BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260615T224308Z
UID:fd082d8a-015b-47c6-88bc-e85411a51676
DTSTART:20250319T090000Z
DTEND:20250319T170000Z
DESCRIPTION:This webinar will explore how Large Language Models can acceler
 ate protein classification by automatically generating descriptive annotat
 ions for previously unannotated protein families. Traditionally\, the proc
 ess of curating protein family descriptions relies on manual literature re
 view and expert knowledge\, a time-consuming approach that often delays in
 tegration into biological databases. In this session\, we will discuss our
  innovative workflow that leverages LLMs to synthesise functional summarie
 s from existing curated data\, thereby streamlining the annotation process
 . We will also highlight a comparative evaluation of using both a state-of
 -the-art GTP model and a fine-tuned local model\, demonstrating that small
 er\, cost-effective LLMs can produce high-quality descriptions that suppor
 t rapid protein classification.
LOCATION:\, 
SUMMARY:LLM generated summaries for protein classification at InterPro
URL;VALUE=URI:https://www.ebi.ac.uk/training/events/llm-generated-summaries
 -protein-classification-interpro
END:VEVENT
END:VCALENDAR