{"id":"https://openalex.org/W4403345771","doi":"https://doi.org/10.48550/arxiv.2410.07076","title":"MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses","display_name":"MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses","publication_year":2024,"publication_date":"2024-10-09","ids":{"openalex":"https://openalex.org/W4403345771","doi":"https://doi.org/10.48550/arxiv.2410.07076"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.07076","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07076","pdf_url":"https://arxiv.org/pdf/2410.07076","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.07076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778571","display_name":"Zonglin Yang","orcid":"https://orcid.org/0000-0002-8059-6654","observed_orcids":["https://orcid.org/0000-0002-8059-6654"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yang, Zonglin","raw_affiliation_strings":["Nanyang Technological University","Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Wanhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Wanhao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109819194","display_name":"Ben Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Ben","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017600496","display_name":"Xie Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xie, Tong","raw_affiliation_strings":["GreenDynamics","University of New South Wales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GreenDynamics","institution_ids":[]},{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108783365","display_name":"Yuqiang Li","orcid":"https://orcid.org/0000-0002-2243-6038","observed_orcids":["https://orcid.org/0000-0002-2243-6038"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yuqiang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125892447","display_name":"Wanli Ouyang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ouyang, Wanli","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033376109","display_name":"Soujanya Poria","orcid":"https://orcid.org/0000-0001-6924-7931","observed_orcids":["https://orcid.org/0000-0001-6924-7931"]},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Poria, Soujanya","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752356","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280","observed_orcids":["https://orcid.org/0000-0002-3030-1280","https://orcid.org/0009-0009-3320-2526"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cambria, Erik","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112578541","display_name":"Dongzhan Zhou","orcid":"https://orcid.org/0000-0001-6568-5440","observed_orcids":["https://orcid.org/0000-0001-6568-5440","https://orcid.org/0009-0007-2513-9585"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Dongzhan","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.5932999849319458,"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":0.5932999849319458,"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/T10028","display_name":"Topic Modeling","score":0.10490000247955322,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.05829999968409538,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/scientific-hypothesis-generation","display_name":"scientific hypothesis generation","score":0.7440000176429749},{"id":"https://openalex.org/keywords/hypothesis-ranking","display_name":"hypothesis ranking","score":0.9879999756813049},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.4064740240573883},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3792017102241516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3596076965332031},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.26961809396743774}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.07076","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07076","pdf_url":"https://arxiv.org/pdf/2410.07076","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2410.07076","doi":"https://doi.org/10.48550/arxiv.2410.07076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.07076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.07076","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07076","pdf_url":"https://arxiv.org/pdf/2410.07076","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G155108461","display_name":null,"funder_award_id":"STEM RIE2025","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G5987483165","display_name":null,"funder_award_id":"T2EP20123-0005","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403345771.pdf","grobid_xml":"https://content.openalex.org/works/W4403345771.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204807602","https://openalex.org/W4415062263","https://openalex.org/W4388650906","https://openalex.org/W6979310735","https://openalex.org/W7162751963","https://openalex.org/W4410521503","https://openalex.org/W4402683817","https://openalex.org/W4415202617","https://openalex.org/W4416245566","https://openalex.org/W7133221773"],"abstract_inverted_index":{"Scientific":[0],"discovery":[1,76,140],"plays":[2],"a":[3,54,57,60,78,87,93,104,108,131,152,165,234,242],"pivotal":[4],"role":[5],"in":[6,13,38,92],"advancing":[7],"human":[8],"society,":[9],"and":[10,35,107,124,173,187],"recent":[11],"progress":[12],"large":[14],"language":[15],"models":[16],"(LLMs)":[17],"suggests":[18],"their":[19],"potential":[20],"to":[21,115,193,200,222],"accelerate":[22],"this":[23,41,156,161],"process.":[24],"However,":[25],"it":[26,213],"remains":[27],"unclear":[28],"whether":[29,45],"LLMs":[30,46,246],"can":[31,47,100],"autonomously":[32],"generate":[33],"novel":[34],"valid":[36],"hypotheses":[37,51,99,121,126,196],"chemistry.":[39],"In":[40],"work,":[42],"we":[43,85,163,240],"investigate":[44],"discover":[48],"high-quality":[49],"chemistry":[50,98,170],"given":[52],"only":[53],"research":[55,105],"background-comprising":[56],"question":[58],"and/or":[59],"survey-without":[61],"restriction":[62],"on":[63,226,231],"the":[64,67,72,137,201,205],"domain":[65],"of":[66,110,134,155,167],"question.":[68],"We":[69,142],"begin":[70],"with":[71,122,184,197,217,236],"observation":[73],"that":[74,96,150,245],"hypothesis":[75],"is":[77,151,191],"seemingly":[79],"intractable":[80],"task.":[81,141],"To":[82,159],"address":[83],"this,":[84],"propose":[86,241],"formal":[88],"mathematical":[89,157],"decomposition":[90,113],"grounded":[91],"fundamental":[94],"assumption:":[95,244],"most":[97],"be":[101],"composed":[102],"from":[103],"background":[106],"set":[109,133],"inspirations.":[111],"This":[112],"leads":[114],"three":[116],"practical":[117],"subtasks-retrieving":[118],"inspirations,":[119,123,186],"composing":[120],"ranking":[125],"-":[127],"which":[128],"together":[129],"constitute":[130],"sufficient":[132],"subtasks":[135],"for":[136],"overall":[138],"scientific":[139,251],"further":[143],"develop":[144],"an":[145,215],"agentic":[146],"LLM":[147,216],"framework,":[148,162],"MOOSE-Chem,":[149],"direct":[153],"implementation":[154],"decomposition.":[158],"evaluate":[160],"construct":[164],"benchmark":[166],"51":[168],"high-impact":[169],"papers":[171],"published":[172],"online":[174],"after":[175],"January":[176],"2024,":[177],"each":[178],"manually":[179],"annotated":[180],"by":[181,257],"PhD":[182],"chemists":[183],"background,":[185],"hypothesis.":[188],"The":[189],"framework":[190],"able":[192],"rediscover":[194],"many":[195],"high":[198,229],"similarity":[199],"groundtruth,":[202],"successfully":[203],"capturing":[204],"core":[206],"innovations-while":[207],"ensuring":[208],"no":[209],"data":[210],"contamination":[211],"since":[212],"uses":[214],"knowledge":[218,252],"cutoff":[219],"date":[220],"prior":[221],"2024.":[223],"Finally,":[224],"based":[225],"LLM's":[227],"surprisingly":[228],"accuracy":[230],"inspiration":[232],"retrieval,":[233],"task":[235],"inherently":[237],"out-of-distribution":[238],"nature,":[239],"bold":[243],"may":[247],"already":[248],"encode":[249],"latent":[250],"associations":[253],"not":[254],"yet":[255],"recognized":[256],"humans.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2024-10-12T00:00:00"}