New collaboration will apply LabGenius’ machine learning platform to co-optimize NANOBODY therapeutics targeting inflammation.
Biotech LabGenius Therapeutics has entered a new collaboration with AI-powered biopharma company Sanofi to advance AI/ML-driven antibody optimization, marking the second major partnership between the two companies and a continued validation of LabGenius’ platform in the race to build next-generation biologics.
The agreement will see LabGenius apply its machine-learning–powered discovery engine, EVA, to optimize potential therapeutic NANOBODY proteins across several new inflammatory targets [1,2].
For investors watching the computational biology space, the deal signals accelerating confidence in AI-first drug discovery, particularly in synthetic antibody engineering, where speed, precision and manufacturability determine which programs survive.
LabGenius and Sanofi first linked up in 2021, combining LabGenius’ strengths in ML, robotic automation and synthetic biology with Sanofi’s experience in engineering NANOBODY heavy chain variable domains [3].
Over the multi-year program, LabGenius used its platform to explore vast mutational landscapes and co-optimize these small but highly versatile proteins for predefined therapeutic characteristics.
The approach paid off. In 2023, LabGenius presented data at the Single-Domain Antibodies Meeting confirming that a panel of optimized NANOBODY candidates met the collaboration’s success criteria while maintaining strong production characteristics – a key requirement for commercial viability.
NANOBODY molecules, ultra-small antibody fragments derived from species that naturally produce heavy-chain–only antibodies, have become an important modality for complex diseases [4]. Their size gives them access to targets inaccessible to classical antibodies, and they can be linked like “beads on a string” to create multivalent constructs capable of simultaneously binding multiple disease-relevant proteins.
Biopharma’s interest has surged because these formats can consolidate multi-drug regimens into single, multi-action therapeutic molecules. Their stability also opens the door to new delivery routes, including potential oral formulations.
For these reasons, the ability to systematically optimize NANOBODY properties – binding, solubility, expression, stability and immunological performance – represents a significant edge. Investors have increasingly viewed ML-first discovery platforms as accelerators that reduce cycle times and reveal solutions that conventional protein engineering approaches may miss.
For LabGenius, the new collaboration signals strengthened confidence from a major pharmaceutical partner and a fresh runway for expanding EVA across a broader set of targets.
“We are truly excited about this new collaboration with Sanofi,” said LabGenius’ CSO, Dr Angus Sinclair. “This partnership serves as strong validation of our platform’s unique ability to tackle complex antibody co-optimization challenges across a wide range of therapeutic targets, ultimately driving better outcomes for patients.”
LabGenius’ EVA integrates AI, high-throughput robotic experimentation and synthetic biology to explore millions of possible antibody variants and identify which combinations yield the best-performing molecules. The company continues to operate a hybrid model, partnering with biotech and pharma while building its own therapeutic pipeline.
As AI-driven protein design continues to mature, collaborations like this one provide a real-world testbed for how machine learning can shorten timelines and improve the quality of biologics entering development.
For companies investing in computational drug discovery, LabGenius’ expanding partnership with Sanofi underscores how algorithm-native platforms are increasingly shaping the future of therapeutic engineering.
[1] https://labgeniustx.com/technology/
[2] https://www.sanofi.com/en/magazine/our-science/nanobody-technology-platform
[3] https://labgeniustx.com/labgenius-research-collaboration-with-sanofi-yields-positive-results/
[4] https://pmc.ncbi.nlm.nih.gov/articles/PMC10057852/
