BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260611T145139Z
LOCATION:Bldg. 6 - Room 003
DTSTART;TZID=Europe/Stockholm:20260701T113000
DTEND;TZID=Europe/Stockholm:20260701T120000
UID:submissions.pasc-conference.org_PASC26_sess173_pap111@linklings.com
SUMMARY:KBase Research Agent: Automated Multi-Agent Workflow Construction 
 for Reproducible Genome Analysis
DESCRIPTION:Prachi Gupta, William Riehl, Mikaela Cashman, Dylan Chivian, C
 hristopher Neely, and Shane Canon (Lawrence Berkeley National Laboratory);
  Robert Cottingham (Oak Ridge National Laboratory); Chris Henry (Argonne N
 ational Laboratory); and Adam Arkin and Paramvir Dehal (Lawrence Berkeley 
 National Laboratory)\n\nConstructing multi-step bioinformatics workflows, 
 from read quality control through genome assembly to functional annotation
 , requires expertise in both biology and computational tool selection, cre
 ating a bottleneck for scalable and reproducible analysis. We present the 
 KBase Research Agent, a multi-agent system for automating such workflows w
 ithin the DOE Systems Biology Knowledgebase (KBase). Given a set of sequen
 cing reads and a research objective, the agent constructs an analysis plan
  grounded in KBase documentation and a Knowledge Graph (KG) of the KBase a
 pplication catalog, then selects, parameterizes, validates and executes ap
 propriate KBase applications to carry out the workflow. The resulting anal
 ysis is preserved as a reproducible KBase Narrative. We evaluate the syste
 m’s planning and execution quality against ground truth constructed from r
 eference workflows derived from peer-reviewed Microbiology Resource Announ
 cements. We further apply the agent to 100 previously unanalyzed bacterial
  isolate genomes from the JGI IMG/M database, where it autonomously perfor
 med read quality control, genome assembly, taxonomic classification with G
 TDB-Tk, and downstream analysis producing annotated genomes, reproducible 
 Narratives, and draft manuscripts without human intervention. Across these
  experiments, the KBase Research Agent demonstrates the feasibility of dom
 ain-grounded, end-to-end scientific workflow automation in a production bi
 oinformatics platform.\n\nDomain: Engineering, Life Sciences, Physics\n\nS
 ession Chair: Andrei Onut (University of Basel)\n\n
END:VEVENT
END:VCALENDAR