CoCoNet documentation¶
Citation (Work in progress)¶
Arisdakessian C., Nigro O., Steward 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 deep learning to abstract the modeling of the k-mer composition and the coverage for binning contigs assembled form viral metagenomic data. Specifically, our method uses a neural network to learn from the metagenomic data a flexible function for predicting the probability that any pair of contigs originated from the same genome. These probabilities are subsequently combined to infer bins, or clusters representing the species present in the sequenced samples. Our approach was specifically designed for diverse viral metagenomes, such as those found in environmental samples (e.g., oceans, soil, etc.).
Install¶
CoCoNet is available on PyPi and can be installed with pip:
pip3 install coconet-binning --user
Basic usage¶
CoCoNet is available as the command line program. For a list of all the options, open a terminal and run:
coconet run -h
For more details, please see the documentation on ReadTheDocs
Contribute¶
Contents