Metadata-Version: 2.1
Name: Xlassify
Version: 0.0.0
Summary: An alignment-free deep-learning model trained to classify human gut bacteria
Home-page: https://github.com/SenseTime-Knowledge-Mining/Xlassify
Author: kangkun
Author-email: maokangkun@pjlab.org.cn
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/SenseTime-Knowledge-Mining/Xlassify/issues
Keywords: Xlassify,genome,microbiome,taxonomic,bacteria
Platform: any
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7.1
Description-Content-Type: text/markdown
License-File: LICENSE

# Xlassify

Fast and accurate taxonomic classification of bacteria genomes is a key step in human gut microbiome analysis. Here we propose Xlassify, an alignment-free deep-learning model that is specifically trained to classify human gut bacteria.

Xlassify demonstrated 98% accuracy in UHGG genomes dataset and \~90% accuracy on an independent testset of 76 gut bacterial genomes isolated from healthy Chinese individuals. Better than alignment-based methods such as GTDBTk, Xlassify requires only <4GB of memory and reaches thirty-second-per-genome speed on a single CPU.