I've been trying to use CMScaller on RNAseq data pulled from samples available through the PDMR website (https://pdmr.cancer.gov/database/default.htm). I am able to convert the gene symbols to entrez IDs, format the table to look like those found on the TCGA database, and omit "NAs" from the table, but I keep running into issues trying to classify the individual samples. Should I be using NTP if I am analyzing a single sample at a time? Moreover, is there a script I can run to ensure that my data set is correctly formatted to be recognized by the code?
I've been trying to use CMScaller on RNAseq data pulled from samples available through the PDMR website (https://pdmr.cancer.gov/database/default.htm). I am able to convert the gene symbols to entrez IDs, format the table to look like those found on the TCGA database, and omit "NAs" from the table, but I keep running into issues trying to classify the individual samples. Should I be using NTP if I am analyzing a single sample at a time? Moreover, is there a script I can run to ensure that my data set is correctly formatted to be recognized by the code?
Thank you, Jess