{"id":"https://openalex.org/W4281671019","doi":"https://doi.org/10.1186/s13321-022-00611-w","title":"Analysis of the benefits of imputation models over traditional QSAR models for toxicity prediction","display_name":"Analysis of the benefits of imputation models over traditional QSAR models for toxicity prediction","publication_year":2022,"publication_date":"2022-06-07","ids":{"openalex":"https://openalex.org/W4281671019","doi":"https://doi.org/10.1186/s13321-022-00611-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/35672779"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00611-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00611-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00611-w","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/counter/pdf/10.1186/s13321-022-00611-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008780723","display_name":"Moritz Walter","orcid":"https://orcid.org/0009-0007-9021-3999"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Moritz Walter","raw_affiliation_strings":["Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021119424","display_name":"Luke Allen","orcid":"https://orcid.org/0000-0003-2750-3575"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luke N. Allen","raw_affiliation_strings":["Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023019422","display_name":"Antonio de la Vega de Le\u00f3n","orcid":"https://orcid.org/0000-0003-0927-2099"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antonio de la Vega de Le\u00f3n","raw_affiliation_strings":["Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011401103","display_name":"Samuel J. Webb","orcid":"https://orcid.org/0000-0003-1782-0921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel J. Webb","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, LS11 5PS, UK"],"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, LS11 5PS, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030046388","display_name":"Valerie J. Gillet","orcid":"https://orcid.org/0000-0002-8403-3111"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valerie J. Gillet","raw_affiliation_strings":["Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK. v.gillet@sheffield.ac.uk","Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK. v.gillet@sheffield.ac.uk","institution_ids":[]},{"raw_affiliation_string":"Information School, University of Sheffield, 211 Portobello, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008780723"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.5544,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90630025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"14","issue":"1","first_page":"32","last_page":"32"},"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9503999948501587,"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":[{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8133502006530762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5894860625267029},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.5534237623214722},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4003298580646515},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38692519068717957},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3447602689266205},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.11098191142082214}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8133502006530762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5894860625267029},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.5534237623214722},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4003298580646515},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38692519068717957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3447602689266205},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.11098191142082214}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-022-00611-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00611-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00611-w","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:35672779","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35672779","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:doaj.org/article:9c394aa713b1463b9f35b8b720813f4f","is_oa":true,"landing_page_url":"https://doaj.org/article/9c394aa713b1463b9f35b8b720813f4f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 14, Iss 1, Pp 1-27 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9172131","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9172131","pdf_url":null,"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 Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-022-00611-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00611-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00611-w","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281671019.pdf","grobid_xml":"https://content.openalex.org/works/W4281671019.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W774034202","https://openalex.org/W1490347130","https://openalex.org/W1508604947","https://openalex.org/W1967186380","https://openalex.org/W1973879072","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1988195734","https://openalex.org/W1995875735","https://openalex.org/W1999798000","https://openalex.org/W2033757486","https://openalex.org/W2056534811","https://openalex.org/W2064176611","https://openalex.org/W2135125546","https://openalex.org/W2136588642","https://openalex.org/W2189911347","https://openalex.org/W2253823912","https://openalex.org/W2295598076","https://openalex.org/W2473190403","https://openalex.org/W2594183968","https://openalex.org/W2714724074","https://openalex.org/W2751756351","https://openalex.org/W2803318906","https://openalex.org/W2907473220","https://openalex.org/W2913930293","https://openalex.org/W2919115771","https://openalex.org/W2972499938","https://openalex.org/W3014594638","https://openalex.org/W3023785973","https://openalex.org/W3029333120","https://openalex.org/W3134386172","https://openalex.org/W3170120958","https://openalex.org/W4250367016"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1967793880","https://openalex.org/W2792066564","https://openalex.org/W1965106906","https://openalex.org/W1186905254"],"abstract_inverted_index":{"Recently,":[0],"imputation":[1,55,86,152],"techniques":[2,56],"have":[3],"been":[4],"adapted":[5],"to":[6,27,96],"predict":[7],"activity":[8,30,38],"values":[9,31,110],"among":[10],"sparse":[11],"bioactivity":[12],"matrices,":[13],"showing":[14],"improvements":[15,82,127],"in":[16,79,158],"predictive":[17,159,167],"performance":[18,160],"over":[19,161],"traditional":[20,162],"QSAR":[21],"models.":[22,87,168],"These":[23],"models":[24],"are":[25],"able":[26],"use":[28],"experimental":[29,109],"for":[32,111],"auxiliary":[33],"assays":[34,67,136],"when":[35],"predicting":[36],"the":[37,81,85,115,121,126,132,135],"of":[39,63,108,123,134,147],"a":[40,44,105,144,155],"test":[41,91,102],"compound":[42],"on":[43,57,125],"specific":[45],"assay.":[46],"In":[47],"this":[48],"study,":[49],"we":[50,77],"tested":[51],"three":[52,58],"different":[53],"multi-task":[54,166],"classification-based":[59],"toxicity":[60],"datasets:":[61],"two":[62],"small":[64,145],"scale":[65,72],"(12":[66],"each)":[68],"and":[69,165],"one":[70],"large":[71,106],"with":[73,104,154],"417":[74],"assays.":[75],"Moreover,":[76],"analyzed":[78],"detail":[80],"shown":[83],"by":[84],"We":[88,118],"found":[89],"that":[90,93,142],"compounds":[92,103],"were":[94],"dissimilar":[95],"training":[97],"compounds,":[98],"as":[99,101,129,131],"well":[100,130],"number":[107],"other":[112],"assays,":[113],"showed":[114],"largest":[116],"improvements.":[117],"also":[119],"investigated":[120],"impact":[122],"sparsity":[124],"seen":[128],"relatedness":[133],"being":[137],"considered.":[138],"Our":[139],"results":[140],"show":[141],"even":[143],"amount":[146],"additional":[148],"information":[149],"can":[150],"provide":[151],"methods":[153],"strong":[156],"boost":[157],"single":[163],"task":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}