{"id":"https://openalex.org/W7124600178","doi":"https://doi.org/10.1186/s13321-025-01096-z","title":"Universal feature selection for simultaneous interpretability of multitask datasets","display_name":"Universal feature selection for simultaneous interpretability of multitask datasets","publication_year":2026,"publication_date":"2026-01-17","ids":{"openalex":"https://openalex.org/W7124600178","doi":"https://doi.org/10.1186/s13321-025-01096-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/41547940"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01096-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01096-z","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://doi.org/10.1186/s13321-025-01096-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015100129","display_name":"Matt Raymond","orcid":"https://orcid.org/0000-0001-6824-8692"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matt Raymond","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109, USA. mattrmd@umich.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109, USA. mattrmd@umich.edu","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035589705","display_name":"Jacob C. Saldinger","orcid":"https://orcid.org/0000-0001-5005-614X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Charles Saldinger","raw_affiliation_strings":["Chemical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA","Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038460282","display_name":"Paolo Elvati","orcid":"https://orcid.org/0000-0002-6882-6023"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paolo Elvati","raw_affiliation_strings":["Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051494789","display_name":"Angela Violi","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210114445","display_name":"Michigan Medicine","ror":"https://ror.org/01zcpa714","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210114445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angela Violi","raw_affiliation_strings":["Chemical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu","Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu","Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210114445"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. avioli@umich.edu","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210114445"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015100129"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09335622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"23","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.47690001130104065,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.47690001130104065,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.33649998903274536,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.032600000500679016,"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/interpretability","display_name":"Interpretability","score":0.9610000252723694},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7366999983787537},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6241000294685364},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5896999835968018},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5425999760627747},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5324000120162964}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9610000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710000276565552},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7366999983787537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-025-01096-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01096-z","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41547940","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41547940","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:db23bf2328194aa888134656545a4469","is_oa":true,"landing_page_url":"https://doaj.org/article/db23bf2328194aa888134656545a4469","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11703348","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12896148","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12896148","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12896148/","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01096-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01096-z","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7631419897079468,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G6495125840","display_name":null,"funder_award_id":"DGE 1256260","funder_id":"https://openalex.org/F4562087700","funder_display_name":"National Science Foundation Graduate Research Fellowship Program"},{"id":"https://openalex.org/G8963760552","display_name":null,"funder_award_id":"W911NF-18-1-0240","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4562087700","display_name":"National Science Foundation Graduate Research Fellowship Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1967849786","https://openalex.org/W1990067687","https://openalex.org/W1995808589","https://openalex.org/W2065180801","https://openalex.org/W2065905896","https://openalex.org/W2066273100","https://openalex.org/W2084714454","https://openalex.org/W2088068024","https://openalex.org/W2090467197","https://openalex.org/W2095252775","https://openalex.org/W2103459159","https://openalex.org/W2122383747","https://openalex.org/W2129018774","https://openalex.org/W2295598076","https://openalex.org/W2314259864","https://openalex.org/W2509907061","https://openalex.org/W2513486311","https://openalex.org/W2526192484","https://openalex.org/W2579555219","https://openalex.org/W2619803032","https://openalex.org/W2773987374","https://openalex.org/W2943780190","https://openalex.org/W2967018247","https://openalex.org/W3026511954","https://openalex.org/W3042344738","https://openalex.org/W3129073614","https://openalex.org/W3177828909","https://openalex.org/W3216660278","https://openalex.org/W4210727149","https://openalex.org/W4248437541","https://openalex.org/W4289524482","https://openalex.org/W4367599083","https://openalex.org/W4390221451","https://openalex.org/W4399813249","https://openalex.org/W4406476221","https://openalex.org/W6926284302"],"related_works":[],"abstract_inverted_index":{"Extracting":[0],"meaningful":[1],"features":[2,52,59,88,132],"from":[3,122,163],"complex,":[4],"high-dimensional":[5],"datasets":[6,56],"across":[7,133,141],"scientific":[8],"domains":[9],"remains":[10],"challenging.":[11],"Current":[12],"methods":[13],"often":[14],"struggle":[15],"with":[16],"scalability,":[17],"limiting":[18],"their":[19,32],"applicability":[20],"to":[21,34,54,82,100,104,160],"large":[22],"datasets,":[23,70,94,145],"or":[24],"make":[25],"restrictive":[26],"assumptions":[27],"about":[28],"feature-property":[29],"relationships,":[30],"hindering":[31],"ability":[33],"capture":[35],"complex":[36],"interactions.":[37],"BoUTS's":[38,86],"general":[39],"and":[40,57,95,150,157,166],"scalable":[41,156],"feature":[42,74],"selection":[43,151],"algorithm":[44],"surpasses":[45],"these":[46,98],"limitations":[47],"by":[48,119],"identifying":[49],"both":[50],"universal":[51,87],"relevant":[53],"all":[55],"task-specific":[58],"predictive":[60],"for":[61,115],"specific":[62],"subsets.":[63],"Evaluated":[64],"on":[65],"seven":[66,142],"diverse":[67],"chemical":[68,174],"regression":[69],"BoUTS":[71,112,127,153],"achieves":[72],"state-of-the-art":[73],"sparsity":[75],"while":[76],"generally":[77],"maintaining":[78],"prediction":[79],"accuracy":[80],"comparable":[81],"specialized":[83],"methods.":[84],"Notably,":[85],"enable":[89],"domain-specific":[90],"knowledge":[91],"transfer":[92],"between":[93,171],"we":[96],"expect":[97],"results":[99,168],"be":[101],"broadly":[102],"useful":[103],"manually-guided":[105],"inverse":[106],"problems.":[107],"Beyond":[108],"its":[109],"current":[110],"application,":[111],"holds":[113],"potential":[114],"elucidating":[116],"data-poor":[117],"systems":[118],"leveraging":[120],"information":[121],"similar":[123],"data-rich":[124],"systems.Scientific":[125],"Contribution:":[126],"selects":[128],"nonlinear,":[129],"universally":[130],"informative":[131],"multiple":[134],"datasets.":[135],"We":[136],"identify":[137,169],"crucial":[138],"\"universal":[139],"features\"":[140],"real-world":[143],"chemistry":[144],"which":[146],"enhance":[147],"cross-dataset":[148],"interpretability":[149],"stability.":[152],"is":[154,158],"highly":[155],"applicable":[159],"tabular":[161],"data":[162],"many":[164],"domains,":[165],"our":[167],"connections":[170],"seemingly":[172],"unrelated":[173],"domains.":[175]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-01-19T00:00:00"}