{"id":"https://openalex.org/W4408649919","doi":"https://doi.org/10.1021/acs.jcim.4c01644","title":"Unsupervised Machine Learning-Based Image Recognition of Raw Infrared Spectra: Toward Chemist-like Chemical Structural Classification and Beyond Numerical Data","display_name":"Unsupervised Machine Learning-Based Image Recognition of Raw Infrared Spectra: Toward Chemist-like Chemical Structural Classification and Beyond Numerical Data","publication_year":2025,"publication_date":"2025-03-20","ids":{"openalex":"https://openalex.org/W4408649919","doi":"https://doi.org/10.1021/acs.jcim.4c01644","pmid":"https://pubmed.ncbi.nlm.nih.gov/40108114"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c01644","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01644","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/A5056737807","display_name":"Kentaro Fuku","orcid":"https://orcid.org/0009-0003-6368-2803"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I4210166862","display_name":"Advanced Engineering (Czechia)","ror":"https://ror.org/05w67p097","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210166862"]}],"countries":["CZ","JP"],"is_corresponding":false,"raw_author_name":"Kentarou Fuku","raw_affiliation_strings":["Faculty of Advanced Engineering","Tokyo University of Science","Faculty of Advanced Engineering, Tokyo University of Science, Tokyo 125-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Advanced Engineering","institution_ids":["https://openalex.org/I4210166862"]},{"raw_affiliation_string":"Tokyo University of Science","institution_ids":["https://openalex.org/I161296585"]},{"raw_affiliation_string":"Faculty of Advanced Engineering, Tokyo University of Science, Tokyo 125-8585, Japan","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026093970","display_name":"Takefumi Yoshida","orcid":"https://orcid.org/0000-0003-3479-7890"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takefumi Yoshida","raw_affiliation_strings":["Cluster of Nanomaterials, Graduate School of Systems Engineering, Wakayama University,930 Sakaedani, Wakayama 640-8510, Japan"],"affiliations":[{"raw_affiliation_string":"Cluster of Nanomaterials, Graduate School of Systems Engineering, Wakayama University,930 Sakaedani, Wakayama 640-8510, Japan","institution_ids":["https://openalex.org/I75198481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026093970"],"corresponding_institution_ids":["https://openalex.org/I75198481"],"apc_list":null,"apc_paid":null,"fwci":2.84,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89922877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"65","issue":"7","first_page":"3176","last_page":"3185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9990000128746033,"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":0.9990000128746033,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical 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/T11948","display_name":"Machine Learning in Materials Science","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chemist","display_name":"Chemist","score":0.6246318817138672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5810182690620422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5676485300064087},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5493606328964233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4772219955921173},{"id":"https://openalex.org/keywords/infrared-spectroscopy","display_name":"Infrared spectroscopy","score":0.41926223039627075},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.34418874979019165},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3300090432167053},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.16516488790512085}],"concepts":[{"id":"https://openalex.org/C2779714115","wikidata":"https://www.wikidata.org/wiki/Q593644","display_name":"Chemist","level":2,"score":0.6246318817138672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5810182690620422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5676485300064087},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5493606328964233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4772219955921173},{"id":"https://openalex.org/C153642686","wikidata":"https://www.wikidata.org/wiki/Q70906","display_name":"Infrared spectroscopy","level":2,"score":0.41926223039627075},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.34418874979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3300090432167053},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.16516488790512085},{"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":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D013055","descriptor_name":"Spectrophotometry, Infrared","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013055","descriptor_name":"Spectrophotometry, Infrared","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c01644","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01644","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:40108114","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40108114","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/G1230690574","display_name":null,"funder_award_id":"JP20K15293","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G815832304","display_name":null,"funder_award_id":"JP23K13761","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F1224032724","display_name":"Yamada Science Foundation","ror":"https://ror.org/05nr5jj06"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W1989705029","https://openalex.org/W2016381774","https://openalex.org/W2118470029","https://openalex.org/W2150593711","https://openalex.org/W2213443318","https://openalex.org/W2295124130","https://openalex.org/W2299467264","https://openalex.org/W2319902168","https://openalex.org/W2327079070","https://openalex.org/W2523785361","https://openalex.org/W2529996553","https://openalex.org/W2614157797","https://openalex.org/W2769254256","https://openalex.org/W2772285008","https://openalex.org/W2948233954","https://openalex.org/W2977004589","https://openalex.org/W2977127463","https://openalex.org/W2996448308","https://openalex.org/W2997960618","https://openalex.org/W3010662401","https://openalex.org/W3012727703","https://openalex.org/W3023114766","https://openalex.org/W3045792597","https://openalex.org/W3092198360","https://openalex.org/W3120780657","https://openalex.org/W3129115975","https://openalex.org/W3137237498","https://openalex.org/W3161704673","https://openalex.org/W3176750058","https://openalex.org/W3209814067","https://openalex.org/W3213967242","https://openalex.org/W4242767732","https://openalex.org/W4311387115","https://openalex.org/W4319819110","https://openalex.org/W4360949780","https://openalex.org/W4386085260","https://openalex.org/W4386346430","https://openalex.org/W4396509571","https://openalex.org/W4400460710","https://openalex.org/W4401535000"],"related_works":["https://openalex.org/W2054471173","https://openalex.org/W1966719565","https://openalex.org/W2327339815","https://openalex.org/W2604396727","https://openalex.org/W2374187762","https://openalex.org/W4253256314","https://openalex.org/W2328286757","https://openalex.org/W608995688","https://openalex.org/W4392171204","https://openalex.org/W4235448076"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,97,102],"artificial":[3],"intelligence":[4],"have":[5],"significantly":[6],"improved":[7],"spectral":[8,27,48,88,222,262,268],"data":[9,198,205,224,269],"analysis.":[10],"In":[11],"this":[12,211],"study,":[13],"we":[14],"used":[15,136],"unsupervised":[16],"machine":[17,38,218],"learning":[18,39,219],"to":[19,87,130,137],"classify":[20],"chemical":[21,33,41,95,226],"compounds":[22,68],"based":[23],"on":[24,31],"infrared":[25],"(IR)":[26],"images,":[28],"without":[29],"relying":[30],"prior":[32],"knowledge.":[34],"The":[35,132,152],"potential":[36],"of":[37,66,92,178,206,216],"for":[40,54,225,252],"classification":[42,168,201,227],"was":[43,135],"demonstrated":[44,127],"by":[45],"extracting":[46],"IR":[47,221],"images":[49],"from":[50,149,183],"the":[51,83,103,106,125,139,157,167,174,179,187,196,207,214,238],"Spectral":[52],"Database":[53],"Organic":[55],"Compounds":[56],"and":[57,90,118,161,228,260],"converting":[58],"them":[59],"into":[60],"208,620-dimensional":[61],"vector":[62],"data.":[63],"Hierarchical":[64],"clustering":[65,120,180],"230":[67],"revealed":[69],"distinct":[70],"main":[71],"clusters":[72],"(<b>A</b>-<b>G</b>),":[73],"each":[74],"with":[75,99,220,244],"specific":[76],"subclusters":[77],"exhibiting":[78],"higher":[79],"intracluster":[80],"similarities.":[81],"Despite":[82],"challenges,":[84],"including":[85],"sensitivity":[86],"deviations":[89],"difficulty":[91],"distinguishing":[93],"delicate":[94],"structures":[96],"spectra":[98],"low":[100],"transparency":[101],"fingerprint":[104],"area,":[105],"proposed":[107],"image":[108,197,223],"recognition":[109],"approach":[110,248],"exhibits":[111],"good":[112],"potential.":[113],"Both":[114],"principal":[115],"component":[116],"analysis":[117],"k-means":[119],"produced":[121],"similar":[122],"results.":[123],"Furthermore,":[124],"method":[126],"high":[128],"robustness":[129],"noise.":[131],"Tanimoto":[133],"coefficient":[134],"evaluate":[138],"molecular":[140,162,184],"similarity,":[141],"providing":[142],"valuable":[143],"insights.":[144],"However,":[145],"some":[146],"results":[147,169,181],"deviated":[148],"chemists'":[150,245],"intuitions.":[151,246],"study":[153,212],"also":[154],"highlighted":[155],"that":[156,195,233],"scaling":[158],"composition":[159],"formulas":[160],"weights":[163],"did":[164],"not":[165,241],"affect":[166],"because":[170],"high-dimensional":[171],"features":[172],"dominated":[173],"process.":[175],"A":[176],"comparison":[177],"obtained":[182],"fingerprints,":[185],"using":[186,217],"adjusted":[188],"Rand":[189],"index":[190],"as":[191,255],"a":[192,230],"metric,":[193],"indicated":[194],"provided":[199],"better":[200],"performance":[202],"than":[203],"numerical":[204],"same":[208],"resolution.":[209],"Overall,":[210],"demonstrates":[213],"feasibility":[215],"offers":[229],"novel":[231],"perspective":[232],"complements":[234],"traditional":[235],"methods,":[236],"although":[237],"classifications":[239],"may":[240],"always":[242],"align":[243],"This":[247],"has":[249],"broader":[250],"implications":[251],"fields":[253],"such":[254],"drug":[256],"discovery,":[257],"materials":[258],"science,":[259],"automated":[261],"analysis,":[263],"where":[264],"handling":[265],"large,":[266],"raw":[267],"sets":[270],"is":[271],"essential.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}