Project title
Deep learning for protein-ligand binding affinity prediction
Collaborators and funding
-
School of Biomedical Sciences, The University of Western Australia
-
Molecular Endocrinology and Pharmacology, Harry Perkins Institute of Medical Research
This work is primarily supported by an Australian Government Research Training Program Scholarship at The University of Western Australia.
Contact(s)
- Caleb Thomas, The University of Western Australia, 21496215@student.uwa.edu.au
Project description and aims
The aim of this project is to train a deep learning model that can accurately predict binding affinity constants while robustly generalising to new protein and ligand types. If successful, this software would have great practical utility for drug development, with example applications including virtual screening for drug repurposing, or accelerating research into uncharacterised proteins by ranking candidate ligands. If the model’s predictions are accurate, this could save significant time and money that would otherwise be spent conducting high throughput screening experiments.
How is ABLeS supporting this work?
This work is supported through software accelerator scheme provided by ABLeS. The supports includes unlimited temporary storage on scratch, 3 TB long term storage and 50 KSUs per quarter.
Expected outputs enabled by participation in ABLeS
If the model training is successful, all associated materials (e.g. source code, weights, documentation) will be published as open source on GitHub. Additionally, we intend to store any publications on a preprint server such as arXiv or bioRxiv.
These details have been provided by project members at project initiation. For more information on the project, please consult the contact(s) or project links above.