XtalPi's Kodexia: generative AI plus automated experiments make siRNA drug discovery a closed loop
## XtalPi's Kodexia: turning siRNA drug discovery into an AI closed loop
On October 6, XtalPi disclosed details of its Kodexia platform, in which generative AI, biological modeling and automated experiments form a closed loop to accelerate the discovery of small interfering RNA (siRNA) therapies.
**Key points**
- **What siRNA is**: It "silences" a disease-causing gene before it is expressed as a protein, and can hit targets out of reach of traditional small-molecule drugs; but sequence design, chemical modification, validation of activity in animals and extrahepatic delivery are all tough problems.
- **The closed-loop approach**: AI generates designs, automated experiments validate them, and the results flow back to guide the next round of AI design. Once the design-make-test-analyze (DMTA) cycle is turning, dry-lab and wet-lab work no longer wait on each other in series but feed each other.
- **Pipeline progress**: Six in-house preclinical programs cover metabolic, kidney, respiratory and central nervous system diseases, and more than half have completed animal efficacy testing.
- **Industry signal**: In the second half of AI drug discovery, the contest is not only about models but about whose dry-wet closed loop turns faster and whose experimental data flows back more smoothly.
> Source: [read the original](https://www.techrepublic.com/article/news-xtalpi-kodexia-ai-sirna-drug-discovery/). This text is a summary for reference only.
