Help With Binder Design Denoiser
Hi there, I've been using the google colab version of the program and wanted to know where do I key in the denoiser.noise_scale and denoiser.noise_scale_frame command on the code? Also would like to know how to filter i_pae results down to < 10. Thank you! Love the program, keep up the great work! :)
@sokrypton would be the best person to ask about doing this in colab!
Regarding i_pae filtering, from this file the i_pae is calculated as:
pae = prediction_result['predicted_aligned_error']
pae_interaction1 = np.mean( pae[:binderlen,binderlen:] )
pae_interaction2 = np.mean( pae[binderlen:,:binderlen] )
pae_binder = np.mean( pae[:binderlen,:binderlen] )
pae_target = np.mean( pae[binderlen:,binderlen:] )
pae_interaction_total = ( pae_interaction1 + pae_interaction2 ) / 2
Thanks for the help!
I tried keying in the denoiser function before the run_inference.py command and it always yields this error "test...traj.pdb not found". Not sure what to do here :/
opts.append(f"'contigmap.contigs=[{' '.join(contigs)}]'") opts += ["inference.dump_pdb=True","inference.dump_pdb_path='/dev/shm'"] opts.append("denoiser.noise_scale=0.5") opts.append("denoiser.noise_scale_frame=0.5")
print("mode:", mode) print("output:", full_path) print("contigs:", contigs)
opts_str = " ".join(opts) cmd = f"./RFdiffusion/run_inference.py {opts_str}" print(cmd)
In colab, when trying a binder design I always get this type of error:
No such file or directory: 'outputs/traj/mymodel_0_pX0_traj.pdb'
Aparently the outputs/traj/ is never created.
Does it work with the default example?
On Tue, Aug 8, 2023, 7:39 PM Alejandro Garciarrubio < @.***> wrote:
In colab, when trying a binder design I always get this type of error: No such file or directory: 'outputs/traj/mymodel_0_pX0_traj.pdb' Aparently the outputs/traj/ is never created.
— Reply to this email directly, view it on GitHub https://github.com/RosettaCommons/RFdiffusion/issues/40#issuecomment-1670450726, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA76LAVQVKRM2V3FPRHR4ILXULEZRANCNFSM6AAAAAAXRTLITI . You are receiving this because you were mentioned.Message ID: @.***>
Yes! It does run with the default example. In fact it was my mistake: a negative numeric range. Thank you
Thanks for the help!
I tried keying in the denoiser function before the run_inference.py command and it always yields this error "test...traj.pdb not found". Not sure what to do here :/
opts.append(f"'contigmap.contigs=[{' '.join(contigs)}]'") opts += ["inference.dump_pdb=True","inference.dump_pdb_path='/dev/shm'"] opts.append("denoiser.noise_scale=0.5") opts.append("denoiser.noise_scale_frame=0.5")
print("mode:", mode) print("output:", full_path) print("contigs:", contigs)
opts_str = " ".join(opts) cmd = f"./RFdiffusion/run_inference.py {opts_str}" print(cmd)
Hi there. Where should I key in the denoise command? Thanks in advance!