Vamb is a metagenomic binner which feeds sequence composition information from a contig catalogue and co-abundance information from BAM files into a variational autoencoder and clusters the latent representation. It performs excellently with multiple samples, and pretty good on single-sample data. Vamb is implemented purely in Python (with a little bit of Cython) and can be used both from command line and from within a Python interpreter.
module spider vamb to find out what environment modules are available for this application.
- HPC_VAMB_DIR - installation directory
- HPC_VAMB_BIN- executable directory