PPR-Meta: a tool for identifying phages and plasmids from metagenomic fragments using deep learning

Abstract

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.

Microbiome-Informed Food Safety and Quality: Longitudinal Consistency and Cross-Sectional Distinctiveness of Retail Chicken Breast Microbiomes

“…Only samples with unique k-mer numbers Ն1,000 for Salmonella enterica were considered positive results (60). (iii) To reduce the false-positive Salmonella detection caused by Salmonella-like mobile genetic elements, such as plasmids and phages, that were present in non-Salmonella organisms, reads classified as "Salmonella enterica" by KrakenUniq were analyzed by PPR_Meta with default settings (77) to determine whether these sequences came from chromosomes, plasmids, or phages. Only samples with at least one chromosomal read classified as S. enterica were considered Salmonella positive.…”

<strong>Data Science in Unveiling COVID-19 Pathogenesis and Diagnosis: Evolutionary Origin to Drug Repurposing</strong>

“…A prediction model has been proposed to detect what kind of target or host a virus can infect [74]. A Bi-path CNN (Bi-PathCNN) [75] is used where each viral sequence is represented by a one-hot matrix for nucleotide bases and codons separately. Experimental outcome reports six genomes of SARS-COV-2 having high infection possibility (p-value¡0.05) to humans.…”

Host and infectivity prediction of Wuhan 2019 novel coronavirus using deep learning algorithm

“…Aiming to give reliable predicted hosts and potential of infecting human of novel virus, VHP could play an important role in public health service and provide strong assistance for take precautions of novel viruses which have potential to infect human.At the end of this report, we provide a brief description of VHP method and the verification of the algorithm. To construct the VHP model, we utilized a Bi-path Convolutional Neural Networks (BiPathCNN)(18), where each viral sequence was represented by one-hot matrix of its base and codon separately. Considering difference in input sequence lengths, two BiPathCNNs (BiPathCNN-A and BiPathCNN-B) were built for predicting hosts of viral sequences from 100 bp to 400 bp and 400 bp to 800 bp respectively.…”