Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Error When Running AlphaPanda #1

Open
aaaaaaaaa21-code opened this issue Sep 20, 2024 · 6 comments
Open

Error When Running AlphaPanda #1

aaaaaaaaa21-code opened this issue Sep 20, 2024 · 6 comments

Comments

@aaaaaaaaa21-code
Copy link

Hello,

I’m interested in using the model, but I’m encountering an error when I try to run it. During execution, the data seq heavy seqmap prints information like:

{('B', 1, ' '): 0, ('B', 2, ' '): 1, ('B', 3, ' '): 2, ..., ('B', 16, ' '): 15, ...}

After that, the program fails with the following error:

Sampling: 0%| | 0/100 [00:06<?, ?it/s]
antibody.pdb-H_CDR1: 0%| | 0/2 [00:06<?, ?it/s]
Traceback (most recent call last):
File "design_AlphaPanda.py", line 4, in
design_for_pdb(args_from_cmdline())
File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/tools/runner/design_for_pdb.py", line 233, in design_for_pdb
traj_batch = model.sample(batch, sample_opt={
File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/models/diffab.py", line 134, in sample
traj = self.diffusion.sample(v_0, p_0, s_0, res_feat, pair_feat, mask_generate, mask_res, batch, **sample_opt)
File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 995, in sample
v_next, R_next, eps_p, c_denoised = self.eps_net(
File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 692, in forward
res_feat2=res_feat.reshape(L, self.res_feat_dim)
RuntimeError: shape '[128, 128]' is invalid for input of size 98304

I would greatly appreciate any assistance in identifying the cause of this RuntimeError and guidance on how to fix it.

Thank you!
@YueHuLab
Copy link
Owner

YueHuLab commented Sep 20, 2024 via email

@aaaaaaaaa21-code
Copy link
Author

Thanks for your attention. how about your input file？ 胡岳 @.***
…
---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:31 To YueHuLab/AlphaPanda @.> Cc Subscribed @.***> Subject [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) Hello, I’m interested in using the model, but I’m encountering an error when I try to run it. During execution, the data seq heavy seqmap prints information like: {('B', 1, ' '): 0, ('B', 2, ' '): 1, ('B', 3, ' '): 2, ..., ('B', 16, ' '): 15, ...} After that, the program fails with the following error: Sampling: 0%| | 0/100 [00:06<?, ?it/s] antibody.pdb-H_CDR1: 0%| | 0/2 [00:06<?, ?it/s] Traceback (most recent call last): File "design_AlphaPanda.py", line 4, in design_for_pdb(args_from_cmdline()) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/tools/runner/design_for_pdb.py", line 233, in design_for_pdb traj_batch = model.sample(batch, sample_opt={ File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/models/diffab.py", line 134, in sample traj = self.diffusion.sample(v_0, p_0, s_0, res_feat, pair_feat, mask_generate, mask_res, batch, **sample_opt) File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 995, in sample v_next, R_next, eps_p, c_denoised = self.eps_net( File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(input, kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 692, in forward res_feat2=res_feat.reshape(L, self.res_feat_dim) RuntimeError: shape '[128, 128]' is invalid for input of size 98304 I would greatly appreciate any assistance in identifying the cause of this RuntimeError and guidance on how to fix it. Thank you! — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.>

I input a PDB file of an antigen-antibody complex, where the B chain is the heavy chain of the antibody. I was able to successfully run Diffab with this PDB file.

@YueHuLab
Copy link
Owner

YueHuLab commented Sep 20, 2024 via email

@aaaaaaaaa21-code
Copy link
Author

you may design antibody once a time. The software only support design one structure in one run. Have a try. The checkpoint is a toy one. when published, we would make a useful checkpoint public. 胡岳 @.***
…
---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:46 To YueHuLab/AlphaPanda @.> Cc Yue Hu @.>, Comment @.> Subject Re: [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) Thanks for your attention. how about your input file？ 胡岳 @.*** … ---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:31 To YueHuLab/AlphaPanda @.> Cc Subscribed @.***> Subject [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) Hello, I’m interested in using the model, but I’m encountering an error when I try to run it. During execution, the data seq heavy seqmap prints information like: {('B', 1, ' '): 0, ('B', 2, ' '): 1, ('B', 3, ' '): 2, ..., ('B', 16, ' '): 15, ...} After that, the program fails with the following error: Sampling: 0%| | 0/100 [00:06<?, ?it/s] antibody.pdb-H_CDR1: 0%| | 0/2 [00:06<?, ?it/s] Traceback (most recent call last): File "design_AlphaPanda.py", line 4, in design_for_pdb(args_from_cmdline()) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/tools/runner/design_for_pdb.py", line 233, in design_for_pdb traj_batch = model.sample(batch, sample_opt={ File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/models/diffab.py", line 134, in sample traj = self.diffusion.sample(v_0, p_0, s_0, res_feat, pair_feat, mask_generate, mask_res, batch, **sample_opt) File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(args, kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 995, in sample v_next, R_next, eps_p, c_denoised = self.eps_net( File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(input, kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 692, in forward res_feat2=res_feat.reshape(L, self.res_feat_dim) RuntimeError: shape '[128, 128]' is invalid for input of size 98304 I would greatly appreciate any assistance in identifying the cause of this RuntimeError and guidance on how to fix it. Thank you! — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.> I input a PDB file of an antigen-antibody complex, where the B chain is the heavy chain of the antibody. I was able to successfully run Diffab with this PDB file. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

Thank you for your response. I tried modifying the input to include only the antibody's PDB, but the same error still occurs. I look forward to your new checkpoints.

@YueHuLab
Copy link
Owner

YueHuLab commented Sep 20, 2024 via email

@aaaaaaaaa21-code
Copy link
Author

Thanks. It not the only antibody pdb,but the complex pdb. Change the .yml file, to design 1 structure in a run. 胡岳 @.**
…
---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:58 To YueHuLab/AlphaPanda @.> Cc Yue Hu @.>, Comment @.> Subject Re: [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) you may design antibody once a time. The software only support design one structure in one run. Have a try. The checkpoint is a toy one. when published, we would make a useful checkpoint public. 胡岳 @.*** … ---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:46 To YueHuLab/AlphaPanda @.> Cc Yue Hu @.>, Comment @.> Subject Re: [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) Thanks for your attention. how about your input file？ 胡岳 @.*** … ---- Replied Message ---- From aaaaaaaaa21-code @.> Date 09/20/2024 16:31 To YueHuLab/AlphaPanda @.> Cc Subscribed @.***> Subject [YueHuLab/AlphaPanda] Error When Running AlphaPanda (Issue #1) Hello, I’m interested in using the model, but I’m encountering an error when I try to run it. During execution, the data seq heavy seqmap prints information like: {('B', 1, ' '): 0, ('B', 2, ' '): 1, ('B', 3, ' '): 2, ..., ('B', 16, ' '): 15, ...} After that, the program fails with the following error: Sampling: 0%| | 0/100 [00:06<?, ?it/s] antibody.pdb-H_CDR1: 0%| | 0/2 [00:06<?, ?it/s] Traceback (most recent call last): File "design_AlphaPanda.py", line 4, in design_for_pdb(args_from_cmdline()) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/tools/runner/design_for_pdb.py", line 233, in design_for_pdb traj_batch = model.sample(batch, sample_opt={ File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, *kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/models/diffab.py", line 134, in sample traj = self.diffusion.sample(v_0, p_0, s_0, res_feat, pair_feat, mask_generate, mask_res, batch, sample_opt) File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(args, kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 995, in sample v_next, R_next, eps_p, c_denoised = self.eps_net( File "/media/dell/newdisk/mambaforge/envs/AlphaPanda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(input, kwargs) File "/media/dell/newdisk/AlphaPanda-main/AlphaPanda/modules/diffusion/dpm_full.py", line 692, in forward res_feat2=res_feat.reshape(L, self.res_feat_dim) RuntimeError: shape '[128, 128]' is invalid for input of size 98304 I would greatly appreciate any assistance in identifying the cause of this RuntimeError and guidance on how to fix it. Thank you! — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.> I input a PDB file of an antigen-antibody complex, where the B chain is the heavy chain of the antibody. I was able to successfully run Diffab with this PDB file. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> Thank you for your response. I tried modifying the input to include only the antibody's PDB, but the same error still occurs. I look forward to your new checkpoints. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

Thank you for your help! After changing the design quantity to 1, it successfully ran.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@YueHuLab @aaaaaaaaa21-code