Dose–response modeling in high-throughput cancer drug screenings: an end-to-end approach

Abstract

Summary Personalized cancer treatments based on the molecular profile of a patient’s tumor are an emerging and exciting class of treatments in oncology. As genomic tumor profiling is becoming more common, targeted treatments for specific molecular alterations are gaining traction. To discover new potential therapeutics that may apply to broad classes of tumors matching some molecular pattern, experimentalists and pharmacologists rely on high-throughput, in vitro screens of many compounds against many different cell lines. We propose a hierarchical Bayesian model of how cancer cell lines respond to drugs in these experiments and develop a method for fitting the model to real-world high-throughput screening data. Through a case study, the model is shown to capture nontrivial associations between molecular features and drug response, such as requiring both wild type TP53 and overexpression of MDM2 to be sensitive to Nutlin-3(a). In quantitative benchmarks, the model outperforms a standard approach in biology, with $\approx20\%$ lower predictive error on held out data. When combined with a conditional randomization testing procedure, the model discovers markers of therapeutic response that recapitulate known biology and suggest new avenues for investigation. All code for the article is publicly available at https://github.com/tansey/deep-dose-response.

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.…”

“…In both cases, the authors did not use their models for dosage-dependent inference of biomarker effects. Additionally, the highly non-linear neural network model in Tansey et al [27] makes interpretation of biomarker effects challenging.…”

Drug combinations screening using a Bayesian ranking approach based on dose–response models

“…We used a hierarchical 4PLL model to estimate the dose–response relationships of candidate treatments, assuming interpatient variability on $$IC_{50}$$s. Although the operating characteristics of the ranking method were robust in the hormetic and MuSyC scenarios more complex models could be used, notably to relax the monotonicity assumption on the dose–response relationships for anticancer agents (Yoshimasu et al., 2015) or to include others types of interpatient variability or batch effects for instance (Tansey et al., 2022). In the case of known heterogeneity in the patients population, interaction terms with covariates could also be included in the model.…”

bayesynergy: flexible Bayesian modelling of synergistic interaction effects inin vitrodrug combination experiments

“…The noise term \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$\epsilon $\end{document} captures the measurement error around the dose–response curve, and is given a zero-mean normal distribution, independent across replicates, with a heteroscedastic variance: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}\begin{align*}& \textrm{Var}\left[\epsilon_{ijr}\right] = \sigma^2\left(f(\mathbf{x}_{ij})+\lambda\right). \end{align*}\end{document} A similar structure was used in [ 15 ] directly, from a log-transformation, and in [ 16 ] indirectly, through modelling the raw fluorescent intensity output from the plate reader. The heteroscedastic structure arises from the normalization procedure itself.…”