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:20241120T082409Z
LOCATION:HG F 26.5
DTSTART;TZID=Europe/Stockholm:20240603T153000
DTEND;TZID=Europe/Stockholm:20240603T160000
UID:submissions.pasc-conference.org_PASC24_sess165_msa304@linklings.com
SUMMARY:Leveraging Large Datasets to Assess the Potential of Machine Learn
 ing for Drug Target Prediction through Reverse Screening
DESCRIPTION:Minisymposium\n\nVincent Zoete (University of Lausanne)\n\nEst
 imating protein targets of compounds based on the similarity principle is 
 a long-standing strategy in drug discovery. Building upon prior quantifica
 tion of this principle, the large-scale assessment of its predictive power
  was performed using an unprecedented vast external test set of more than 
 300’000 active small molecules against another bioactivity set of more tha
 n 500’000 compounds. It was found that machine-learning can predict the co
 rrect targets, with the highest probability among 2069 proteins, for more 
 than 51% of the external molecules. The strong enrichment thus obtained de
 monstrates its usefulness in supporting phenotypic screens, polypharmacolo
 gy, or repurposing. Moreover, the impact of the bioactivity knowledge avai
 lable for proteins in terms of number and diversity of actives was investi
 gated. This study advocates for the adoption of application-oriented bench
 marking strategies to prevent accidental overestimation of their predictiv
 e ability, and the use of large, high-quality, non-overlapping datasets.\n
 \nDomain: Chemistry and Materials, Life Sciences\n\nSession Chair: Andreas
  Vitalis (University of Zurich)
END:VEVENT
END:VCALENDAR