data":[75,83,103],"sets":[76,104],"tested":[77],"6":[79],"9":[81],"classification":[82],"sets.":[84],"further":[86],"show":[87],"including":[89],"GNN":[91],"derived":[93],"boosts":[96],"model's":[99],"performance":[100,117],"several":[102],"where":[105],"it":[106,124],"otherwise":[107],"would":[108],"have":[109],"underperformed.":[110],"conclude":[112],"achieve":[115],"optimal":[116],"across":[118],"wide":[120],"problems,":[123],"is":[125],"vital":[126],"combine":[128],"use":[137],"models":[143],"make":[145],"predictions.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-11T23:18:09.558992","created_date":"2025-10-23T00:00:00"}