Background: Phages and plasmids are the major components of mobile genetic elements, and fragments from such elements generally co-exist with chromosome-derived fragments in sequenced metagenomic data. However, there is a lack of efficient methods that can simultaneously identify phages and plasmids in metagenomic data, and the existing tools identifying either phages or plasmids have not yet presented satisfactory performance. Findings: We present PPR-Meta, a 3-class classifier that allows simultaneous identification of both phage and plasmid fragments from metagenomic assemblies. PPR-Meta consists of several modules for predicting sequences of different lengths. Using deep learning, a novel network architecture, referred to as the Bi-path Convolutional Neural Network, is designed to improve the performance for short fragments. PPR-Meta demonstrates much better performance than currently available similar tools individually for phage or plasmid identification, while testing on both artificial contigs and real metagenomic data. PPR-Meta is freely available via http://cqb.pku.edu.cn/ZhuLab/PPR_Meta or https://github.com/zhenchengfang/PPR-Meta. Conclusions: To the best of our knowledge, PPR-Meta is the first tool that can simultaneously identify phage and plasmid fragments efficiently and reliably. The software is optimized and can be easily run on a local PC by non-computer professionals. We developed PPR-Meta to promote the research on mobile genetic elements and horizontal gene transfer.

Background: Prokaryotic viruses referred to as phages can be divided into virulent and temperate phages. Distinguishing virulent and temperate phage–derived sequences in metavirome data is important for elucidating their different roles in interactions with bacterial hosts and regulation of microbial communities. However, there is no experimental or computational approach to effectively classify their sequences in culture-independent metavirome. We present a new computational method, DeePhage, which can directly and rapidly judge each read or contig as a virulent or temperate phage–derived fragment. Findings: DeePhage uses a “one-hot” encoding form to represent DNA sequences in detail. Sequence signatures are detected via a convolutional neural network to obtain valuable local features. The accuracy of DeePhage on 5-fold cross-validation reaches as high as 89%, nearly 10% and 30% higher than that of 2 similar tools, PhagePred and PHACTS. On real metavirome, DeePhage correctly predicts the highest proportion of contigs when using BLAST as annotation, without apparent preferences. Besides, DeePhage reduces running time vs PhagePred and PHACTS by 245 and 810 times, respectively, under the same computational configuration. By direct detection of the temperate viral fragments from metagenome and metavirome, we furthermore propose a new strategy to explore phage transformations in the microbial community. The ability to detect such transformations provides us a new insight into the potential treatment for human disease. Conclusions: DeePhage is a novel tool developed to rapidly and efficiently identify 2 kinds of phage fragments especially for metagenomics analysis. DeePhage is freely available via http://cqb.pku.edu.cn/ZhuLab/DeePhage or https://github.com/shufangwu/DeePhage.

To characterize long non-coding RNAs (lncRNAs), both identifying and functionally annotating them are essential to be addressed. Moreover, a comprehensive construction for lncRNA annotation is desired to facilitate the research in the field. We present LncADeep, a novel lncRNA identification and functional annotation tool. For lncRNA identification, LncADeep integrates intrinsic and homology features into a deep belief network and constructs models targeting both full- and partial-length transcripts. For functional annotation, LncADeep predicts a lncRNA’s interacting proteins based on deep neural networks, using both sequence and structure information. Furthermore, LncADeep integrates KEGG and Reactome pathway enrichment analysis and functional module detection with the predicted interacting proteins, and provides the enriched pathways and functional modules as functional annotations for lncRNAs. Test results show that LncADeep outperforms state-of-the-art tools, both for lncRNA identification and lncRNA–protein interaction prediction, and then presents a functional interpretation. We expect that LncADeep can contribute to identifying and annotating novel lncRNAs. LncADeep is freely available for academic use at http://cqb.pku.edu.cn/ZhuLab/lncadeep/ and https://github.com/cyang235/LncADeep/. Supplementary data are available at Bioinformatics online.

Shine-Dalgarno (SD) signal has long been viewed as the dominant translation initiation signal in prokaryotes. Recently, leaderless genes, which lack 5'-untranslated regions (5'-UTR) on their mRNAs, have been shown abundant in archaea. However, current large-scale in silico analyses on initiation mechanisms in bacteria are mainly based on the SD-led initiation way, other than the leaderless one. The study of leaderless genes in bacteria remains open, which causes uncertain understanding of translation initiation mechanisms for prokaryotes.

Background: Metagenomic sequencing is becoming a powerful technology for exploring micro-ogranisms from various environments, such as human body, without isolation and cultivation. Accurately identifying genes from metagenomic fragments is one of the most fundamental issues. Results: In this article, we present a novel gene prediction method named MetaGUN for metagenomic fragments based on a machine learning approach of SVM. It implements in a three-stage strategy to predict genes. Firstly, it classifies input fragments into phylogenetic groups by a k-mer based sequence binning method. Then, protein-coding sequences are identified for each group independently with SVM classifiers that integrate entropy density profiles (EDP) of codon usage, translation initiation site (TIS) scores and open reading frame (ORF) length as input patterns. Finally, the TISs are adjusted by employing a modified version of MetaTISA. To identify protein-coding sequences, MetaGun builds the universal module and the novel module. The former is based on a set of representative species, while the latter is designed to find potential functionary DNA sequences with conserved domains. Conclusions: Comparisons on artificial shotgun fragments with multiple current metagenomic gene finders show that MetaGUN predicts better results on both 3' and 5' ends of genes with fragments of various lengths. Especially, it makes the most reliable predictions among these methods. As an application, MetaGUN was used to predict genes for two samples of human gut microbiome. It identifies thousands of additional genes with significant evidences. Further analysis indicates that MetaGUN tends to predict more potential novel genes than other current metagenomic gene finders.