News Picture Generic

AI designs it. Robots build It. Humans decide. Inside Astellas' human-in-the-loop drug discovery.

August 18, 2026
Featured Article

Drug discovery has always been a numbers game with brutal odds. In Japan, only about 1 in 23,000 small molecules becomes a medicine, and a single program can run 9 to 16 years. Astellas set out to change those odds. Since 2019, the company has been building a "Human-in-the-Loop" platform that connects human expertise, AI prediction, and lab robotics into one continuous workflow, so that scientists spend less time on repetitive bench work and more time on the decisions that actually move a project forward. It is the same principle Chemspeed builds its automation around: close the loop between make and analyze, and let researchers focus on the science.

  • Astellas runs a closed loop where AI designs and predicts compound properties, robotics handle synthesis, and researchers evaluate results, often remotely, then feed the data back to sharpen the next round.
  • The approach cut the time to turn an early hit compound into a viable drug candidate by roughly 70 percent versus traditional methods.
  • The platform surfaced promising compounds that manual selection might have overlooked, presenting activity and property data in one clear, decision-ready view.
  • Adoption was earned, not forced. A small pilot group refined the system first, and breaking down silos between departments turned early skeptics into daily users.
  • An AI-designed, AI-predicted, robot-synthesized compound has now advanced into clinical trials.

When human judgment, AI, and robotics run in the same loop instead of separate lanes, discovery stops waiting on the bottleneck and starts moving at the speed of the science. Closing that loop from synthesis to analysis is exactly what Chemspeed automation is built to do.

Source: Astellas Newsroom

This post references publicly available material published by Astellas Pharma Inc. All company names, trademarks, logos, videos, and article content remain the property of their respective owners and are referenced here for informational purposes only, with no claim of ownership or endorsement implied. No original text has been reproduced. All links point to the original sources.

Other Recent News

Discover more news articles you might be interested in

Read more about High-throughput solid microsampling through stochastic robotic automation
News Picture 1 1 V2
Featured
Jul
14

High-throughput solid microsampling through stochastic robotic automation

Solid sampling at the sub-milligram and milligram scale remains a major bottleneck for high-throughput chemistry or material sciences, as existing approaches rely on manual handling or slow deterministic microsampling that do not readily scale.

Here we present STORMS, an automated STOchastic Robotic MicroSampling system that enables fast, reliable and parallel sampling of solid materials at sub-milligram and milligram masses. 

Read more about Parameter efficient multi-model vision assistant for polymer solvation behaviour inference
News Picture 1 1 V2
Jun
30

Parameter efficient multi-model vision assistant for polymer solvation behaviour inference

Polymer–solvent systems exhibit complex solvation behaviours encompassing a diverse range of phenomena, including swelling, gelation, and dispersion. Accurate interpretation is often hindered by subjectivity, particularly in manual rapid screening assessments. While computer vision models hold significant promise to replace the reliance on human evaluation for inference, their adoption is limited by the lack of domain-specific datasets tailored, in our case, to polymer–solvent systems.

© Chemspeed (part of Bruker) 2026