Skip to content
DopeSwagYolo

// bio & health

AI in Biotech: Drug Discovery News and Explainers

News and explainers on AI drug discovery, AlphaFold and protein design, AI-first biotech companies, lab automation and clinical trials of AI-discovered drug candidates.

Latest in AI in Biotech

What we cover in AI in Biotech

This section follows how artificial intelligence is being applied to the discovery and design of medicines and proteins. Coverage spans structure-prediction models such as AlphaFold and generative tools that propose new molecules and proteins. It also covers AI-first biotech companies, automated laboratories, and clinical-trial results for candidates that AI helped find. AI tools used in patient care are covered in the AI in Medicine section.

The field has drawn both recognition and investment. The 2024 Nobel Prize in Chemistry was split between David Baker, for computational protein design, and Demis Hassabis and John Jumper of Google DeepMind, for protein structure prediction. Hassabis leads Isomorphic Labs, a drug design company. It said in May 2026 that it had raised $2.1 billion in a Series B round led by Thrive Capital. Established drugmakers are spending too. Nvidia and Eli Lilly said in January 2026 that they would jointly invest in an AI lab for drug discovery. They said the investment would be up to $1 billion over five years.

Clinical evidence remains limited. One closely watched candidate is Insilico Medicine's rentosertib, for the lung disease idiopathic pulmonary fibrosis. It began a Phase 3 trial in China in September 2026, according to its ClinicalTrials.gov record. The company says no regulator has approved it. A perspective article appeared in Nature Reviews Drug Discovery in August 2026. It judged the evidence that AI methods have had clinically relevant impact to be limited so far. Articles here state each candidate's trial phase and approval status precisely. They attribute company claims to the companies making them. They do not treat a promising model or an early trial as a cure.

AI in Biotech reference

AI in Biotech: common questions

What is AlphaFold used for?
AlphaFold is an AI system from Google DeepMind. It predicts the three-dimensional shape of a protein from its amino acid sequence. Researchers use the predictions to study how proteins work and what goes wrong in disease. The 2024 Nobel Prize announcement cited research on antibiotic resistance and on enzymes that break down plastic. A free public database cited more than 260 million predicted structures on its home page in October 2026.
Has AI discovered any drugs?
AI has produced drug candidates that are being tested in people, but none discussed here is approved. Rentosertib, whose target and molecule Insilico Medicine says were found with generative AI, entered Phase 3 in September 2026. In a 71-patient Phase 2a trial published in 2025, overall adverse-event rates were similar to placebo. But treatment-related events were more common on the drug. Insilico says no regulator has approved it. The drug is not on the FDA's 2026 novel drug approvals list through September 28.
How does AI drug discovery work?
Software trained on biological and chemical data is applied at several steps. One is ranking the proteins most likely to drive a disease. Another is predicting protein shapes. A third is generating candidate molecules that chemists then make and test. For rentosertib, Insilico Medicine reported taking roughly 18 months to go from target discovery to a preclinical candidate. A candidate must still go through preclinical testing and then, typically, Phase 1, 2 and 3 trials in people before approval can be sought.
Is AI going to cure cancer?
That is not something anyone can promise. AI is a research tool that may help scientists find and design drug candidates faster. It is not a treatment in itself. Cancer drug development is complicated by the way tumors vary, evolve and develop resistance, a 2026 perspective in BJC Reports notes. A separate 2026 perspective in Nature Reviews Drug Discovery found limited evidence so far that AI has had clinically relevant impact. Any candidate must still prove itself in trials.

Sources