design: The design matrix
In jpvert/kmr4toxicogenetics: Kernel multitask regression for toxicogenetics

The design matrix processed from the Dream 8 toxicogenetics challenge dataset.

design

A data frame with 884 cell lines in rows and 1,237 variables in columns of three categories:

covariate: 16 variables binarized from 3 attributes (sex, population, batch) characterizing the nature of cell lines provided by the challenge.
RNAgram: 337 variables corresponding to RNA Gram matrix (linear kernel) of normalized and NA-fixed RNA-seq counts of cell lines.
SNPgram: 884 variables corresponding to genotypic SNP distance matrix (squared Euclidean distance) of SNP data of cell lines.

RNA-seq data are available only for 337 cells from the challenge.

jpvert/kmr4toxicogenetics documentation built on May 24, 2019, 2:04 a.m.