{"id":"https://openalex.org/W4413641247","doi":"https://doi.org/10.1021/acs.jcim.5c01042","title":"Enhancing Toxicity Prediction of Synthetic Chemicals via Novel SMILES Fragmentation and Interpretable Deep Learning","display_name":"Enhancing Toxicity Prediction of Synthetic Chemicals via Novel SMILES Fragmentation and Interpretable Deep Learning","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4413641247","doi":"https://doi.org/10.1021/acs.jcim.5c01042","pmid":"https://pubmed.ncbi.nlm.nih.gov/40856693"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c01042","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01042","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/A5107945034","display_name":"Y. Zhou","orcid":"https://orcid.org/0000-0002-9003-0726"},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yumian Zhou","raw_affiliation_strings":["Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103004435","display_name":"Yu He","orcid":"https://orcid.org/0000-0002-8960-7081"},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yu He","raw_affiliation_strings":["Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035009213","display_name":"Wenzheng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wenzheng Zhou","raw_affiliation_strings":["Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112008371","display_name":"Z. Q. Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhencheng Hua","raw_affiliation_strings":["Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068090174","display_name":"Yijing Wang","orcid":"https://orcid.org/0000-0002-7886-8366"},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yijing Wang","raw_affiliation_strings":["Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103192243","display_name":"Chao Chen","orcid":"https://orcid.org/0009-0000-4788-4796"},"institutions":[{"id":"https://openalex.org/I4210114506","display_name":"Ministry of Education","ror":"https://ror.org/01p262204","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210114506"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Department of Occupational Medicine and Environmental Health, School of Public Health, Key Laboratory of Public Health Safety and Emergency Prevention and Control Technology of Higher Education Institutions in Jiangsu Province, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Occupational Medicine and Environmental Health, School of Public Health, Key Laboratory of Public Health Safety and Emergency Prevention and Control Technology of Higher Education Institutions in Jiangsu Province, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]},{"raw_affiliation_string":"Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Jiangning District, Nanjing 21166, Jiangsu, China","institution_ids":["https://openalex.org/I4210114506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103192243"],"corresponding_institution_ids":["https://openalex.org/I4210114506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27097662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"17","first_page":"8969","last_page":"8979"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.982699990272522,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9699000120162964,"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/fragmentation","display_name":"Fragmentation (computing)","score":0.6513255834579468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43262794613838196},{"id":"https://openalex.org/keywords/smiles-rearrangement","display_name":"Smiles rearrangement","score":0.4295452833175659},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.41829657554626465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3963887393474579},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.33408811688423157},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17743471264839172},{"id":"https://openalex.org/keywords/stereochemistry","display_name":"Stereochemistry","score":0.0970911979675293}],"concepts":[{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.6513255834579468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43262794613838196},{"id":"https://openalex.org/C2779587451","wikidata":"https://www.wikidata.org/wiki/Q898710","display_name":"Smiles rearrangement","level":2,"score":0.4295452833175659},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.41829657554626465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3963887393474579},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33408811688423157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17743471264839172},{"id":"https://openalex.org/C71240020","wikidata":"https://www.wikidata.org/wiki/Q186011","display_name":"Stereochemistry","level":1,"score":0.0970911979675293},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"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":"D009152","descriptor_name":"Mutagenicity Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009152","descriptor_name":"Mutagenicity Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c01042","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01042","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:40856693","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40856693","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":[{"id":"https://metadata.un.org/sdg/2","score":0.41999998688697815,"display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G332922212","display_name":null,"funder_award_id":"82103873","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1983401069","https://openalex.org/W1984385866","https://openalex.org/W1988037271","https://openalex.org/W2035538685","https://openalex.org/W2049178128","https://openalex.org/W2095104272","https://openalex.org/W2140889813","https://openalex.org/W2334266062","https://openalex.org/W2763892102","https://openalex.org/W2940132190","https://openalex.org/W2947423323","https://openalex.org/W2969394227","https://openalex.org/W2972677623","https://openalex.org/W3023042104","https://openalex.org/W3093934881","https://openalex.org/W3103092523","https://openalex.org/W3119059058","https://openalex.org/W3128797821","https://openalex.org/W3138324257","https://openalex.org/W3138781613","https://openalex.org/W3158507782","https://openalex.org/W3209097202","https://openalex.org/W4206730269","https://openalex.org/W4283574835","https://openalex.org/W4292546430","https://openalex.org/W4311326710","https://openalex.org/W4312018564","https://openalex.org/W4323565291","https://openalex.org/W4362581606","https://openalex.org/W4365457471","https://openalex.org/W4387740953","https://openalex.org/W4388517978","https://openalex.org/W4389479893","https://openalex.org/W4391294276","https://openalex.org/W4392752318","https://openalex.org/W4393382207","https://openalex.org/W4399121593","https://openalex.org/W4401798130","https://openalex.org/W4404965619","https://openalex.org/W4405072102","https://openalex.org/W4408020190"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"Toxicity":[0],"prediction":[1],"and":[2,18,62,72,153,166,178,188],"identification":[3,190],"of":[4,117,191],"structural":[5],"alerts":[6],"(SAs)":[7],"for":[8,13,58,137,186],"synthetic":[9,139,192],"chemicals":[10],"are":[11,170],"critical":[12,171],"assessing":[14],"risks":[15],"to":[16,76,173],"environmental":[17],"human":[19],"health.":[20],"Traditional":[21],"methods,":[22,68],"which":[23],"rely":[24],"heavily":[25],"on":[26,94,130],"molecular":[27],"descriptors,":[28],"often":[29],"suffer":[30],"from":[31,82],"poor":[32],"interpretability.":[33],"Here,":[34],"we":[35],"introduce":[36],"a":[37,46],"novel":[38],"framework":[39],"that":[40,159],"integrates":[41],"SMILES":[42],"fragmentation":[43,67,89],"strategies":[44],"with":[45],"1D":[47],"convolutional":[48],"neural":[49],"network":[50],"deep":[51],"learning":[52],"model":[53],"(denoted":[54,79],"as":[55,80],"the":[56,95,118],"SFDL)":[57],"predicting":[59],"chemical":[60],"toxicity":[61,120,133,187],"associated":[63],"SAs.":[64],"Four":[65],"distinct":[66],"single-atom,":[69],"single-symbol,":[70],"atom-centered,":[71],"symbol-centered,":[73],"were":[74,135,144],"evaluated":[75],"generate":[77],"tokenizers":[78],"GenTok)":[81],"581537":[83],"high-interest":[84],"PubChem":[85],"compounds.":[86],"The":[87],"symbol-centered":[88],"approach":[90],"demonstrated":[91,110],"superior":[92],"performance":[93,113],"ISSSTY":[96],"AMES":[97],"mutagenicity":[98],"data":[99],"set":[100],"(AUC":[101,123],"=":[102,105,124,127],"0.87,":[103],"PRAUC":[104,126],"0.90).":[106],"This":[107,180],"SFDL-GenTok":[108],"strategy":[109],"robust":[111],"predictive":[112],"across":[114],"6":[115],"out":[116],"10":[119],"end":[121],"points":[122],"0.81\u223c0.93,":[125],"0.70\u223c0.94).":[128],"Based":[129],"these":[131],"models,":[132],"predictions":[134],"conducted":[136],"28160":[138],"chemicals.":[140,193],"Potential":[141],"toxic":[142],"compounds":[143],"subsequently":[145],"categorized":[146],"into":[147],"three":[148],"groups:":[149],"endocrine":[150,174],"disruption,":[151,175],"mutagenicity,":[152],"mitochondrial":[154,176],"toxicity.":[155],"SAs":[156,189],"analysis":[157],"revealed":[158],"halogenated":[160],"fragments,":[161],"nitro":[162],"or":[163],"phenolic":[164],"groups,":[165],"reactive":[167],"electrophilic":[168],"motifs":[169],"contributors":[172],"toxicity,":[177],"mutagenicity.":[179],"study":[181],"provides":[182],"an":[183],"interpretable":[184],"tool":[185]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}