Domains as words, genomes as documents.
Project description
nanotext
Name inspired by fastText.
Run tests:
cd .../nanotext/
pytest # or python setup.py test
TODO: turn embedding in gensim fmt into something similar to glove (bin?)
would then be easier to train/ unfreeze and then save again, to be loaded w/ some model eg for PUL prediction
https://github.com/plasticityai/magnitude
nanotext compute
takes annotation (load domains) and our model and computes vector
nanotext train corpus model
nanotext compare ...
nanotext search ...
nanotext taxonomy (calculate a gtdb based taxonomy and get closest functional genome and use that or distance)
like sourmash really
check sourmash publication
nanotext predict model=medium
nanotext predict model=pul
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nanotext-0.0.1.tar.gz
(5.7 kB
view hashes)
