{"id":"https://openalex.org/W2054860606","doi":"https://doi.org/10.1021/ci050056i","title":"Prediction of Properties from Simulations:\u2009 A Re-examination with Modern Statistical Methods","display_name":"Prediction of Properties from Simulations:\u2009 A Re-examination with Modern Statistical Methods","publication_year":2005,"publication_date":"2005-10-07","ids":{"openalex":"https://openalex.org/W2054860606","doi":"https://doi.org/10.1021/ci050056i","mag":"2054860606","pmid":"https://pubmed.ncbi.nlm.nih.gov/16309286"},"language":"en","primary_location":{"id":"doi:10.1021/ci050056i","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci050056i","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/A5091342619","display_name":"Ralph Mansson","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["AU","GB"],"is_corresponding":true,"raw_author_name":"R. A. Mansson","raw_affiliation_strings":["School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025830443","display_name":"Jeremy G. Frey","orcid":"https://orcid.org/0000-0003-0842-4302"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"J. G. Frey","raw_affiliation_strings":["School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067820273","display_name":"Jonathan W. Essex","orcid":"https://orcid.org/0000-0003-2639-2746"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"J. W. Essex","raw_affiliation_strings":["School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072168381","display_name":"A. H. Welsh","orcid":"https://orcid.org/0000-0002-3165-9559"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"A. H. Welsh","raw_affiliation_strings":["School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and School of Chemistry, University of Southampton, Highfield, Southampton SO17 1BJ, U.K., and Centre for Mathematics and its Applications, The Australian National University, Canberra ACT 0200, Australia","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091342619"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":1.7568,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83937174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"45","issue":"6","first_page":"1791","last_page":"1803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9975000023841858,"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":0.9975000023841858,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12852","display_name":"Chemical Thermodynamics and Molecular Structure","score":0.9577999711036682,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.5764614343643188},{"id":"https://openalex.org/keywords/generalized-linear-model","display_name":"Generalized linear model","score":0.540012001991272},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.4885138273239136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48519256711006165},{"id":"https://openalex.org/keywords/marginal-model","display_name":"Marginal model","score":0.4662225544452667},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4635355472564697},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4582144618034363},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.45622333884239197},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4549202620983124},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.43603450059890747},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4280340075492859},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41380006074905396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3819892406463623},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3235305845737457}],"concepts":[{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.5764614343643188},{"id":"https://openalex.org/C41587187","wikidata":"https://www.wikidata.org/wiki/Q1501882","display_name":"Generalized linear model","level":2,"score":0.540012001991272},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.4885138273239136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48519256711006165},{"id":"https://openalex.org/C197656967","wikidata":"https://www.wikidata.org/wiki/Q17058458","display_name":"Marginal model","level":3,"score":0.4662225544452667},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4635355472564697},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4582144618034363},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.45622333884239197},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4549202620983124},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.43603450059890747},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4280340075492859},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41380006074905396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3819892406463623},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3235305845737457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1021/ci050056i","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci050056i","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:16309286","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16309286","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},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/85319","is_oa":false,"landing_page_url":"https://openresearch-repository.anu.edu.au/bitstream/1885/85319/5/MigratedxPub13662_2005.pdf.jpg","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"Journal article"},{"id":"pmh:oai:eprints.soton.ac.uk:15866","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/15866/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2040049891","https://openalex.org/W2071180837","https://openalex.org/W2486008048","https://openalex.org/W2498631646","https://openalex.org/W3015387428","https://openalex.org/W4249303080","https://openalex.org/W4298872162"],"related_works":["https://openalex.org/W3081465059","https://openalex.org/W49891529","https://openalex.org/W1510072949","https://openalex.org/W4242077822","https://openalex.org/W1969243170","https://openalex.org/W3169986371","https://openalex.org/W4386783521","https://openalex.org/W4238542755","https://openalex.org/W2022710330","https://openalex.org/W3046956321"],"abstract_inverted_index":{"We":[0],"discuss":[1],"models":[2,42,147,196,208,227,242,279],"fit":[3,80,164],"to":[4,11,51,69,77,81,103,110,159,162,176,277],"data":[5,29,46,200],"collected":[6],"by":[7],"Duffy":[8,265],"and":[9,16,25,57,168,201,209,266,282],"Jorgensen":[10],"predict":[12],"solvation":[13],"free":[14],"energies":[15],"partition":[17],"equilibria":[18],"of":[19,54,74,91,114,133,156,165,185,217,231,249,257,264,275],"drugs,":[20],"organic":[21],"molecules,":[22],"aromatic":[23],"heterocycles,":[24],"other":[26],"molecules.":[27],"These":[28],"were":[30,243],"originally":[31],"examined":[32],"using":[33,127,152],"linear":[34,128,195],"regression,":[35],"but":[36],"here":[37],"more":[38,130],"recently":[39],"developed":[40],"statistical":[41],"are":[43,122,150,173,191],"applied.":[44],"The":[45],"set":[47],"is":[48,67,102,284],"complicated":[49,131],"due":[50],"the":[52,61,75,82,92,97,112,118,134,153,163,178,199,212,220,229,238,253,261,273],"presence":[53],"discrepant":[55,115],"observations":[56,76,93,116],"also":[58,174,270],"curvature":[59],"in":[60,85,237,252],"response.":[62],"In":[63,204,223,240],"some":[64],"cases":[65],"it":[66],"possible":[68],"discard":[70],"a":[71,166],"small":[72],"number":[73],"get":[78],"good":[79],"data,":[83],"but,":[84],"others,":[86],"discarding":[87],"an":[88,192,247],"increasing":[89],"proportion":[90],"does":[94],"not":[95],"improve":[96],"fit.":[98,239],"Our":[99],"general":[100,205],"preference":[101],"use":[104,274],"robust":[105,206,225],"parameter":[106],"estimation":[107],"which":[108],"downweights":[109],"reduce":[111],"influence":[113],"on":[117,194],"fitted":[119],"models.":[120,183],"Models":[121],"selected":[123],"for":[124,181,197],"four":[125,221],"responses":[126],"or":[129,142],"representations":[132],"explanatory":[135],"variables,":[136],"such":[137],"as":[138],"cubic":[139],"polynomials,":[140],"B-splines,":[141],"smoothers":[143],"via":[144],"generalized":[145],"additive":[146],"(GAMs).":[148],"Variables":[149],"chosen":[151],"traditional":[154],"approach":[155],"formal":[157],"tests":[158],"assess":[160,177],"contribution":[161],"model,":[167],"resampling":[169],"methods":[170],"including":[171],"bootstrap":[172],"considered":[175],"prediction":[179,218,258],"error":[180],"given":[182],"Results":[184],"our":[186],"analysis":[187],"indicate":[188],"that":[189,234,245,272],"GAMs":[190,210],"improvement":[193,248],"describing":[198],"making":[202],"predictions.":[203],"regression":[207,226],"have":[211],"smallest":[213],"conditional":[214,254],"expected":[215,255],"loss":[216,256],"over":[219],"responses.":[222],"addition,":[224],"offer":[228],"advantage":[230],"identifying":[232],"molecules":[233],"perform":[235],"poorly":[236],"general,":[241],"identified":[244],"yielded":[246],"approximately":[250],"50%":[251],"compared":[259],"with":[260],"original":[262],"parametrization":[263],"Jorgensen.":[267],"It":[268],"was":[269,280],"found":[271],"cross-validation":[276],"compare":[278],"unreliable,":[281],"bootstrapping":[283],"preferred.":[285]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}