{"id":"https://openalex.org/W7167740683","doi":"https://doi.org/10.1016/j.compchemeng.2026.109789","title":"Transfer learning-derived molecular descriptors enable reliable property prediction under extreme data scarcity","display_name":"Transfer learning-derived molecular descriptors enable reliable property prediction under extreme data scarcity","publication_year":2026,"publication_date":"2026-07-08","ids":{"openalex":"https://openalex.org/W7167740683","doi":"https://doi.org/10.1016/j.compchemeng.2026.109789"},"language":"en","primary_location":{"id":"doi:10.1016/j.compchemeng.2026.109789","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compchemeng.2026.109789","pdf_url":null,"source":{"id":"https://openalex.org/S150671403","display_name":"Computers & Chemical Engineering","issn_l":"0098-1354","issn":["0098-1354","1873-4375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers & Chemical Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.compchemeng.2026.109789","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102729147","display_name":"Yuya Murakami","orcid":"https://orcid.org/0000-0002-7866-1234"},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuya Murakami","raw_affiliation_strings":["Department of Applied Chemistry and Biochemical Engineering, Faculty of Engineering, Shizuoka University, 3-5-1 Johoku, Chuo-ku, Hamamatsu-shi, 432-8561, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Chemistry and Biochemical Engineering, Faculty of Engineering, Shizuoka University, 3-5-1 Johoku, Chuo-ku, Hamamatsu-shi, 432-8561, Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102729147"],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":{"value":4070,"currency":"USD","value_usd":4070},"apc_paid":{"value":4070,"currency":"USD","value_usd":4070},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81980824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"214","issue":null,"first_page":"109789","last_page":"109789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8342000246047974,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8342000246047974,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.1446000039577484,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6776000261306763},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.656499981880188},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6359000205993652},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6029999852180481},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.5878000259399414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5235000252723694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5037000179290771},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.4178999960422516}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6776000261306763},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6359000205993652},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.5878000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248000025749207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5235000252723694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5037000179290771},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45410001277923584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35030001401901245},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.compchemeng.2026.109789","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compchemeng.2026.109789","pdf_url":null,"source":{"id":"https://openalex.org/S150671403","display_name":"Computers & Chemical Engineering","issn_l":"0098-1354","issn":["0098-1354","1873-4375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers & Chemical Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.compchemeng.2026.109789","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.compchemeng.2026.109789","pdf_url":null,"source":{"id":"https://openalex.org/S150671403","display_name":"Computers & Chemical Engineering","issn_l":"0098-1354","issn":["0098-1354","1873-4375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers & Chemical Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316548","display_name":"Tonen General Sekiyu Research/Development Encouragement and Scholarship Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1798528872","https://openalex.org/W1976883040","https://openalex.org/W1988037271","https://openalex.org/W1992985800","https://openalex.org/W2008620264","https://openalex.org/W2016979469","https://openalex.org/W2021748110","https://openalex.org/W2033495141","https://openalex.org/W2044834685","https://openalex.org/W2056139823","https://openalex.org/W2066273100","https://openalex.org/W2066636486","https://openalex.org/W2071128523","https://openalex.org/W2073773252","https://openalex.org/W2080635178","https://openalex.org/W2084421176","https://openalex.org/W2116341502","https://openalex.org/W2134329894","https://openalex.org/W2136806041","https://openalex.org/W2145488108","https://openalex.org/W2200017991","https://openalex.org/W2230728100","https://openalex.org/W2541404351","https://openalex.org/W2582187633","https://openalex.org/W2619383789","https://openalex.org/W2753962198","https://openalex.org/W2766856748","https://openalex.org/W2773133389","https://openalex.org/W2777416523","https://openalex.org/W2884430236","https://openalex.org/W2887280559","https://openalex.org/W2907492528","https://openalex.org/W2949095042","https://openalex.org/W2950022236","https://openalex.org/W2962876364","https://openalex.org/W2966357564","https://openalex.org/W2968923792","https://openalex.org/W2999615587","https://openalex.org/W3042722891","https://openalex.org/W3129238601","https://openalex.org/W3130274530","https://openalex.org/W3152893301","https://openalex.org/W3163993681","https://openalex.org/W4313485929","https://openalex.org/W4361247736","https://openalex.org/W4384522218","https://openalex.org/W4390221451","https://openalex.org/W4398250535","https://openalex.org/W4406293627","https://openalex.org/W4412176878","https://openalex.org/W7133230605","https://openalex.org/W7133256332","https://openalex.org/W7161483260"],"related_works":[],"abstract_inverted_index":{"Reliable":[0],"prediction":[1,193,208],"of":[2,31,72,89,137,192],"experimental":[3,52,127],"physicochemical":[4,53,206],"properties":[5,54],"remains":[6],"difficult":[7],"when":[8,125],"only":[9,76],"a":[10,21,32,163,189,200],"few":[11],"measured":[12],"data":[13,40,113,128],"points":[14],"are":[15,129],"available.":[16],"Here,":[17],"we":[18],"developed":[19],"FP200,":[20],"fixed":[22,141],"200-dimensional":[23],"molecular":[24,65],"descriptor":[25,60,175,203],"extracted":[26],"from":[27],"the":[28,82,90,94,103,111,135,210],"graph-level":[29],"representation":[30],"message-passing":[33],"neural":[34],"network":[35],"pretrained":[36,202],"on":[37],"QM9":[38,138],"quantum-chemical":[39],"using":[41],"DFT-optimized":[42],"coordinates":[43],"and":[44,55,69,140,154,178,215],"atomic":[45],"species.":[46],"FP200":[47,80,106,160,198],"was":[48,99],"evaluated":[49,211],"for":[50,87,93,144,204],"ten":[51,91],"compared":[56],"with":[57,169],"eleven":[58],"established":[59],"sets,":[61],"including":[62],"group-contribution-based":[63],"descriptors,":[64,68],"fingerprints,":[66],"RDKit":[67],"direct":[70],"use":[71],"QM9-calculated":[73],"properties.":[74],"With":[75],"25":[77],"model-construction":[78,112],"samples,":[79],"achieved":[81],"lowest":[83],"mean":[84],"absolute":[85],"error":[86],"seven":[88],"properties;":[92],"remaining":[95],"three,":[96],"its":[97,216],"performance":[98],"statistically":[100],"comparable":[101],"to":[102],"best":[104],"descriptor.":[105],"also":[107],"remained":[108],"competitive":[109],"as":[110,162,188,199],"size":[114],"increased,":[115],"indicating":[116],"that":[117,159,183],"quantum-chemistry-informed":[118],"learned":[119],"descriptors":[120],"can":[121,186],"be":[122],"effective":[123],"even":[124],"downstream":[126],"severely":[130],"limited.":[131],"Ablation":[132],"analyses":[133,157,180],"confirmed":[134],"importance":[136],"pretraining":[139],"feature":[142],"extraction":[143],"obtaining":[145],"stable":[146],"small-data":[147,205],"performance.":[148],"Principal":[149],"component":[150],"analysis,":[151],"principal-component":[152],"compression,":[153],"Shapley-value-based":[155],"feature-attribution":[156],"suggested":[158],"acts":[161],"redundant":[164],"yet":[165],"broadly":[166],"utilized":[167],"representation,":[168],"predictive":[170],"information":[171],"distributed":[172],"across":[173],"correlated":[174],"components.":[176],"Generalization":[177],"applicability-domain":[179],"further":[181],"showed":[182],"descriptor-space":[184],"distance":[185],"serve":[187],"practical":[190],"indicator":[191],"reliability.":[194],"These":[195],"findings":[196],"support":[197],"feature-based":[201],"property":[207],"within":[209],"QM9-derived":[212],"chemical":[213],"space":[214],"applicability":[217],"domain.":[218]},"counts_by_year":[],"updated_date":"2026-07-11T05:44:25.926202","created_date":"2026-07-09T00:00:00"}