I would like to know if the SV numbering scheme used in training data set is the same as the test data set, i.e., whether a variant in the test data will have the same SV number as in the training data.
Created by ThomasJi Hi Thomas,
The SV numbering will not be shared from the training to validation set (as there is effectively no overlap between the two in sequence space).
Phylotype numbering / IDs are, however, shared between the training and validation sets. Alpha diversity, CST assignments are also directly shared.
Cheers,
Jim
Drop files to upload
Sequence Variant Formatting in Testing Data page is loading…