Metadata-Version: 1.1
Name: deepsignal
Version: 0.1.6
Summary: A deep-learning method for detecting DNA methylation state from Oxford Nanopore sequencing reads
Home-page: https://github.com/bioinfomaticsCSU/deepsignal
Author: Peng Ni, Neng Huang
Author-email: 543943952@qq.com
License: GNU General Public License v3 (GPLv3)
Download-URL: https://github.com/bioinfomaticsCSU/deepsignal/archive/v0.1.6.tar.gz
Description-Content-Type: UNKNOWN
Description: deepsignal
        ==========
        
        
        Documentation
        -------------
        
        v0.1.6
        -------------
        add option --positions in extract_features module,
        add option/function of binary_format feature file to speed up training
        
        v0.1.5
        -------------
        normalize probs before output
        
        v0.1.4
        -------------
        change the loss function to weighted_cross_entropy_with_logits,
        allow training using unbalanced samples.
        
        v0.1.3
        -------------
        fix the deadlock issue in multiprocessing
        
        v0.1.2
        -------------
        add MANIFEST.in file
        
        v0.1.1
        -------------
        3 modules (extract, call_mods, train) supported
Keywords: methylation,nanopore,neural network
Platform: any
Classifier: Programming Language :: Python :: 3
Classifier: Development Status :: 4 - Beta
Classifier: Natural Language :: English
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
