CogMol: Framework developed by IBM based on deep learning to accelerate therapeutic developments for COVID-19

The global novel Coronavirus (COVID-19) pandemic is rapidly evolving and expanding. There is still a lot of news coverage about community spread every day. While the medical diagnostic companies were successfully able to develop a rapid test for COVID-19, but the therapeutic developments are still far away. The traditional drug discovery process could take up to 10 years and can cost as much as $2billion.

To deal with new infectious diseases, including viral outbreaks and epidemics, such as COVID-19, we need more rapid drug discovery processes. While Generative AI models have shown good signs for automating the discovery of molecules, they are not efficient in handling design tasks with multiple discovery constraints, have limited exploratory and expansion capabilities, and require expensive model retraining to learn beyond limited training data.

With a vision to help the researchers to accelerate therapeutic developments for infectious diseases like COVID-19, the IBM Research team have developed a framework (CogMol) based on deep learning generative modeling. CogMol has been developed to overcome the challenges for available Generative AI models to create novel peptides, proteins, drug candidates, and materials. Through their new AI frameworks like CogMol, the IBM research team believes that by releasing these novel molecules, the research and drug design communities can accelerate the process of identifying promising new drug candidates for coronavirus and potential similar, new outbreaks.


In their research paper the author explains how the research team applies this framework to three relevant proteins of the SARS-CoV-2, the virus responsible for COVID-19, namely non-structural protein 9 (NSP9) replicase, main protease, and the receptor-binding domain (RBD) of the S protein. Docking to the target proteins demonstrate the potential of these generated molecules as ligands.

How it works

1. Select a biological target and filter generated molecules by important characteristics

2. View related molecules and nearest match in PubChem

3. See relationships among molecules

4. Save and export your findings for further evaluation


Web Page:

Asif Razzaq is the CEO of Marktechpost Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.

๐Ÿ Join the Fastest Growing AI Research Newsletter Read by Researchers from Google + NVIDIA + Meta + Stanford + MIT + Microsoft and many others...