MoFormer: Multi-objective Antimicrobial Peptide Generation Based on Conditional Transformer Joint Multi-modal Fusion Descriptor

TL;DR

MoFormer is a novel multi-objective deep learning framework that optimizes antimicrobial peptides by balancing multiple attributes, outperforming existing methods in activity enhancement and toxicity reduction through structured latent space manipulation.

Contribution

The paper introduces MoFormer, a multi-objective AMP generation pipeline that uses conditional transformers and multi-modal fusion to improve peptide properties simultaneously.

Findings

MoFormer achieves better antimicrobial activity and lower hemolysis than existing methods.

The model effectively navigates the latent space for multi-attribute optimization.

Hierarchical ranking of peptide candidates enhances selection for desired properties.

Abstract

Deep learning holds a big promise for optimizing existing peptides with more desirable properties, a critical step towards accelerating new drug discovery. Despite the recent emergence of several optimized Antimicrobial peptides(AMP) generation methods, multi-objective optimizations remain still quite challenging for the idealism-realism tradeoff. Here, we establish a multi-objective AMP synthesis pipeline (MoFormer) for the simultaneous optimization of multi-attributes of AMPs. MoFormer improves the desired attributes of AMP sequences in a highly structured latent space, guided by conditional constraints and fine-grained multi-descriptor.We show that MoFormer outperforms existing methods in the generation task of enhanced antimicrobial activity and minimal hemolysis. We also utilize a Pareto-based non-dominated sorting algorithm and proxies based on large model fine-tuning to hierarchically rank the candidates. We demonstrate substantial property improvement using MoFormer from two perspectives: (1) employing molecular simulations and scoring interactions among amino acids to decipher the structure and functionality of AMPs; (2) visualizing latent space to examine the qualities and distribution features, verifying an effective means to facilitate multi-objective optimization AMPs with design constraints