AI drug discovery will have to deliver medicines that are faster, cheaper and better to justify its promise, oncologist and Manas AI chief executive Siddhartha Mukherjee told the Hindustan Times Leadership Summit. He described how his company combines AI with the rules of physics and chemistry to design drug candidates, and gave a striking account of the speed involved.
Watch Desk analysis
What happened
Mukherjee said Manas AI uses a “design-make-test” cycle: it proposes compounds for chemical companies to test, then uses the returned data to improve the next batch. He said the company sends 50 to 100 proposed compounds every three weeks and gets test data back in about three weeks.
He also cited a pancreatic-cancer drug example, saying a human researcher took about ten years to find the relevant protein-binding “keyhole”, while Manas AI’s algorithm found it in two hours. That is Mukherjee’s account of the work, not independent evidence that the overall drug-development process has been shortened by the same factor.
Why it matters
Drug discovery is a demanding test for AI: a promising prediction still has to survive laboratory work and, ultimately, clinical development. Mukherjee’s description offers a concrete view of how AI might fit into that process, rather than asking readers to settle for the word “revolution” and a dramatic backdrop.
The potential stakes are substantial. Mukherjee argued that medicines have become more expensive as approvals have declined over time, and said AI should be judged on whether it can help reverse that trend. His talk did not establish that it has.
Our read
The useful detail is the repeated design, testing and learning cycle, not the headline-grabbing two-hour comparison on its own. If the approach produces candidates more quickly, that could matter; whether it leads to better or cheaper medicines is the harder question, and the evidence here is Mukherjee’s account of his company’s work.
What to watch
- Whether Manas AI publishes evidence about the compounds and targets it is working on.
- How proposed compounds fare in subsequent testing and clinical development.
- Whether AI-assisted discovery leads to medicines that are genuinely faster, cheaper or better.
Discussion spark: Should AI drug-discovery companies be judged first on how quickly they find promising targets, or only on whether those targets lead to better, cheaper medicines?
Sources and evidence
- Medicine is AI’s real test, and India has a historic opportunity: Siddhartha Mukherjee | India News (14 November 2026, 13:09 UTC)
Watch Desk is operated by WittyWires as an independent cross-cutting AI news tracker. It does not speak for the organisations or people it covers.