{"id":"https://openalex.org/W4385210687","doi":"https://doi.org/10.1021/acs.jcim.3c00523","title":"PREFER: A New Predictive Modeling Framework for Molecular Discovery","display_name":"PREFER: A New Predictive Modeling Framework for Molecular Discovery","publication_year":2023,"publication_date":"2023-07-24","ids":{"openalex":"https://openalex.org/W4385210687","doi":"https://doi.org/10.1021/acs.jcim.3c00523","pmid":"https://pubmed.ncbi.nlm.nih.gov/37487018"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00523","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00523","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":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006854022","display_name":"Jessica Lanini","orcid":"https://orcid.org/0009-0007-9194-008X"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jessica Lanini","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030428816","display_name":"Gianluca Santarossa","orcid":null},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gianluca Santarossa","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044129967","display_name":"Finton Sirockin","orcid":"https://orcid.org/0000-0003-2536-7485"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Finton Sirockin","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015356572","display_name":"Richard A. Lewis","orcid":null},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Richard Lewis","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002248255","display_name":"Nikolas Fechner","orcid":"https://orcid.org/0000-0003-3852-3950"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikolas Fechner","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074349603","display_name":"Hubert Misztela","orcid":null},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hubert Misztela","raw_affiliation_strings":["AI Innovation Lab, Novartis Pharma AG, Dublin 4, Irland"],"affiliations":[{"raw_affiliation_string":"AI Innovation Lab, Novartis Pharma AG, Dublin 4, Irland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063609461","display_name":"Sarah Lewis","orcid":"https://orcid.org/0000-0001-5308-6619"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sarah Lewis","raw_affiliation_strings":["Microsoft Research AI4Science, Cambridge CB1 2FB, U.K"],"affiliations":[{"raw_affiliation_string":"Microsoft Research AI4Science, Cambridge CB1 2FB, U.K","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022880503","display_name":"Krzysztof Maziarz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krzysztof Maziarz","raw_affiliation_strings":["Microsoft Research AI4Science, Cambridge CB1 2FB, U.K"],"affiliations":[{"raw_affiliation_string":"Microsoft Research AI4Science, Cambridge CB1 2FB, U.K","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081369853","display_name":"Megan Stanley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Megan Stanley","raw_affiliation_strings":["Microsoft Research AI4Science, Cambridge CB1 2FB, U.K"],"affiliations":[{"raw_affiliation_string":"Microsoft Research AI4Science, Cambridge CB1 2FB, U.K","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007543032","display_name":"Marwin Segler","orcid":"https://orcid.org/0000-0001-8008-0546"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marwin Segler","raw_affiliation_strings":["Microsoft Research AI4Science, Cambridge CB1 2FB, U.K"],"affiliations":[{"raw_affiliation_string":"Microsoft Research AI4Science, Cambridge CB1 2FB, U.K","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057292715","display_name":"Nikolaus Stiefl","orcid":"https://orcid.org/0000-0003-2562-7080"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikolaus Stiefl","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031496441","display_name":"Nadine Schneider","orcid":"https://orcid.org/0000-0001-5824-2764"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Nadine Schneider","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5006854022","https://openalex.org/A5031496441"],"corresponding_institution_ids":["https://openalex.org/I1283582996"],"apc_list":null,"apc_paid":null,"fwci":3.1695,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93126312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"63","issue":"15","first_page":"4497","last_page":"4504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9927999973297119,"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/python","display_name":"Python (programming language)","score":0.8486595153808594},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.8213825225830078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778837084770203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6145593523979187},{"id":"https://openalex.org/keywords/prioritization","display_name":"Prioritization","score":0.5933709144592285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233806371688843},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4593724012374878},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42023730278015137},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4106355905532837},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3569808602333069},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16097846627235413},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.12286308407783508}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8486595153808594},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8213825225830078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778837084770203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6145593523979187},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5933709144592285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233806371688843},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4593724012374878},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42023730278015137},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4106355905532837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3569808602333069},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16097846627235413},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.12286308407783508},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c00523","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00523","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:37487018","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37487018","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1975147762","https://openalex.org/W2019334008","https://openalex.org/W2019678805","https://openalex.org/W2044834685","https://openalex.org/W2053154970","https://openalex.org/W2112364454","https://openalex.org/W2525356667","https://openalex.org/W2558999090","https://openalex.org/W2784226073","https://openalex.org/W2784499877","https://openalex.org/W2901476322","https://openalex.org/W2949676527","https://openalex.org/W2955219525","https://openalex.org/W2966284335","https://openalex.org/W2972499938","https://openalex.org/W3014476516","https://openalex.org/W3037490090","https://openalex.org/W3097145107","https://openalex.org/W3097605476","https://openalex.org/W3098949126","https://openalex.org/W3119655479","https://openalex.org/W3170120958","https://openalex.org/W3198664897","https://openalex.org/W4293257826","https://openalex.org/W4310222865"],"related_works":["https://openalex.org/W1573015311","https://openalex.org/W1570419641","https://openalex.org/W4386509167","https://openalex.org/W2889938001","https://openalex.org/W4293771607","https://openalex.org/W3165034028","https://openalex.org/W2296499206","https://openalex.org/W3210319767","https://openalex.org/W2789551765","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Machine-learning":[0],"and":[1,21,29,31,45,65,78,92,97,109],"deep-learning":[2],"models":[3],"have":[4],"been":[5],"extensively":[6],"used":[7],"in":[8,61],"cheminformatics":[9],"to":[10,14,22,41],"predict":[11],"molecular":[12,36,57,76],"properties,":[13],"reduce":[15],"the":[16,32,87,114,125],"need":[17],"for":[18,56],"direct":[19],"measurements,":[20],"accelerate":[23],"compound":[24],"prioritization.":[25],"However,":[26],"different":[27,75],"setups":[28],"frameworks":[30],"large":[33],"number":[34],"of":[35,86,89,99,116,124],"representations":[37,77],"make":[38],"it":[39],"difficult":[40],"properly":[42],"evaluate,":[43],"reproduce,":[44],"compare":[46],"them.":[47],"Here":[48],"we":[49,112],"present":[50],"a":[51],"new":[52],"PREdictive":[53],"modeling":[54],"FramEwoRk":[55],"discovery":[58],"(PREFER),":[59],"written":[60],"Python":[62],"(version":[63,69],"3.7.7)":[64],"based":[66],"on":[67,103,118,130],"AutoSklearn":[68],"0.14.7),":[70],"that":[71],"allows":[72],"comparison":[73],"between":[74],"common":[79],"machine-learning":[80],"models.":[81],"We":[82],"provide":[83],"an":[84],"overview":[85],"design":[88],"our":[90],"framework":[91,126],"show":[93],"exemplary":[94],"use":[95,115],"cases":[96],"results":[98],"several":[100],"representation-model":[101],"combinations":[102],"diverse":[104],"data":[105,120],"sets,":[106],"both":[107],"public":[108],"in-house.":[110],"Finally,":[111],"discuss":[113],"PREFER":[117],"small":[119],"sets.":[121],"The":[122],"code":[123],"is":[127],"freely":[128],"available":[129],"GitHub.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
