{"id":"https://openalex.org/W4404719819","doi":"https://doi.org/10.1186/s13321-024-00928-8","title":"Suitability of large language models for extraction of high-quality chemical reaction dataset from patent literature","display_name":"Suitability of large language models for extraction of high-quality chemical reaction dataset from patent literature","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4404719819","doi":"https://doi.org/10.1186/s13321-024-00928-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/39593165"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00928-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00928-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00928-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00928-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054798716","display_name":"Sarveswara Rao Vangala","orcid":"https://orcid.org/0000-0001-6699-3488"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarveswara Rao Vangala","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102810785","display_name":"Sowmya Ramaswamy Krishnan","orcid":"https://orcid.org/0000-0001-5404-3266"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sowmya Ramaswamy Krishnan","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027584199","display_name":"Navneet Bung","orcid":"https://orcid.org/0000-0002-6376-277X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Navneet Bung","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057379781","display_name":"D. Nandagopal","orcid":"https://orcid.org/0000-0003-0722-9724"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhandapani Nandagopal","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074120196","display_name":"Gomathi Ramasamy","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gomathi Ramasamy","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022777908","display_name":"Satyam Kumar","orcid":"https://orcid.org/0000-0003-4817-1768"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satyam Kumar","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019940590","display_name":"Sridharan Sankaran","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sridharan Sankaran","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112449421","display_name":"Rajgopal Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajgopal Srinivasan","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042990614","display_name":"Arijit Roy","orcid":"https://orcid.org/0000-0002-1961-2483"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arijit Roy","raw_affiliation_strings":["TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India. roy.arijit3@tcs.com","TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India. roy.arijit3@tcs.com","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"TCS Research (Life Sciences Division), Tata Consultancy Services Limited, Hyderabad, 500081, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042990614"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.9893,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9021347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"131","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9933000206947327,"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/T10028","display_name":"Topic Modeling","score":0.9811000227928162,"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/computer-science","display_name":"Computer science","score":0.7789750695228577},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.6798501014709473},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6459524035453796},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6167600154876709},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5316821932792664},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.517259418964386},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.500112771987915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46879634261131287},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4324079155921936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929517865180969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3397054672241211},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3244484066963196},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.23552370071411133},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12482595443725586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789750695228577},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.6798501014709473},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6459524035453796},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6167600154876709},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5316821932792664},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.517259418964386},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.500112771987915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46879634261131287},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4324079155921936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929517865180969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3397054672241211},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3244484066963196},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.23552370071411133},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12482595443725586},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C35753019","wikidata":"https://www.wikidata.org/wiki/Q644785","display_name":"Total synthesis","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00928-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00928-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00928-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:39593165","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39593165","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11590295","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11590295","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11590295/pdf/13321_2024_Article_928.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:c9e88226009a45499129c6be0dbaf310","is_oa":true,"landing_page_url":"https://doaj.org/article/c9e88226009a45499129c6be0dbaf310","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 16, Iss 1, Pp 1-13 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00928-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00928-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00928-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404719819.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1989405983","https://openalex.org/W2034354062","https://openalex.org/W2045155277","https://openalex.org/W2111044246","https://openalex.org/W2481382694","https://openalex.org/W2775684663","https://openalex.org/W2790808809","https://openalex.org/W2911489562","https://openalex.org/W2929387033","https://openalex.org/W2968071222","https://openalex.org/W3097184250","https://openalex.org/W3118349318","https://openalex.org/W3125539506","https://openalex.org/W3146384714","https://openalex.org/W3146601652","https://openalex.org/W3158543275","https://openalex.org/W3168661259","https://openalex.org/W3194082573","https://openalex.org/W3209726219","https://openalex.org/W4221153690","https://openalex.org/W4239934460","https://openalex.org/W4381252028","https://openalex.org/W4382198765","https://openalex.org/W4386884238","https://openalex.org/W4389300644","https://openalex.org/W4389996830","https://openalex.org/W4391836235","https://openalex.org/W4392247262","https://openalex.org/W4392596618","https://openalex.org/W4394577612","https://openalex.org/W4403547227","https://openalex.org/W6604666239"],"related_works":["https://openalex.org/W2155289933","https://openalex.org/W4244321733","https://openalex.org/W1997389443","https://openalex.org/W2317928565","https://openalex.org/W4281772408","https://openalex.org/W2140972311","https://openalex.org/W2151971404","https://openalex.org/W2078293348","https://openalex.org/W2902857455","https://openalex.org/W3209805961"],"abstract_inverted_index":{"With":[0],"the":[1,28,48,60,81,92,98,136,143,153,168,187,193,196,206,209],"advent":[2],"of":[3,30,50,62,69,84,103,117,157,170,195,208],"artificial":[4],"intelligence":[5],"(AI),":[6],"it":[7],"is":[8,27],"now":[9],"possible":[10],"to":[11,38],"design":[12],"diverse":[13],"and":[14,114,155,204],"novel":[15],"molecules":[16],"from":[17,74,86,181],"previously":[18,137],"unexplored":[19],"chemical":[20,71,178,202],"space.":[21],"However,":[22],"a":[23,51,147,176],"challenge":[24],"for":[25,42,67,115,174],"chemists":[26],"synthesis":[29,158],"such":[31],"molecules.":[32],"Recently,":[33],"there":[34],"have":[35],"been":[36],"attempts":[37],"develop":[39],"AI":[40],"models":[41,65,160,173],"retrosynthesis":[43],"prediction,":[44],"which":[45],"rely":[46],"on":[47,80],"availability":[49],"high-quality":[52,70,177],"training":[53],"dataset.":[54,139],"In":[55],"this":[56,164],"work,":[57],"we":[58,166],"explore":[59],"suitability":[61,169],"large":[63,171],"language":[64,172],"(LLMs)":[66],"extraction":[68],"reaction":[72,112,179,197,210],"data":[73],"patent":[75,149,182],"documents.":[76],"A":[77,123],"comparative":[78],"study":[79,89],"same":[82],"set":[83],"patents":[85],"an":[87],"earlier":[88],"showed":[90,185],"that":[91,186],"proposed":[93,144,188],"automated":[94],"approach":[95,189],"can":[96,151,190],"enhance":[97],"current":[99],"datasets":[100],"by":[101,199,212],"addition":[102],"26%":[104],"new":[105],"reactions.":[106],"Several":[107],"challenges":[108],"were":[109,121,133],"identified":[110,134],"during":[111],"mining,":[113],"some":[116],"them":[118],"alternative":[119],"solutions":[120],"proposed.":[122],"detailed":[124],"analysis":[125],"was":[126],"also":[127],"performed":[128],"wherein":[129],"several":[130],"wrong":[131],"entries":[132],"in":[135,161],"curated":[138],"Reactions":[140],"extracted":[141],"using":[142],"pipeline":[145],"over":[146],"larger":[148],"dataset":[150,180],"improve":[152,192,205],"accuracy":[154],"efficiency":[156],"prediction":[159],"future.Scientific":[162],"contributionIn":[163],"work":[165],"evaluated":[167],"mining":[175],"literature.":[183],"We":[184],"significantly":[191],"quantity":[194],"database":[198,211],"identifying":[200],"more":[201],"reactions":[203],"quality":[207],"correcting":[213],"previous":[214],"errors/false":[215],"positives.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":10}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}