BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A General Framework for Designing Evolutionary Experiments to Sele
 ct Specific Phage Phenotypes Using Neural Networks\, Statistical Simulatio
 ns\, and Symbolic Regression - Hassan Alam (University of Cambridge)
DTSTART:20250911T141000Z
DTEND:20250911T141500Z
UID:TALK233338@talks.cam.ac.uk
DESCRIPTION:Understanding how environmental conditions shape the evolution
  of bacteriophages (phages) is critical for designing correct evolutionary
  experiments that select specific phage traits. This study provides a gene
 ral mathematical framework that integrates physics-informed neural network
 s\, agent-based statistical simulations\, and symbolic regression machine 
 learning techniques to design evolutionary experiments targeting specific 
 phage traits such as high variability in phage phenotypes.&nbsp\;&nbsp\;In
  the study\, we used agent-based statistical simulations to generate synth
 etic time series data for evolutionary scenarios with diverse phenotypic o
 utcomes. Subsequently\, we trained Physics-informed neural networks (PINNs
 ) embedded in differential equations on the synthetic time series to revea
 l possible environments that select given phage traits and uncovered hidde
 n interactions in the system [1].&nbsp\;\n&nbsp\;\nReference:&nbsp\;[1] Gr
 igorian\, G.\, George\, S.V. and Arridge\, S.\, 2024. Learning Governing E
 quations of Unobserved States in Dynamical Systems. arXiv preprint arXiv:2
 404.18572.&nbsp\;
LOCATION:External
END:VEVENT
END:VCALENDAR