Gene prediction in plasmid metagenomic short reads using deep learning




INTRODUCTION        
PlasGUN is the gene prediction tool for plasmid metagenomic short reads using deep learning. PlasGUN takes the short reads file in "fasta" format as input and output a tabular file that contains the coordinates of the predicted ORFs. This software is suitable for metagenomic data in which plasmid DNA is enriched using either experimental or computational approach. PlasGUN presents better performance on plasmid short read data than traditional tools, which are designed primarily for chromosomal short reads. Tests also showed that PlasGUN could identify more potential novel genes than other gene prediction tools, which was important for plasmid study.

Please direct your questions or comments to fangzc@pku.edu.cn or hqzhu@pku.edu.cn
DOWNLOAD        
DATA        
Data used to train and test PlasGUN, related results and scripts are stored at here
CITATION        
Zhencheng Fang, Jie Tan, Shufang Wu, Mo Li, Chunhui Wang, Yongchu Liu and Huaiqiu Zhu. PlasGUN: Gene prediction in plasmid metagenomic short reads using deep learning.
REFERENCES        

  • Hyatt,D. et al. (2012) Gene and translation initiation site prediction in metagenomic sequences. Bioinformatics, 28, 2223-2230.

  • Liu,Y. et al. (2013) Gene prediction in metagenomic fragments based on the SVM algorithm. BMC Bioinformatics, 14, S12.

  • Noguchi,H. et al. (2008) MetaGeneAnnotator: detecting species-specific patterns of ribosomal binding site for precise gene prediction in anonymous prokaryotic and phage genomes. DNA Res., 15, 387-396.

  • Rho,M. et al. (2010) FragGeneScan: predicting genes in short and error-prone reads. Nucleic Acids Res., 38, e191.

  • Zhu,W. et al. (2010) Ab initio gene identification in metagenomic sequences. Nucleic Acids Res., 38, e132.


Lastest update on July 15th, 2019 Department of Biomedical Engineering and Center for Quantitative Biology, PKU