We need to set up two workspace for analyzing 1000 Genomes and SFARI - they will mirror each other in terms of data models and methods.
In particular, for each workspace we need to do following:
Choose samples and cohort/case sample division; create the data model
Set up gCNV cohort/case methods; import good hyperparameter values (or find them using cross validation) from previous runs and upload corresponding jsons
Finally add the validation script and run all samples through each tool and validation
We need to set up two workspace for analyzing 1000 Genomes and SFARI - they will mirror each other in terms of data models and methods.
In particular, for each workspace we need to do following: