Spaces:
Running
on
Zero
Apply for community grant: Academic project (gpu)
Accurate prediction of drug-target interactions (DTIs) is critical for advancing drug discovery.
By reducing time and cost, ML and DL can accelerate this discovery process.
Our approach utilises the powerful Barlow Twins architecture for feature-extraction while considering the structure of the target protein, achieving state-of-the-art predictive performance against multiple established benchmarks, while requiring only 1D input.
The use of GBM as the underlying predictor ensures fast and efficient predictions without the need for large computational resources.
We also investigate how the model reaches its decision based on the training samples.
In addition, we further benchmarked new baselines against existing methods.
Together, these innovations improve the efficiency and effectiveness of DTI predictions, providing robust tools for accelerating drug development and deepening the understanding of molecular interactions.
Therefore, we want to provide an easy-to-use web interface to the scientific community, which would be more enjoyable with GPUs. Thank you for consideration!
