BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:In-Silico Prediction of Bioactive Small Molecules - Avid Afzal (Un
 iversity of Cambridge)
DTSTART:20160513T110000Z
DTEND:20160513T114000Z
UID:TALK65737@talks.cam.ac.uk
CONTACT:Alex Thom
DESCRIPTION:Suggesting target proteins for compounds that give rise to a p
 articular cellular phenotype but have unknown protein targets is crucial i
 n drug research. This can be done through experimental target finding meth
 ods\, or via computational approaches. Computational methods are increasin
 gly gaining preference because they are less time consuming and reduce hyp
 othesis space to a smaller number of testable biological targets. Ligand-b
 ased approaches\, which form a subgroup of target prediction algorithms\, 
 mine large bioactivity databases and employs pattern recognition/machine l
 earning techniques to find the target protein associated with the compound
 . To this end\, I implemented two in silico protocols and compared their p
 erformance. The first protocol compared two probabilistic models by a vari
 ety of performance measurements\, being the Naïve Bayes classifier and th
 e inverse Ising model. The second protocol addresses the promiscuity of th
 e bioactive compounds.
LOCATION:Unilever Lecture Theatre\, Department of Chemistry
END:VEVENT
END:VCALENDAR