{"id":"https://openalex.org/W7214085804","doi":"https://doi.org/10.26434/chemrxiv.15009333/v1","title":"Data-Efficient Machine Learning Potentials for Organic Reactions through Active-Learning-Guided Fine-Tuning","display_name":"Data-Efficient Machine Learning Potentials for Organic Reactions through Active-Learning-Guided Fine-Tuning","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214085804","doi":"https://doi.org/10.26434/chemrxiv.15009333/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009333/v1","doi":"https://doi.org/10.26434/chemrxiv.15009333/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009333/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009333/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009333/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111297340","display_name":"Kaipai Ren","orcid":"https://orcid.org/0009-0004-6559-4054","observed_orcids":["https://orcid.org/0009-0004-6559-4054"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaipai Ren","raw_affiliation_strings":["MOE Key Laboratory of Bio-Intelligent Manufacturing , School of Bioengineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":"https://orcid.org/0009-0004-6559-4054","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bio-Intelligent Manufacturing , School of Bioengineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056705076","display_name":"Yujing Zhao","orcid":"https://orcid.org/0009-0002-5172-3412","observed_orcids":["https://orcid.org/0009-0002-5172-3412"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Zhao","raw_affiliation_strings":["MOE Key Laboratory of Bio-Intelligent Manufacturing , School of Bioengineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bio-Intelligent Manufacturing , School of Bioengineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102810570","display_name":"Kun Tang","orcid":"https://orcid.org/0009-0001-5735-9343","observed_orcids":["https://orcid.org/0009-0001-5735-9343"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4391767660","display_name":"State Key Laboratory of Fine Chemicals","ror":"https://ror.org/03j33bp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Tang","raw_affiliation_strings":["State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152526594","display_name":"Juntao Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4391767660","display_name":"State Key Laboratory of Fine Chemicals","ror":"https://ror.org/03j33bp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juntao Wang","raw_affiliation_strings":["State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141021178","display_name":"Guangran Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4391767660","display_name":"State Key Laboratory of Fine Chemicals","ror":"https://ror.org/03j33bp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangran Zhang","raw_affiliation_strings":["State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078146295","display_name":"Qilei Liu","orcid":"https://orcid.org/0000-0002-3879-1827","observed_orcids":["https://orcid.org/0000-0002-3879-1827"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4391767660","display_name":"State Key Laboratory of Fine Chemicals","ror":"https://ror.org/03j33bp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilei Liu","raw_affiliation_strings":["State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fine Chemicals , Frontiers Science Center for Smart Materials Oriented Chemical Engineering , Department of Pharmaceutical Sciences , Institute of Chemical Process Systems Engineering , School of Chemical Engineering , Dalian University of Technology , Dalian 116024 , China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4391767660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9336000084877014,"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":0.9336000084877014,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.039000000804662704,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transition-state-optimization","display_name":"transition state optimization","score":0.7419999837875366},{"id":"https://openalex.org/keywords/reaction-energy-barrier","display_name":"reaction barriers","score":0.6230000257492065},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.7580000162124634},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9160000085830688},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.824999988079071},{"id":"https://openalex.org/keywords/organic-reactions","display_name":"organic reactions","score":0.6890000104904175},{"id":"https://openalex.org/keywords/potential-energy-surface","display_name":"potential energy surface","score":0.6269999742507935},{"id":"https://openalex.org/keywords/transferability","display_name":"transferability","score":0.6150000095367432},{"id":"https://openalex.org/keywords/ugi-reaction","display_name":"Ugi reaction","score":0.8009999990463257},{"id":"https://openalex.org/keywords/reaction-mechanism","display_name":"reaction mechanism","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.7215999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5692999958992004},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C177801218","wikidata":"https://www.wikidata.org/wiki/Q36534","display_name":"Chemical reaction","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.39160001277923584},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.387800008058548},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C2984497647","wikidata":"https://www.wikidata.org/wiki/Q174211","display_name":"Organic molecules","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C192937433","wikidata":"https://www.wikidata.org/wiki/Q2134627","display_name":"Reactive intermediate","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C65024703","wikidata":"https://www.wikidata.org/wiki/Q373406","display_name":"Reaction mechanism","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2985358483","wikidata":"https://www.wikidata.org/wiki/Q174211","display_name":"Organic chemicals","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009333/v1","doi":"https://doi.org/10.26434/chemrxiv.15009333/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009333/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009333/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009333/v1","doi":"https://doi.org/10.26434/chemrxiv.15009333/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009333/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009333/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214085804.pdf","grobid_xml":"https://content.openalex.org/works/W7214085804.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2116257507","https://openalex.org/W2321750218","https://openalex.org/W2335025434","https://openalex.org/W2473519184","https://openalex.org/W2736178248","https://openalex.org/W3141927472","https://openalex.org/W3185836256","https://openalex.org/W3200417146","https://openalex.org/W4239462015","https://openalex.org/W4283021369","https://openalex.org/W4294957924","https://openalex.org/W4312119492","https://openalex.org/W4327900113","https://openalex.org/W4385186651","https://openalex.org/W4387010574","https://openalex.org/W4389680298","https://openalex.org/W4391597589","https://openalex.org/W4404065473","https://openalex.org/W4406884476","https://openalex.org/W4412373906","https://openalex.org/W4414084992","https://openalex.org/W4416524231","https://openalex.org/W4417363132","https://openalex.org/W6891811738","https://openalex.org/W7102614548","https://openalex.org/W7116751874","https://openalex.org/W7131432983","https://openalex.org/W7148589921","https://openalex.org/W7155101225","https://openalex.org/W7160697806","https://openalex.org/W7171667704"],"related_works":["https://openalex.org/W7160697806","https://openalex.org/W7160384047","https://openalex.org/W7202096962","https://openalex.org/W7084076169","https://openalex.org/W4408690571","https://openalex.org/W4411211306","https://openalex.org/W7167913193","https://openalex.org/W4416666600","https://openalex.org/W4412373906","https://openalex.org/W7140316645"],"abstract_inverted_index":{"Transition":[0],"states":[1],"(TSs)":[2],"are":[3],"central":[4],"to":[5,143,170],"reaction":[6,152,174,194],"barriers":[7],"and":[8,38,78,116,173,196],"mechanisms,":[9],"yet":[10],"their":[11],"accurate":[12],"localization":[13],"remains":[14],"computationally":[15],"demanding.":[16],"Reactive":[17],"machine":[18],"learning":[19],"potentials":[20,189],"can":[21],"accelerate":[22],"TS":[23,76,114],"optimization":[24,77],"by":[25,140],"rapidly":[26],"predicting":[27],"potential":[28],"energy":[29],"surfaces,":[30],"but":[31],"achieving":[32],"chemical":[33,40,56],"transferability":[34],"requires":[35],"extensive":[36],"sampling":[37],"quantum":[39],"(QC)":[41],"labeling":[42,63,88],"of":[43,64,92,110,122,165,193],"reactive":[44,66,188],"conformations.":[45,97],"Here,":[46],"we":[47],"introduce":[48],"an":[49,104,131],"active-learning-guided":[50],"fine-tuning":[51,135,178],"strategy":[52],"that":[53],"couples":[54],"pretrained":[55,145],"knowledge":[57],"for":[58,68,89,113,125,190],"broad":[59],"generalization":[60],"with":[61,156],"adaptive":[62],"informative":[65],"conformations":[67],"data":[69],"efficiency.":[70],"The":[71],"resulting":[72],"MACEPre-DeePEST-OS":[73,102],"enables":[74],"efficient":[75],"barrier":[79,138,163],"predictions":[80],"across":[81],"diverse":[82],"organic":[83],"reactions":[84],"while":[85],"requiring":[86],"QC":[87],"only":[90],"~2%":[91],"approximately":[93],"19":[94],"million":[95],"candidate":[96],"Across":[98],"three":[99],"in-distribution":[100],"benchmarks,":[101],"achieves":[103],"average":[105],"root":[106],"mean":[107,118],"square":[108],"deviation":[109],"0.080":[111],"\u00c5":[112],"geometries":[115],"a":[117,150,162,183],"absolute":[119],"error":[120],"(MAE)":[121],"0.938":[123],"kcal/mol":[124],"barriers.":[126],"In":[127],"cross-dataset":[128],"evaluation":[129],"on":[130,149],"external":[132],"OrgReact":[133],"subset,":[134],"reduces":[136],"the":[137,144,177],"MAE":[139,164],"58%":[141],"relative":[142],"model.":[146],"Out-of-distribution":[147],"testing":[148],"Ugi":[151],"network":[153],"containing":[154],"structures":[155],"more":[157],"than":[158],"70":[159],"atoms":[160],"yields":[161],"1.09":[166],"kcal/mol,":[167],"indicating":[168],"transfer":[169],"molecular":[171],"sizes":[172],"complexity":[175],"beyond":[176],"data.":[179],"These":[180],"results":[181],"establish":[182],"data-efficient":[184],"route":[185],"toward":[186],"transferable":[187],"quantitative":[191],"analysis":[192],"mechanisms":[195],"competing":[197],"pathways.":[198]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-24T00:00:00"}