Ngo, N. K. | Search bioRxiv

bioRxiv2024

Latent-based Directed Evolution accelerated by Gradient Ascent for Protein Sequence Design

Directed evolution has been the most effective method for protein engineering that optimizes biological functionalities through a resource-intensive process of screening or selecting among a vast range of mutations. To mitigate this extensive procedure, recent advancements in machine learning-guided methodologies center around the establishment of a surrogate sequence-function model. In this paper, we propose Latent-based Directed Evolution (LDE), an evolutionary algorithm designed to prioritize the exploration of high-fitness mutants in the latent space. At its core, LDE is a regularized variational autoencoder (VAE), harnessing the capabilities of the state-of-the-art Protein Language Model (pLM), ESM-2, to construct a meaningful latent space of sequences. From this encoded representation, we present a novel approach for efficient traversal on the fitness landscape, employing a combination of gradient-based methods and directed evolution. Experimental evaluations conducted on eight protein sequence design tasks demonstrate the superior performance of our proposed LDE over previous baseline algorithms. Our implementation is publicly available at https://github.com/HySonLab/LatentDE.

bioinformatics↗

bioRxiv2023

Target-aware Variational Auto-encoders for Ligand Generation with Multimodal Protein Representation Learning

Without knowledge of specific pockets, generating ligands based on the global structure of a protein target plays a crucial role in drug discovery as it helps reduce the search space for potential drug-like candidates in the pipeline. However, contemporary methods require optimizing tailored networks for each protein, which is arduous and costly. To address this issue, we introduce TargetVAE, a target-aware variational auto-encoder that generates ligands with high binding affinities to arbitrary protein targets, guided by a novel multimodal deep neural network built based on graph Transformers as the prior for the generative model. This is the first effort to unify different representations of proteins (e.g., sequence of amino-acids, 3D structure) into a single model that we name as Protein Multimodal Network (PMN). Our multimodal architecture learns from the entire protein structures and is able to capture their sequential, topological and geometrical information. We showcase the superiority of our approach by conducting extensive experiments and evaluations, including the assessment of generative model quality, ligand generation for unseen targets, docking score computation, and binding affinity prediction. Empirical results demonstrate the promising performance of our proposed approach. Our software package is publicly available at https://github.com/HySonLab/Ligand_Generation.

biochemistry↗