{"id":"https://openalex.org/W4410541764","doi":"https://doi.org/10.1021/acs.jcim.5c00516","title":"Machine Learning Pipeline for Molecular Property Prediction Using ChemXploreML","display_name":"Machine Learning Pipeline for Molecular Property Prediction Using ChemXploreML","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410541764","doi":"https://doi.org/10.1021/acs.jcim.5c00516","pmid":"https://pubmed.ncbi.nlm.nih.gov/40392187"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00516","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00516","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/A5079713775","display_name":"Aravindh N. Marimuthu","orcid":"https://orcid.org/0000-0001-5444-6401"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aravindh Nivas Marimuthu","raw_affiliation_strings":["Department of Chemistry","Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019616488","display_name":"Brett A. McGuire","orcid":"https://orcid.org/0000-0003-1254-4817"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I2609998029","display_name":"National Radio Astronomy Observatory","ror":"https://ror.org/04m24yn62","country_code":"US","type":"facility","lineage":["https://openalex.org/I2609998029","https://openalex.org/I867387847"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brett A. McGuire","raw_affiliation_strings":["Department of Chemistry","Massachusetts Institute of Technology","National Radio Astronomy Observatory"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"National Radio Astronomy Observatory","institution_ids":["https://openalex.org/I2609998029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019616488","https://openalex.org/A5079713775"],"corresponding_institution_ids":["https://openalex.org/I2609998029","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.6516,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84723177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"65","issue":"11","first_page":"5424","last_page":"5437"},"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":0.9983000159263611,"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/T12327","display_name":"Various Chemistry Research Topics","score":0.9420999884605408,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical 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/pipeline","display_name":"Pipeline (software)","score":0.7783560752868652},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6530162692070007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5024979114532471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4591168761253357},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4351925253868103},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09044966101646423},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08777621388435364}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7783560752868652},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6530162692070007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5024979114532471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4591168761253357},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4351925253868103},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09044966101646423},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08777621388435364},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":"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}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00516","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00516","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:40392187","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40392187","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":[],"funders":[{"id":"https://openalex.org/F4320316572","display_name":"Schmidt Family Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1523859212","https://openalex.org/W1614298861","https://openalex.org/W1669602624","https://openalex.org/W1678356000","https://openalex.org/W1972234779","https://openalex.org/W1975147762","https://openalex.org/W1975764853","https://openalex.org/W1988037271","https://openalex.org/W1997362383","https://openalex.org/W2039749139","https://openalex.org/W2045270356","https://openalex.org/W2079476300","https://openalex.org/W2092039835","https://openalex.org/W2119512897","https://openalex.org/W2131241448","https://openalex.org/W2131672132","https://openalex.org/W2170973067","https://openalex.org/W2189911347","https://openalex.org/W2295598076","https://openalex.org/W2472085920","https://openalex.org/W2513463569","https://openalex.org/W2527672088","https://openalex.org/W2556014018","https://openalex.org/W2620416363","https://openalex.org/W2740924709","https://openalex.org/W2777416523","https://openalex.org/W2806843144","https://openalex.org/W2914757825","https://openalex.org/W2944466104","https://openalex.org/W2962897394","https://openalex.org/W2964884706","https://openalex.org/W2966357564","https://openalex.org/W2967655665","https://openalex.org/W2968734407","https://openalex.org/W2995165731","https://openalex.org/W3009321976","https://openalex.org/W3045928028","https://openalex.org/W3087318293","https://openalex.org/W3093934881","https://openalex.org/W3094098325","https://openalex.org/W3101432423","https://openalex.org/W3187461934","https://openalex.org/W3194266919","https://openalex.org/W3198212015","https://openalex.org/W4286695273","https://openalex.org/W4287117648","https://openalex.org/W4293508416","https://openalex.org/W4366850565","https://openalex.org/W4376454522","https://openalex.org/W4386221938","https://openalex.org/W4388724267","https://openalex.org/W4389625920","https://openalex.org/W4405720113","https://openalex.org/W6600377926"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"We":[0],"present":[1],"ChemXploreML,":[2],"a":[3,95,161],"modular":[4,147],"desktop":[5],"application":[6,170],"designed":[7],"for":[8,111,120,164,199],"machine":[9,27,157,192],"learning-based":[10],"molecular":[11,22,51,75,179],"property":[12,166],"prediction.":[13],"The":[14,106,169],"framework's":[15,44],"flexible":[16,162],"architecture":[17],"allows":[18],"integration":[19,151],"of":[20,102,152,178],"any":[21],"embedding":[23,52,154],"technique":[24],"with":[25,60,114],"modern":[26],"learning":[28,158,193],"algorithms,":[29,159],"enabling":[30],"researchers":[31],"to":[32,118],"customize":[33],"their":[34],"prediction":[35,167],"pipelines":[36],"without":[37],"extensive":[38],"programming":[39],"expertise.":[40],"To":[41],"demonstrate":[42],"the":[43,99],"capabilities,":[45],"we":[46],"implement":[47],"and":[48,54,70,88,104,156,183],"evaluate":[49],"two":[50],"approaches\u2500Mol2Vec":[53],"VICGAE":[55,133],"(Variance-Invariance-Covariance":[56],"regularized":[57],"GRU":[58],"Auto-Encoder)\u2500combined":[59],"state-of-the-art":[61],"tree-based":[62],"ensemble":[63],"methods":[64],"(Gradient":[65],"Boosting":[66],"Regression,":[67],"XGBoost,":[68],"CatBoost,":[69],"LightGBM).":[71],"Using":[72],"five":[73],"fundamental":[74],"properties":[76],"as":[77],"test":[78],"cases\u2500melting":[79],"point,":[80,82],"boiling":[81],"vapor":[83],"pressure,":[84],"critical":[85,89],"temperature":[86],"(CT),":[87],"pressure\u2500we":[90],"validate":[91],"our":[92],"framework":[93],"on":[94],"data":[96,173],"set":[97],"from":[98],"CRC":[100],"Handbook":[101],"Chemistry":[103],"Physics.":[105],"models":[107],"achieve":[108],"excellent":[109],"performance":[110,139,184],"well-distributed":[112],"properties,":[113],"<i>R</i><sup>2</sup>":[115],"values":[116],"up":[117],"0.93":[119],"CT":[121],"predictions.":[122],"Notably,":[123],"while":[124,196],"Mol2Vec":[125],"embeddings":[126,134],"(300":[127],"dimensions)":[128,136],"delivered":[129],"slightly":[130],"higher":[131],"accuracy,":[132],"(32":[135],"exhibited":[137],"comparable":[138],"yet":[140],"offered":[141],"significantly":[142],"improved":[143],"computational":[144],"efficiency.":[145],"ChemXploreML's":[146],"design":[148],"facilitates":[149],"easy":[150],"new":[153],"techniques":[155,194],"providing":[160],"platform":[163],"customized":[165],"tasks.":[168],"automates":[171],"chemical":[172],"preprocessing":[174],"(including":[175],"UMAP-based":[176],"exploration":[177],"space),":[180],"model":[181],"optimization,":[182],"analysis":[185],"through":[186],"an":[187],"intuitive":[188],"interface,":[189],"making":[190],"sophisticated":[191],"accessible":[195],"maintaining":[197],"extensibility":[198],"advanced":[200],"cheminformatics":[201],"users.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}