Deep Learning Approach for Secondary Structure Protein Prediction based on First Level Features Extraction using a Latent CNN Structure
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 4
Abstract
In Bioinformatics, Protein Secondary Structure Prediction (PSSP) has been considered as one of the main challenging tasks in this field. Today, secondary structure protein prediction approaches have been categorized into three groups (Neighbor-based, model-based, and meta predicator-based model). The main purpose of the model-based approaches is to detect the protein sequence-structure by utilizing machine learning techniques to train and learn a predictive model for that. In this model, different supervised learning approaches have been proposed such as neural networks, hidden Markov chain, and support vector machines have been proposed. In this paper, our proposed approach which is a Latent Deep Learning approach relies on detecting the first level features based on using Stacked Sparse Autoencoder. This approach allows us to detect new features out of the set of training data using the sparse autoencoder which will have used later as convolved filters in the Convolutional Neural Network (CNN) structure. The experimental results show that the highest accuracy of the prediction is 86.719% in the testing set of our approach when the backpropagation framework has been used to pre-trained techniques by relying on the unsupervised fashion where the whole network can be fine-tuned in a supervised learning fashion.
Authors and Affiliations
Adil Al-Azzawi
Keywords
Related Articles
- EP ID EP258280
- DOI 10.14569/IJACSA.2017.080402
- Views 67
- Downloads 0
Laguerre Kernels –Based SVM for Image Classification
Support vector machines (SVMs) have been promising methods for classification and regression analysis because of their solid mathematical foundations which convey several salient properties that other methods hardly prov...
Extracting the Features of Modern Web Applications based on Web Engineering Methods
With the revolution of the information, an advanced version of the web proposed from web 1.0 to web 4.0. In each version, many web applications appeared. In the new versions, modern web applications (MWAs) proposed. Thes...
Spontaneous-braking and lane-changing effect on traffic congestion using cellular automata model applied to the two-lane traffic
In the real traffic situations, vehicle would make a braking as the response to avoid collision with another vehicle or avoid some obstacle like potholes, snow, or pedestrian that crosses the road unexpectedly. However,...
Implementation of Central Dogma Based Cryptographic Algorithm in Data Warehouse Architecture for Performance Enhancement
Data warehouse is a set of integrated databases deliberated to expand decision-making and problem solving, espousing exceedingly condensed data. Data warehouse happens to be progressively more accepted theme for contempo...
Quizzes: Quiz Application Development Using Android-Based MIT APP Inventor Platform
This work deals with the development of Android-based multiple-choice question examination system, namely: Quizzes. This application is developed for educational purposes, allowing the users to prepare the multiple choic...