Protein Function Prediction: Combining Statistical Features with Deep Learning

4 Pages Posted: 11 Apr 2019

See all articles by Deepa Kumari

Deepa Kumari

National Institute of Technology (NIT), Patna

Ashish Ranjan

National Institute of Technology (NIT), Patna

Akshay Deepak

National Institute of Technology (NIT), Patna - Department of Computer Science and Engineering

Date Written: February 8, 2019

Abstract

Functional annotation of proteins to reduce gap between the available proteins and their known functional annotations based on protein sequences is a challenging task. This requires transformation of protein sequences into feature vectors for efficient analysis from computational perspective using machine learning algorithms. However, such transformation is difficult task due to high diversity among the protein sequences from the same family. Most existing sequence features performed low when annotating proteins with large number of functional classes. In this paper, three sequence features are combined with deep learning techniques for better performance. Evaluation scores show better results when combined with deep CNN. F1-score for PseAAC + CNN improves by a factor of +9.5% compared to PseAAC + DNN. The corresponding number for AAID + CNN and SGT + CNN is +3.22% and +2.33% respectively.

Keywords: Pseudo Amino Acid Composition (PseAAC), Amino Acid Index Distribution (AAID), Sequence Graph Transform (SGT), Deep Neural Network (DNN)

Suggested Citation

Kumari, Deepa and Ranjan, Ashish and Deepak, Akshay, Protein Function Prediction: Combining Statistical Features with Deep Learning (February 8, 2019). Proceedings of 2nd International Conference on Advanced Computing and Software Engineering (ICACSE) 2019. Available at SSRN: https://ssrn.com/abstract=3349575 or http://dx.doi.org/10.2139/ssrn.3349575

Deepa Kumari (Contact Author)

National Institute of Technology (NIT), Patna ( email )

Ashok Rajpath, Mahendru
Patna - 800005, Bihar
Patna, Bihar 800005
India

Ashish Ranjan

National Institute of Technology (NIT), Patna ( email )

Ashok Rajpath, Mahendru
Patna - 800005, Bihar
Patna, Bihar 800005
India

Akshay Deepak

National Institute of Technology (NIT), Patna - Department of Computer Science and Engineering ( email )

Ashok Rajpath, Mahendru
Patna, Bihar 800005
India

Register to save articles to
your library

Register

Paper statistics

Downloads
18
Abstract Views
171
PlumX Metrics