Detection of thermophilic proteins using deep learning
Loading...
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UMT Lahore
Abstract
Bio informatics has made significant advancements in recent years, particularly in the study of thermophiles. Neural Networks may be able to fill the inherent gaps and limitations in machine learning techniques. In proteomics and genomics, deep learning (DL) and neural networks have gained appeal due to their capacity to unearth complex correlations that are concealed in vast amounts of biological data. This study began by examining state-of-the-art statistical techniques for finding thermophiles. According to studies, machine learning techniques and a range of feature extraction techniques are used in the majority of the work done to predict the thermophiles sites. There are various issues and restrictions with these machine learning-based forecasts that required to be resolved. A possible method to improve the reliability of thermophilic protein predictions is deep learning. Chou’s five-step rule is used in this paper to include a deep learning-based method for better prediction of thermophilic proteins. the deep learning methodology uses the gated recurrent unit, long short-term memory unit, and convolutional neural network. the results show a dataset improvement with the highest accuracy at 86% using the FCN model