Anagenex fuses DNA with software to forge a new path for next-gen drug discovery

Drug discovery is a crucial process for delivering transformative outcomes to patients, but it’s time- and resource-intensive, as well as fairly unpredictable. From target identification through basic research and candidate drug selection through lead discovery, identifying a suitable and safe drug can take 12-15 years. But advancements in technology and our understanding of biology are ushering in a new era of drug discovery. At the forefront of this new generation are intrepid startups like Anagenex.

Anagenex, a young biotech based in the San Francisco Bay Area, is striving to make drug discovery faster and more efficient by harnessing machine learning (ML) and DNA encoded library (DEL) technology. Nicolas Tilmans, founder and CEO of Anagenex, started Anagenex to revolutionize drug discovery by identifying targets faster, cheaper, and with more confidence. Anagenex re-imagines the lab, considering wet lab techniques and computing power as partners, enabling the company to use DNA sequence readouts as tools for understanding molecules of interest and identifying ideal drug candidates. For Tilmans, this unique blend of biology and software stands to “make the research process more efficient, more productive, and more pleasant” for scientists on the cutting edge of drug discovery.

“I don’t think anybody’s put the pieces together quite the way we have...We’re asking data questions no one has asked because no one really could before."

– Nicolas Tilmans, CEO @ Anagenex

Anagenex’s unique approach calls for a data management partner that can handle the complexity of their novel research and scale with them as they grow. Because both the ML and DEL techniques that Anagenx uses rely on massive datasets that require comprehensive management, they turned to Benchling to implement a highly flexible and scalable data management infrastructure. Benchling keeps pace with the growing complexity of Anagenex’s unique life science workflows, standardizes their data operations so they can discern biologically-relevant insights, and matches their business model which puts computation at the forefront of everything they do.