Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions

TL;DR

This paper benchmarks existing protein data augmentation techniques, introduces two novel semantic-aware methods, and proposes an adaptive framework that improves performance across multiple protein-related tasks.

Contribution

It extends image and text augmentation methods to proteins, introduces new semantic augmentation techniques, and develops an adaptive framework for optimal augmentation selection.

Findings

APA improves performance by an average of 10.55% across tasks.

Semantic-aware augmentations enhance biological relevance.

Benchmark results demonstrate effectiveness of proposed methods.

Abstract

Augmentation is an effective alternative to utilize the small amount of labeled protein data. However, most of the existing work focuses on design-ing new architectures or pre-training tasks, and relatively little work has studied data augmentation for proteins. This paper extends data augmentation techniques previously used for images and texts to proteins and then benchmarks these techniques on a variety of protein-related tasks, providing the first comprehensive evaluation of protein augmentation. Furthermore, we propose two novel semantic-level protein augmentation methods, namely Integrated Gradients Substitution and Back Translation Substitution, which enable protein semantic-aware augmentation through saliency detection and biological knowledge. Finally, we integrate extended and proposed augmentations into an augmentation pool and propose a simple but effective framework, namely Automated Protein Augmentation (APA), which can adaptively select the most suitable augmentation combinations for different tasks. Extensive experiments have shown that APA enhances the performance of five protein related tasks by an average of 10.55% across three architectures compared to vanilla implementations without augmentation, highlighting its potential to make a great impact on the field.