Macromolecule Classification Based on the Amino-acid Sequence

TL;DR

This paper applies deep learning models to classify amino acid sequences into DNA, RNA, protein, or hybrid classes, achieving nearly 99% accuracy using various neural network architectures.

Contribution

It introduces the use of NLP-inspired word embedding techniques for protein sequence classification with deep learning models.

Findings

Achieved 99% accuracy in classifying sequences

Compared CNN, LSTM, BiLSTM, and GRU architectures

Demonstrated effectiveness of NLP techniques in bioinformatics

Abstract

Deep learning is playing a vital role in every field which involves data. It has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using traditional machine learning techniques in the past. In this study we focused on classification of protein sequences with deep learning techniques. The study of amino acid sequence is vital in life sciences. We used different word embedding techniques from Natural Language processing to represent the amino acid sequence as vectors. Our main goal was to classify sequences to four group of classes, that are DNA, RNA, Protein and hybrid. After several tests we have achieved almost 99% of train and test accuracy. We have experimented on CNN, LSTM, Bidirectional LSTM, and GRU.