Snakemake rehaul #35
Closed
Snakemake rehaul #35
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| edge_feats: none # label, onehot, or none | ||
| drugs: | ||
| max_num_atoms: 150 | ||
| node_feats: label # label, onehot, glycan |
There was a problem hiding this comment.
another option is "IUPAC"
|
The esm-script raises the following error: Traceback (most recent call last):
File "/home/rjo21/Desktop/rindti/.snakemake/scripts/tmphxhv1pa3.prot_esm.py", line 38, in <module>
prots = generate_esm_python(prots)
File "/home/rjo21/Desktop/rindti/.snakemake/scripts/tmphxhv1pa3.prot_esm.py", line 22, in generate_esm_python
results = model(batch_tokens, repr_layers=[33], return_contacts=True)
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/esm/model.py", line 155, in forward
x, attn = layer(x, self_attn_padding_mask=padding_mask, need_head_weights=need_head_weights)
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/esm/modules.py", line 107, in forward
x, attn = self.self_attn(
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/rjo21/anaconda3/envs/gpcr/lib/python3.9/site-packages/esm/multihead_attention.py", line 359, in forward
attn_weights = torch.bmm(q, k.transpose(1, 2))
RuntimeError: [enforce fail at CPUAllocator.cpp:68] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 60985180160 bytes. Error code 12 (Cannot allocate memory)I also added a length restriction to the sequence length in generate_esm_python. Should be 1022. I know, esm-input is supposed to be of length 1024, but this doesn't work, raises error stating the sequence is too long |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #28, closes #25, closes #26, closes #28, closes #27, closes #19.
Massive overall rehaul, should be much more extensible and sane to use.