search

gcorso / DiffDock

Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
https://arxiv.org/abs/2210.01776
MIT License
976 stars 238 forks source link

Installation issue #213

Open SaveenaSolanki opened 2 months ago

SaveenaSolanki commented 2 months ago

After creating environment and all the dependencies the final command line python3 -m inference.py --config default_inference_args.yaml --protein_ligand_csv data/protein_ligand_example_csv.csv --out_dir results/user_predictions_small

give error terminate called after throwing an instance of 'std::bad_alloc' what(): std::bad_alloc Aborted (core dumped)

any solution for this ?

one more thing if we have multiple ligand for single PDB how to smoothly run for those?

tornikeo commented 2 months ago

It'd be nice to get a full traceback, not just the last error that you've encountered.

jsilter commented 2 months ago

We changed the name of the example CSV and forgot to update the README, that has now been updated. The correct command is:

python3 -m inference --config default_inference_args.yaml --protein_ligand_csv data/protein_ligand_example.csv --out_dir results/user_predictions_small

For multiple ligands, you could create a CSV with the same PDB repeated across multiple rows and different ligand files. If you mean multiple ligands at the same time, you'd need to combine them into one SDF file.

SaveenaSolanki commented 2 months ago

I hope this email finds you well. I want to express my gratitude for promptly addressing the previous issue.

I have another query regarding the utilization of multiple SMILEs and their respective fragments for SMILE, along with experimental PDB data. I aim to employ a different docking procedure to assess the confidence scores for these SMILEs and PDB data compared to their fragments and PDB. Consequently, I will have a diverse dataset comprising multiple SMILEs, Fragments, and PDB data.

Could you kindly provide guidance on the optimal approach for running DiffDock in this scenario? Currently, I have DiffDock set up, and I'm contemplating whether updating the dataset in the input file would suffice for seamless operation.

Thanks & Regards,

Saveena Solanki Ph.D. Scholar The Chemosensory Lab Department of Computational Biology (IIITD)

On Fri, Apr 26, 2024 at 8:24 PM Jacob Silterra @.***> wrote:

We changed the name of the example CSV and forgot to update the README, that has now been updated. The correct command is:

python3 -m inference --config default_inference_args.yaml --protein_ligand_csv data/protein_ligand_example.csv --out_dir results/user_predictions_small

For multiple ligands, you could create a CSV with the same PDB repeated across multiple rows and different ligand files. If you mean multiple ligands at the same time, you'd need to combine them into one SDF file.

— Reply to this email directly, view it on GitHub https://github.com/gcorso/DiffDock/issues/213#issuecomment-2079554562, or unsubscribe https://github.com/notifications/unsubscribe-auth/A3B3YNOJDBVIYBUGW6SLTXLY7JTDPAVCNFSM6AAAAABGDZBK2WVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANZZGU2TINJWGI . You are receiving this because you authored the thread.Message ID: @.***>

velocirraptor23 commented 1 month ago

ok. what why it was killed it was working before the update and then after not anymore, I was not sure, I almost gave up. I will reinstall the things