{"id":"https://openalex.org/W3133888656","doi":"https://doi.org/10.1021/acs.jcim.0c01267","title":"Correlation-Based Framework for Extraction of Insights from Quantum Chemistry Databases: Applications for Nanoclusters","display_name":"Correlation-Based Framework for Extraction of Insights from Quantum Chemistry Databases: Applications for Nanoclusters","publication_year":2021,"publication_date":"2021-03-09","ids":{"openalex":"https://openalex.org/W3133888656","doi":"https://doi.org/10.1021/acs.jcim.0c01267","mag":"3133888656","pmid":"https://pubmed.ncbi.nlm.nih.gov/33685128"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c01267","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01267","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062472155","display_name":"Johnatan Mucelini","orcid":"https://orcid.org/0000-0001-5687-8603"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Johnatan Mucelini","raw_affiliation_strings":["S\u00e3o Carlos Institute of Chemistry, University of S\u00e3o Paulo, P. O. Box 780, 13560-970 S\u00e3o Carlos, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S\u00e3o Carlos Institute of Chemistry, University of S\u00e3o Paulo, P. O. Box 780, 13560-970 S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041084845","display_name":"Marcos G. Quiles","orcid":"https://orcid.org/0000-0001-8147-554X"},"institutions":[{"id":"https://openalex.org/I88273585","display_name":"Universidade Federal de S\u00e3o Paulo","ror":"https://ror.org/02k5swt12","country_code":"BR","type":"education","lineage":["https://openalex.org/I88273585"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos G. Quiles","raw_affiliation_strings":["Department of Science and Technology, Federal University of S\u00e3o Paulo, 12247-014 S\u00e3o Jose dos Campos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8147-554X","affiliations":[{"raw_affiliation_string":"Department of Science and Technology, Federal University of S\u00e3o Paulo, 12247-014 S\u00e3o Jose dos Campos, SP, Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005717519","display_name":"Ronaldo C. Prati","orcid":"https://orcid.org/0000-0001-8597-4987"},"institutions":[{"id":"https://openalex.org/I71715416","display_name":"Universidade Federal do ABC","ror":"https://ror.org/028kg9j04","country_code":"BR","type":"education","lineage":["https://openalex.org/I71715416"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ronaldo C. Prati","raw_affiliation_strings":["Center for Mathematics, Computation and Cognition, Federal University of ABC, 09210-580 Santo Andr\u00e9, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Mathematics, Computation and Cognition, Federal University of ABC, 09210-580 Santo Andr\u00e9, SP, Brazil","institution_ids":["https://openalex.org/I71715416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077065362","display_name":"Juarez L. F. Da Silva","orcid":"https://orcid.org/0000-0003-0645-8760"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Juarez L. F. Da Silva","raw_affiliation_strings":["S\u00e3o Carlos Institute of Chemistry, University of S\u00e3o Paulo, P. O. Box 780, 13560-970 S\u00e3o Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-0645-8760","affiliations":[{"raw_affiliation_string":"S\u00e3o Carlos Institute of Chemistry, University of S\u00e3o Paulo, P. O. Box 780, 13560-970 S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077065362"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.6088,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71136761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"61","issue":"3","first_page":"1125","last_page":"1135"},"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":0.9998999834060669,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9797000288963318,"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/nanoclusters","display_name":"Nanoclusters","score":0.6925944685935974},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6826838254928589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6733739376068115},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5923750996589661},{"id":"https://openalex.org/keywords/spearmans-rank-correlation-coefficient","display_name":"Spearman's rank correlation coefficient","score":0.5556982755661011},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.5277079939842224},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5142073631286621},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.508799135684967},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.4418552815914154},{"id":"https://openalex.org/keywords/quantum-chemical","display_name":"Quantum chemical","score":0.42654669284820557},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.29220008850097656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18907544016838074},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.17653098702430725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16867515444755554},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16794168949127197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16631293296813965},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.16087451577186584},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.13532888889312744}],"concepts":[{"id":"https://openalex.org/C2778402822","wikidata":"https://www.wikidata.org/wiki/Q22302226","display_name":"Nanoclusters","level":2,"score":0.6925944685935974},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6826838254928589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733739376068115},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5923750996589661},{"id":"https://openalex.org/C159744936","wikidata":"https://www.wikidata.org/wiki/Q1126730","display_name":"Spearman's rank correlation coefficient","level":2,"score":0.5556982755661011},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.5277079939842224},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5142073631286621},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.508799135684967},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.4418552815914154},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.42654669284820557},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.29220008850097656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18907544016838074},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.17653098702430725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16867515444755554},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16794168949127197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16631293296813965},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.16087451577186584},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.13532888889312744},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.0c01267","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01267","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:33685128","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33685128","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G217965651","display_name":null,"funder_award_id":"2018/11152-0","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G3032252599","display_name":null,"funder_award_id":"142393/2018-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3559446800","display_name":null,"funder_award_id":"2017/11631-2","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G8410538189","display_name":null,"funder_award_id":"2018/21401-7","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320307816","display_name":"Shell","ror":"https://ror.org/00b5m4j81"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323909","display_name":"Ag\u00eancia Nacional do Petr\u00f3leo, G\u00e1s Natural e Biocombust\u00edveis","ror":"https://ror.org/00phthq42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1545231783","https://openalex.org/W1656197828","https://openalex.org/W1727682642","https://openalex.org/W1865667476","https://openalex.org/W1970127494","https://openalex.org/W1978239142","https://openalex.org/W2029413789","https://openalex.org/W2031314768","https://openalex.org/W2044768445","https://openalex.org/W2045210181","https://openalex.org/W2102572148","https://openalex.org/W2121076213","https://openalex.org/W2137130182","https://openalex.org/W2145979309","https://openalex.org/W2146292423","https://openalex.org/W2159556073","https://openalex.org/W2159795178","https://openalex.org/W2167590372","https://openalex.org/W2206541345","https://openalex.org/W2312187508","https://openalex.org/W2338402873","https://openalex.org/W2342249984","https://openalex.org/W2507462991","https://openalex.org/W2529996553","https://openalex.org/W2559506073","https://openalex.org/W2561267009","https://openalex.org/W2614799534","https://openalex.org/W2780173879","https://openalex.org/W2788484525","https://openalex.org/W2791365408","https://openalex.org/W2899987996","https://openalex.org/W2905472553","https://openalex.org/W2949169065","https://openalex.org/W2963339823","https://openalex.org/W2971315753","https://openalex.org/W2984517521","https://openalex.org/W2996484871","https://openalex.org/W3003257820","https://openalex.org/W3012320417","https://openalex.org/W3023748241","https://openalex.org/W3080199112","https://openalex.org/W3098269892","https://openalex.org/W3101744125","https://openalex.org/W3103145119","https://openalex.org/W3104850868","https://openalex.org/W3106063097"],"related_works":["https://openalex.org/W1911095394","https://openalex.org/W2749680699","https://openalex.org/W2146096861","https://openalex.org/W2999441357","https://openalex.org/W2773390159","https://openalex.org/W1478087083","https://openalex.org/W3152154711","https://openalex.org/W2963320501","https://openalex.org/W1996619012","https://openalex.org/W4232364410"],"abstract_inverted_index":{"The":[0],"amount":[1],"of":[2,17,22,32,59],"quantum":[3],"chemistry":[4],"(QC)":[5],"data":[6,40,52,181],"is":[7,142,189],"increasing":[8],"year":[9,11],"by":[10,38],"due":[12],"to":[13,55,87,101,145,165,192],"the":[14,57,89,139,178],"continuous":[15],"increase":[16],"computational":[18],"power":[19],"and":[20,85,109,117,122,147,162],"development":[21],"new":[23,173,194],"algorithms.":[24],"However,":[25],"in":[26],"most":[27],"cases,":[28],"our":[29,99,132,135],"atom-level":[30],"knowledge":[31],"molecular":[33,75],"systems":[34],"has":[35],"been":[36],"obtained":[37],"manual":[39],"analyses":[41],"based":[42],"on":[43],"selected":[44],"descriptors.":[45],"In":[46],"this":[47,160],"work,":[48],"we":[49,153,169],"introduce":[50],"a":[51,67,94,172],"mining":[53,182],"framework":[54,100],"accelerate":[56],"extraction":[58],"insights":[60,119],"from":[61],"QC":[62,180],"datasets,":[63],"which":[64,184],"starts":[65],"with":[66,93],"featurization":[68],"process":[69],"that":[70,127,138,156,176],"converts":[71],"atomic":[72],"features":[73,91],"into":[74],"properties":[76],"(AtoMF).":[77],"Then,":[78],"it":[79],"employs":[80],"correlation":[81,124],"coefficients":[82],"(Pearson,":[83],"Spearman,":[84],"Kendall)":[86],"investigate":[88,102],"AtoMF":[90],"relationship":[92],"target":[95],"property.":[96],"We":[97,113],"applied":[98],"three":[103],"nanocluster":[104],"systems,":[105],"namely,":[106],"PtnTM55\u2013n,":[107],"CenZr15\u2013nO30,":[108],"(CHn":[110],"+":[111],"mH)/TM13.":[112],"found":[114],"several":[115],"interesting":[116],"consistent":[118],"using":[120],"Spearman":[121],"Kendall":[123],"coefficients,":[125],"indicating":[126],"they":[128],"are":[129],"suitable":[130],"for":[131],"approach;":[133],"however,":[134],"results":[136],"indicate":[137],"Pearson":[140],"coefficient":[141],"very":[143],"sensitive":[144],"outliers":[146],"should":[148],"not":[149],"be":[150,186],"used.":[151],"Moreover,":[152],"highlight":[154],"problems":[155],"can":[157,185],"occur":[158],"during":[159],"analysis":[161],"discuss":[163],"how":[164],"handle":[166],"them.":[167],"Finally,":[168],"make":[170],"available":[171],"Python":[174],"package":[175],"implements":[177],"proposed":[179],"framework,":[183],"used":[187],"as":[188],"or":[190],"modified":[191],"include":[193],"features.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}