{"id":"https://openalex.org/W4386156561","doi":"https://doi.org/10.1021/acs.jcim.3c00242","title":"Effect of Flattened Structures of Molecules and Materials on Machine Learning Model Training","display_name":"Effect of Flattened Structures of Molecules and Materials on Machine Learning Model Training","publication_year":2023,"publication_date":"2023-08-25","ids":{"openalex":"https://openalex.org/W4386156561","doi":"https://doi.org/10.1021/acs.jcim.3c00242","pmid":"https://pubmed.ncbi.nlm.nih.gov/37625081"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00242","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1021/acs.jcim.3c00242","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":true,"raw_author_name":"Luis Cesar de Azevedo","raw_affiliation_strings":["Center of Mathematics, Computation and Cognition, Federal University of ABC, Avenida dos Estados, 5001, 09210-580 Santo Andr\u00e9, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Mathematics, Computation and Cognition, Federal University of ABC, Avenida dos Estados, 5001, 09210-580 Santo Andr\u00e9, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I71715416"]}]},{"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, Avenida dos Estados, 5001, 09210-580 Santo Andr\u00e9, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-8597-4987","affiliations":[{"raw_affiliation_string":"Center of Mathematics, Computation and Cognition, Federal University of ABC, Avenida dos Estados, 5001, 09210-580 Santo Andr\u00e9, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I71715416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005717519","https://openalex.org/A5049836546"],"corresponding_institution_ids":["https://openalex.org/I71715416"],"apc_list":null,"apc_paid":null,"fwci":0.0934,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34197028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"63","issue":"17","first_page":"5446","last_page":"5456"},"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":0.9997000098228455,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9401000142097473,"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":0.7005754113197327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6498143076896667},{"id":"https://openalex.org/keywords/convex-hull","display_name":"Convex hull","score":0.644294798374176},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6103670597076416},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.588169515132904},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5743395090103149},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5491462349891663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45384401082992554},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4494646191596985},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.44730114936828613},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4161073863506317},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41590604186058044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37410426139831543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33792197704315186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1835658848285675},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.1390996277332306},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1217833161354065},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.10970130562782288},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.095120370388031},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09110349416732788}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7005754113197327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498143076896667},{"id":"https://openalex.org/C206194317","wikidata":"https://www.wikidata.org/wiki/Q1138624","display_name":"Convex hull","level":3,"score":0.644294798374176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6103670597076416},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.588169515132904},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5743395090103149},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5491462349891663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45384401082992554},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4494646191596985},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.44730114936828613},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4161073863506317},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41590604186058044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37410426139831543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33792197704315186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1835658848285675},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.1390996277332306},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1217833161354065},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.10970130562782288},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.095120370388031},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09110349416732788},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c00242","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1021/acs.jcim.3c00242","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:37625081","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37625081","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/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/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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1591039139","https://openalex.org/W1596134677","https://openalex.org/W1965555277","https://openalex.org/W1975997599","https://openalex.org/W2025444507","https://openalex.org/W2031975877","https://openalex.org/W2047165001","https://openalex.org/W2079270977","https://openalex.org/W2080635178","https://openalex.org/W2247585390","https://openalex.org/W2337496963","https://openalex.org/W2620687153","https://openalex.org/W2883021798","https://openalex.org/W2923868908","https://openalex.org/W2937681869","https://openalex.org/W2955229766","https://openalex.org/W2967510802","https://openalex.org/W2975845070","https://openalex.org/W2985604485","https://openalex.org/W3003769243","https://openalex.org/W3010488723","https://openalex.org/W3013487850","https://openalex.org/W3022530152","https://openalex.org/W3100221827","https://openalex.org/W3105379789","https://openalex.org/W3132234269","https://openalex.org/W3133931590","https://openalex.org/W3189924482","https://openalex.org/W3204699439","https://openalex.org/W4213455561","https://openalex.org/W4220751823","https://openalex.org/W4319074048"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W2580722822","https://openalex.org/W2772305933","https://openalex.org/W1550998911","https://openalex.org/W2050904480"],"abstract_inverted_index":{"A":[0],"key":[1],"aspect":[2],"of":[3,14,16,45,50,62,83,89,95,111,116],"producing":[4],"accurate":[5],"and":[6,39,59,73,97,107],"reliable":[7],"machine":[8],"learning":[9],"models":[10],"for":[11],"the":[12,46,81,86,109],"prediction":[13,63],"properties":[15],"quantum":[17],"chemistry":[18],"(QC)":[19],"data":[20,24,88,121,130],"is":[21],"identifying":[22],"possible":[23],"characteristics":[25,115],"that":[26,37,102],"may":[27,53],"negatively":[28],"influence":[29,82],"model":[30,57,91,105],"training.":[31],"In":[32,65],"previous":[33],"work,":[34],"we":[35,68],"identified":[36],"molecules":[38,96],"materials":[40],"with":[41],"a":[42,60,75,90],"low":[43],"volume":[44],"convex":[47],"hull":[48],"(VCH)":[49],"atomic":[51],"positions":[52],"be":[54],"harmful":[55],"in":[56],"training":[58,87,106,125],"source":[61],"outliers.":[64],"this":[66,70],"paper,":[67],"extend":[69],"analysis":[71],"further":[72],"develop":[74],"biased":[76],"sampling":[77],"study":[78,100],"to":[79],"evaluate":[80],"VCH":[84,103],"on":[85],"using":[92,112],"different":[93],"structures":[94,117],"materials.":[98],"Our":[99],"confirms":[101],"influences":[104],"shows":[108],"importance":[110],"homogeneous":[113],"geometric":[114],"when":[118],"building":[119],"new":[120],"sets":[122,126],"or":[123],"selecting":[124],"from":[127],"larger":[128],"QC":[129],"sets.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}