{"id":"https://openalex.org/W7133221954","doi":"https://doi.org/10.1186/s13321-026-01174-w","title":"Data curation in cheminformatics: importance and implementation","display_name":"Data curation in cheminformatics: importance and implementation","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133221954","doi":"https://doi.org/10.1186/s13321-026-01174-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/41772705"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01174-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01174-w","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/s13321-026-01174-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018312648","display_name":"Tsuyoshi Esaki","orcid":"https://orcid.org/0000-0001-8780-6346"},"institutions":[{"id":"https://openalex.org/I171494771","display_name":"Shiga University","ror":"https://ror.org/01vvhy971","country_code":"JP","type":"education","lineage":["https://openalex.org/I171494771"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tsuyoshi Esaki","raw_affiliation_strings":["Faculty of Data Science, Shiga University, 1-1-1 Banba, Hikone, Shiga, 522-8522, Japan. tsuyoshi-esaki@biwako.shiga-u.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, Shiga University, 1-1-1 Banba, Hikone, Shiga, 522-8522, Japan. tsuyoshi-esaki@biwako.shiga-u.ac.jp","institution_ids":["https://openalex.org/I171494771"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038763185","display_name":"Kazuyoshi Ikeda","orcid":"https://orcid.org/0000-0002-8433-8206"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]},{"id":"https://openalex.org/I4210150921","display_name":"RIKEN Center for Integrative Medical Sciences","ror":"https://ror.org/04mb6s476","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210150921"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Ikeda","raw_affiliation_strings":["Division of Physics for Life Functions, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-Ku, Tokyo, 105-8512, Japan. kazuyoshi.ikeda@riken.jp","HPC- and AI-Driven Drug Development Platform Division, RIKEN Center for Computational Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama City, Kanagawa, 230-0045, Japan. kazuyoshi.ikeda@riken.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Physics for Life Functions, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-Ku, Tokyo, 105-8512, Japan. kazuyoshi.ikeda@riken.jp","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"HPC- and AI-Driven Drug Development Platform Division, RIKEN Center for Computational Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama City, Kanagawa, 230-0045, Japan. kazuyoshi.ikeda@riken.jp","institution_ids":["https://openalex.org/I4210150921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018312648"],"corresponding_institution_ids":["https://openalex.org/I171494771"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":15.9881,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98141892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9067000150680542,"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":0.9067000150680542,"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":0.01769999973475933,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.011500000022351742,"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/cheminformatics","display_name":"Cheminformatics","score":0.9286999702453613},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.9200999736785889},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5507000088691711},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.34619998931884766},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3449000120162964},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.34060001373291016},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9286999702453613},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.9200999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664999961853027},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-026-01174-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01174-w","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:41772705","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41772705","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:012f6ac155f84cf6a4cf115915467393","is_oa":true,"landing_page_url":"https://doaj.org/article/012f6ac155f84cf6a4cf115915467393","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:pubmedcentral.nih.gov:13059370","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13059370/","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01174-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01174-w","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":0.6100032329559326,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3447499788","display_name":null,"funder_award_id":"JP23K14382","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G919763269","display_name":null,"funder_award_id":"JP25ama121028","funder_id":"https://openalex.org/F4320311405","funder_display_name":"Japan Agency for Medical Research and Development"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1496195305","https://openalex.org/W1510223697","https://openalex.org/W1835740130","https://openalex.org/W1952553890","https://openalex.org/W1971761242","https://openalex.org/W1972650279","https://openalex.org/W1972650408","https://openalex.org/W1975147762","https://openalex.org/W1983464445","https://openalex.org/W2016455326","https://openalex.org/W2016976521","https://openalex.org/W2039152088","https://openalex.org/W2045717408","https://openalex.org/W2050226017","https://openalex.org/W2057069496","https://openalex.org/W2072750586","https://openalex.org/W2080026691","https://openalex.org/W2087563523","https://openalex.org/W2096541451","https://openalex.org/W2125411686","https://openalex.org/W2128245586","https://openalex.org/W2170484170","https://openalex.org/W2170973067","https://openalex.org/W2412746331","https://openalex.org/W2503131032","https://openalex.org/W2549115005","https://openalex.org/W2775461895","https://openalex.org/W2793396277","https://openalex.org/W2803083648","https://openalex.org/W2887459817","https://openalex.org/W2894369333","https://openalex.org/W2903800243","https://openalex.org/W2911489562","https://openalex.org/W3000673710","https://openalex.org/W3006508031","https://openalex.org/W3012585755","https://openalex.org/W3013954280","https://openalex.org/W3046375318","https://openalex.org/W3048584318","https://openalex.org/W3082081167","https://openalex.org/W3123007855","https://openalex.org/W3198396834","https://openalex.org/W3208039415","https://openalex.org/W3215034190","https://openalex.org/W4205460523","https://openalex.org/W4206907302","https://openalex.org/W4220785481","https://openalex.org/W4281698562","https://openalex.org/W4307468223","https://openalex.org/W4308255662","https://openalex.org/W4312122703","https://openalex.org/W4313597804","https://openalex.org/W4315778078","https://openalex.org/W4317754118","https://openalex.org/W4323294421","https://openalex.org/W4323781060","https://openalex.org/W4327810158","https://openalex.org/W4366090395","https://openalex.org/W4384661704","https://openalex.org/W4385711246","https://openalex.org/W4386256707","https://openalex.org/W4387345715","https://openalex.org/W4387670873","https://openalex.org/W4387740953","https://openalex.org/W4388455891","https://openalex.org/W4390041933","https://openalex.org/W4391962651","https://openalex.org/W4392500218","https://openalex.org/W4392817267","https://openalex.org/W4402170913","https://openalex.org/W4402429489","https://openalex.org/W4402820212","https://openalex.org/W4402868135","https://openalex.org/W4403243236","https://openalex.org/W4403559264","https://openalex.org/W4404511389","https://openalex.org/W4404968258","https://openalex.org/W4405224584","https://openalex.org/W4405804475","https://openalex.org/W4406478661","https://openalex.org/W4406633314","https://openalex.org/W4407720291","https://openalex.org/W4407767386","https://openalex.org/W4408280008","https://openalex.org/W4408969965","https://openalex.org/W4411532907","https://openalex.org/W4412530104","https://openalex.org/W4412932540","https://openalex.org/W4413043772","https://openalex.org/W4414260876","https://openalex.org/W4415666428"],"related_works":[],"abstract_inverted_index":{"Data":[0],"curation":[1,77,83,85,216,230,254,266,269,304],"is":[2],"a":[3,190,196,202,243,248,260],"fundamental":[4],"yet":[5],"often":[6],"underappreciated":[7],"aspect":[8],"of":[9,24,86,105,206,252,274,327],"cheminformatics":[10,71,235,275],"and":[11,17,32,35,46,55,62,84,97,107,116,134,140,144,152,164,180,211,228,267,286,292,295,309,316,321,330,334],"computational":[12],"drug":[13],"discovery.":[14],"Large":[15],"public":[16,165],"proprietary":[18],"databases":[19],"now":[20],"provide":[21,201],"vast":[22],"amounts":[23],"chemical":[25,75],"structure,":[26],"physicochemical,":[27],"absorption,":[28],"distribution,":[29],"metabolism,":[30],"excretion,":[31],"toxicity":[33],"(ADMET),":[34],"bioactivity":[36,150],"data.":[37],"However,":[38],"these":[39],"resources":[40],"contain":[41],"structural":[42,82,91,227,265],"inconsistencies,":[43],"annotation":[44],"errors,":[45],"heterogeneous":[47],"experimental":[48,87,124],"conditions":[49],"that":[50,129,263,302],"can":[51],"limit":[52],"model":[53],"performance":[54,308],"reproducibility.":[56,310],"This":[57,219,238],"narrative":[58,204],"review":[59,94,220],"summarizes":[60],"why":[61],"how":[63,172],"data":[64,76,215,253],"should":[65],"be":[66],"curated":[67,173],"before":[68],"use":[69,326],"in":[70,142,217,255],"workflows.":[72],"We":[73,257,311],"frame":[74],"around":[78],"two":[79],"complementary":[80],"pillars:":[81],"conditions.":[88],"On":[89,122],"the":[90,123,162,226,325],"side,":[92,125],"we":[93,126,153,170,200],"existing":[95],"standardization":[96],"quantitative":[98],"structure-activity":[99],"relationship":[100],"(QSAR)-ready":[101],"workflows,":[102,284],"including":[103,324],"handling":[104],"salts":[106],"mixtures,":[108],"parent-child":[109],"policies,":[110],"aromatization,":[111],"tautomer":[112],"handling,":[113],"stereochemistry":[114],"validation,":[115],"duplicate":[117],"detection":[118],"with":[119],"conflict":[120],"resolution.":[121],"synthesize":[127],"evidence":[128],"assay":[130],"protocols,":[131],"measurement":[132],"methods,":[133],"reporting":[135],"practices":[136,281],"introduce":[137,242],"substantial":[138],"uncertainty":[139],"bias":[141],"physicochemical":[143],"ADMET":[145],"endpoints":[146],"as":[147,149,270],"well":[148],"data,":[151],"outline":[154],"practical":[155],"strategies":[156],"for":[157,214,289,319,335,339],"assembling":[158],"condition-aware":[159,293],"datasets":[160],"from":[161],"literature":[163],"databases.":[166],"Across":[167],"case":[168,299],"studies,":[169],"highlight":[171],"structure-condition":[174],"pairs":[175],"yield":[176],"more":[177],"accurate,":[178],"robust,":[179],"reproducible":[181],"models":[182],"than":[183,188],"raw,":[184],"unfiltered":[185],"collections.":[186],"Rather":[187],"introducing":[189],"new":[191,244],"predictive":[192,307],"method":[193],"or":[194],"performing":[195],"formal":[197],"statistical":[198],"meta-analysis,":[199],"structured":[203,250],"synthesis":[205,251],"current":[207],"best":[208,280],"practices,":[209],"tools,":[210],"decision":[212,287],"points":[213],"cheminformatics.":[218,256],"offers":[221],"practical,":[222],"evidence-based":[223],"guidance":[224],"on":[225],"experimental-condition":[229,268],"required":[231],"to":[232],"build":[233],"reliable":[234],"models.Scientific":[236],"Contribution:":[237],"article":[239],"does":[240],"not":[241],"algorithm":[245],"but":[246],"provides":[247],"practice-oriented,":[249],"(i)":[258],"formulate":[259],"two-pillar":[261],"framework":[262],"treats":[264],"equally":[271],"important":[272],"components":[273],"workflows;":[276],"(ii)":[277],"consolidate":[278],"scattered":[279],"into":[282],"concrete":[283],"checklists,":[285],"maps":[288],"building":[290],"\"QSAR-ready\"":[291],"datasets;":[294],"(iii)":[296],"integrate":[297],"endpoint-specific":[298],"studies":[300],"showing":[301],"rigorous":[303],"materially":[305],"improves":[306],"also":[312],"identify":[313],"open":[314],"challenges":[315],"research":[317],"directions":[318],"scaling":[320],"automating":[322],"curation,":[323],"workflow":[328],"technologies":[329],"large":[331],"language":[332],"models,":[333],"establishing":[336],"community":[337],"standards":[338],"condition":[340],"metadata.":[341]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-09T15:46:55.921056","created_date":"2026-03-03T00:00:00"}