{"id":"https://openalex.org/W2794704841","doi":"https://doi.org/10.1063/1.5020441","title":"Constant size descriptors for accurate machine learning models of molecular properties","display_name":"Constant size descriptors for accurate machine learning models of molecular properties","publication_year":2018,"publication_date":"2018-03-27","ids":{"openalex":"https://openalex.org/W2794704841","doi":"https://doi.org/10.1063/1.5020441","mag":"2794704841","pmid":"https://pubmed.ncbi.nlm.nih.gov/29960361"},"language":"en","primary_location":{"id":"doi:10.1063/1.5020441","doi":"https://doi.org/10.1063/1.5020441","is_oa":false,"landing_page_url":"https://doi.org/10.1063/1.5020441","pdf_url":null,"source":{"id":"https://openalex.org/S77047749","display_name":"The Journal of Chemical Physics","issn_l":"0021-9606","issn":["0021-9606","1089-7690","1520-9032"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Chemical Physics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1701.06649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090833347","display_name":"Christopher R. Collins","orcid":"https://orcid.org/0009-0002-7901-0705","observed_orcids":["https://orcid.org/0009-0002-7901-0705"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R. Collins","raw_affiliation_strings":["Department of Chemistry, Carnegie Mellon University 1 , Pittsburgh, Pennsylvania 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Carnegie Mellon University 1 , Pittsburgh, Pennsylvania 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012830032","display_name":"Geoffrey J. Gordon","orcid":"https://orcid.org/0009-0007-9960-2114","observed_orcids":["https://orcid.org/0009-0007-9960-2114"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey J. Gordon","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University 2 , Pittsburgh, Pennsylvania 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University 2 , Pittsburgh, Pennsylvania 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088793872","display_name":"O. Anatole von Lilienfeld","orcid":"https://orcid.org/0000-0001-7419-0466","observed_orcids":["https://orcid.org/0000-0001-7419-0466"]},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"O. Anatole von Lilienfeld","raw_affiliation_strings":["Department of Chemistry, Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials (MARVEL), University of Basel 3 , 4056 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials (MARVEL), University of Basel 3 , 4056 Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084936713","display_name":"David Yaron","orcid":"https://orcid.org/0000-0001-8485-8685","observed_orcids":["https://orcid.org/0000-0001-8485-8685"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Yaron","raw_affiliation_strings":["Department of Chemistry, Carnegie Mellon University 1 , Pittsburgh, Pennsylvania 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Carnegie Mellon University 1 , Pittsburgh, Pennsylvania 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3500,"currency":"USD","value_usd":3500},"apc_paid":null,"fwci":7.0417,"has_fulltext":true,"cited_by_count":123,"citation_normalized_percentile":{"value":0.98311069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"148","issue":"24","first_page":"241718","last_page":"241718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.7437000274658203,"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":0.7437000274658203,"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":0.15809999406337738,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0869000032544136,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/molecular-descriptors","display_name":"molecular descriptors","score":0.8930000066757202},{"id":"https://openalex.org/keywords/coulomb-matrix","display_name":"Coulomb matrix","score":0.9909999966621399},{"id":"https://openalex.org/keywords/3d-molecular-geometry","display_name":"3D molecular geometry","score":0.8370000123977661},{"id":"https://openalex.org/keywords/atomization-energies","display_name":"atomization energies","score":0.7149999737739563},{"id":"https://openalex.org/keywords/thermodynamic-properties","display_name":"thermodynamic properties","score":0.7160000205039978},{"id":"https://openalex.org/keywords/electronic-properties","display_name":"electronic properties","score":0.9860000014305115},{"id":"https://openalex.org/keywords/small-organic-molecules","display_name":"small organic molecules","score":0.6650000214576721},{"id":"https://openalex.org/keywords/kernel-ridge-regression","display_name":"kernel ridge regression","score":0.6890000104904175},{"id":"https://openalex.org/keywords/smiles","display_name":"SMILES","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.749488353729248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43750640749931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4200742244720459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37873148918151855},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.33448752760887146},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16387516260147095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1063/1.5020441","doi":"https://doi.org/10.1063/1.5020441","is_oa":false,"landing_page_url":"https://doi.org/10.1063/1.5020441","pdf_url":null,"source":{"id":"https://openalex.org/S77047749","display_name":"The Journal of Chemical Physics","issn_l":"0021-9606","issn":["0021-9606","1089-7690","1520-9032"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Chemical Physics","raw_type":"journal-article"},{"id":"pmid:29960361","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29960361","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,"listed_in":[],"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":"The Journal of chemical physics","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:1701.06649","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.06649","pdf_url":"https://arxiv.org/pdf/1701.06649","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2582662689","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1701.06649.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:edoc.unibas.ch:68689","doi":null,"is_oa":false,"landing_page_url":"https://edoc.unibas.ch/68689/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401836","display_name":"edoc (University of Basel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1850255","host_organization_name":"University of Basel","host_organization_lineage":["https://openalex.org/I1850255"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1701.06649","doi":"https://doi.org/10.48550/arxiv.1701.06649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1701.06649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1701.06649","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.06649","pdf_url":"https://arxiv.org/pdf/1701.06649","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1966729305","display_name":null,"funder_award_id":"1027985","funder_id":"https://openalex.org/F4320337393","funder_display_name":"Division of Chemistry"},{"id":"https://openalex.org/G5871174318","display_name":"CDI-Type I: Using Machine Learning to Develop New Approaches to Semiempirical Quantum Chemistry","funder_award_id":"1027985","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G940776785","display_name":null,"funder_award_id":"CHE-1027985","funder_id":"https://openalex.org/F4320337393","funder_display_name":"Division of Chemistry"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794704841.pdf","grobid_xml":"https://content.openalex.org/works/W2794704841.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1499888549","https://openalex.org/W1501145371","https://openalex.org/W1513260206","https://openalex.org/W1531674615","https://openalex.org/W1780364926","https://openalex.org/W1812560530","https://openalex.org/W1843396089","https://openalex.org/W1865667476","https://openalex.org/W1964189755","https://openalex.org/W1971044734","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1998260904","https://openalex.org/W2003209620","https://openalex.org/W2011092162","https://openalex.org/W2014550002","https://openalex.org/W2025444507","https://openalex.org/W2029413789","https://openalex.org/W2033206800","https://openalex.org/W2037464828","https://openalex.org/W2044834685","https://openalex.org/W2044990793","https://openalex.org/W2045063489","https://openalex.org/W2049529694","https://openalex.org/W2052512084","https://openalex.org/W2053080554","https://openalex.org/W2058370262","https://openalex.org/W2058889787","https://openalex.org/W2079935930","https://openalex.org/W2080635178","https://openalex.org/W2089843324","https://openalex.org/W2101234009","https://openalex.org/W2102965080","https://openalex.org/W2104489082","https://openalex.org/W2105616783","https://openalex.org/W2107416467","https://openalex.org/W2114416296","https://openalex.org/W2114704115","https://openalex.org/W2118578397","https://openalex.org/W2121076213","https://openalex.org/W2134207659","https://openalex.org/W2153693853","https://openalex.org/W2158081577","https://openalex.org/W2164524421","https://openalex.org/W2165371996","https://openalex.org/W2173027866","https://openalex.org/W2200990053","https://openalex.org/W2290847742","https://openalex.org/W2313966941","https://openalex.org/W2337496963","https://openalex.org/W2406709014","https://openalex.org/W2460256350","https://openalex.org/W2514794892","https://openalex.org/W2529996553","https://openalex.org/W2541404351","https://openalex.org/W2551487748","https://openalex.org/W2620906374","https://openalex.org/W2749580687","https://openalex.org/W2753962198","https://openalex.org/W2962872055","https://openalex.org/W3085090411"],"related_works":["https://openalex.org/W2582662689","https://openalex.org/W3121097143","https://openalex.org/W2753962198","https://openalex.org/W3104850868","https://openalex.org/W1844083939","https://openalex.org/W4281484873","https://openalex.org/W2923129034","https://openalex.org/W7134984285","https://openalex.org/W7117964929","https://openalex.org/W2917391695"],"abstract_inverted_index":{"Two":[0],"different":[1],"classes":[2],"of":[3,11,26,37,43,50,61,85,95,121,132,153,175,211,215],"molecular":[4,122],"representations":[5,19,44],"for":[6],"use":[7],"in":[8,53,63,103,178,196],"machine":[9],"learning":[10],"thermodynamic":[12],"and":[13,28,93,106,143,231],"electronic":[14],"properties":[15],"are":[16,20,156,184,190],"studied.":[17],"The":[18,78],"evaluated":[21],"by":[22,158],"monitoring":[23],"the":[24,48,54,59,64,82,86,90,99,104,130,173,179,197,201,220],"performance":[25],"linear":[27],"kernel":[29],"ridge":[30],"regression":[31],"models":[32,135],"on":[33,140,147],"well-studied":[34],"data":[35,199],"sets":[36,155],"small":[38],"organic":[39],"molecules.":[40,149],"One":[41],"class":[42,80],"studied":[45],"here":[46,128],"counts":[47,183],"occurrence":[49],"bonding":[51],"patterns":[52],"molecule.":[55,87],"These":[56,88],"require":[57],"only":[58],"connectivity":[60],"atoms":[62,176],"molecule":[65],"as":[66],"may":[67,137],"be":[68,138],"obtained":[69],"from":[70],"a":[71,75,114,164,207],"line":[72],"diagram":[73],"or":[74,166],"SMILES":[76],"string.":[77],"second":[79],"utilizes":[81],"three-dimensional":[83],"structure":[84],"include":[89],"Coulomb":[91],"matrix":[92],"Bag":[94],"Bonds,":[96,108],"which":[97,109],"list":[98],"inter-atomic":[100],"distances":[101],"present":[102],"molecule,":[105],"Encoded":[107,124,188,223],"encode":[110],"such":[111],"lists":[112],"into":[113],"feature":[115,154,204],"vector":[116],"whose":[117],"length":[118],"is":[119],"independent":[120],"size.":[123],"Bonds'":[125],"features":[126],"introduced":[127],"have":[129],"advantage":[131],"leading":[133],"to":[134,172],"that":[136],"trained":[139],"smaller":[141],"molecules":[142],"then":[144],"used":[145,229],"successfully":[146],"larger":[148],"A":[150],"wide":[151],"range":[152],"constructed":[157],"selecting,":[159],"at":[160],"each":[161],"rank,":[162],"either":[163],"graph":[165,237],"geometry-based":[167],"feature.":[168],"Here,":[169],"rank":[170,185,191],"refers":[171],"number":[174],"involved":[177],"feature,":[180],"e.g.,":[181],"atom":[182],"1,":[186],"while":[187],"Bonds":[189,224],"2.":[192],"For":[193],"atomization":[194],"energies":[195],"QM7":[198],"set,":[200],"best":[202],"graph-based":[203],"set":[205],"gives":[206],"mean":[208],"absolute":[209],"error":[210],"3.4":[212],"kcal/mol.":[213],"Inclusion":[214],"3D":[216],"geometry":[217],"substantially":[218],"enhances":[219],"performance,":[221],"with":[222,236],"giving":[225],"2.4":[226],"kcal/mol,":[227,233],"when":[228,234],"alone,":[230],"1.19":[232],"combined":[235],"features.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2018-04-06T00:00:00"}