Urgent.News

What's breaking now, across hundreds of outlets.

AI

XtalPi Details Kodexia AI Platform for siRNA Drug Discovery

XtalPi’s Kodexia combines generative AI and automated lab testing for siRNA drug discovery. Explore its workflow, reported results and preclinical limits. The post XtalPi Details Kodexia AI Platform for siRNA Drug Discovery appeared first on TechRepublic .

XtalPi has unveiled Kodexia, a closed-loop platform that integrates generative AI, biological modeling, and automated experiments to expedite the development of small interfering RNA (siRNA) therapies. The company announced six preclinical programs targeting metabolic, renal, respiratory, and central nervous system diseases, with more than half having completed animal efficacy testing.

The core of Kodexia is XtalPi's siFormer architecture, which leverages RNA interference biology and nucleic acid chemistry to generate candidate molecules. The system considers factors like RNA thermodynamics, strand loading, target accessibility, and silencing efficiency to design effective sequences. While conventional siRNA discovery involves identifying a working laboratory test sequence, Kodexia aims to ensure the sequence survives the transition to animal testing, maintains activity, avoids adverse effects, and navigates intellectual property challenges.

Kodexia connects computational design with automated testing, with the company conducting over 500 in vitro and 30 in vivo experiments weekly. Internal preclinical benchmarking showed that molecular design efficiency is nearly three times more efficient than traditional workflows. More than 50% of first-round designs across multiple programs reportedly exhibited stronger in vivo activity than positive controls.

Kodexia also co-designs siRNA molecules with delivery systems, optimizing conjugates for research targeting the kidney, spleen, and fat tissue. Additionally, the platform supports dual-target siRNAs, addressing two disease-related targets with a single molecule. The lead IgA nephropathy program represents the earliest test of this approach, achieving non-human primate efficacy data in seven months and demonstrating greater activity and durability compared to a clinical-stage reference molecule targeting the same target.

For pharmaceutical R&D teams, Kodexia offers a connected workflow where experimental results inform the next round of AI-generated designs. This efficiency could potentially compress several stages of RNA discovery into a seamless workflow, enabling researchers to spend less time moving candidates between disconnected design, testing, and delivery processes. Early results suggest that Kodexia could help researchers tackle challenging targets more practically while providing earlier data for investment decisions.

Rewritten by urgent.news; may contain errors — check the original.

Read the original at techrepublic.com →

Report a problem with this story

More in AI

More from Wednesday 7 October →