{"id":"https://openalex.org/W3189924482","doi":"https://doi.org/10.1021/acs.jcim.1c00503","title":"Systematic Investigation of Error Distribution in Machine Learning Algorithms Applied to the Quantum-Chemistry QM9 Data Set Using the Bias and Variance Decomposition","display_name":"Systematic Investigation of Error Distribution in Machine Learning Algorithms Applied to the Quantum-Chemistry QM9 Data Set Using the Bias and Variance Decomposition","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3189924482","doi":"https://doi.org/10.1021/acs.jcim.1c00503","mag":"3189924482","pmid":"https://pubmed.ncbi.nlm.nih.gov/34387994"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00503","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00503","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/A5049836546","display_name":"Luis Cesar de Azevedo","orcid":"https://orcid.org/0000-0001-6783-8009"},"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":"Luis Cesar de Azevedo","raw_affiliation_strings":["Center of Mathematics, Computation and Cognition, Federal University of ABC, Av. dos Estados, 5001, 09210-580 Santo Andr\u00e9, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Mathematics, Computation and Cognition, Federal University of ABC, Av. dos Estados, 5001, 09210-580 Santo Andr\u00e9, SP, Brazil","institution_ids":["https://openalex.org/I71715416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003723732","display_name":"Gabriel A. Pinheiro","orcid":"https://orcid.org/0000-0001-8657-247X"},"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":"Gabriel A. Pinheiro","raw_affiliation_strings":["Institute of Science and Technology, Federal University of S\u00e3o Paulo (Unifesp), 12247-014 S\u00e3o Jos\u00e9 dos Campos, SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technology, Federal University of S\u00e3o Paulo (Unifesp), 12247-014 S\u00e3o Jos\u00e9 dos Campos, SP, Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"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":["Institute of Science and Technology, Federal University of S\u00e3o Paulo (Unifesp), 12247-014 S\u00e3o Jos\u00e9 dos Campos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8147-554X","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology, Federal University of S\u00e3o Paulo (Unifesp), 12247-014 S\u00e3o Jos\u00e9 dos Campos, SP, Brazil","institution_ids":["https://openalex.org/I88273585"]}]},{"author_position":"middle","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":false,"raw_author_name":"Juarez L. F. Da Silva","raw_affiliation_strings":["S\u00e3o Carlos Institute of Chemistry, University of S\u00e3o Paulo, PO 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, PO Box 780, 13560-970 S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","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":true,"raw_author_name":"Ronaldo C. Prati","raw_affiliation_strings":["Center of Mathematics, Computation and Cognition, Federal University of ABC, Av. dos Estados, 5001, 09210-580 Santo Andr\u00e9, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8597-4987","affiliations":[{"raw_affiliation_string":"Center of Mathematics, Computation and Cognition, Federal University of ABC, Av. dos Estados, 5001, 09210-580 Santo Andr\u00e9, SP, Brazil","institution_ids":["https://openalex.org/I71715416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005717519"],"corresponding_institution_ids":["https://openalex.org/I71715416"],"apc_list":null,"apc_paid":null,"fwci":0.6406,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.62860614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"61","issue":"9","first_page":"4210","last_page":"4223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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"}},"topics":[{"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9969000220298767,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9933000206947327,"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/outlier","display_name":"Outlier","score":0.7050731778144836},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6655893325805664},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5593600869178772},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5328629016876221},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5117514133453369},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46618884801864624},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4493902921676636},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43974217772483826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4376524090766907},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43544501066207886},{"id":"https://openalex.org/keywords/convex-hull","display_name":"Convex hull","score":0.4222428798675537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4085898995399475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4038558900356293},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.23256248235702515}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7050731778144836},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6655893325805664},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5593600869178772},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5328629016876221},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5117514133453369},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46618884801864624},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4493902921676636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43974217772483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4376524090766907},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43544501066207886},{"id":"https://openalex.org/C206194317","wikidata":"https://www.wikidata.org/wiki/Q1138624","display_name":"Convex hull","level":3,"score":0.4222428798675537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4085898995399475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4038558900356293},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.23256248235702515},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c00503","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00503","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:34387994","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34387994","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":[],"awards":[{"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"}],"funders":[{"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/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1521062204","https://openalex.org/W1524525881","https://openalex.org/W1540358749","https://openalex.org/W1584846110","https://openalex.org/W1591039139","https://openalex.org/W1969178306","https://openalex.org/W1973012451","https://openalex.org/W1975997599","https://openalex.org/W1977886272","https://openalex.org/W2002465357","https://openalex.org/W2025444507","https://openalex.org/W2044969303","https://openalex.org/W2080635178","https://openalex.org/W2114704115","https://openalex.org/W2123162799","https://openalex.org/W2292646695","https://openalex.org/W2310703973","https://openalex.org/W2337496963","https://openalex.org/W2487770199","https://openalex.org/W2620687153","https://openalex.org/W2753962198","https://openalex.org/W2787894218","https://openalex.org/W2800168263","https://openalex.org/W2883021798","https://openalex.org/W2884441791","https://openalex.org/W2955229766","https://openalex.org/W2967510802","https://openalex.org/W2967766509","https://openalex.org/W2975845070","https://openalex.org/W2996945874","https://openalex.org/W3003769243","https://openalex.org/W3010488723","https://openalex.org/W3012035124","https://openalex.org/W3014334357","https://openalex.org/W3014550317","https://openalex.org/W3022256936","https://openalex.org/W3038008928","https://openalex.org/W3089428833","https://openalex.org/W3098278859","https://openalex.org/W3104850868","https://openalex.org/W3105379789","https://openalex.org/W3126732720","https://openalex.org/W3133931590","https://openalex.org/W3142659815","https://openalex.org/W3166272013","https://openalex.org/W3170966572","https://openalex.org/W4230965853","https://openalex.org/W4300109386"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W4390662392","https://openalex.org/W71955863","https://openalex.org/W2359185137","https://openalex.org/W2610918223","https://openalex.org/W2085200861","https://openalex.org/W2789383625"],"abstract_inverted_index":{"Most":[0],"machine":[1],"learning":[2],"applications":[3],"in":[4,108,220],"quantum-chemistry":[5],"(QC)":[6],"data":[7,59],"sets":[8],"rely":[9],"on":[10,118],"a":[11,41,157,204,215],"single":[12],"statistical":[13],"error":[14,21],"parameter":[15],"such":[16],"as":[17],"the":[18,45,49,52,57,99,112,119,132,137,161,166,176,180,191,209,221],"mean":[19],"square":[20],"(MSE)":[22],"to":[23,97,128,175,198,207],"evaluate":[24,98],"their":[25],"performance.":[26],"However,":[27,154],"this":[28,62],"approach":[29],"has":[30],"limitations":[31],"or":[32],"can":[33],"even":[34],"yield":[35],"incorrect":[36],"interpretations.":[37],"Here,":[38],"we":[39,64],"report":[40],"systematic":[42],"investigation":[43],"of":[44,48,93,106,114,170,182,193,201,218],"two":[46],"components":[47,186],"MSE,":[50,210],"i.e.,":[51],"bias":[53,115,133,187,206],"and":[54,76,86,89,111,116,165,188,190],"variance,":[55],"using":[56,103,214],"QM9":[58],"set.":[60,223],"To":[61],"end,":[63],"experiment":[65],"with":[66,74,84,147,179,203],"three":[67],"descriptors,":[68],"namely":[69],"(i)":[70],"symmetry":[71],"functions":[72],"(SF,":[73],"two-body":[75],"three-body":[77,87],"functions),":[78],"(ii)":[79],"many-body":[80],"tensor":[81],"representation":[82],"(MBTR,":[83],"two-":[85],"terms),":[88],"(iii)":[90],"smooth":[91],"overlap":[92],"atomic":[94],"positions":[95],"(SOAP),":[96],"prediction":[100],"process's":[101],"performance":[102],"different":[104,152],"numbers":[105],"molecules":[107,146,219],"training":[109,222],"samples":[110],"effect":[113],"variance":[117],"final":[120],"MSE.":[121,130],"Overall,":[122],"low":[123,205],"sample":[124],"sizes":[125],"are":[126],"related":[127],"higher":[129,148],"Moreover,":[131],"component":[134],"strongly":[135],"influences":[136],"larger":[138],"MSEs.":[139],"Furthermore,":[140],"there":[141,155],"is":[142,156,196],"little":[143],"agreement":[144],"among":[145,160],"errors":[149],"(outliers)":[150],"across":[151],"descriptors.":[153],"high":[158],"prevalence":[159],"outliers":[162],"intersection":[163],"set":[164],"convex":[167],"hull":[168],"volume":[169],"geometric":[171],"coordinates":[172],"(VCH).":[173],"According":[174],"obtained":[177],"results":[178],"distribution":[181],"MSE":[183],"(and":[184],"its":[185],"variance)":[189],"appearance":[192],"outliers,":[194],"it":[195],"suggested":[197],"use":[199],"ensembles":[200],"models":[202],"minimize":[208],"more":[211],"specifically":[212],"when":[213],"small":[216],"number":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}