Open adimil opened 1 year ago
I got the same problem, I didn't find the solution yet.
Same here, though I'm getting @adimil 's 'CPU' error when I'm running on GPU:
RoseTTAFold2NA/network/parsers.py:116: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison
msa[msa == "U"] = 30
Running on GPU
Traceback (most recent call last):
File "RoseTTAFold2NA/network/predict.py", line 374, in <module>
pred.predict(inputs=args.inputs, out_prefix=args.prefix, ffdb=ffdb)
File "RoseTTAFold2NA/network/predict.py", line 250, in predict
self._run_model(Ls, msa_orig, ins_orig, t1d, t2d, xyz_t, xyz_t[:,0], alpha_t, same_chain, mask_t_2d, "%s_%02d"%(out_prefix, i_trial))
File "RoseTTAFold2NA/network/predict.py", line 256, in _run_model
seq, msa_seed_orig, msa_seed, msa_extra, mask_msa = MSAFeaturize(
File "RoseTTAFold2NA/network/data_loader.py", line 118, in MSAFeaturize
raw_profile = torch.nn.functional.one_hot(msa, num_classes=NAATOKENS)
RuntimeError: Class values must be smaller than num_classes.
How do I fix the "Class values must be smaller than num_classes." error?
msa size: torch.Size([6142, 1064]) num_classes: 32
It looks like I need to either reduce the msa size or increase NAATOKENS drastically... that does not sound right?
Hello, can you try the latest version? This was a bug where 32 was hardcoded. If this does not work, can you post your MSA?
@fdimaio I downloaded the package last week, so I just updated network/parsers.py and restarted predict.py.
I'm now getting the error from https://github.com/uw-ipd/RoseTTAFold2NA/issues/15
Running on GPU
Traceback (most recent call last):
File "RoseTTAFold2NA/network/predict.py", line 374, in
RNA MSA attached.
@fdimaio my bad. Just realised my alignment has lots of sequences with illegal bases: -UCCCGUUCGUCUAGAGGCCUAGGACACCGCCCUUUCACGGCGGUAACAGGGGKUCGACU CCCMUARGSGM----- GUCCCCAUCGUCUAGAGGCCUAGGACACYGCCCUUUCACGGCGRYAACCGGGGUUCGAAU
:(
Fixed this issue with a quick and dirty hack:
# remove RNA sequences with illegal characters from alignment
perl -ne ' if (/^>/) {$h = $_} else { if (/^[ NUCGA-]+$/i) {print $h, $_} }' my_crappy_RNA_file.afa > tRNA_Glu.afa
now fighting https://github.com/uw-ipd/RoseTTAFold2NA/issues/13 ;-)
Hello,
I am getting the following error message when running on GPU:
Or when running on CPU:
Do you have any idea what might cause this and how to fix?
Thanks!