search

rdpstaff / classifier

RDP extensible sequence classifier for fungal lsu, bacterial and archaeal 16s
GNU General Public License v2.0
53 stars 32 forks source link

custom training data error #20

Open TurbulentCupcake opened 6 years ago

TurbulentCupcake commented 6 years ago

Hi RDP Team,

I have run into an issue while training the classifier with a custom dataset. I get an error similar to the followng :

Exception in thread "main" java.lang.IllegalArgumentException: Sequence GAXI01005455.1.1233 has different lowest rank: L_7 from the previous lowest rank: L_11 Any idea why this happens?

Edit : to elaborate, Im trying to train the RDP classifier with the SILVA v128 SSU Ref99 (available here : https://www.arb-silva.de/fileadmin/silva_databases/release_128/Exports/SILVA_128_SSURef_Nr99_tax_silva.fasta.gz). I rebuilt a taxonomy file from scratch using the lineage2taxTrain.py script.