training_data: Training set

training_dataR Documentation

Training set

Description

The training set is the expression profiles of a 15-gene panel from TCGA RNA-Seq pan-cancer (involving colon, gastric, and endometrial cancers) dataset.

Usage

training_data

Format

A dataframe with 1383 rows (tumor samples) and 16 columns (MSI status of tumor samples, and 15 gene features). The column names are as follows:

MSI_status

MSI_status

DDX27

DEAD-box helicase 27

EPM2AIP1

EPM2A interacting protein 1

HENMT1

HEN methyltransferase 1

LYG1

lysozyme g1

MLH1

mutL homolog 1

MSH4

mutS homolog 4

NHLRC1

NHL repeat containing E3 ubiquitin protein ligase 1

NOL4L

nucleolar protein 4 like

RNLS

renalase, FAD dependent amine oxidase

RPL22L1

ribosomal protein L22 like 1

RTF2

replication termination factor 2

SHROOM4

shroom family member 4

SMAP1

small ArfGAP 1

TTC30A

tetratricopeptide repeat domain 30A

ZSWIM3

zinc finger SWIM-type containing 3

Source

https://xenabrowser.net/datapages/


WangX-Lab/PreMSIm documentation built on Oct. 16, 2024, 1:40 a.m.