# Dose-response modeling in high-throughput cancer drug screenings: An end-to-end approach

## TL;DR

This paper introduces a hierarchical Bayesian model for analyzing high-throughput cancer drug screening data, improving prediction accuracy and uncovering biologically relevant biomarkers for personalized therapy.

## Contribution

The authors develop a novel hierarchical Bayesian framework for dose-response modeling in cancer screenings, enhancing predictive performance and biomarker discovery over existing methods.

## Key findings

- Model captures complex molecular-drug response relationships
- Outperforms standard approaches with ~20% lower error
- Identifies known and novel biomarkers for drug sensitivity

## Abstract

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 to 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 ~20% lower predictive error on held out data. When combined with a conditional randomization testing procedure, the model discovers biomarkers of therapeutic response that recapitulate known biology and suggest new avenues for investigation. All code for the paper is publicly available at https://github.com/tansey/deep-dose-response.