Lattice Protein Folding with Variational Annealing

TL;DR

This paper introduces a novel machine learning approach using dilated RNNs and annealing to efficiently find low-energy folds in lattice protein models, advancing computational methods in protein folding research.

Contribution

It presents a new upper-bound training scheme with masking and annealing for predicting optimal lattice protein folds, scalable to higher dimensions and larger alphabets.

Findings

Accurately predicts optimal folds for up to 60-bead systems.

Effectively masks invalid folds without losing sampling properties.

Generalizable to 3D and larger alphabet models.

Abstract

Understanding the principles of protein folding is a cornerstone of computational biology, with implications for drug design, bioengineering, and the understanding of fundamental biological processes. Lattice protein folding models offer a simplified yet powerful framework for studying the complexities of protein folding, enabling the exploration of energetically optimal folds under constrained conditions. However, finding these optimal folds is a computationally challenging combinatorial optimization problem. In this work, we introduce a novel upper-bound training scheme that employs masking to identify the lowest-energy folds in two-dimensional Hydrophobic-Polar (HP) lattice protein folding. By leveraging Dilated Recurrent Neural Networks (RNNs) integrated with an annealing process driven by temperature-like fluctuations, our method accurately predicts optimal folds for benchmark systems of up to 60 beads. Our approach also effectively masks invalid folds from being sampled without compromising the autoregressive sampling properties of RNNs. This scheme is generalizable to three spatial dimensions and can be extended to lattice protein models with larger alphabets. Our findings emphasize the potential of advanced machine learning techniques in tackling complex protein folding problems and a broader class of constrained combinatorial optimization challenges.