Benjamin James

Since the data set size is very low (500 sequences), an easy workaround for now may be to provide alignment scores via `--align` instead of using the classification which doesn't...

Ok I had success, I manually specified the identity parameter to be anything above 0.9 and it worked. The alignment error message is a known bug, and I have been...

New commit should fix this issue

No solution yet, but am working on it Do you have data that caused the error? Thanks

Thanks

Not yet

Close, fixed in a few places but not in all cases yet

master should fix this bug

Thanks for the input From my experience, it looks like all the features contain the same values, giving a singular training matrix. I'll see what I can do