Gene Prediction in Metagenomic Fragments with Deep Learning.

Journal: BioMed research international
Published Date: Nov 8, 2017

Abstract

Next generation sequencing technologies used in metagenomics yield numerous sequencing fragments which come from thousands of different species. Accurately identifying genes from metagenomics fragments is one of the most fundamental issues in metagenomics. In this article, by fusing multifeatures (i.e., monocodon usage, monoamino acid usage, ORF length coverage, and Z-curve features) and using deep stacking networks learning model, we present a novel method (called Meta-MFDL) to predict the metagenomic genes. The results with 10 CV and independent tests show that Meta-MFDL is a powerful tool for identifying genes from metagenomic fragments.

Authors

  • Shao-Wu Zhang
    College of Automation, Northwestern Polytechnical University, 710072, Xi'an, China, and Key Laboratory of Information Fusion Technology, Ministry of Education, 710072, Xi'an, China. zhangsw@nwpu.edu.cn.
  • Xiang-Yang Jin
    Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China.
  • Teng Zhang
    College of Veterinary Medicine, Hebei Agricultural University, Baoding, Hebei 071000, China.

Keywords

External Resources

Popular Topics
Recent Journals