BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201804Z
LOCATION:241
DTSTART;TZID=America/Chicago:20251116T153000
DTEND;TZID=America/Chicago:20251116T160000
UID:submissions.supercomputing.org_SC25_sess209_ws_fgai107@linklings.com
SUMMARY:BioR5: A Three-Layer Architecture for Biological Reasoning in Scie
 ntific AI
DESCRIPTION:Peng Ding (University of Chicago, Argonne National Laboratory 
 (ANL)); Thomas Brettin (Argonne National Laboratory (ANL)); and Rick Steve
 ns (Argonne National Laboratory (ANL), University of Chicago)\n\nBiologica
 l research requires diverse reasoning modes, from phylogenetic analysis to
  mechanistic understanding, each demanding specific methods and data types
 . Current AI systems typically employ single methodologies, limiting effec
 tiveness in complex biological domains. We present BioR5, a three-layer ar
 chitecture implementing eleven distinct biological reasoning modes with in
 telligent triage and specialized tool integration. Layer A provides parame
 tric memory via large language models, Layer B incorporates specialized fo
 undation models for multimodal data, and Layer C connects external databas
 es and computational tools. Our system features an intelligent reasoning m
 ode selection combining keyword matching with LLM analysis to choose appro
 priate strategies automatically. We demonstrate the framework through toxi
 cology specialization, integrating TX-Gemma predictions with PubChem, ToxC
 ast, and ChEMBL data. The open-source implementation supports dynamic regi
 stration of new reasoning modes and tools, enabling collaborative developm
 ent and community-driven expansion. BioR5 represents an architecture-first
  approach to developing reasoning-mode-aware AI systems that scale easily 
 with new biological use cases.\n\nRecording: Livestreamed, Recorded\n\nReg
 istration Category: Technical Program Reg Pass, Workshop Reg Pass\n\nSessi
 on Chairs: Charlie Catlett (Argonne National Laboratory (ANL), University 
 of Chicago); Javier Aula-Blasco (Barcelona Supercomputing Center (BSC)); V
 alerie Taylor (Argonne National Laboratory (ANL), University of Chicago); 
 Laura Morselli (CINECA); and Rio Yokota (Institute of Science Tokyo)\n\n
END:VEVENT
END:VCALENDAR