Causal Models, Prediction, and Extrapolation in Cell Line Perturbation Experiments

TL;DR

This paper compares causal and non-causal models for predicting cellular responses to perturbations, highlighting that causal models like Cellbox can extrapolate to unseen drugs, but may underperform regression models on existing data.

Contribution

It introduces a closed-form solution for the Cellbox causal model and systematically compares its extrapolation capabilities to regression models in cell line perturbation data.

Findings

Causal models enable extrapolation to unseen perturbations.

Regression models outperform causal models on observed data.

Analytic solutions facilitate comparison of modeling approaches.

Abstract

In cell line perturbation experiments, a collection of cells is perturbed with external agents (e.g. drugs) and responses such as protein expression measured. Due to cost constraints, only a small fraction of all possible perturbations can be tested in vitro. This has led to the development of computational (in silico) models which can predict cellular responses to perturbations. Perturbations with clinically interesting predicted responses can be prioritized for in vitro testing. In this work, we compare causal and non-causal regression models for perturbation response prediction in a Melanoma cancer cell line. The current best performing method on this data set is Cellbox which models how proteins causally effect each other using a system of ordinary differential equations (ODEs). We derive a closed form solution to the Cellbox system of ODEs in the linear case. These analytic results facilitate comparison of Cellbox to regression approaches. We show that causal models such as Cellbox, while requiring more assumptions, enable extrapolation in ways that non-causal regression models cannot. For example, causal models can predict responses for never before tested drugs. We illustrate these strengths and weaknesses in simulations. In an application to the Melanoma cell line data, we find that regression models outperform the Cellbox causal model.