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?
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.pyto prepare thepocket.pkl.When I run
sample_single_pocket.pywith--use_pharma True, taking as inputspocket.pkland 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: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?