I am trying to build a features matrix to be used for Random Forest based classification. I'd like to add, as features, short motifs which are common to all the protein sequences belonging to a specific gene family.
I tried to use MEME but I'd like to know if there are also other good tools (online or command line). Keep in mind I have more than 10.000 sequences and that I prefer short motifs (3/4 aa long).