{"id":"https://openalex.org/W4220904544","doi":"https://doi.org/10.1186/s13321-022-00590-y","title":"MolData, a molecular benchmark for disease and target based machine learning","display_name":"MolData, a molecular benchmark for disease and target based machine learning","publication_year":2022,"publication_date":"2022-03-07","ids":{"openalex":"https://openalex.org/W4220904544","doi":"https://doi.org/10.1186/s13321-022-00590-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/35255958"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00590-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00590-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00590-y","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/s13321-022-00590-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034752225","display_name":"Arash Keshavarzi Arshadi","orcid":"https://orcid.org/0000-0003-4050-0897"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arash Keshavarzi Arshadi","raw_affiliation_strings":["Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL, USA. arashka@knights.ucf.edu","Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL, USA. arashka@knights.ucf.edu","institution_ids":[]},{"raw_affiliation_string":"Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018479551","display_name":"Milad Salem","orcid":"https://orcid.org/0000-0002-6703-6839"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milad Salem","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077543858","display_name":"Arash Firouzbakht","orcid":"https://orcid.org/0000-0003-4877-5350"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arash Firouzbakht","raw_affiliation_strings":["Department of Chemistry, University of Illinois at Urbana, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Illinois at Urbana, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085073001","display_name":"J.S. Yuan","orcid":"https://orcid.org/0000-0002-2548-8327"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiann Shiun Yuan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034752225"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":6.1619,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96961942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":"1","first_page":"10","last_page":"10"},"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":0.9972000122070312,"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/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.9474514722824097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646799087524414},{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.7277671098709106},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.7189509868621826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6967312097549438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6407065391540527},{"id":"https://openalex.org/keywords/repurposing","display_name":"Repurposing","score":0.6383499503135681},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6034903526306152},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.577384352684021},{"id":"https://openalex.org/keywords/drug-repositioning","display_name":"Drug repositioning","score":0.4736389219760895},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35289138555526733},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.27970513701438904},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2519233226776123},{"id":"https://openalex.org/keywords/drug","display_name":"Drug","score":0.18715748190879822},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11266282200813293}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.9474514722824097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646799087524414},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.7277671098709106},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.7189509868621826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6967312097549438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407065391540527},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.6383499503135681},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6034903526306152},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.577384352684021},{"id":"https://openalex.org/C103637391","wikidata":"https://www.wikidata.org/wiki/Q5308921","display_name":"Drug repositioning","level":3,"score":0.4736389219760895},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35289138555526733},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27970513701438904},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2519233226776123},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.18715748190879822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11266282200813293},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C98274493","wikidata":"https://www.wikidata.org/wiki/Q128406","display_name":"Pharmacology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-022-00590-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00590-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00590-y","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:35255958","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35255958","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:f9d3795795bd4b319b61df74463f928f","is_oa":true,"landing_page_url":"https://doaj.org/article/f9d3795795bd4b319b61df74463f928f","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 1-18 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8899453","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8899453","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/s13321-022-00590-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00590-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00590-y","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/W4220904544.pdf","grobid_xml":"https://content.openalex.org/works/W4220904544.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W74826915","https://openalex.org/W1827723601","https://openalex.org/W1963533285","https://openalex.org/W1975147762","https://openalex.org/W1983208005","https://openalex.org/W1988037271","https://openalex.org/W1994311174","https://openalex.org/W2033588393","https://openalex.org/W2049415080","https://openalex.org/W2060531713","https://openalex.org/W2084277433","https://openalex.org/W2096560421","https://openalex.org/W2103667952","https://openalex.org/W2106603184","https://openalex.org/W2130839195","https://openalex.org/W2144552075","https://openalex.org/W2151697120","https://openalex.org/W2155130960","https://openalex.org/W2155478691","https://openalex.org/W2168996312","https://openalex.org/W2189911347","https://openalex.org/W2290847742","https://openalex.org/W2319721327","https://openalex.org/W2342805349","https://openalex.org/W2346452181","https://openalex.org/W2558217333","https://openalex.org/W2586210924","https://openalex.org/W2594183968","https://openalex.org/W2776381475","https://openalex.org/W2784072336","https://openalex.org/W2790282224","https://openalex.org/W2790808809","https://openalex.org/W2805632711","https://openalex.org/W2894996849","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2911612351","https://openalex.org/W2934302500","https://openalex.org/W3000139398","https://openalex.org/W3014476516","https://openalex.org/W3017028039","https://openalex.org/W3077459578","https://openalex.org/W3097280976","https://openalex.org/W3100157108","https://openalex.org/W3117240765","https://openalex.org/W3123157506","https://openalex.org/W3155648953","https://openalex.org/W3163493952","https://openalex.org/W3212846763","https://openalex.org/W3212883348","https://openalex.org/W4206145369","https://openalex.org/W4221024791","https://openalex.org/W4225741330","https://openalex.org/W4226342384"],"related_works":["https://openalex.org/W2920928233","https://openalex.org/W4240782442","https://openalex.org/W4249248884","https://openalex.org/W3201640553","https://openalex.org/W4386453949","https://openalex.org/W4386823632","https://openalex.org/W4233725430","https://openalex.org/W3087749121","https://openalex.org/W2460225311","https://openalex.org/W2079781933"],"abstract_inverted_index":{"Deep":[0],"learning's":[1],"automatic":[2],"feature":[3],"extraction":[4],"has":[5],"been":[6],"a":[7,84,110,200,233],"revolutionary":[8],"addition":[9],"to":[10,55,122,139,160,216],"computational":[11,221],"drug":[12,131,151,185,222],"discovery,":[13],"infusing":[14],"both":[15],"the":[16,41,59,76,103,136,143,178,218,226,248],"capabilities":[17],"of":[18,43,64,81,86,171,177,202,228],"learning":[19,28,105,128],"abstract":[20],"features":[21],"and":[22,34,48,62,88,113,124,163,173,194,224],"discovering":[23],"complex":[24,94],"molecular":[25,30,126,144,229],"patterns":[26],"via":[27],"from":[29,118,154],"data.":[31],"Since":[32],"biological":[33,95],"chemical":[35],"knowledge":[36],"are":[37],"necessary":[38],"for":[39,53,79,129,141,184,187,220],"overcoming":[40],"challenges":[42],"data":[44,78,239],"curation,":[45],"balancing,":[46],"training,":[47],"evaluation,":[49],"it":[50],"is":[51,116,134,240],"important":[52],"databases":[54],"contain":[56,93],"information":[57,183],"regarding":[58],"exact":[60],"target":[61],"disease":[63,112],"each":[65,209],"bioassay.":[66],"The":[67,236],"existing":[68],"depositories":[69],"such":[70],"as":[71,244,246],"PubChem":[72,119],"or":[73],"ChEMBL":[74],"offer":[75],"screening":[77,152],"millions":[80],"molecules":[82,158],"against":[83],"variety":[85],"cells":[87],"targets,":[89],"however,":[90],"their":[91,100],"bioassays":[92,180],"descriptions":[96],"which":[97],"can":[98],"hinder":[99],"usage":[101],"by":[102],"machine":[104,127,145],"community.":[106],"In":[107],"this":[108],"work,":[109],"comprehensive":[111],"target-based":[114],"dataset":[115],"collected":[117],"in":[120,232],"order":[121],"facilitate":[123],"accelerate":[125,225],"better":[130],"discovery.":[132],"MolData":[133,179,214,237],"one":[135],"largest":[137],"efforts":[138],"date":[140],"democratizing":[142],"learning,":[146],"with":[147],"roughly":[148],"170":[149],"million":[150,156],"results":[153],"1.4":[155],"unique":[157,169],"assigned":[159],"specific":[161],"diseases":[162,189],"targets.":[164],"It":[165],"also":[166],"provides":[167],"30":[168,205],"categories":[170],"targets":[172],"diseases.":[174,196],"Correlation":[175],"analysis":[176],"unveils":[181],"valuable":[182],"repurposing":[186],"multiple":[188],"including":[190],"cancer,":[191],"metabolic":[192],"disorders,":[193],"infectious":[195],"Finally,":[197],"we":[198],"provide":[199],"benchmark":[201,238],"more":[203],"than":[204],"models":[206],"trained":[207],"on":[208],"category":[210],"using":[211],"multitask":[212],"learning.":[213],"aims":[215],"pave":[217],"way":[219],"discovery":[223],"advancement":[227],"artificial":[230],"intelligence":[231],"practical":[234],"manner.":[235],"available":[241],"at":[242],"https://GitHub.com/Transilico/MolData":[243],"well":[245],"within":[247],"additional":[249],"files.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}