Matwings Supports GenSci148 Protein Program Cleared for China Clinical Trial

Aug 20, 2026
Matwings said GenSci148 Injection received clinical trial clearance in China and described its work on four AI and wet lab protein engineering cycles covering 222 variants.

Matwings said in a press release that GenSci148 Injection has received clinical trial clearance in China for neovascular age related macular degeneration, diabetic macular edema, and retinal vein occlusion. The investigational ophthalmic biologic was developed by GenSci, with Matwings supporting protein engineering work.

The program used four iterative AI and wet lab cycles covering 222 protein variants. The first two rounds tested 92 and 30 variants with a focus on biological activity, while the next two rounds tested 50 variants each and added objectives such as formulation viscosity, stability, expression, and broader developability.

Tested variants showed up to about 10 fold improvement in VEGF A binding affinity, up to about 3 fold improvement in VEGF A, C, and D functional blockade, thermal stability gains of up to about 4.5°C, protein expression gains of up to about 27.6%, and viscosity reduction of about 13 cP in high concentration formulation. In a nonclinical retinal model, the optimized molecule maintained inhibitory activity 84 days after dosing. The findings are preclinical and do not establish clinical safety or efficacy.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.