{"id":"https://openalex.org/W3048947632","doi":"https://doi.org/10.1021/acs.jcim.0c00591","title":"Systematic Investigation of the Data Set Dependency of Protein Stability Predictors","display_name":"Systematic Investigation of the Data Set Dependency of Protein Stability Predictors","publication_year":2020,"publication_date":"2020-08-10","ids":{"openalex":"https://openalex.org/W3048947632","doi":"https://doi.org/10.1021/acs.jcim.0c00591","mag":"3048947632","pmid":"https://pubmed.ncbi.nlm.nih.gov/32786698"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c00591","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00591","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":true,"oa_status":"green","oa_url":"https://orbit.dtu.dk/en/publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002860465","display_name":"Octav Caldararu","orcid":"https://orcid.org/0000-0002-5900-6568"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Octav Caldararu","raw_affiliation_strings":["DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040795565","display_name":"Rukmankesh Mehra","orcid":"https://orcid.org/0000-0001-6010-1514"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rukmankesh Mehra","raw_affiliation_strings":["DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001029093","display_name":"Tom L. Blundell","orcid":"https://orcid.org/0000-0002-2708-8992"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom L. Blundell","raw_affiliation_strings":["Department of Biochemistry, University of Cambridge, Cambridge CB2 1GA, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry, University of Cambridge, Cambridge CB2 1GA, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084810235","display_name":"Kasper P. Kepp","orcid":"https://orcid.org/0000-0002-6754-7348"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Kasper P. Kepp","raw_affiliation_strings":["DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-6754-7348","affiliations":[{"raw_affiliation_string":"DTU Chemistry, Technical University of Denmark, Building 206, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084810235"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":3.2603,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.93211794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"60","issue":"10","first_page":"4772","last_page":"4784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9749000072479248,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9684000015258789,"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/mutation","display_name":"Mutation","score":0.6153995990753174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.596701443195343},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5786895155906677},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.5177258849143982},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5093346834182739},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48891201615333557},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4570399224758148},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.4389820098876953},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43218135833740234},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4268413484096527},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3178514838218689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28809690475463867},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20287096500396729},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.19751834869384766}],"concepts":[{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.6153995990753174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.596701443195343},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5786895155906677},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.5177258849143982},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5093346834182739},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48891201615333557},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4570399224758148},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.4389820098876953},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43218135833740234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4268413484096527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3178514838218689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28809690475463867},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20287096500396729},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.19751834869384766},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D055550","descriptor_name":"Protein Stability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055550","descriptor_name":"Protein Stability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055550","descriptor_name":"Protein Stability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.0c00591","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00591","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:32786698","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32786698","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:pure.atira.dk:publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","pdf_url":"https://orbit.dtu.dk/en/publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Caldararu , O , Mehra , R , Blundell , T L &amp; Kepp , K P 2020 , ' Systematic Investigation of the Data Set Dependency of Protein Stability Predictors ' , Journal of Chemical Information and Modeling , vol. 60 , no. 10 , pp. 4772\u20134784 . https://doi.org/10.1021/acs.jcim.0c00591","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","pdf_url":"https://orbit.dtu.dk/en/publications/63d09ae8-4cce-404d-a06b-595e2aea7e96","source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Caldararu , O , Mehra , R , Blundell , T L &amp; Kepp , K P 2020 , ' Systematic Investigation of the Data Set Dependency of Protein Stability Predictors ' , Journal of Chemical Information and Modeling , vol. 60 , no. 10 , pp. 4772\u20134784 . https://doi.org/10.1021/acs.jcim.0c00591","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4329770299","display_name":null,"funder_award_id":"8022-00041B","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"}],"funders":[{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048947632.pdf","grobid_xml":"https://content.openalex.org/works/W3048947632.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W194434573","https://openalex.org/W579166296","https://openalex.org/W1963697504","https://openalex.org/W1966979475","https://openalex.org/W1974599488","https://openalex.org/W1990939702","https://openalex.org/W1996576490","https://openalex.org/W2002052142","https://openalex.org/W2002452896","https://openalex.org/W2004360551","https://openalex.org/W2005756796","https://openalex.org/W2008819364","https://openalex.org/W2017818880","https://openalex.org/W2023490488","https://openalex.org/W2025670719","https://openalex.org/W2031239680","https://openalex.org/W2031553026","https://openalex.org/W2041476324","https://openalex.org/W2054243594","https://openalex.org/W2056053449","https://openalex.org/W2085560162","https://openalex.org/W2092387745","https://openalex.org/W2093519658","https://openalex.org/W2093847279","https://openalex.org/W2103459989","https://openalex.org/W2104418738","https://openalex.org/W2114304598","https://openalex.org/W2115503115","https://openalex.org/W2125652418","https://openalex.org/W2130479394","https://openalex.org/W2134488721","https://openalex.org/W2135503340","https://openalex.org/W2136513422","https://openalex.org/W2140040671","https://openalex.org/W2145644903","https://openalex.org/W2146491495","https://openalex.org/W2146841526","https://openalex.org/W2149580316","https://openalex.org/W2151529283","https://openalex.org/W2153457180","https://openalex.org/W2159707853","https://openalex.org/W2167775670","https://openalex.org/W2168749685","https://openalex.org/W2171741848","https://openalex.org/W2172034373","https://openalex.org/W2180229411","https://openalex.org/W2207955902","https://openalex.org/W2326486590","https://openalex.org/W2346045962","https://openalex.org/W2519539312","https://openalex.org/W2560705618","https://openalex.org/W2615554674","https://openalex.org/W2794503008","https://openalex.org/W2794541436","https://openalex.org/W2799513065","https://openalex.org/W2893067056","https://openalex.org/W2902559445","https://openalex.org/W2916078022","https://openalex.org/W2964915524"],"related_works":["https://openalex.org/W4399895933","https://openalex.org/W2161221533","https://openalex.org/W4229699405","https://openalex.org/W1666484574","https://openalex.org/W2216382288","https://openalex.org/W2355491300","https://openalex.org/W4234629551","https://openalex.org/W2153421756","https://openalex.org/W2054489697","https://openalex.org/W2077818434"],"abstract_inverted_index":{"Prediction":[0],"of":[1,9,41,54,69,82,98,179,189,199,205,214],"protein":[2,13,18,22,57],"stability":[3],"changes":[4],"caused":[5],"by":[6],"mutation":[7,55,111,153],"is":[8,30,48],"major":[10,25,160],"importance":[11],"to":[12,27,58,106,129,148,211],"engineering":[14],"and":[15,21,67,93,117,202,217],"for":[16,43,89,193],"understanding":[17],"misfolding":[19],"diseases":[20],"evolution.":[23],"The":[24],"limitation":[26],"these":[28,124,200],"applications":[29],"the":[31,65,90,121,150,159,180,186,203,212,222],"fact":[32],"that":[33,101,168],"different":[34],"prediction":[35,170,219],"methods":[36,122,171,220],"vary":[37],"substantially":[38],"in":[39,162,221],"terms":[40],"performance":[42,47,66],"specific":[44],"proteins;":[45],"i.e.,":[46],"not":[49,176],"transferable":[50,218],"from":[51,177,185],"one":[52],"type":[53],"or":[56,195],"another.":[59],"In":[60,139],"this":[61],"study,":[62],"we":[63,141,156],"investigated":[64],"transferability":[68],"eight":[70],"widely":[71],"used":[72,192],"methods.":[73],"We":[74],"first":[75],"constructed":[76],"a":[77,96,143],"new":[78,206],"data":[79,92,133,191,208],"set":[80,134],"composed":[81],"2647":[83],"mutations":[84],"using":[85],"strict":[86],"selection":[87,187],"criteria":[88],"experimental":[91,190],"then":[94],"defined":[95],"variety":[97],"subdata":[99,125],"sets":[100,126],"are":[102],"unbiased":[103],"with":[104],"respect":[105],"various":[107],"aspects":[108],"such":[109],"as":[110,158],"type,":[112,116,154],"stabilization":[113],"extent,":[114],"structure":[115],"solvent":[118],"exposure.":[119],"Benchmarking":[120],"against":[123],"enabled":[127],"us":[128],"systematically":[130],"investigate":[131],"how":[132],"biases":[135,188,201],"affect":[136],"predictor":[137],"performance.":[138],"particular,":[140],"use":[142],"reduced":[144],"amino":[145],"acid":[146],"alphabet":[147],"quantify":[149],"bias":[151,161],"toward":[152],"which":[155],"identify":[157],"current":[163],"approaches.":[164],"Our":[165,197],"results":[166],"show":[167],"all":[169],"exhibit":[172],"large":[173],"biases,":[174],"stemming":[175],"failures":[178],"models":[181],"applied":[182],"but":[183],"mostly":[184],"training":[194],"parametrization.":[196],"identification":[198],"construction":[204],"mutation-type-balanced":[207],"should":[209],"lead":[210],"development":[213],"more":[215],"balanced":[216],"future.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
