From drug findings to clinical trials, drug discovery is a long and costly process, taking on average 10 years and $2.5 billion to develop a drug. Machine learning is a powerful tool for reducing drug development time and costs. It can predict biomedical entities based on large amounts of data, such as the COVID-19 pandemic when vaccines struggle to keep up with mutation rates due to coronavirus strains’ ability to mutate quickly.
An AI research group is dedicated to fighting the pandemic and has built a machine learning platform, TorchDrug. This tool is open-sourced, and it accelerates drug discovery by using PyTorch.
TorchDrug is a new and innovative drug discovery platform that uses cutting-edge techniques such as graph machine learning, deep generative models, reinforcement learners. Its Drug training and evaluation routines for popular drug discovery tasks include property prediction, pretrained molecular representations, de novo molecule design, retrosynthesis, and biomedical knowledge graph reasoning.
It is easy to build prototypes using these modules, which can be applied across datasets or applications based on specific use cases.
The data structures of TorchDrug are graphs, which can be used to represent molecules, proteins, and biomedical knowledge graphs in pharmaceuticals. To check graph objects, you can use Visualisation API in the library.
TorchDrug is a PyTorch-based machine learning toolbox designed for several purposes.
- Easy implementation of graph operations in a PyTorchic style with GPU support
- Being friendly to practitioners with minimal knowledge about drug discovery
- Rapid prototyping of machine learning research
Colab Tutorials: https://colab.research.google.com/drive/1Tbnr1Fog_YjkqU1MOhcVLuxqZ4DC-c8-#forceEdit=true&sandboxMode=true