Hello, The patients listed in the clinical files have IDs such as "MMRF_1157", but in the RNA-seq gene expression data sets, the column headers contain IDs such as "MMRF_1157_4_BM". I understand how to deal with this in the training data, but I do not know what to expect for the column headers in the validation data. Are we safe in assuming that the IDs in the clinical validation file and the column headers in the gene expression validation data will match verbatim? If not, what will the format be? Thanks! -Tony

Created by Tony Szedlak tonyszedlak
Yes, of course. Now I understand. Thanks a lot!
Dear Tony, In addition to the Patient column there are separate colums MA_geneLevelExpFileSamplId , RNASeq_transLevelExpFileSamplId and RNASeq_geneLevelExpFileSamplId providing the header id matching the patient in that data type. please read through [this portion of the challenge wiki(https://www.synapse.org/#!Synapse:syn6187098/wiki/449441) for more details.

Will clinical IDs and column headers match in the validation data? page is loading…