README.md

In crarlus/data4paprbag: Trained classifiers for Pathogenicity Prediction for Bacterial Genomes

data4paprbag

This package provides trained classifiers to be used together with the package paprbag.

Available data

Data is stored in directory data

• classifier_small_foldX.rda provides a trained pathogenicity classfier for cross validation fold X. The small classifier was built from 200,000 training reads

• labels_foldX.rda provides a list of Bioproject accessions and their associated pathogenicity phenotype for the bacterial strains trained in fold X

• Labels.rda provides a list of all Bioproject accessions and their associated labels.

• classifier_foldX.rda The large classifiers for cross validation fold X are supplied in the release.

Note that each large classifier is approx. 250 MB and the package itsself (without the large classifiers) is 141 MB.

Usage

Either download and install the package (via devtools::install_github("crarlus/data4paprbag"))

or

manually download the files of your choice from directory data and the release tab.

crarlus/data4paprbag documentation built on May 14, 2019, 11:31 a.m.