name: maxbin2
description: MaxBin is a software that is capable of clustering metagenomic contigs
keywords:
  - metagenomics
  - assembly
  - binning
  - maxbin2
  - de novo assembly
  - mags
  - metagenome-assembled genomes
  - contigs
tools:
  - maxbin2:
      description: MaxBin is software for binning assembled metagenomic sequences based on an Expectation-Maximization algorithm.
      homepage: https://sourceforge.net/projects/maxbin/
      documentation: https://sourceforge.net/projects/maxbin/
      tool_dev_url: https://sourceforge.net/projects/maxbin/
      doi: "10.1093/bioinformatics/btv638"
      licence: ['BSD 3-clause']

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - contigs:
      type: file
      description: Multi FASTA file containing assembled contigs of a given sample
      pattern: "*.fasta"
  - reads:
      type: file
      description: Reads used to assemble contigs in FASTA or FASTQ format. Do not supply at the same time as abundance files.
      pattern: "*.fasta"
  - abund:
      type: file
      description: Contig abundance files, i.e. reads against each contig. See MaxBin2 README for details. Do not supply at the same time as read files.

output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - binned_fastas:
      type: file
      description: Binned contigs, one per bin designated with numeric IDs
      pattern: "*.fasta.gz"
  - summary:
      type: file
      description: Summary file describing which contigs are being classified into which bin
      pattern: "*.summary"
  - log:
      type: file
      description: Log file recording the core steps of MaxBin algorithm
      pattern: "*.log.gz"
  - marker:
      type: file
      description: Marker gene presence numbers for each bin
      pattern: "*.marker.gz"
  - unbinned_fasta:
      type: file
      description: All sequences that pass the minimum length threshold but are not classified successfully.
      pattern: "*.noclass.gz"
  - tooshort_fasta:
      type: file
      description: All sequences that do not meet the minimum length threshold.
      pattern: "*.tooshort.gz"
  - marker_genes:
      type: file
      description: All sequences that do not meet the minimum length threshold.
      pattern: "*.marker_of_each_gene.tar.gz"

authors:
  - "@jfy133"