First of all, thank you for the good work.
It seems there are only 8406 sequences in the dataset directory "from_Rfam14.5". However, according to table 1 from the paper, this Rfam dataset should contain 9351 sequences. Could you explain why the number doesn't match, or am I misunderstanding something here?
Is this dataset with 8406 sequences the one actually used to report these F1 values in the paper?
First of all, thank you for the good work.
It seems there are only 8406 sequences in the dataset directory "from_Rfam14.5". However, according to table 1 from the paper, this Rfam dataset should contain 9351 sequences. Could you explain why the number doesn't match, or am I misunderstanding something here?
Is this dataset with 8406 sequences the one actually used to report these F1 values in the paper?