Skip to content

VAMB Specifications

Process Details

  • Name: VAMB
  • Process UUID: f931usxzlq5h3u2ac66umbnw872gqh
  • Process Group: Binning

Overview

VAMB (Variational Autoencoders for Metagenomic Binning) is a specialized binning tool designed for generating metagenome-assembled genomes (MAGs) from short-read sequencing data. This process performs unsupervised clustering of contigs to group them into bins representing individual microbial genomes based on sequence composition and abundance patterns across samples.

This process is implemented in Bash, which invokes Python scripts for creating FASTA files from binning results.

Key Functionality

  • Contig Binning: Groups assembled contigs into bins representing individual microbial genomes using variational autoencoder clustering
  • Abundance-based Clustering: Utilizes BAM alignment files to incorporate coverage information for improved binning accuracy
  • Quality Filtering: Applies minimum contig length and bin size thresholds to ensure high-quality output bins
  • FASTA Generation: Creates individual FASTA files for each bin containing the constituent contigs

Input/Output Specification

Inputs

Required Inputs

  • Input Directory
    • Description: Directory containing assembled contigs (FASTA format) and sorted BAM alignment files
    • Format: Directory

Outputs

  • Output Directory

    • Description: Directory containing individual bin FASTA files (bin.1.fa, bin.2.fa, etc.) and the original assembly
    • Format: Directory
  • Log File

    • Description: Process execution log containing directory listings and binning statistics
    • Format: Log file

Parameters & Settings

These parameters can be adjusted in the Foundry UI when running this process.

  • Minimum Contig Length

    • Description: Write the minimum expected contig length for VAMB to work on. The value should be an integer!
    • Default value: 2500
  • Minimum Bin Size

    • Description: Write the minimum expected bin size in total basepairs for VAMB output. The value should be an integer!
    • Default value: 500000
  • Flags

    • Description: For expert users; the VAMB flags can be entered here.
    • Default value: (empty)

References & Resources

  • Tool Documentation: Contact the team for details on create_fasta.py
  • Related Papers: Nissen, J.N., Johansen, J., Allesøe, R.L. et al. Improved metagenome binning and assembly using deep variational autoencoders. Nat Biotechnol 39, 555–560 (2021). https://doi.org/10.1038/s41587-020-00777-4