Compositional Deep Probabilistic Models of DNA Encoded Libraries

TL;DR

This paper introduces DEL-Compose, a hierarchical probabilistic model that decomposes DNA-Encoded Library molecules into building blocks, improving analysis, interpretation, and noise handling of complex DEL screening data.

Contribution

The paper presents a novel compositional deep probabilistic model that leverages molecular hierarchy and latent reactions to analyze DEL data more effectively and interpretably.

Findings

DEL-Compose outperforms baseline models on benchmark datasets

It enhances pharmacophore identification and interpretability

The model effectively accounts for data noise through covariate integration

Abstract

DNA-Encoded Library (DEL) has proven to be a powerful tool that utilizes combinatorially constructed small molecules to facilitate highly-efficient screening assays. These selection experiments, involving multiple stages of washing, elution, and identification of potent binders via unique DNA barcodes, often generate complex data. This complexity can potentially mask the underlying signals, necessitating the application of computational tools such as machine learning to uncover valuable insights. We introduce a compositional deep probabilistic model of DEL data, DEL-Compose, which decomposes molecular representations into their mono-synthon, di-synthon, and tri-synthon building blocks and capitalizes on the inherent hierarchical structure of these molecules by modeling latent reactions between embedded synthons. Additionally, we investigate methods to improve the observation models for DEL count data such as integrating covariate factors to more effectively account for data noise. Across two popular public benchmark datasets (CA-IX and HRP), our model demonstrates strong performance compared to count baselines, enriches the correct pharmacophores, and offers valuable insights via its intrinsic interpretable structure, thereby providing a robust tool for the analysis of DEL data.