{"id":"https://openalex.org/W4406194289","doi":"https://doi.org/10.1021/acs.jcim.4c01281","title":"CovCysPredictor: Predicting Selective Covalently Modifiable Cysteines Using Protein Structure and Interpretable Machine Learning","display_name":"CovCysPredictor: Predicting Selective Covalently Modifiable Cysteines Using Protein Structure and Interpretable Machine Learning","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406194289","doi":"https://doi.org/10.1021/acs.jcim.4c01281","pmid":"https://pubmed.ncbi.nlm.nih.gov/39780548"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c01281","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01281","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/A5081731297","display_name":"Bryn Reimer","orcid":"https://orcid.org/0000-0001-6133-5785"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bryn Marie Reimer","raw_affiliation_strings":["Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States","Manning College of Information & Computer Sciences, University of Massachusetts Amherst, 140 Governors Drive, Amherst, Massachusetts 01003, United States"],"affiliations":[{"raw_affiliation_string":"Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States","institution_ids":[]},{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts Amherst, 140 Governors Drive, Amherst, Massachusetts 01003, United States","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065514882","display_name":"Ernest Awoonor\u2010Williams","orcid":"https://orcid.org/0000-0002-9127-8539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ernest Awoonor-Williams","raw_affiliation_strings":["Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053977995","display_name":"Andrei A. Golosov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei A. Golosov","raw_affiliation_strings":["Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069016592","display_name":"Viktor Horn\u0306\u00e1k","orcid":"https://orcid.org/0000-0002-2344-9586"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Viktor Hornak","raw_affiliation_strings":["Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Computer-Aided Drug Discovery, Global Discovery Chemistry, Novartis Biomedical Research, 181 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069016592","https://openalex.org/A5081731297"],"corresponding_institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":7.2792,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96841913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"65","issue":"2","first_page":"544","last_page":"553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11440","display_name":"Click Chemistry and Applications","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11440","display_name":"Click Chemistry and Applications","score":0.9995999932289124,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991000294685364,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9979000091552734,"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/in-silico","display_name":"In silico","score":0.6222251057624817},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.5873889327049255},{"id":"https://openalex.org/keywords/covalent-bond","display_name":"Covalent bond","score":0.5601915717124939},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5531969666481018},{"id":"https://openalex.org/keywords/cysteine","display_name":"Cysteine","score":0.5366904735565186},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.5107457637786865},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.4967246651649475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44000017642974854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4142664968967438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3877027928829193},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.2292516529560089},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18014439940452576}],"concepts":[{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.6222251057624817},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.5873889327049255},{"id":"https://openalex.org/C180577832","wikidata":"https://www.wikidata.org/wiki/Q127920","display_name":"Covalent bond","level":2,"score":0.5601915717124939},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5531969666481018},{"id":"https://openalex.org/C2779201268","wikidata":"https://www.wikidata.org/wiki/Q186474","display_name":"Cysteine","level":3,"score":0.5366904735565186},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.5107457637786865},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.4967246651649475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44000017642974854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4142664968967438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3877027928829193},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.2292516529560089},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18014439940452576},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003545","descriptor_name":"Cysteine","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D003545","descriptor_name":"Cysteine","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D003545","descriptor_name":"Cysteine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D003545","descriptor_name":"Cysteine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D003545","descriptor_name":"Cysteine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c01281","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01281","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:39780548","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39780548","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":[{"score":0.550000011920929,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333796","display_name":"Novartis Institutes for BioMedical Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2010993054","https://openalex.org/W2018339027","https://openalex.org/W2028964260","https://openalex.org/W2029079594","https://openalex.org/W2051627306","https://openalex.org/W2056728743","https://openalex.org/W2071648775","https://openalex.org/W2073841855","https://openalex.org/W2078047353","https://openalex.org/W2085094809","https://openalex.org/W2114850508","https://openalex.org/W2130479394","https://openalex.org/W2164088236","https://openalex.org/W2167854315","https://openalex.org/W2187318534","https://openalex.org/W2217901364","https://openalex.org/W2224077464","https://openalex.org/W2315466337","https://openalex.org/W2430132928","https://openalex.org/W2506658812","https://openalex.org/W2511955955","https://openalex.org/W2517550655","https://openalex.org/W2598528124","https://openalex.org/W2599955249","https://openalex.org/W2615598191","https://openalex.org/W2762419582","https://openalex.org/W2766801067","https://openalex.org/W2915847557","https://openalex.org/W2916884115","https://openalex.org/W2923145509","https://openalex.org/W2933867250","https://openalex.org/W2973195589","https://openalex.org/W3013682926","https://openalex.org/W3018223376","https://openalex.org/W3038238188","https://openalex.org/W3048193491","https://openalex.org/W3109863631","https://openalex.org/W3113053264","https://openalex.org/W3203691553","https://openalex.org/W3207110989","https://openalex.org/W4200153374","https://openalex.org/W4224258248","https://openalex.org/W4244040184","https://openalex.org/W4285284393","https://openalex.org/W4286615456","https://openalex.org/W4293084539","https://openalex.org/W4295706178","https://openalex.org/W4297519262","https://openalex.org/W4310566860","https://openalex.org/W4361266198","https://openalex.org/W4384207762","https://openalex.org/W4393973757"],"related_works":["https://openalex.org/W4205140848","https://openalex.org/W2068663075","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W4393677513","https://openalex.org/W4390832911","https://openalex.org/W829257147","https://openalex.org/W4385302116","https://openalex.org/W2150344375","https://openalex.org/W2077515371"],"abstract_inverted_index":{"Targeted":[0],"covalent":[1,16,48,169],"inhibition":[2,49],"is":[3,37,50],"a":[4,51,120,133],"powerful":[5],"therapeutic":[6],"modality":[7],"in":[8,15,19,39,57,110,151],"the":[9,65,147,190],"drug":[10,17,170],"discoverer's":[11],"toolbox.":[12],"Recent":[13],"advances":[14],"discovery,":[18,171],"particular,":[20],"targeting":[21],"cysteines,":[22],"have":[23,60,73],"led":[24],"to":[25,82,88,178,189],"significant":[26],"breakthroughs":[27],"for":[28,46,167],"traditionally":[29],"challenging":[30],"targets":[31],"such":[32],"as":[33,54,193],"mutant":[34],"KRAS,":[35],"which":[36],"implicated":[38],"diverse":[40],"human":[41],"cancers.":[42],"However,":[43],"identifying":[44],"cysteines":[45,84,166,173],"targeted":[47,168],"difficult":[52],"task,":[53],"experimental":[55],"and":[56,69,75,106],"silico":[58],"tools":[59],"shown":[61],"limited":[62],"accuracy.":[63],"Using":[64],"recently":[66],"released":[67],"CovPDB":[68],"CovBinderInPDB":[70],"databases,":[71],"we":[72,160],"trained":[74],"tested":[76,131],"interpretable":[77],"machine":[78],"learning":[79],"(ML)":[80],"models":[81],"identify":[83],"that":[85,159,174],"are":[86,175],"liable":[87],"be":[89,179],"covalently":[90],"modified":[91],"(i.e.,":[92],"\"ligandable\"":[93],"cysteines).":[94],"We":[95,185],"explored":[96],"myriad":[97],"physicochemical":[98],"features":[99],"(p<i>K</i><sub>a</sub>,":[100],"solvent":[101],"exposure,":[102],"residue":[103],"electrostatics,":[104],"etc.)":[105],"protein-ligand":[107],"pocket":[108],"descriptors":[109],"our":[111,139],"ML":[112],"models.":[113],"Our":[114],"final":[115],"logistic":[116],"regression":[117],"model":[118,140],"achieved":[119],"median":[121],"F<sub>1</sub>":[122],"score":[123],"of":[124,136],"0.73":[125],"on":[126,132],"held-out":[127],"test":[128],"sets.":[129],"When":[130],"small":[134],"sample":[135],"<i>holo</i>":[137],"proteins,":[138],"also":[141],"showed":[142],"reasonable":[143],"performance,":[144],"accurately":[145,162],"predicting":[146],"most":[148,152],"ligandable":[149,165],"cysteine":[150],"cases.":[153],"Taken":[154],"together,":[155],"these":[156],"results":[157],"indicate":[158],"can":[161],"predict":[163],"potential":[164],"privileging":[172],"more":[176],"likely":[177],"selective":[180],"rather":[181],"than":[182],"purely":[183],"reactive.":[184],"release":[186],"this":[187],"tool":[188],"scientific":[191],"community":[192],"CovCysPredictor.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}
