How AI helps scientists design the next generation of medicines

2026-07-23 · Source: MIT Technology Review · Field: Health & Wellbeing — Pharmaceuticals & Biotechnology, Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Advanced, medium

Summary

AI is rapidly transforming the design and discovery of biologic medicines, which are complex protein-based therapies. Companies like AstraZeneca are integrating AI into their R&D infrastructure, employing a build-measure-learn loop where AI computationally generates and prioritizes candidate molecules for scientists to test. This approach shortens cycle times, increases productivity, and enables the pursuit of previously untreatable disease targets. McKinsey estimates generative AI could cut drug discovery timelines by up to 50%. AstraZeneca is building a "lab of the future" in Kendall Square, Cambridge, MA, to create a closed-loop AI and robotic automation system for autonomous discovery. The ultimate goal is "de novo" design, where AI generates entirely new protein sequences from scratch, requiring rich training data, robust evaluation, and human oversight for safety and ethical considerations.

Key takeaway

For AI Engineers and Research Scientists developing drug discovery platforms, prioritize building robust, closed-loop AI and robotic systems that integrate diverse, high-quality biological data. Your focus should be on creating explainable AI models that act as "thinking partners" for scientists, ensuring human oversight for safety and ethical considerations. Invest in advanced screening technologies to generate the necessary data volume for fine-tuning frontier models, accelerating the path to "de novo" biologic design and potentially "drugging the undruggable."

Key insights

AI fundamentally accelerates and expands complex biologic medicine design, enabling previously impossible discoveries.

Principles

• AI-driven build-measure-learn loops enhance drug R&D.
• High-quality, proprietary data is a key differentiator for AI models.
• Human oversight ensures explainable and ethical AI in drug design.

Method

AI generates and prioritizes candidate molecules; scientists test top designs. This feedback loop shortens development cycles and reduces dead ends.

In practice

• Apply AI to optimize multi-specific biologic parameters.
• Invest in deep screening for high-volume, AI-ready datasets.
• Develop virtual clinical trials for safety prediction.

Topics

• Biologic Drug Discovery
• AI in Pharmaceutical R&D
• Generative AI
• De Novo Drug Design
• Robotic Automation
• Drug Safety Prediction

Best for: Executive, AI Scientist, Research Scientist, AI Engineer

Related on AIssential

• Using AI to Develop New Drugs — AI is fundamentally transforming drug discovery and development processes.
• Demis Hassabis On What AI Will Do Next — AI is evolving into a co-creative partner, poised to accelerate scientific discovery and revolutionize human health within decades.
• Job titles of the future: Nature’s drug designer — Precision drug design, enhanced by AI, can be applied to conservation for targeted ecological health solutions.
• Two AI-based science assistants succeed with drug-retargeting tasks — AI-powered agentic systems can accelerate scientific discovery by synthesizing vast literature and generating testable hypotheses.
• He Raised $70M to Cure Every Disease With AI — AI agents, particularly specialized models, significantly accelerate scientific discovery by removing human talent bottlenecks and enabling high-throughput reasoning.
• 3 Questions: Using AI to accelerate the discovery and design of therapeutic drugs — AI, particularly deep learning and generative models, significantly accelerates novel antibiotic discovery and design.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by MIT Technology Review.