EquiBind, a Deep Learning Model Capable of Finding Drugs 1000 Times Faster
New deep learning AI model called EquiBind is 1,000 times faster than existing models
A research team from the Massachusetts Institute of Technology built a geometric deep learning AI model called EquiBind that is 1,000 times faster than existing models at finding potential drug molecules. EquiBind is based on its predecessor, EquiDock, which specializes in binding two proteins using a technique developed by the late Octavian-Eugen Ganea, a recent MIT Computer Science and Artificial Intelligence Laboratory and Abdul Latif Jameel Clinic for Machine Learning in Health postdoc, who also co-authored the EquiBind paper. This EquiBind will significantly reduce the chances and costs of drug trial failures.
EquiBind, a new deep learning model:
The use of artificial intelligence (AI) has been increasing in various sectors of society, particularly the pharmaceutical industry. EquiBind is an extremely fast computational binding method that would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. EquiBind provides a unique solution to the docking problem that incorporates both pose prediction and binding site identification.
However, the process of drug discovery can be costly both financially and computationally, with billions of dollars poured into the process and over a decade of development and testing before final approval from the Food and Drug Administration. Before drug development can even take place, drug researchers must find promising drug-like molecules after successfully docking to the protein, the binding drug, also known as the ligand, can stop a protein from functioning.
It is the number of molecules that have potential drug-like traits is gargantuan, estimated to be around 1060. By comparison, the Milky Way galaxy has around 108 stars. The findings have already attracted the attention of industry figures, with hopes that they can be used to find treatments for lung cancer, leukemia, and gastrointestinal tumors. This EquiBind paper Geometric Deep Learning for Drug Binding Structure Prediction’, will be presented at the International Conference on Machine Learning (ICML).
More Trending Stories
- US$10k is Coming for Bitcoin! But What Awaits After That?
- Where is Andrej Karpathy Headed After Leaving Tesla’s ‘Autopilot’?
- Google’s AI is Not a Pro in Data Labeling! But the Comp Fails to Admit it
- How Law will Solve Metaverse Crimes? Who will be the Witness?
- AI Image Generators Like Dall.E and Imagen Steal Ideas from Humans
- From Model-Centric to Data-Centric, How the AI Ecosystem is Moving?
- Top 10 Mini Ethical Hacking Projects Aspirants Should Add in Resume
