{"id":"https://openalex.org/W2215622966","doi":"https://doi.org/10.1021/ci020386s","title":"Predicting p<i>K</i><sub>a</sub>by Molecular Tree Structured Fingerprints and PLS","display_name":"Predicting p<i>K</i><sub>a</sub>by Molecular Tree Structured Fingerprints and PLS","publication_year":2003,"publication_date":"2003-03-13","ids":{"openalex":"https://openalex.org/W2215622966","doi":"https://doi.org/10.1021/ci020386s","mag":"2215622966","pmid":"https://pubmed.ncbi.nlm.nih.gov/12767145"},"language":"en","primary_location":{"id":"doi:10.1021/ci020386s","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci020386s","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","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/A5103347049","display_name":"Li Xing","orcid":"https://orcid.org/0000-0002-4186-7909"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li Xing","raw_affiliation_strings":["Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014283781","display_name":"Robert C. Glen","orcid":"https://orcid.org/0000-0003-1759-2914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert C. Glen","raw_affiliation_strings":["Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048661632","display_name":"Robert D. Clark","orcid":"https://orcid.org/0000-0001-9509-8132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert D. Clark","raw_affiliation_strings":["Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tripos, Inc., 1699 S. Hanley Road, St. Louis, Missouri 63144","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5103347049"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8801,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.91501784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"43","issue":"3","first_page":"870","last_page":"879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T13013","display_name":"Free Radicals and Antioxidants","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.8093143701553345},{"id":"https://openalex.org/keywords/protonation","display_name":"Protonation","score":0.7421692609786987},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.659712016582489},{"id":"https://openalex.org/keywords/deprotonation","display_name":"Deprotonation","score":0.6164175271987915},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6068586707115173},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5443645119667053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47000107169151306},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.45473793148994446},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.44964680075645447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3917735815048218},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3697032332420349},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3240528106689453},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.31663745641708374},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.25774428248405457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23311471939086914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21078142523765564},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.0882611870765686},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.08571282029151917},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.06321927905082703}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8093143701553345},{"id":"https://openalex.org/C30095370","wikidata":"https://www.wikidata.org/wiki/Q899488","display_name":"Protonation","level":3,"score":0.7421692609786987},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.659712016582489},{"id":"https://openalex.org/C118629725","wikidata":"https://www.wikidata.org/wiki/Q2686738","display_name":"Deprotonation","level":3,"score":0.6164175271987915},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6068586707115173},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5443645119667053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47000107169151306},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45473793148994446},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.44964680075645447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3917735815048218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3697032332420349},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3240528106689453},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.31663745641708374},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.25774428248405457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23311471939086914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21078142523765564},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0882611870765686},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.08571282029151917},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.06321927905082703},{"id":"https://openalex.org/C145148216","wikidata":"https://www.wikidata.org/wiki/Q36496","display_name":"Ion","level":2,"score":0.0},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001682","descriptor_name":"Biological Availability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001682","descriptor_name":"Biological Availability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001682","descriptor_name":"Biological Availability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002264","descriptor_name":"Carboxylic Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D002264","descriptor_name":"Carboxylic Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D002264","descriptor_name":"Carboxylic Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005544","descriptor_name":"Forecasting","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006571","descriptor_name":"Heterocyclic Compounds","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006571","descriptor_name":"Heterocyclic Compounds","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006571","descriptor_name":"Heterocyclic Compounds","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D006863","descriptor_name":"Hydrogen-Ion Concentration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007093","descriptor_name":"Imidazoles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D007093","descriptor_name":"Imidazoles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D007093","descriptor_name":"Imidazoles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D007700","descriptor_name":"Kinetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007700","descriptor_name":"Kinetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007700","descriptor_name":"Kinetics","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":"D011522","descriptor_name":"Protons","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011522","descriptor_name":"Protons","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011522","descriptor_name":"Protons","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011725","descriptor_name":"Pyridines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011725","descriptor_name":"Pyridines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011725","descriptor_name":"Pyridines","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci020386s","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci020386s","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","raw_type":"journal-article"},{"id":"pmid:12767145","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12767145","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 computer sciences","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1546557734","https://openalex.org/W1964755033","https://openalex.org/W1985764534","https://openalex.org/W1996469316","https://openalex.org/W2019249078","https://openalex.org/W2020979927","https://openalex.org/W2023139079","https://openalex.org/W2032618103","https://openalex.org/W2034946707","https://openalex.org/W2040816544","https://openalex.org/W2041248383","https://openalex.org/W2063614010","https://openalex.org/W2075662564","https://openalex.org/W2099195105","https://openalex.org/W2101432637","https://openalex.org/W2214015925","https://openalex.org/W2478269152","https://openalex.org/W2952519971","https://openalex.org/W4244806755"],"related_works":["https://openalex.org/W326847207","https://openalex.org/W1982308651","https://openalex.org/W2065961539","https://openalex.org/W2070921557","https://openalex.org/W1991795963","https://openalex.org/W2001771354","https://openalex.org/W2072409349","https://openalex.org/W2150105749","https://openalex.org/W3124354710","https://openalex.org/W2604302222"],"abstract_inverted_index":{"This":[0],"is":[1],"the":[2,6,51,99,103],"second":[3],"phase":[4],"of":[5,44,54,91,102],"pK(a)":[7,92],"predictor":[8],"published":[9],"earlier":[10],"(J.":[11],"Chem.":[12],"Inf.":[13],"Comput.":[14],"Sci.":[15],"2002,":[16],"42,":[17],"796-805).":[18],"The":[19,62,86],"algorithm":[20],"has":[21,94],"been":[22,95],"extended":[23],"by":[24],"treating":[25],"specific":[26],"chemical":[27,55],"classes":[28],"separately":[29],"and":[30,47,60,73,77,88],"generating":[31],"tree-structured":[32],"molecular":[33],"descriptors":[34],"tailored":[35],"to":[36],"each":[37],"individual":[38],"class.":[39],"A":[40],"training":[41],"set":[42],"consisting":[43],"625":[45],"acids":[46,72],"412":[48],"bases":[49],"covers":[50],"major":[52],"areas":[53],"space":[56],"involved":[57],"in":[58],"protonation":[59],"deprotonation.":[61],"models":[63],"obtained":[64],"demonstrate":[65],"excellent":[66],"statistics":[67],"(SE":[68],"=":[69],"0.41":[70],"for":[71,75],"0.30":[74],"bases)":[76],"yielded":[78],"accurate":[79],"predictions":[80],"on":[81],"an":[82],"external":[83],"test":[84],"set.":[85],"quality":[87],"statistical":[89],"performance":[90],"prediction":[93],"improved":[96],"considerably":[97],"over":[98],"initial":[100],"implementation":[101],"method.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2016-06-24T00:00:00"}
