DEL-Dock: Molecular Docking-Enabled Modeling of DNA-Encoded Libraries

TL;DR

DEL-Dock introduces a novel approach combining ligand descriptors with 3-D docking information to improve the denoising of DNA-encoded library data and predict binding affinities more accurately.

Contribution

It is the first model to integrate 3-D spatial data from docked complexes with DEL data, enhancing binding affinity prediction and pose selection without external supervision.

Findings

Better correlation with experimental binding data

Implicitly learns docking pose quality

Outperforms prior models in denoising DEL data

Abstract

DNA-Encoded Library (DEL) technology has enabled significant advances in hit identification by enabling efficient testing of combinatorially-generated molecular libraries. DEL screens measure protein binding affinity though sequencing reads of molecules tagged with unique DNA-barcodes that survive a series of selection experiments. Computational models have been deployed to learn the latent binding affinities that are correlated to the sequenced count data; however, this correlation is often obfuscated by various sources of noise introduced in its complicated data-generation process. In order to denoise DEL count data and screen for molecules with good binding affinity, computational models require the correct assumptions in their modeling structure to capture the correct signals underlying the data. Recent advances in DEL models have focused on probabilistic formulations of count data, but existing approaches have thus far been limited to only utilizing 2-D molecule-level representations. We introduce a new paradigm, DEL-Dock, that combines ligand-based descriptors with 3-D spatial information from docked protein-ligand complexes. 3-D spatial information allows our model to learn over the actual binding modality rather than using only structured-based information of the ligand. We show that our model is capable of effectively denoising DEL count data to predict molecule enrichment scores that are better correlated with experimental binding affinity measurements compared to prior works. Moreover, by learning over a collection of docked poses we demonstrate that our model, trained only on DEL data, implicitly learns to perform good docking pose selection without requiring external supervision from expensive-to-source protein crystal structures.