{"id":"https://openalex.org/W2896072522","doi":"https://doi.org/10.1186/s13321-018-0304-9","title":"Evaluating parameters for ligand-based modeling with random forest on sparse data sets","display_name":"Evaluating parameters for ligand-based modeling with random forest on sparse data sets","publication_year":2018,"publication_date":"2018-10-10","ids":{"openalex":"https://openalex.org/W2896072522","doi":"https://doi.org/10.1186/s13321-018-0304-9","mag":"2896072522","pmid":"https://pubmed.ncbi.nlm.nih.gov/30306349"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-018-0304-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0304-9","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0304-9","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0304-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035042630","display_name":"Alexander Kensert","orcid":"https://orcid.org/0000-0002-5295-010X"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Alexander Kensert","raw_affiliation_strings":["Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden. alexander.kensert@gmail.com","Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-5295-010X","affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden. alexander.kensert@gmail.com","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027509528","display_name":"Jonathan Alvarsson","orcid":"https://orcid.org/0000-0002-8682-7206"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonathan Alvarsson","raw_affiliation_strings":["Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067014994","display_name":"Ulf Norinder","orcid":"https://orcid.org/0000-0003-3107-331X"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]},{"id":"https://openalex.org/I28166907","display_name":"Karolinska Institutet","ror":"https://ror.org/056d84691","country_code":"SE","type":"education","lineage":["https://openalex.org/I28166907"]},{"id":"https://openalex.org/I4210160701","display_name":"Kista Photonics Research Center","ror":"https://ror.org/05j59av97","country_code":"SE","type":"facility","lineage":["https://openalex.org/I4210160701"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ulf Norinder","raw_affiliation_strings":["Department of Computer and Systems Sciences, Stockholm University, Box 7003, SE-164 07, Kista, Sweden","Unit of Toxicology Sciences, Karolinska Institutet, Swetox, Forskargatan 20, SE-15136, S\u00f6dert\u00e4lje, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Systems Sciences, Stockholm University, Box 7003, SE-164 07, Kista, Sweden","institution_ids":["https://openalex.org/I161593684","https://openalex.org/I4210160701"]},{"raw_affiliation_string":"Unit of Toxicology Sciences, Karolinska Institutet, Swetox, Forskargatan 20, SE-15136, S\u00f6dert\u00e4lje, Sweden","institution_ids":["https://openalex.org/I28166907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046663348","display_name":"Ola Spjuth","orcid":"https://orcid.org/0000-0002-8083-2864"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ola Spjuth","raw_affiliation_strings":["Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035042630"],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":1329,"currency":"EUR","value_usd":1433},"fwci":4.7392,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.95870165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"49","last_page":"49"},"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":0.996999979019165,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9714000225067139,"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/random-forest","display_name":"Random forest","score":0.6843414902687073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6620163321495056},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5464058518409729},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35229384899139404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.217777818441391}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6843414902687073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620163321495056},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5464058518409729},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35229384899139404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.217777818441391}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/s13321-018-0304-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0304-9","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0304-9","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},{"id":"pmid:30306349","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30306349","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 cheminformatics","raw_type":null},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/660712","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/660712","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Journal Of Cheminformatics, vol. 10 (1), Art.No. ARTN 49","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6755600","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6755600","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_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 Cheminform","raw_type":"Text"},{"id":"pmh:oai:DiVA.org:oru-83055","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-83055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400130","display_name":"\u00d6rebro University (\u00d6rebro University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26437253","host_organization_name":"\u00d6rebro University","host_organization_lineage":["https://openalex.org/I26437253"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:DiVA.org:uu-368445","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-368445","pdf_url":null,"source":{"id":"https://openalex.org/S4306402042","display_name":"Uppsala University Publications (Uppsala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123387679","host_organization_name":"Uppsala University","host_organization_lineage":["https://openalex.org/I123387679"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:d1e4c95911014903976a9ab48d8fbd72","is_oa":false,"landing_page_url":"https://doaj.org/article/d1e4c95911014903976a9ab48d8fbd72","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 10, Iss 1, Pp 1-10 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-018-0304-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0304-9","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0304-9","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4806904401","display_name":null,"funder_award_id":"FORMAS EDC-2020: 2016-0203","funder_id":"https://openalex.org/F4320321033","funder_display_name":"Svenska Forskningsr\u00e5det Formas"},{"id":"https://openalex.org/G6373717446","display_name":null,"funder_award_id":"KAW: 2013.0253","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"}],"funders":[{"id":"https://openalex.org/F4320321033","display_name":"Svenska Forskningsr\u00e5det Formas","ror":"https://ror.org/03pjs1y45"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320336376","display_name":"Uppsala Multidisciplinary Center for Advanced Computational Science","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2896072522.pdf","grobid_xml":"https://content.openalex.org/works/W2896072522.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1536984618","https://openalex.org/W1594031697","https://openalex.org/W1933697021","https://openalex.org/W1974880836","https://openalex.org/W1975448236","https://openalex.org/W1976253807","https://openalex.org/W1983515051","https://openalex.org/W1988037271","https://openalex.org/W1988195734","https://openalex.org/W1999589609","https://openalex.org/W2007698848","https://openalex.org/W2010524461","https://openalex.org/W2011301426","https://openalex.org/W2014722063","https://openalex.org/W2022603596","https://openalex.org/W2039987382","https://openalex.org/W2044834685","https://openalex.org/W2052396986","https://openalex.org/W2060062036","https://openalex.org/W2065177836","https://openalex.org/W2065656474","https://openalex.org/W2066532920","https://openalex.org/W2077483199","https://openalex.org/W2090846279","https://openalex.org/W2101234009","https://openalex.org/W2122210511","https://openalex.org/W2135860083","https://openalex.org/W2142602210","https://openalex.org/W2153635508","https://openalex.org/W2155653793","https://openalex.org/W2157825442","https://openalex.org/W2218645992","https://openalex.org/W2276859037","https://openalex.org/W2289034962","https://openalex.org/W2473238561","https://openalex.org/W2479597298","https://openalex.org/W2607893089","https://openalex.org/W2790322107","https://openalex.org/W2798936682","https://openalex.org/W2911964244","https://openalex.org/W3085162807","https://openalex.org/W3210109776"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3171520305","https://openalex.org/W1924178503","https://openalex.org/W3135126032","https://openalex.org/W2390279801"],"abstract_inverted_index":{"Ligand-based":[0],"predictive":[1,8,91],"modeling":[2,26,89,137],"is":[3,157],"widely":[4],"used":[5],"to":[6,31,36],"generate":[7],"models":[9],"aiding":[10],"decision":[11],"making":[12],"in":[13,136],"e.g.":[14],"drug":[15],"discovery":[16],"projects.":[17],"With":[18],"growing":[19],"data":[20,33,48,60],"sets":[21,34,49],"and":[22,39,50,68,71,93,139,146,171],"requirements":[23,95],"on":[24,58,88],"low":[25,147],"time":[27,138],"comes":[28],"the":[29,52,83,143,151,181,189,196],"necessity":[30],"analyze":[32],"efficiently":[35],"support":[37,112,168,182],"rapid":[38],"robust":[40],"modeling.":[41],"In":[42],"this":[43],"study":[44],"we":[45],"analyzed":[46],"four":[47],"studied":[51],"efficiency":[53],"of":[54,65,77,99,150,195],"machine":[55,114,184],"learning":[56],"methods":[57],"sparse":[59,165],"structures,":[61],"utilizing":[62],"Morgan":[63,197],"fingerprints":[64,121,128],"different":[66,78],"radii":[67],"hash":[69],"sizes,":[70],"compared":[72,109],"with":[73,110,132],"molecular":[74],"signatures":[75],"descriptor":[76],"height.":[79],"We":[80,107],"specifically":[81],"evaluated":[82],"effect":[84],"these":[85],"parameters":[86],"had":[87],"time,":[90],"performance,":[92],"memory":[94,140,148],"using":[96,188],"two":[97],"implementations":[98],"random":[100,172],"forest;":[101],"Scikit-learn":[102],"as":[103,105],"well":[104,176],"FEST.":[106],"also":[108],"a":[111,158],"vector":[113,169,183],"implementation.":[115],"Our":[116],"results":[117,178],"showed":[118],"that":[119,155,180],"unhashed":[120],"yield":[122],"significantly":[123],"better":[124,186],"accuracy":[125],"than":[126],"hashed":[127],"([Formula:":[129],"see":[130],"text]),":[131],"no":[133],"pronounced":[134],"deterioration":[135],"usage.":[141],"Furthermore,":[142],"fast":[144],"execution":[145],"usage":[149],"FEST":[152],"algorithm":[153],"suggest":[154],"it":[156],"good":[159],"alternative":[160],"for":[161],"large,":[162],"high":[163],"dimensional":[164],"data.":[166],"Both":[167],"machines":[170],"forest":[173],"performed":[174],"equally":[175],"but":[177],"indicate":[179],"was":[185],"at":[187],"extra":[190],"information":[191],"from":[192],"larger":[193],"values":[194],"fingerprint's":[198],"radius.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}