Predicting probability distributions for cancer therapy drug selection optimization

TL;DR

This paper advocates predicting entire probability distributions of drug responses in cancer therapy to improve drug selection, proposing mixture of Gaussians models for better extreme value predictions over traditional expected value approaches.

Contribution

It introduces a novel approach of predicting full probability distributions, specifically using Gaussian mixtures, for more accurate drug selection in cancer therapy.

Findings

Distribution prediction outperforms expected value methods.

Mixture of Gaussians effectively models binomial-like distributions.

Enhanced identification of optimal drugs based on distribution tails.

Abstract

Large variability between cell lines brings a difficult optimization problem of drug selection for cancer therapy. Standard approaches use prediction of value for this purpose, corresponding e.g. to expected value of their distribution. This article shows superiority of working on, predicting the entire probability distributions - proposing basic tools for this purpose. We are mostly interested in the best drug in their batch to be tested - proper optimization of their selection for extreme statistics requires knowledge of the entire probability distributions, which for distributions of drug properties among cell lines often turn out binomial, e.g. depending on corresponding gene. Hence for basic prediction mechanism there is proposed mixture of two Gaussians, trying to predict its weight based on additional information.