A statistical framework for assessing pharmacological response and biomarkers using uncertainty estimates

Abstract

Drug high-throughput screenings across large molecular-characterised cancer cell line panels enable the discovery of biomarkers, and thereby, cancer precision medicine. The ability to experimentally generate drug response data has accelerated. However, this data is typically quantified by a summary statistic from a best-fit dose response curve, whilst neglecting the uncertainty of the curve fit and the potential variability in the raw readouts. Here, we model the experimental variance using Gaussian Processes, and subsequently, leverage this uncertainty for identifying associated biomarkers with a new statistical framework based on Bayesian testing. Applied to the Genomics of Drug Sensitivity in Cancer, in vitro screening data on 265 compounds across 1,074 cell lines, our uncertainty models identified 24 clinically established drug response biomarkers, and in addition provided evidence for 6 novel biomarkers. We validated our uncertainty estimates with an additional drug screen of 26 drugs, 10 cell lines with 8 to 9 replicates. Our method is applicable to drug high-throughput screens without replicates, and enables robust biomarker discovery for new cancer therapies.

A regularized functional regression model enabling transcriptome-wide dosage-dependent association study of cancer drug response

“…The advantage of using varying coefficient models along with a variable screening algorithm on genomic data sets was first introduced to explore the effect of genetic mutations on lung function [24]. Recently, Wang et al [26] and Tansey et al [27] independently proposed methods for modeling drug-response curves via Gaussian processes and linking them to biomarkers. In both cases, the authors did not use their models for dosage-dependent inference of biomarker effects.…”

bayesynergy: flexible Bayesian modelling of synergistic interaction effects in in-vitro drug combination experiments

“…From here, the user can analyse the drug combination screen either qualitatively by going further into the biology, or quantitatively by plugging the output of the model into other algorithms for further analysis. One such avenue might be bio-marker discovery models as in the style of [28], who utilises both the efficacy estimate and its corresponding uncertainty to find bio-markers of single therapy responses. The output can also be used as training data for machine learning algorithms attempting to predict the combined drug efficacy or synergy for untested experiments.…”