PaccMann$^{RL}$: Designing anticancer drugs from transcriptomic data via reinforcement learning

TL;DR

This paper introduces a novel reinforcement learning-based generative model that designs anticancer drugs tailored to specific transcriptomic profiles, integrating genetic data into molecule generation to improve targeted therapy development.

Contribution

It presents the first model combining transcriptomic data with molecule generation using dual variational autoencoders conditioned via reinforcement learning.

Findings

Generated compounds show high similarity to known effective drugs.

The model can bias molecule generation towards specific cancer types.

Effective compounds are predicted to have high inhibitory effects.

Abstract

With the advent of deep generative models in computational chemistry, in silico anticancer drug design has undergone an unprecedented transformation. While state-of-the-art deep learning approaches have shown potential in generating compounds with desired chemical properties, they disregard the genetic profile and properties of the target disease. Here, we introduce the first generative model capable of tailoring anticancer compounds for a specific biomolecular profile. Using a RL framework, the transcriptomic profiles of cancer cells are used as a context for the generation of candidate molecules. Our molecule generator combines two separately pretrained variational autoencoders (VAEs) - the first VAE encodes transcriptomic profiles into a smooth, latent space which in turn is used to condition a second VAE to generate novel molecular structures on the given transcriptomic profile. The generative process is optimized through PaccMann, a previously developed drug sensitivity prediction model to obtain effective anticancer compounds for the given context (i.e., transcriptomic profile). We demonstrate how the molecule generation can be biased towards compounds with high predicted inhibitory effect against individual cell lines or specific cancer sites. We verify our approach by investigating candidate drugs generated against specific cancer types and find the highest structural similarity to existing compounds with known efficacy against these cancer types. We envision our approach to transform in silico anticancer drug design by leveraging the biomolecular characteristics of the disease in order to increase success rates in lead compound discovery.