coconet-binning 0.2

A contig binning tool from viral metagenomes

Citation (Work in progress)

Arisdakessian C., Nigro O., Stewart G., Poisson G., Belcaid M. CoCoNet: An Efficient Deep Learning Tool for Viral Metagenome Binning

Description

CoCoNet (Composition and Coverage Network) is a binning method for viral metagenomes. It leverages the flexibility and the effectiveness of deep learning models to learn the probability density function of co-occurrence of contigs in the same genome and therefore provides a rigorous probabilistic framework for binning contigs. The derived probability are then used to compute an adjacency matrix for a subset of strategically selected contigs, and infer homogenous clusters representing contigs of the same genome.

Usage

CoCoNet is available in the command line. For a list of all the options, open a terminal and run:

python coconet.py run -h

For more details, please see the documentation on ReadTheDocs

Contribute

• Issue Tracker: github

• Source Code: github