Comments (8)
I got the same problem, I didn't find the solution yet.
from rosettafold2na.
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.
from rosettafold2na.
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?
from rosettafold2na.
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?
from rosettafold2na.
@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 #15
Running on GPU
Traceback (most recent call last):
File "RoseTTAFold2NA/network/predict.py", line 374, in
pred.predict(inputs=args.inputs, out_prefix=args.prefix, ffdb=ffdb)
File "RoseTTAFold2NA/network/predict.py", line 160, in predict
msa_i, ins_i = parse_fasta(a3m_i, rna_alphabet=is_rna, dna_alphabet=is_dna)
File "RoseTTAFold2NA/network/parsers.py", line 119, in parse_fasta
assert (np.all(msa<=31))
AssertionError
from rosettafold2na.
RNA MSA attached.
from rosettafold2na.
@fdimaio my bad. Just realised my alignment has lots of sequences with illegal bases:
-UCCCGUUCGUCUAGAGGCCUAGGACACCGCCCUUUCACGGCGGUAACAGGGGKUCGACU
CCCMUARGSGM-----
GUCCCCAUCGUCUAGAGGCCUAGGACACYGCCCUUUCACGGCGRYAACCGGGGUUCGAAU
:(
from rosettafold2na.
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 #13 ;-)
from rosettafold2na.
Related Issues (20)
- reprocess_rnac.pl - Out of memory HOT 1
- Please provide pre-processed files for RNA
- Error: (803.7) [makeblastdb] Blast-def-line-set.E.title HOT 3
- Cannot load Graphbolt C++ library HOT 2
- About whether RoseTTAFold2NA can generate multiple models?
- Downloading pre-trained weights
- Regression: run_RF2NA.sh - R:RNA.fa No such file or directory HOT 2
- NVTX functions not installed HOT 2
- A SOLUTION for Package Dependency Issues 📦 HOT 2
- run_RF2NA.sh: Logging issues HOT 2
- make_rna_msa.sh: line 9: [: missing `]' HOT 2
- UnboundLocalError: local variable 'is_ignore' referenced before assignment HOT 3
- dimaio/new_config: Conda environment needs to be activated
- UserWarning: Using torch.cross without specifying the dim arg is deprecated. HOT 1
- Unaccepted characters after Rfam-database-check HOT 4
- Antibody structure prediction HOT 1
- Is the training dataset exclusive and is it available?
- hardware requirements
- RNA Secondary Structure
- How the weight file is generated, and whether the code has been open-sourced
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rosettafold2na.