BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2025//speaker//RCGPHK
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20240820T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Machine learning for ecotoxicology and bee pesticide toxicity pred
 iction - Jakub Adamczyk
DTSTART;TZID=Europe/Warsaw:20250820T103000
DTEND;TZID=Europe/Warsaw:20250820T110000
DTSTAMP:20260908T062312Z
UID:pretalx-euroscipy-2025-T88GQE@pretalx.com
DESCRIPTION:Machine learning (ML) is widely applied in medicinal chemistry
  and pharmaceutical industry. Chemoinformatics and molecular ML have been 
 used for decades for safer\, faster drug design. However\, the important a
 rea of agrochemistry has been relatively neglected. New regulations\, with
  strong focus on ecotoxicology\, necessitate creation of novel\, safer pes
 ticides.\n\nIn this talk\, I will describe how and why we can apply ML in 
 predictive ecotoxicology\, and how those models can be applied in agrochem
 istry. In particular\, I will present ApisTox\, a novel dataset about pest
 icide bee toxicity\, how we can construct such datasets from publicly avai
 lable data sources\, and what are the challenges.\n\nThen\, we will cover 
 predictive ML applications in ecotoxicology\, and how to apply data scienc
 e tools for agrochemical data. Examples include molecular fingerprints\, g
 raph kernels\, and graph neural networks. We will also discuss quantitativ
 e measures for describing differences between medicinal chemistry and agro
 chemistry\, and how it impacts practical results.
LOCATION:Room 1.20 (Ground Floor\, Shannon)
URL:https://pretalx.com/euroscipy-2025/talk/T88GQE/
END:VEVENT
END:VCALENDAR