This company develops novel therapeutics using a machine-driven platform to design custom mini-proteins and single domain antibodies. Their Design Engine leverages generative AI and reinforcement learning to create *de novo* protein sequences optimized for specific product profiles. This process accelerates drug discovery by delivering highly stable, configurable, and effective therapeutic candidates faster than traditional methods.
Funding
$24.2M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Traditional antibody-based therapeutics can be limited by their large size, complex manufacturing requirements, and potential for off-target effects. Developing novel treatments for diseases with high unmet needs often requires lengthy and costly discovery processes.
Solution
Ordaōs offers a generative AI-driven Design Engine that creates de novo miniPRO proteins, a class of mini-proteins approximately 20 times smaller than traditional monoclonal antibodies. These miniPROs are designed for enhanced stability, ease of manufacturing, and improved tissue penetration. The Design Engine leverages multitask meta-learning and reinforcement learning to generate, evaluate, and optimize protein sequences and structures in silico, accelerating the identification of therapeutic candidates. This approach enables drug hunters to develop safer and more effective therapeutics with reduced timelines.
Target Audience
The primary target audience includes pharmaceutical and biotechnology companies, as well as drug discovery researchers seeking to develop novel protein therapeutics for a range of diseases.
Features
- Generative AI-driven Design Engine for de novo miniPRO protein creation
- miniPRO proteins are 20x smaller than traditional monoclonal antibodies (40-160 amino acids)
- Improved thermostability and solubility, minimizing aggregation risks
- Configurable binding optimized for on-target vs off-target binding
- Humanized and optimized to minimize immunogenicity
- Scalable and repeatable design process
- In silico evaluation of binding affinity, specificity, and drug-like properties