A new method for binary classification of proteins with Machine Learning

TL;DR

This paper introduces a deep learning approach using pre-trained convolutional neural networks to classify protein structures from PDB data represented as images, aiming to improve accuracy in protein classification.

Contribution

The work applies and compares multiple pre-trained CNNs for protein structure classification, demonstrating the effectiveness of image-based deep learning methods in bioinformatics.

Findings

InceptionResNetV2 achieved the highest classification accuracy.

Pre-trained CNNs can effectively extract features from protein structure images.

The method outperforms traditional classification approaches.

Abstract

In this work we set out to find a method to classify protein structures using a Deep Learning methodology. Our Artificial Intelligence has been trained to recognize complex biomolecule structures extrapolated from the Protein Data Bank (PDB) database and reprocessed as images; for this purpose various tests have been conducted with pre-trained Convolutional Neural Networks, such as InceptionResNetV2 or InceptionV3, in order to extract significant features from these images and correctly classify the molecule. A comparative analysis of the performances of the various networks will therefore be produced.