example.data: Example datasets

example.dataR Documentation

Example datasets

Description

This data list, example.data, includes three datasets generated based on Saturation mutagenesis results (M. Kircher, et al.,2019) and the DeepSEA features (Zhou & Troyanskaya, 2015). The training and testing datasets in the data list include binary response vectors, which are truncations of the P values of tissue K562 from the Saturation mutagenesis results, and reduced versions of the DeepSEA features for a faster computational demonstration. The full.data dataset includes the original P values, chromosome and allelic information, and the complete DeepSEA features.

Usage

example.data

Format

The example.data$train.data and example.data$test.data are dataframes with 220 and 1574 observations and 146 variables.

response

A binary response vector

features

Standardized 145 DeepSEA features

The example.data$full.data is a dataframe with 1794 observations and 924 variables, i.e., including all 919 DeepSEA features.

chr

The chromosome of SNPs

pos

The position of SNPs

ref.alt

The reference and alternative alleles of SNPs

p.value

The P value of SNPs

features

The original 919 DeepSEA features


Iuliana-Ionita-Laza/PO.EN documentation built on April 19, 2022, 7:10 a.m.