{"id":"https://openalex.org/W7166153882","doi":"https://doi.org/10.1145/3815572.3815744","title":"KBase Research Agent: Automated Multi-Agent Workflow Construction for Reproducible Genome Analysis","display_name":"KBase Research Agent: Automated Multi-Agent Workflow Construction for Reproducible Genome Analysis","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166153882","doi":"https://doi.org/10.1145/3815572.3815744"},"language":null,"primary_location":{"id":"doi:10.1145/3815572.3815744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3815572.3815744","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018846294","display_name":"Prachi Gupta","orcid":"https://orcid.org/0000-0002-1255-2684"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prachi Gupta","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1255-2684","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000539447","display_name":"William J. Riehl","orcid":"https://orcid.org/0000-0002-3405-2744"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William J. Riehl","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3405-2744","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087768840","display_name":"Mikaela Cashman","orcid":"https://orcid.org/0000-0003-0620-7830"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikaela Cashman","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0620-7830","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029432420","display_name":"Dylan Chivian","orcid":"https://orcid.org/0000-0001-8189-8729"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan C. Chivian","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8189-8729","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014963126","display_name":"Christopher J. Neely","orcid":"https://orcid.org/0000-0002-2620-8948"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. Neely","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2620-8948","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057883387","display_name":"Shane Canon","orcid":"https://orcid.org/0000-0002-8440-738X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shane R. Canon","raw_affiliation_strings":["National Energy Research Scientific Computing Center, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8440-738X","affiliations":[{"raw_affiliation_string":"National Energy Research Scientific Computing Center, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068737378","display_name":"Robert W. Cottingham","orcid":"https://orcid.org/0000-0002-2775-3905"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert W. Cottingham","raw_affiliation_strings":["Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-2775-3905","affiliations":[{"raw_affiliation_string":"Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017949757","display_name":"Christopher S. Henry","orcid":"https://orcid.org/0000-0001-8058-9123"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris S. Henry","raw_affiliation_strings":["Biosciences Division, Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-8058-9123","affiliations":[{"raw_affiliation_string":"Biosciences Division, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066623854","display_name":"Adam P. Arkin","orcid":"https://orcid.org/0000-0002-4999-2931"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam P. Arkin","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA and Bioengineering, University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4999-2931","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA and Bioengineering, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013558711","display_name":"Paramvir Dehal","orcid":"https://orcid.org/0000-0001-5810-2497"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paramvir S. Dehal","raw_affiliation_strings":["Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5810-2497","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83838886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5863000154495239,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.5863000154495239,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.029100000858306885,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.01720000058412552,"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/workflow","display_name":"Workflow","score":0.6796000003814697},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.32429999113082886},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.29010000824928284},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.27730000019073486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2720000147819519}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6796000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129999756813049},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.29010000824928284},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3815572.3815744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3815572.3815744","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2859249641","https://openalex.org/W4246668299","https://openalex.org/W4304481015","https://openalex.org/W4304976098","https://openalex.org/W4309157457","https://openalex.org/W4390114191","https://openalex.org/W4396723768","https://openalex.org/W4402667024","https://openalex.org/W4402671506","https://openalex.org/W4403099947","https://openalex.org/W4406833248","https://openalex.org/W4410515589","https://openalex.org/W4412759774"],"related_works":[],"abstract_inverted_index":{"Constructing":[0],"multi-step":[1],"bioinformatics":[2,189],"workflows,":[3],"from":[4,117,121,138],"read":[5,147],"quality":[6,112,148],"control":[7],"through":[8],"genome":[9,150],"assembly":[10],"to":[11,90,131],"functional":[12],"annotation,":[13],"requires":[14],"expertise":[15],"in":[16,68,186],"both":[17],"biology":[18],"and":[19,28,57,71,85,110,156,164],"computational":[20],"tool":[21],"selection,":[22],"creating":[23],"a":[24,37,52,58,72,101,187],"bottleneck":[25],"for":[26,40],"scalable":[27],"reproducible":[29,102,162],"analysis.":[30],"We":[31,105,126],"present":[32],"the":[33,45,61,77,93,107,129,139,173,178],"KBase":[34,69,78,88,103,174],"Research":[35,175],"Agent,":[36],"multi-agent":[38],"system":[39],"automating":[41],"such":[42],"workflows":[43,119],"within":[44],"DOE":[46],"Systems":[47],"Biology":[48],"Knowledgebase":[49],"(KBase).":[50],"Given":[51],"set":[53],"of":[54,76,180],"sequencing":[55],"reads":[56],"research":[59],"objective,":[60],"agent":[62,130],"constructs":[63],"an":[64],"analysis":[65,97,158],"plan":[66],"grounded":[67],"documentation":[70],"Knowledge":[73],"Graph":[74],"(KG)":[75],"application":[79],"catalog,":[80],"then":[81],"selects,":[82],"parameterizes,":[83],"validates":[84],"executes":[86],"appropriate":[87],"applications":[89],"carry":[91],"out":[92],"workflow.":[94],"The":[95],"resulting":[96],"is":[98],"preserved":[99],"as":[100],"Narrative.":[104],"evaluate":[106],"system's":[108],"planning":[109],"execution":[111],"against":[113],"ground":[114],"truth":[115],"constructed":[116],"reference":[118],"derived":[120],"peer-reviewed":[122],"Microbiology":[123],"Resource":[124],"Announcements.":[125],"further":[127],"apply":[128],"100":[132],"previously":[133],"unanalyzed":[134],"bacterial":[135],"isolate":[136],"genomes":[137],"JGI":[140],"IMG/M":[141],"database,":[142],"where":[143],"it":[144],"autonomously":[145],"performed":[146],"control,":[149],"assembly,":[151],"taxonomic":[152],"classification":[153],"with":[154],"GTDB-Tk,":[155],"downstream":[157],"producing":[159],"annotated":[160],"genomes,":[161],"Narratives,":[163],"draft":[165],"manuscripts":[166],"without":[167],"human":[168],"intervention.":[169],"Across":[170],"these":[171],"experiments,":[172],"Agent":[176],"demonstrates":[177],"feasibility":[179],"domain-grounded,":[181],"end-to-end":[182],"scientific":[183],"workflow":[184],"automation":[185],"production":[188],"platform.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-27T00:00:00"}
