Exploring The Potential Of GANs In Biological Sequence Analysis

TL;DR

This paper investigates the use of Generative Adversarial Networks (GANs) to generate synthetic data for biological sequence analysis, aiming to address data imbalance issues and improve classification accuracy across multiple datasets.

Contribution

It introduces a novel GAN-based data augmentation method specifically designed for biological sequence datasets to enhance machine learning classification performance.

Findings

GANs effectively generate realistic synthetic data

Improved classification accuracy on multiple biological datasets

GAN-based augmentation outperforms traditional methods like SMOTE

Abstract

Biological sequence analysis is an essential step toward building a deeper understanding of the underlying functions, structures, and behaviors of the sequences. It can help in identifying the characteristics of the associated organisms, like viruses, etc., and building prevention mechanisms to eradicate their spread and impact, as viruses are known to cause epidemics that can become pandemics globally. New tools for biological sequence analysis are provided by machine learning (ML) technologies to effectively analyze the functions and structures of the sequences. However, these ML-based methods undergo challenges with data imbalance, generally associated with biological sequence datasets, which hinders their performance. Although various strategies are present to address this issue, like the SMOTE algorithm, which creates synthetic data, however, they focus on local information rather than the overall class distribution. In this work, we explore a novel approach to handle the data imbalance issue based on Generative Adversarial Networks (GANs) which use the overall data distribution. GANs are utilized to generate synthetic data that closely resembles the real one, thus this generated data can be employed to enhance the ML models' performance by eradicating the class imbalance problem for biological sequence analysis. We perform 3 distinct classification tasks by using 3 different sequence datasets (Influenza A Virus, PALMdb, VDjDB) and our results illustrate that GANs can improve the overall classification performance.