{"id":"https://openalex.org/W3164427032","doi":"https://doi.org/10.1021/acs.jcim.1c00331","title":"SolTranNet\u2013A Machine Learning Tool for Fast Aqueous Solubility Prediction","display_name":"SolTranNet\u2013A Machine Learning Tool for Fast Aqueous Solubility Prediction","publication_year":2021,"publication_date":"2021-05-26","ids":{"openalex":"https://openalex.org/W3164427032","doi":"https://doi.org/10.1021/acs.jcim.1c00331","mag":"3164427032","pmid":"https://pubmed.ncbi.nlm.nih.gov/34038123"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00331","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_indexed_in_scopus":true,"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8900744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069398964","display_name":"Paul Francoeur","orcid":"https://orcid.org/0000-0002-1440-567X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"funder","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul G. Francoeur","raw_affiliation_strings":["Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040700924","display_name":"David Ryan Koes","orcid":"https://orcid.org/0000-0002-6892-6614"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"funder","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Koes","raw_affiliation_strings":["Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States","institution_ids":["https://openalex.org/I170201317"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069398964"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":7.64,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.999892,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"61","issue":"6","first_page":"2530","last_page":"2536"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9999,"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":0.9999,"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":0.9993,"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/T11881","display_name":"Crystallization and Solubility Studies","score":0.9892,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.68191504},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.67448926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65175796},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5811397},{"id":"https://openalex.org/C184651966","wikidata":"https://www.wikidata.org/wiki/Q906356","display_name":"Aqueous solution","level":2,"score":0.5206822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51626134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5131698},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2940873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19076616},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14840409},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.10223368}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00331","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_indexed_in_scopus":true,"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8900744","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34038123","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_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8900744","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences","award_id":"R01GM108340"}],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W2008505552","https://openalex.org/W2036291177","https://openalex.org/W2050953367","https://openalex.org/W2076498053","https://openalex.org/W2079086794","https://openalex.org/W2101234009","https://openalex.org/W2135732933","https://openalex.org/W2169527365","https://openalex.org/W2318093614","https://openalex.org/W2773785180","https://openalex.org/W2883393965","https://openalex.org/W2912171584","https://openalex.org/W2966357564","https://openalex.org/W2966797369","https://openalex.org/W3006187295","https://openalex.org/W3007488165","https://openalex.org/W3049693203","https://openalex.org/W3082411326","https://openalex.org/W3099878876","https://openalex.org/W3159157674","https://openalex.org/W4248107770","https://openalex.org/W4405318654"],"related_works":["https://openalex.org/W4387465941","https://openalex.org/W2393951301","https://openalex.org/W2080187647","https://openalex.org/W2007219878","https://openalex.org/W2005109573","https://openalex.org/W1990608904","https://openalex.org/W1934224411","https://openalex.org/W1564792705","https://openalex.org/W1561807720","https://openalex.org/W1539400370"],"abstract_inverted_index":{"While":[0],"accurate":[1],"prediction":[2],"of":[3,92,99,124],"aqueous":[4,52],"solubility":[5,53],"remains":[6],"a":[7,46,55,84,102,113,122],"challenge":[8],"in":[9,25,40],"drug":[10],"discovery,":[11],"machine":[12,37],"learning":[13,38],"(ML)":[14],"approaches":[15],"have":[16],"become":[17],"increasingly":[18],"popular":[19],"for":[20],"this":[21,68],"task.":[22],"For":[23],"instance,":[24],"the":[26,127,135,140],"Second":[27],"Challenge":[28],"to":[29,50,115,139],"Predict":[30],"Aqueous":[31],"Solubility":[32],"(SC2),":[33],"all":[34],"groups":[35],"utilized":[36],"methods":[39,137],"their":[41],"submissions.":[42],"We":[43,106],"present":[44],"SolTranNet,":[45],"molecule":[47],"attention":[48],"transformer":[49],"predict":[51],"from":[54],"molecule's":[56],"SMILES":[57],"representation.":[58],"Atypically,":[59],"we":[60],"demonstrate":[61,108],"that":[62],"larger":[63],"models":[64],"perform":[65],"worse":[66],"at":[67,153],"task,":[69],"with":[70,134],"SolTranNet's":[71],"final":[72],"architecture":[73],"having":[74],"3,393":[75],"parameters":[76],"while":[77],"outperforming":[78],"linear":[79],"ML":[80],"approaches.":[81],"SolTranNet":[82,120,142],"has":[83],"3-fold":[85],"scaffold":[86],"split":[87],"cross-validation":[88],"root-mean-square":[89],"error":[90],"(RMSE)":[91],"1.459":[93],"on":[94,101,126],"AqSolDB":[95],"and":[96,131,147],"an":[97],"RMSE":[98],"1.711":[100],"withheld":[103],"test":[104],"set.":[105],"also":[107],"that,":[109],"when":[110],"used":[111],"as":[112],"classifier":[114],"filter":[116],"out":[117],"insoluble":[118],"compounds,":[119],"achieves":[121],"sensitivity":[123],"94.8%":[125],"SC2":[128],"data":[129],"set":[130],"is":[132,143,151],"competitive":[133],"other":[136],"submitted":[138],"competition.":[141],"distributed":[144],"via":[145],"pip,":[146],"its":[148],"source":[149],"code":[150],"available":[152],"https://github.com/gnina/SolTranNet.":[154]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3164427032","counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":1}],"updated_date":"2025-04-16T17:31:59.668128","created_date":"2021-06-07"}