3CAC: improving the classification of phages and plasmids in metagenomic assemblies using assembly graphs

Abstract

Motivation Bacteriophages and plasmids usually coexist with their host bacteria in microbial communities and play important roles in microbial evolution. Accurately identifying sequence contigs as phages, plasmids and bacterial chromosomes in mixed metagenomic assemblies is critical for further unraveling their functions. Many classification tools have been developed for identifying either phages or plasmids in metagenomic assemblies. However, only two classifiers, PPR-Meta and viralVerify, were proposed to simultaneously identify phages and plasmids in mixed metagenomic assemblies. Due to the very high fraction of chromosome contigs in the assemblies, both tools achieve high precision in the classification of chromosomes but perform poorly in classifying phages and plasmids. Short contigs in these assemblies are often wrongly classified or classified as uncertain. Results Here we present 3CAC, a new three-class classifier that improves the precision of phage and plasmid classification. 3CAC starts with an initial three-class classification generated by existing classifiers and improves the classification of short contigs and contigs with low confidence classification by using proximity in the assembly graph. Evaluation on simulated metagenomes and on real human gut microbiome samples showed that 3CAC outperformed PPR-Meta and viralVerify in both precision and recall, and increased F1-score by 10–60 percentage points. Availability and implementation The 3CAC software is available on https://github.com/Shamir-Lab/3CAC. Supplementary information Supplementary data are available at Bioinformatics online.

Evaluation of computational phage detection tools for metagenomic datasets

“…Despite these limitations, we hope the developed benchmark may be informative to users and would be further developed to include new computational challenges. It should be noted that the results presented here are limited to those tools that could be installed and run by July 2021, and since then many more tools have been published [we are aware of 3CAC ( Pu and Shamir, 2022 ), DeepMicrobeFinder ( Hou et al, 2021 ), INHERIT ( Bai et al, 2022 ), PHAMB ( Johansen et al, 2022 ), PhaMer ( Shang et al, 2022 ), VirMine 2.0 ( Johnson and Putonti, 2022 ), and virSearcher ( Liu Q. et al, 2022 )]. Additionally, modular pipelines such as the IMG/VR viral discovery pipeline ( Paez-Espino et al, 2017 ) and computational pipelines combining several tools presented here, were not evaluated in this work but could be assessed using the same benchmark datasets developed here.…”

4CAC: 4-class classifier of metagenome contigs using machine learning and assembly graphs

“…In the 4CAC algorithm, we exploit the assembly graph to improve the initial classification by the following two steps. The description here follows [33].…”

Classification of bacterial plasmid and chromosome derived sequences using machine learning

“…PlasFlow [17] and PlasClass [13] are two previously published ML plasmid classifiers trained using logistic regression and a neural network, respectively. Both of the models perform best for fragments greater than 10kb, but are also compatible with 5-kb fragments classification.…”

“…Another promising approach to differentiating plasmid and chromosomal contigs is the use of machine learning (ML) techniques [14]. ML models can potentially learn unique sequence features that differentiate plasmids and chromosomes, and recently, several studies that use ML models to distinguish plasmid and chromosome sequences have been published [15][16][17][18]. For example, PlasFlow employs a neural network for identifying bacterial plasmid sequences in environmental samples and achieved accuracies of up to 96%.…”