Protein Secondary Structure Prediction Using Transformers

TL;DR

This paper introduces a transformer-based model for predicting protein secondary structures from amino acid sequences, leveraging attention mechanisms and data augmentation to improve accuracy and generalization across variable-length sequences.

Contribution

The work presents a novel transformer architecture tailored for protein secondary structure prediction, incorporating a sliding-window data augmentation technique.

Findings

Transformer achieves high accuracy on CB513 dataset

Effective capturing of local and long-range interactions

Improved generalization across sequence lengths

Abstract

Predicting protein secondary structures such as alpha helices, beta sheets, and coils from amino acid sequences is essential for understanding protein function. This work presents a transformer-based model that applies attention mechanisms to protein sequence data to predict structural motifs. A sliding-window data augmentation technique is used on the CB513 dataset to expand the training samples. The transformer shows strong ability to generalize across variable-length sequences while effectively capturing both local and long-range residue interactions.