Korean team builds 7-million-entry AI dataset to speed drug discovery
In short
- The dataset holds more than 7 million chemical entries for screening candidate therapies.
- It was built under a Ministry of Science and ICT program for AI foundation models.
- The data covers 66 drug development tasks, including predicting how compounds behave.
Why it's good news
The dataset was built by SK Biopharmaceuticals within a medical AI consortium led by Lunit. It is designed around tasks researchers actually need in the lab. The source does not report any new drug reaching patients, so this is a tool for discovery rather than a treatment.
From The Korea Times
SK Biopharmaceuticals, a Korean firm focused on developing original prescription drugs, has built a massive artificial intelligence (AI) dataset of more than 7 million chemical entries to streamline candidate screening for new therapies. The project is part of the Ministry of Science and ICTβs program to develop AI foundation models for specific fields. A foundation model is a large AI model trained on vast amounts of data that can be adapted for many tasks. SK Biopharmaceuticals belongs to a medical and health care consortium led by medical AI firm Lunit, along with Trillion Labs, Kakao...