Error When Running AlphaPanda

[aaaaaaaaa21-code]

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]

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: @.>

[aaaaaaaaa21-code]

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]

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: **@.***>

[aaaaaaaaa21-code]

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]

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: **@.***>

[aaaaaaaaa21-code]

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.