Applications of Deep learning models in Bioinformatics

Abstract

Deep learning (DL) models have had an influence on machine learning-based in bioinformatics applications since they allow for the learning of complicated non-linear interactions between functionalities. Deep learning models also enable information utilized from large unlabeled data that is unrelated to the problem under investigation. Protein-protein interactions (PPIs) are important in a variety of biological functions, including cell signaling, immune function, and cellular organization. PPIs analysis is thus vital, as it may spotlight the detection of targeted proteins and their role in the disease and thus help in designing treatments for it. PPIs play critical roles in life processes, and abnormal interactions are linked to a variety of disorders. Identification of interaction sites is critical for understanding disease mechanisms and designing new drugs. Because of the overall cost of experimental methods, effective and efficient computational methods for PPI prediction are extremely valuable. Machine learning and deep learning techniques have produced remarkable results, but their efficacy is highly reliant on protein interpretation and feature extraction. This chapter will explain various deep learning models that can be used in Bioinformatics as well as the challenges they face.

A novel optimized deep learning method for protein-protein prediction in bioinformatics

“…Using advanced techniques to calculate PPI is not only laborious and costly, but it also produces an excessive number of false positives and false negatives [7], [8]. As a result, computational tools that can aid in the process of discovering genuine protein interactions are required.…”