{"id":"https://openalex.org/W4206220087","doi":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","title":"Protein pKa prediction with machine learning","display_name":"Protein pKa prediction with machine learning","publication_year":2021,"publication_date":"2021-07-29","ids":{"openalex":"https://openalex.org/W4206220087","doi":"https://doi.org/10.33774/chemrxiv-2021-7gk5l"},"language":"en","primary_location":{"id":"doi:10.33774/chemrxiv-2021-7gk5l","doi":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","is_oa":true,"landing_page_url":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/6102590d88044360cde45170/original/protein-p-ka-prediction-with-machine-learning.pdf","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/6102590d88044360cde45170/original/protein-p-ka-prediction-with-machine-learning.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076500831","display_name":"Zhitao Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhitao Cai","raw_affiliation_strings":["Jimei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jimei University","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055733769","display_name":"Fangfang Luo","orcid":"https://orcid.org/0000-0002-0241-048X","observed_orcids":["https://orcid.org/0000-0002-0241-048X"]},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Luo","raw_affiliation_strings":["Jimei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jimei University","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034520237","display_name":"Yongxian Wang","orcid":"https://orcid.org/0000-0002-6752-0436","observed_orcids":["https://orcid.org/0000-0002-6752-0436"]},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxian Wang","raw_affiliation_strings":["Jimei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jimei University","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Enling Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enling Li","raw_affiliation_strings":["Jimei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jimei University","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064599430","display_name":"Yandong Huang","orcid":"https://orcid.org/0000-0002-1452-6383","observed_orcids":["https://orcid.org/0000-0002-1452-6383","https://orcid.org/0000-0003-4025-6767"]},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yandong Huang","raw_affiliation_strings":["Jimei University"],"raw_orcid":"https://orcid.org/0000-0002-1452-6383","affiliations":[{"raw_affiliation_string":"Jimei University","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161346416"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8726000189781189,"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":0.8726000189781189,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.07050000131130219,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.046300001442432404,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/electrostatics","display_name":"electrostatics","score":0.6779999732971191},{"id":"https://openalex.org/keywords/finite-size-effects","display_name":"finite-size effects","score":0.671999990940094},{"id":"https://openalex.org/keywords/protein-ligand-binding-affinity-prediction","display_name":"protein-ligand binding affinity prediction","score":0.8019999861717224},{"id":"https://openalex.org/keywords/machine-learning-predictors","display_name":"machine learning predictors","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967913866043091},{"id":"https://openalex.org/C117626034","wikidata":"https://www.wikidata.org/wiki/Q26336","display_name":"Electrostatics","level":2,"score":0.5568175911903381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.531624972820282},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.5111733078956604},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5086227655410767},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5015325546264648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43098700046539307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4226161241531372},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41234296560287476},{"id":"https://openalex.org/C188082385","wikidata":"https://www.wikidata.org/wiki/Q73792","display_name":"Charge (physics)","level":2,"score":0.4116334617137909},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.37249696254730225},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2142818570137024},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.20277246832847595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1219680905342102},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"score":0.10658690333366394},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08924973011016846},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.33774/chemrxiv-2021-7gk5l","doi":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","is_oa":true,"landing_page_url":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/6102590d88044360cde45170/original/protein-p-ka-prediction-with-machine-learning.pdf","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.33774/chemrxiv-2021-7gk5l","doi":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","is_oa":true,"landing_page_url":"https://doi.org/10.33774/chemrxiv-2021-7gk5l","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/6102590d88044360cde45170/original/protein-p-ka-prediction-with-machine-learning.pdf","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4353214475","display_name":"\u6052\u5b9apH\u4e0b\u7535\u538b\u95e8\u63a7\u8d28\u5b50\u901a\u9053Hv1\u7684\u5206\u5b50\u673a\u5236\u7814\u7a76","funder_award_id":"11804114","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206220087.pdf","grobid_xml":"https://content.openalex.org/works/W4206220087.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W998400604","https://openalex.org/W1031578623","https://openalex.org/W2027408247","https://openalex.org/W2032187756","https://openalex.org/W2035687084","https://openalex.org/W2046102151","https://openalex.org/W2056728743","https://openalex.org/W2076790509","https://openalex.org/W2080735247","https://openalex.org/W2105103540","https://openalex.org/W2106140689","https://openalex.org/W2107317356","https://openalex.org/W2132262459","https://openalex.org/W2152130162","https://openalex.org/W2168240189","https://openalex.org/W2169678694","https://openalex.org/W2194775991","https://openalex.org/W2333852722","https://openalex.org/W2472763914","https://openalex.org/W2529068577","https://openalex.org/W2788212154","https://openalex.org/W2804822363","https://openalex.org/W2810398033","https://openalex.org/W2884858098","https://openalex.org/W2887029338","https://openalex.org/W2927778654","https://openalex.org/W2933867250","https://openalex.org/W2982700906","https://openalex.org/W2998499403","https://openalex.org/W3034390811","https://openalex.org/W3047460304","https://openalex.org/W3084762951","https://openalex.org/W3112388947","https://openalex.org/W3169629772","https://openalex.org/W3177828909","https://openalex.org/W4240985758","https://openalex.org/W4255838607","https://openalex.org/W4296060337"],"related_works":["https://openalex.org/W4372257622","https://openalex.org/W3201918806","https://openalex.org/W4205389190","https://openalex.org/W4293085679","https://openalex.org/W4413082423","https://openalex.org/W7214183057","https://openalex.org/W4393190078","https://openalex.org/W7160132642","https://openalex.org/W291206810","https://openalex.org/W4406962718"],"abstract_inverted_index":{"Protein":[0],"pKa":[1,26,115,137],"prediction":[2,97],"is":[3,30,101,147],"essential":[4],"for":[5],"the":[6,49,53,76,88,96,119,130,142,155],"investigation":[7],"of":[8,44,132],"pH-associated":[9],"relationship":[10],"between":[11],"protein":[12,25,114,136],"structure":[13],"and":[14,63,149],"function.":[15],"In":[16,117],"this":[17,124],"work,":[18],"we":[19],"introduce":[20],"a":[21],"deep":[22],"learning":[23,134],"based":[24,135],"predictor":[27],"DeepKa,":[28],"which":[29],"trained":[31],"with":[32,75],"12809":[33],"pKa's":[34],"derived":[35],"from":[36],"continuous":[37],"constant":[38],"pH":[39],"molecular":[40,55],"dynamics":[41,56],"(CpHMD)":[42],"simulations":[43],"279":[45],"soluble":[46],"proteins.":[47],"Here":[48],"CpHMD":[50,106],"implemented":[51],"in":[52,123,139],"Amber":[54],"package":[57],"has":[58],"been":[59],"employed":[60],"(Huang,":[61],"Harris,":[62],"Shen":[64],"J.":[65],"Chem.":[66],"Inf.":[67],"Model.":[68],"2018,":[69],"58,":[70],"1372-1383).":[71],"Notably,":[72],"to":[73,83,103,129,151],"deal":[74],"finite-size":[77],"effect,":[78],"grid":[79,144],"charges":[80],"are":[81],"proposed":[82],"represent":[84],"electrostatics,":[85],"but":[86],"rather":[87],"previously":[89],"used":[90],"atomic":[91],"charges.":[92],"We":[93],"show":[94],"that":[95,104],"accuracy":[98],"by":[99,105],"DeepKa":[100,110],"close":[102],"benchmarking":[107],"simulations,":[108],"validating":[109],"as":[111],"an":[112],"efficient":[113],"predictor.":[116],"addition,":[118],"training":[120],"dataset":[121],"created":[122],"study":[125],"can":[126],"be":[127],"applied":[128],"development":[131],"machine":[133],"predictors":[138],"future.":[140],"Finally,":[141],"new":[143],"charge":[145],"representation":[146],"general":[148],"applicable":[150],"other":[152],"topics,":[153],"like":[154],"protein-ligand":[156],"binding":[157],"affinity":[158],"prediction.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2022-01-25T00:00:00"}