{"id":"https://openalex.org/W4389564374","doi":"https://doi.org/10.1186/s13321-023-00787-9","title":"SIMPD: an algorithm for generating simulated time splits for validating machine learning approaches","display_name":"SIMPD: an algorithm for generating simulated time splits for validating machine learning approaches","publication_year":2023,"publication_date":"2023-12-11","ids":{"openalex":"https://openalex.org/W4389564374","doi":"https://doi.org/10.1186/s13321-023-00787-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/38082357"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00787-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00787-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00787-9","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/counter/pdf/10.1186/s13321-023-00787-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056808182","display_name":"Gregory A. Landrum","orcid":"https://orcid.org/0000-0001-6279-4481"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Gregory A. Landrum","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland. glandrum@ethz.ch","Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland. glandrum@ethz.ch","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075073575","display_name":"Maximilian Beckers","orcid":"https://orcid.org/0000-0001-5988-1322"},"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":"Maximilian Beckers","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","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":false,"raw_author_name":"Jessica Lanini","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","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":false,"raw_author_name":"Nadine Schneider","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland"],"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"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"]},{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikolaus Stiefl","raw_affiliation_strings":["F. Hoffman-LaRoche AG, Grenzacherstrasse 124, 4070, Basel, Switzerland","Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland"],"affiliations":[{"raw_affiliation_string":"F. Hoffman-LaRoche AG, Grenzacherstrasse 124, 4070, Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Pharma AG, Novartis Campus, Basel, 4002, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019754904","display_name":"Sereina Riniker","orcid":"https://orcid.org/0000-0003-1893-4031"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sereina Riniker","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland. sriniker@ethz.ch","Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland. sriniker@ethz.ch","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, Zurich, 8093, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056808182"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1456,"currency":"EUR","value_usd":1570},"fwci":4.4757,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95622158,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"119","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9269000291824341,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9265000224113464,"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/chembl","display_name":"chEMBL","score":0.8298901319503784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269867658615112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5719823241233826},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5263503789901733},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4566684067249298},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4153635799884796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4112321138381958},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.322895348072052},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.19852644205093384},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.1888943314552307}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.8298901319503784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269867658615112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5719823241233826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5263503789901733},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4566684067249298},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4153635799884796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4112321138381958},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.322895348072052},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.19852644205093384},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.1888943314552307},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-023-00787-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00787-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00787-9","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:38082357","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38082357","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:pubmedcentral.nih.gov:10712068","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10712068","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10712068/pdf/13321_2023_Article_787.pdf","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:doaj.org/article:560e2e5559bf491d8bf3bd83ce87ad62","is_oa":true,"landing_page_url":"https://doaj.org/article/560e2e5559bf491d8bf3bd83ce87ad62","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 15, Iss 1, Pp 1-16 (2023)","raw_type":"article"},{"id":"pmh:oai:oak.novartis.com:51535","is_oa":true,"landing_page_url":"https://jcheminf.biomedcentral.com/articles/10.1186/s13321-023-00787-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400709","display_name":"The Novartis Repository (Novartis)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1283582996","host_organization_name":"Novartis (Switzerland)","host_organization_lineage":["https://openalex.org/I1283582996"],"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":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00787-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00787-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00787-9","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":[{"score":0.5400000214576721,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389564374.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2019678805","https://openalex.org/W2033495141","https://openalex.org/W2046344452","https://openalex.org/W2075769043","https://openalex.org/W2126105956","https://openalex.org/W2160592148","https://openalex.org/W2558999090","https://openalex.org/W2909055772","https://openalex.org/W2909063104","https://openalex.org/W2911964244","https://openalex.org/W3097605476","https://openalex.org/W3170120958","https://openalex.org/W4293257826","https://openalex.org/W4308683713"],"related_works":["https://openalex.org/W2800402488","https://openalex.org/W2155478691","https://openalex.org/W3005441379","https://openalex.org/W1552948952","https://openalex.org/W4388455891","https://openalex.org/W4310672789","https://openalex.org/W2096541451","https://openalex.org/W1185153672","https://openalex.org/W2145268499","https://openalex.org/W3209881118"],"abstract_inverted_index":{"Time-split":[0],"cross-validation":[1],"is":[2,25],"broadly":[3,27],"recognized":[4],"as":[5],"the":[6,38,58,82,97,106,117,139,166],"gold":[7],"standard":[8,130],"for":[9,14,100,125,158,163],"validating":[10,159],"predictive":[11],"models":[12,161],"intended":[13,162],"use":[15,164],"in":[16,61,89,119,165],"medicinal":[17,41,63,170],"chemistry":[18,42,64,171],"projects.":[19],"Unfortunately":[20],"this":[21],"type":[22],"of":[23,30,81,168],"data":[24,49,66,108,144,152,178],"not":[26],"available":[28,181],"outside":[29],"large":[31],"pharmaceutical":[32],"research":[33],"organizations.":[34],"Here":[35],"we":[36],"introduce":[37],"SIMPD":[39,68,104,140,174],"(simulated":[40],"project":[43,65],"data)":[44],"algorithm":[45,73,141],"to":[46,105,142],"split":[47],"public":[48,151],"sets":[50,55,109,153,179],"into":[51],"training":[52],"and":[53,86,121,148,176],"test":[54],"that":[56],"mimic":[57],"differences":[59,83,118],"observed":[60,124],"real-world":[62,107],"sets.":[67],"uses":[69],"a":[70,169],"multi-objective":[71],"genetic":[72],"with":[74],"objectives":[75],"derived":[76],"from":[77,146],"an":[78],"extensive":[79],"analysis":[80],"between":[84],"early":[85],"late":[87],"compounds":[88],"more":[90,114],"than":[91,128],"130":[92],"lead-optimization":[93],"projects":[94],"run":[95],"within":[96],"Novartis":[98],"Institutes":[99],"BioMedical":[101],"Research.":[102],"Applying":[103],"produced":[110],"training/test":[111],"splits":[112,127],"which":[113,154],"accurately":[115],"reflect":[116],"properties":[120],"machine-learning":[122,160],"performance":[123],"temporal":[126],"other":[129],"approaches":[131],"like":[132],"random":[133],"or":[134],"neighbor":[135],"splits.":[136],"We":[137],"applied":[138],"bioactivity":[143],"extracted":[145],"ChEMBL":[147],"created":[149],"99":[150],"can":[155],"be":[156],"used":[157],"setting":[167],"project.":[172],"The":[173],"code":[175],"simulated":[177],"are":[180],"under":[182],"open-source/open-data":[183],"licenses":[184],"at":[185],"github.com/rinikerlab/molecular_time_series.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
