RuntimeError: _cdist_backward requires X1 to be contiguous about rfdesign

[jueseph]

Can you send the command you ran, and maybe the input pdb?

…

On Thu, Aug 11, 2022 at 12:02 PM philhuett ***@***.***> wrote: I have successfully hallucinated various proteins, but every so often I run into the following error: "RuntimeError: _cdist_backward requires X1 to be contiguous" (see picture attached below) It usually occurs when attempting to hallucinate shorter proteins or use fewer gradient steps. Looking at the job's output file, the job makes it to step 0 of the gradient descent before failing. Has this occurred to anyone else? [image: Picture1] <https://user-images.githubusercontent.com/91504340/184218170-98e5df38-aea2-4711-bd95-b1eb97831297.png> — Reply to this email directly, view it on GitHub <#15>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AABCU54ZL35MSSRZNUFSSQTVYVE2TANCNFSM56JHIWEA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[philhuett]

I emailed your uw email with all the files, let me know if you didn't get it.

In short, the command I ran was:

python ~/Thesis/RFDesign/hallucination/hallucinate.py
--pdb=$folder_with_pdb
--mask=2-10,A1-8,2-10
--out="$output_dir/TRIB1"
--num=100
--steps=g400

I re-ran the job with "--mask=20-40,A1-8,20-40 " and interestingly it is working now. Perhaps it has to do with the length of the hallucinated protein?

[philhuett]

Quick update:

Using various pdbs and trying different command parameters I have found that attempting to hallucinate a protein less than 26 amino acids in length gives me the aforementioned error. It does not have to do with the number of gradient steps, solely with the length (can anyone else try running a job with a desired protein length of less than 26 to corroborate?)

Hope this helps,
Philipp