Hi, We have been testing our models with the new filtered data, but we have found that all files from training strelka indel vcf files are empty... Could this be a issue on the provided data or simply that column is "useless" for genomic based prediction? Best Regards

Created by Ruben Rodrigues rrodrigues
HI Ruben, Many of the Strelka files were very small since I believe that they already have some internal filtering. The original unfiltered files are still there in the same location as the filtered so you can use them if you like. They have the same name as the filtered but with a ".FILTERED" inserted. If you remove "FILTERED" and one dot on either side (but not both sides) you should be good just don't forget to escape the "." since it is a special character (something like gsub("\\.FILTERED", "", filename) in R).

Sub challenge 1 - training WES_mutationFileStrelkaIndel FILTERED VCF files without any data page is loading…