Cradle offers an AI‑driven protein engineering platform that learns from a user’s experimental data and public datasets to generate and rank protein candidates across multiple objectives such as activity, binding affinity, stability, and expression. The cloud‑hosted workspace automates library design, runs large‑scale in‑silico simulations, and provides interactive visualizations to help scientists iterate rapidly, reducing the number of experimental rounds needed to meet target specifications.
Funding
$73M 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.
1OFounders
Product
Problem
Protein engineering projects often require many experimental cycles to optimize multiple properties such as activity, binding affinity, stability, and expression, leading to long timelines, high costs, and low success rates. Traditional workflows rely on sequential optimization and limited data integration, making it difficult to explore complex trade‑offs and de‑risk designs early.
Solution
Cradle provides an AI‑driven protein engineering platform that learns from a user’s experimental data and public datasets to generate and rank protein candidates across multiple objectives simultaneously. The system builds custom models after each round, runs large‑scale in‑silico simulations, and designs curated libraries that balance exploitation of known hits with exploration of novel sequence space. Results are presented through an interactive web workspace where scientists can visualize trade‑offs, upload assay data, and iterate rapidly, reducing the number of experimental rounds needed to reach target specifications.
Target Audience
Primary users are protein scientists in biopharma, industrial biotechnology, and food‑tech companies who need to optimize multiple protein attributes, as well as academic research groups conducting protein design projects.
Features
- Custom AI models that are retrained on each experimental round using the user’s data, public databases, and Cradle’s wet‑lab validated datasets.
- Multi‑objective optimization that simultaneously improves activity, binding, stability, expression, and other user‑defined properties.
- Automated design of de‑risked library plates via tens of thousands of simulations to balance hit discovery and exploration.
- Interactive web interface with visualization tools (e.g., Sankey plots) for inspecting property trade‑offs and guiding design decisions.
- API access for computational workflows and integration with existing lab informatics.
- Granular access controls and unlimited seats to support collaborative teams across an organization.
- Cloud‑hosted analytics that track progress, compile reports, and store all experimental results in a single workspace.