Additional file 9 of MRF: a tool to overcome the barrier of inconsistent genome annotations and perform comparative genomics studies for the largest animal DNA virus

Additional file 9. Sheet 1. The data used for running random forest machine learning model. Only the coding sequences (CDS) that were deleted in all isolates of a phylogenetic cluster are used for this analysis. The CDS gets a code of 1 or 0 based on the presence or deletion respectively in an isolate. Sheet 2. The deletion pattern of certain CDS is same as that of others. Hence the redundant CDS are removed from analysis. This sheet contains the non-redundant data actually used in running random forest model. Sheet 3. List of genes displaying similar deletion trends as that of other genes. Sheet 4. The feature importance extracted in random forest machine learning model.