{"id":"https://openalex.org/W4391451996","doi":"https://doi.org/10.1021/acs.jcim.3c01923","title":"Leveraging DFT and Molecular Fragmentation for Chemically Accurate p<i>K</i><sub>a</sub> Prediction Using Machine Learning","display_name":"Leveraging DFT and Molecular Fragmentation for Chemically Accurate p<i>K</i><sub>a</sub> Prediction Using Machine Learning","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391451996","doi":"https://doi.org/10.1021/acs.jcim.3c01923","pmid":"https://pubmed.ncbi.nlm.nih.gov/38301279"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c01923","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01923","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/A5102770017","display_name":"Alec J. Sanchez","orcid":"https://orcid.org/0009-0008-4757-8383"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec J. Sanchez","raw_affiliation_strings":["Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024869937","display_name":"Sarah Maier","orcid":"https://orcid.org/0000-0002-3817-1476"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Maier","raw_affiliation_strings":["Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011183754","display_name":"Krishnan Raghavachari","orcid":"https://orcid.org/0000-0003-3275-1426"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krishnan Raghavachari","raw_affiliation_strings":["Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States"],"raw_orcid":"https://orcid.org/0000-0003-3275-1426","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Indiana University?, Bloomington, Indiana 47405, United States","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011183754"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":3.4891,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92996875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"64","issue":"3","first_page":"712","last_page":"723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9997000098228455,"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/T13013","display_name":"Free Radicals and Antioxidants","score":0.9965999722480774,"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/generalizability-theory","display_name":"Generalizability theory","score":0.688046932220459},{"id":"https://openalex.org/keywords/density-functional-theory","display_name":"Density functional theory","score":0.6532949805259705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.563815176486969},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5388363003730774},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5115655064582825},{"id":"https://openalex.org/keywords/quantum-chemical","display_name":"Quantum chemical","score":0.5062955617904663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49461767077445984},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4344549775123596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43218252062797546},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.3640919327735901},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.3555574417114258},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3525761365890503},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.31630057096481323},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2709270119667053},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.253503680229187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24313420057296753},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.13729912042617798},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08076730370521545}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.688046932220459},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.6532949805259705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.563815176486969},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5388363003730774},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5115655064582825},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.5062955617904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49461767077445984},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4344549775123596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43218252062797546},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.3640919327735901},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3555574417114258},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3525761365890503},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.31630057096481323},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2709270119667053},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.253503680229187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24313420057296753},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.13729912042617798},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08076730370521545},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011789","descriptor_name":"Quantum Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011789","descriptor_name":"Quantum Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011789","descriptor_name":"Quantum Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011789","descriptor_name":"Quantum Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013816","descriptor_name":"Thermodynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013816","descriptor_name":"Thermodynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013816","descriptor_name":"Thermodynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013816","descriptor_name":"Thermodynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c01923","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01923","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:38301279","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38301279","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8766192071","display_name":null,"funder_award_id":"CHE-2102583","funder_id":"https://openalex.org/F4320337393","funder_display_name":"Division of Chemistry"}],"funders":[{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W120961229","https://openalex.org/W369994751","https://openalex.org/W1488022185","https://openalex.org/W1530949129","https://openalex.org/W1988037271","https://openalex.org/W2000815209","https://openalex.org/W2001258368","https://openalex.org/W2011215428","https://openalex.org/W2016979469","https://openalex.org/W2017360381","https://openalex.org/W2021770275","https://openalex.org/W2022694548","https://openalex.org/W2027423337","https://openalex.org/W2047245810","https://openalex.org/W2063101225","https://openalex.org/W2064440950","https://openalex.org/W2077442778","https://openalex.org/W2086806820","https://openalex.org/W2092930273","https://openalex.org/W2148911913","https://openalex.org/W2200017991","https://openalex.org/W2320294097","https://openalex.org/W2322993209","https://openalex.org/W2331862130","https://openalex.org/W2464725281","https://openalex.org/W2465196018","https://openalex.org/W2532527353","https://openalex.org/W2547611602","https://openalex.org/W2618578095","https://openalex.org/W2787363292","https://openalex.org/W2884534695","https://openalex.org/W2888135782","https://openalex.org/W2888293530","https://openalex.org/W2937576411","https://openalex.org/W2980026765","https://openalex.org/W2981483652","https://openalex.org/W3005889887","https://openalex.org/W3010488723","https://openalex.org/W3021400221","https://openalex.org/W3042595256","https://openalex.org/W3043767409","https://openalex.org/W3080347207","https://openalex.org/W3100710928","https://openalex.org/W3132956480","https://openalex.org/W3178108585","https://openalex.org/W3181755904","https://openalex.org/W3189613542","https://openalex.org/W3193575414","https://openalex.org/W3199250719","https://openalex.org/W3206500648","https://openalex.org/W3210724097","https://openalex.org/W4230250554","https://openalex.org/W4241724526","https://openalex.org/W4285009161","https://openalex.org/W4297179124","https://openalex.org/W4308931182","https://openalex.org/W4362522957","https://openalex.org/W4362677501","https://openalex.org/W4381382068","https://openalex.org/W4385980099","https://openalex.org/W6724202202","https://openalex.org/W6816370964"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"s":[0],"of":[1,43,61,80,87,94,101],"complex":[2,72],"organic":[3],"molecules":[4],"using":[5],"inexpensive":[6],"density":[7],"functional":[8],"theory":[9],"(DFT)":[10],"calculations.":[11],"By":[12],"including":[13],"physics-based":[14,62],"features":[15,22,63],"from":[16,23],"low-level":[17],"DFT":[18],"calculations":[19],"and":[20,41,53,69],"structural":[21],"our":[24,44,89],"connectivity-based":[25],"hierarchy":[26],"(CBH)":[27],"fragmentation":[28],"protocol,":[29],"we":[30],"can":[31],"correct":[32],"the":[33,57,65,78,81,92,99],"systematic":[34],"error":[35],"associated":[36],"with":[37],"DFT.":[38],"The":[39],"generalizability":[40],"performance":[42],"model":[45],"are":[46],"evaluated":[47],"on":[48],"two":[49],"benchmark":[50],"sets":[51],"(SAMPL6":[52],"Novartis).":[54],"We":[55],"believe":[56],"carefully":[58],"curated":[59],"input":[60],"lessens":[64],"model's":[66],"data":[67],"dependence":[68],"need":[70],"for":[71,98,105],"deep":[73],"learning":[74],"architectures,":[75],"without":[76],"compromising":[77],"accuracy":[79],"test":[82],"sets.":[83],"As":[84],"a":[85],"point":[86],"novelty,":[88],"work":[90],"extends":[91],"applicability":[93],"CBH,":[95],"employing":[96],"it":[97],"generation":[100],"viable":[102],"molecular":[103],"descriptors":[104],"ML.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}