Fig. 2: BATCHIE overview.
From: A Bayesian active learning platform for scalable combination drug screens
a The BATCHIE workflow begins by specifying a cell line library, a drug library, and an initial ‘seed batch’ of plates to cover every cell line and drug with at least one experiment. b Selected plates are assembled, run, measured, and post-processed to obtain viability scores. Quality control (QC) checks filter out problematic wells. c A Bayesian tensor factorization model is fit to the current data. Posterior samples are drawn via MCMC. d The joint distributions of candidate experiments are estimated using the current set of posterior samples. e The active learning criterion is applied to the joint distribution estimates to score the utility of individual experiments. f The scores of individual experiments are aggregated to define the most informative batch of experiments to run next, possibly subject to design constraints. g After terminating the active learning loop, the most recently fitted Bayesian model is used to predict top hits for individual combinations. These top hits can then be validated in vitro and, potentially, in vivo. Created in BioRender. Tansey, W. (2024) BioRender.com/t08h139.
