Skip to content

error when running sample_single_pocket.py with --use_pharma False #4

@adrienchaton

Description

@adrienchaton

Hello and thanks for sharing your work!

I am happy that it runs with my custom protein pdb and ligand sdf.
Since they were already split, I only needed to run scripts/prepare_single_complex.py to prepare the pocket.pkl.

When I run sample_single_pocket.py with --use_pharma True, taking as inputs pocket.pkl and the ligand sdf used at the preparation step, it goes through and I get the results saved as expected.

If I do the same, keeping the inputs of the previous job, but switching --use_pharma False, the script crashes during preprocessing of the inputs:

  File "scripts/sample_single_pocket.py", line 205, in <module>
    ref_coords,ref_type_one_hot = prepare_pharama_bacth(ref_positions,ref_node_type, batch_node,args.device)
  File "scripts/sample_single_pocket.py", line 88, in prepare_pharama_bacth
    x[i:i + end_index] = x_values
RuntimeError: The expanded size of the tensor (24) must match the existing size (32) at non-singleton dimension 0.  Target sizes: [24, 3].  Tensor sizes: [32, 3]

In this case, the ligand in my sdf has 32 atoms. I am not sure what is being wrongly extracted with size 24 though...

Did I miss anything specific to running sampling without extracting pharmacophores please?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions