{"id":"https://openalex.org/W4404480129","doi":"https://doi.org/10.1101/2024.11.15.623739","title":"A language model assistant for biocatalysis","display_name":"A language model assistant for biocatalysis","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404480129","doi":"https://doi.org/10.1101/2024.11.15.623739"},"language":"en","primary_location":{"id":"doi:10.1101/2024.11.15.623739","doi":"https://doi.org/10.1101/2024.11.15.623739","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.15.623739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","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://doi.org/10.1101/2024.11.15.623739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088564400","display_name":"Yves Ga\u00ebtan Nana Teukam","orcid":"https://orcid.org/0000-0002-6954-5119","observed_orcids":["https://orcid.org/0000-0002-6954-5119"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yves Gaetan Nana Teukam","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":"https://orcid.org/0000-0002-6954-5119","affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078946433","display_name":"Francesca Grisoni","orcid":"https://orcid.org/0000-0001-8552-6615","observed_orcids":["https://orcid.org/0000-0001-8552-6615"]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Francesca Grisoni","raw_affiliation_strings":["Institute for Complex Molecular Systems and Eindhoven AI Systems Institute, Eindhoven University of Technology"],"raw_orcid":"https://orcid.org/0000-0001-8552-6615","affiliations":[{"raw_affiliation_string":"Institute for Complex Molecular Systems and Eindhoven AI Systems Institute, Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005561269","display_name":"Matteo Manica","orcid":"https://orcid.org/0000-0002-8872-0269","observed_orcids":["https://orcid.org/0000-0002-8872-0269"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Manica","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":"https://orcid.org/0000-0002-8872-0269","affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088564400"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.8476999998092651,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.8476999998092651,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.030799999833106995,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.030500000342726707,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biocatalysis","display_name":"biocatalysis","score":0.9819999933242798},{"id":"https://openalex.org/keywords/enzyme-engineering","display_name":"enzyme engineering","score":0.9980000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/react-framework","display_name":"ReAct framework","score":0.9120000004768372},{"id":"https://openalex.org/keywords/molecular-dynamics-simulation","display_name":"molecular dynamics simulation","score":0.9190000295639038},{"id":"https://openalex.org/keywords/natural-language-query-processing","display_name":"natural language querying","score":0.75},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.7730000019073486},{"id":"https://openalex.org/keywords/computational-biology","display_name":"computational biology","score":0.75}],"concepts":[{"id":"https://openalex.org/C191503008","wikidata":"https://www.wikidata.org/wiki/Q16007026","display_name":"Biocatalysis","level":4,"score":0.7139624357223511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.374137282371521},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3363485336303711},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3261395990848541},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26532018184661865},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10111716389656067},{"id":"https://openalex.org/C161790260","wikidata":"https://www.wikidata.org/wiki/Q82264","display_name":"Catalysis","level":2,"score":0.09724608063697815},{"id":"https://openalex.org/C154881586","wikidata":"https://www.wikidata.org/wiki/Q898579","display_name":"Ionic liquid","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2024.11.15.623739","doi":"https://doi.org/10.1101/2024.11.15.623739","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.15.623739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2024.11.15.623739","doi":"https://doi.org/10.1101/2024.11.15.623739","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.11.15.623739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1031578623","https://openalex.org/W1975147762","https://openalex.org/W1995808589","https://openalex.org/W2035046825","https://openalex.org/W2047178318","https://openalex.org/W2055043387","https://openalex.org/W2073124751","https://openalex.org/W2118265845","https://openalex.org/W2767044445","https://openalex.org/W2802978762","https://openalex.org/W3098935468","https://openalex.org/W4239678514","https://openalex.org/W4286426680","https://openalex.org/W4288066876","https://openalex.org/W4322718191","https://openalex.org/W4366734321","https://openalex.org/W4387937021","https://openalex.org/W4389991792","https://openalex.org/W4390195781","https://openalex.org/W4390507962","https://openalex.org/W4396508870","https://openalex.org/W4396723768","https://openalex.org/W4397004462","https://openalex.org/W4399290669","https://openalex.org/W4403547534","https://openalex.org/W4406275792"],"related_works":["https://openalex.org/W4406275792","https://openalex.org/W7212160920","https://openalex.org/W7133327500","https://openalex.org/W7169604215","https://openalex.org/W7213965456","https://openalex.org/W4396675754","https://openalex.org/W7172294557","https://openalex.org/W7201831486","https://openalex.org/W4388200983","https://openalex.org/W4396508870"],"abstract_inverted_index":{"Abstract":[0],"Language":[1],"model":[2,26,47],"assistants":[3],"have":[4],"transformed":[5],"how":[6],"researchers":[7],"interact":[8],"with":[9,48,99],"computational":[10,32,101,146],"tools,":[11],"offering":[12],"unprecedented":[13],"capabilities":[14],"in":[15,38,91,129,145],"understanding":[16],"and":[17,64,72,80,87,97,117,127],"generating":[18],"complex":[19],"scientific":[20],"queries.":[21],"We":[22],"introduce":[23],"a":[24,31,44],"language":[25,46,57,143],"assistant":[27],"for":[28,68,107,124],"biocatalysis":[29,53],"(LM-ABC),":[30],"tool":[33,70],"designed":[34],"to":[35,51,103,139],"streamline":[36],"workflows":[37],"enzyme":[39,108,150],"engineering":[40,151],"research.":[41],"LM-ABC":[42,84,111,137],"integrates":[43],"large":[45],"domain-specific":[49],"modules":[50],"facilitate":[52],"research":[54,152],"through":[55],"natural":[56,95],"inputs.":[58],"Its":[59],"architecture":[60],"employs":[61],"the":[62,92,122,136,140],"Reasoning":[63],"Acting":[65],"(ReACT)":[66],"framework":[67],"dynamic":[69],"selection":[71],"chaining,":[73],"enabling":[74],"functionalities":[75],"like":[76],"binding":[77],"site":[78],"extraction":[79],"molecular":[81],"dynamics":[82],"simulations.":[83],"can":[85],"interpret":[86],"process":[88],"user":[89],"queries":[90],"form":[93],"of":[94,142],"language,":[96],"interface":[98],"existing":[100],"resources":[102],"generate":[104],"relevant":[105],"results":[106],"engineering.":[109],"Additionally,":[110],"is":[112],"available":[113],"via":[114],"both":[115],"command-line":[116],"web-based":[118],"interfaces,":[119],"which":[120],"lowers":[121],"barriers":[123],"its":[125],"usage":[126],"integration":[128],"various":[130],"disciplines.":[131],"Provided":[132],"as":[133],"open-source":[134],"software,":[135],"contributes":[138],"application":[141],"models":[144],"biology,":[147],"potentially":[148],"accelerating":[149],"processes.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-11-19T00:00:00"}
