Predicting the molecular binding activity of organic molecules to specific receptors using QSAR machine learning models.
Virtual screening techniques such as this one reduce the costs of drug discovery by reducing the number of potential drugs that undergo high throughput screening. This project shows that machine learning models can effectively predict drug candidates from a drug's molecular quantitative structure-activity relationship (QSAR) data.
The code is provided in a ipynb file, which takes a while to run. An in depth description of this project in scientific paper format is provided as well.