Beyond boosting productivity, Novonesis employs genetic engineering as a safety tool. They modify production strains to remove any latent ability to become harmful, ensuring products for food and feed are exceptionally clean and safe, a key advantage over using wild-type strains.
Related Insights
The power of AI for Novonesis isn't the algorithm itself, but its application to a massive, well-structured proprietary dataset. Their organized library of 100,000 strains allows AI to rapidly predict protein shapes and accelerate R&D in ways competitors cannot match.
A key barrier to complex peptide-antibody drugs is manufacturing (CMC). Current methods require separate synthesis and conjugation steps. A fully genetically encoded system—where the entire hybrid molecule is produced in a single cell line—would dramatically lower the barrier to entry and simplify manufacturing, unlocking new drug designs.
Rather than selling single products, Novonesis designs custom blends or "cocktails" of different enzymes and microbes. This tailor-made approach solves specific customer problems so effectively that it makes the solution highly unique and difficult for competitors to replicate.
The company's customer-centric innovation starts with deeply understanding a client's operational issues and end-consumer needs. They then reframe these commercial challenges as specific biological problems that their R&D can measure, target, and solve.
To ensure pharmaceutical-grade consistency from a living organism, Kaiko addresses biological variability with stringent controls. This includes using Specific Pathogen-Free (SPF) grade pupae from specialized facilities and collaborating directly with regulatory bodies like Japan's PMDA to establish clear acceptance criteria, aligning the novel platform with pharmaceutical expectations.
Instead of using CRISPR for gene editing (cut and replace), Seek Labs harnesses its natural function. Their platform programs CRISPR to find and 'chop up' viral DNA and RNA, directly lowering the viral load and allowing the host's immune system to take over.
Consumer fear of GMOs is entrenched and funded, making education efforts ineffective. A better strategy is to use newer technologies like AI-driven breeding or CRISPR to achieve the same goals without triggering irrational consumer backlash, effectively sidestepping the debate.
The danger of AI creating harmful proteins is not in the digital design but in its physical creation. A protein sequence on a computer is harmless. The critical control point is the gene synthesis process. Therefore, biosecurity efforts should focus on providing advanced screening tools to synthesis providers.
Novonesis has shifted enzyme discovery from the lab to computers. Using AI tools like AlphaFold, they predict protein structures and identify new enzyme families based on structural motifs rather than sequence similarity. This allows them to find novel functionalities much faster than traditional methods.
Unlike most biotechs that start with researchers, CRISPR prioritized hiring manufacturing and process development experts early. This 'backwards' approach was crucial for solving the challenge of scaling cell editing from lab to GMP, which they identified as a primary risk.
