{"id":"https://openalex.org/W4385623011","doi":"https://doi.org/10.1021/acs.jcim.3c00165","title":"Comparative Performance of High-Throughput Methods for Protein p<i>K</i><sub>a</sub> Predictions","display_name":"Comparative Performance of High-Throughput Methods for Protein p<i>K</i><sub>a</sub> Predictions","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4385623011","doi":"https://doi.org/10.1021/acs.jcim.3c00165","pmid":"https://pubmed.ncbi.nlm.nih.gov/37549424"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00165","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00165","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.3c00165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018799139","display_name":"Wanlei Wei","orcid":"https://orcid.org/0000-0002-2643-1365"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wanlei Wei","raw_affiliation_strings":["Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada"],"affiliations":[{"raw_affiliation_string":"Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040014835","display_name":"Herv\u00e9 Hogues","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Hogues","raw_affiliation_strings":["Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada"],"affiliations":[{"raw_affiliation_string":"Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019972390","display_name":"Traian Sulea","orcid":"https://orcid.org/0000-0001-5301-8261"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Traian Sulea","raw_affiliation_strings":["Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada"],"affiliations":[{"raw_affiliation_string":"Human Health Therapeutics Research Centre, National Research Council Canada, 6100 Royalmount Avenue, Montreal, Quebec H4P 2R2, Canada","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019972390"],"corresponding_institution_ids":["https://openalex.org/I4210159778"],"apc_list":null,"apc_paid":null,"fwci":4.5027,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95575691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"63","issue":"16","first_page":"5169","last_page":"5181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9983999729156494,"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":0.9983999729156494,"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/T11124","display_name":"Protein purification and stability","score":0.9980000257492065,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9977999925613403,"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7266325354576111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6136926412582397},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5069656372070312},{"id":"https://openalex.org/keywords/in-silico","display_name":"In silico","score":0.46005791425704956},{"id":"https://openalex.org/keywords/high-throughput-screening","display_name":"High-throughput screening","score":0.4290688633918762},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37490400671958923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32549649477005005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27750223875045776},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2232545018196106},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19839036464691162},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15439918637275696},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.11120235919952393}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7266325354576111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136926412582397},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5069656372070312},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.46005791425704956},{"id":"https://openalex.org/C51323132","wikidata":"https://www.wikidata.org/wiki/Q626251","display_name":"High-throughput screening","level":2,"score":0.4290688633918762},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37490400671958923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32549649477005005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27750223875045776},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2232545018196106},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19839036464691162},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15439918637275696},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.11120235919952393},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006863","descriptor_name":"Hydrogen-Ion Concentration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006863","descriptor_name":"Hydrogen-Ion Concentration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006863","descriptor_name":"Hydrogen-Ion Concentration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jcim.3c00165","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00165","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37549424","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37549424","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:cisti-icist.nrc-cnrc.ca:cistinparc:021d9cd0-4c48-437c-9919-ff0623850f85","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=021d9cd0-4c48-437c-9919-ff0623850f85","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=021d9cd0-4c48-437c-9919-ff0623850f85","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10466379","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10466379","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10466379/pdf/ci3c00165.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c00165","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00165","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1516558348","https://openalex.org/W1581858536","https://openalex.org/W1921766784","https://openalex.org/W1994116487","https://openalex.org/W2014042350","https://openalex.org/W2016210086","https://openalex.org/W2021865808","https://openalex.org/W2031145684","https://openalex.org/W2041604060","https://openalex.org/W2045732940","https://openalex.org/W2047912129","https://openalex.org/W2049670194","https://openalex.org/W2053373968","https://openalex.org/W2055742232","https://openalex.org/W2057501036","https://openalex.org/W2070900975","https://openalex.org/W2076407822","https://openalex.org/W2086455899","https://openalex.org/W2091664813","https://openalex.org/W2106648157","https://openalex.org/W2114850508","https://openalex.org/W2117458899","https://openalex.org/W2120715487","https://openalex.org/W2131880125","https://openalex.org/W2138789896","https://openalex.org/W2163168043","https://openalex.org/W2168240189","https://openalex.org/W2190363753","https://openalex.org/W2199567922","https://openalex.org/W2330799739","https://openalex.org/W2597570904","https://openalex.org/W2890361239","https://openalex.org/W2903499437","https://openalex.org/W2916884115","https://openalex.org/W2922028313","https://openalex.org/W2964344211","https://openalex.org/W2966054181","https://openalex.org/W2982700906","https://openalex.org/W2990699742","https://openalex.org/W3019212177","https://openalex.org/W3045469528","https://openalex.org/W3047460304","https://openalex.org/W3104537585","https://openalex.org/W3121183302","https://openalex.org/W3124922934","https://openalex.org/W3125295328","https://openalex.org/W3157018517","https://openalex.org/W4200097115","https://openalex.org/W4205794662","https://openalex.org/W4211114880","https://openalex.org/W4213336207","https://openalex.org/W4214900406","https://openalex.org/W4220787039","https://openalex.org/W4220811910","https://openalex.org/W4234423475","https://openalex.org/W4285589483","https://openalex.org/W4308583764","https://openalex.org/W4309047379"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2158830512"],"abstract_inverted_index":{"The":[0],"medically":[1],"relevant":[2],"field":[3],"of":[4,18,35,62,90,151,169,178,201,211],"protein-based":[5],"therapeutics":[6],"has":[7],"triggered":[8],"a":[9,63,87,166,174,188],"demand":[10],"for":[11,190,213],"protein":[12,36,93],"engineering":[13,23],"in":[14,129],"different":[15],"pH":[16],"environments":[17],"biological":[19],"relevance.":[20],"<i>In":[21],"silico</i>":[22],"workflows":[24],"typically":[25],"employ":[26],"high-throughput":[27,49],"screening":[28],"campaigns":[29],"that":[30],"require":[31,199],"evaluating":[32],"large":[33],"sets":[34],"residues":[37],"and":[38,71,81,119,133,146,162,173,194],"point":[39],"mutations":[40],"by":[41,113,141],"fast":[42],"yet":[43],"accurate":[44],"computational":[45],"algorithms.":[46],"While":[47,102],"several":[48],"p<i>K</i><sub>a</sub>":[50,95,99,171,182,204],"prediction":[51,205],"methods":[52],"exist,":[53],"their":[54],"accuracies":[55],"are":[56],"unclear":[57],"due":[58],"to":[59,165,180],"the":[60,98,106,152,209],"lack":[61],"current":[64],"comprehensive":[65],"benchmarking.":[66],"Here,":[67],"seven":[68],"fast,":[69],"efficient,":[70],"accessible":[72],"approaches":[73],"including":[74],"PROPKA3,":[75,118],"DeepKa,":[76,116],"PKAI,":[77],"PKAI+,":[78,117],"DelPhiPKa,":[79],"MCCE2,":[80],"H++":[82,120],"were":[83],"systematically":[84],"tested":[85],"on":[86],"nonredundant":[88],"subset":[89],"408":[91],"measured":[92],"residue":[94,137],"shifts":[96],"from":[97],"database":[100],"(PKAD).":[101],"no":[103],"method":[104],"outperformed":[105],"null":[107],"hypotheses":[108],"with":[109],"confidence,":[110],"as":[111,139,208],"illustrated":[112],"statistical":[114],"bootstrapping,":[115],"had":[121],"utility.":[122],"More":[123],"specifically,":[124],"DeepKa":[125],"consistently":[126],"performed":[127],"well":[128],"tests":[130],"across":[131],"multiple":[132],"individual":[134],"amino":[135],"acid":[136],"types,":[138],"reflected":[140],"lower":[142],"errors,":[143],"higher":[144],"correlations,":[145],"improved":[147,159],"classifications.":[148],"Arithmetic":[149],"averaging":[150],"best":[153],"empirical":[154],"predictors":[155],"into":[156],"simple":[157],"consensuses":[158],"overall":[160],"transferability":[161],"accuracy":[163],"up":[164],"root-mean-square":[167],"error":[168],"0.76":[170],"units":[172],"correlation":[175],"coefficient":[176],"(<i>R</i><sup>2</sup>)":[177],"0.45":[179],"experimental":[181],"shifts.":[183],"This":[184],"analysis":[185],"should":[186],"provide":[187],"basis":[189],"further":[191],"methodological":[192],"developments":[193],"guide":[195],"future":[196],"applications,":[197],"which":[198],"embedding":[200],"computationally":[202],"inexpensive":[203],"methods,":[206],"such":[207],"optimization":[210],"antibodies":[212],"pH-dependent":[214],"antigen":[215],"binding.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}