Reticular Logo
← Back to blog

We've Launched on Y Combinator!

NP

Nithin Parsan

Co-Founder

October 20, 20245 min read
We've Launched on Y Combinator!

We've Launched on Y Combinator!

October 20, 2024

We're thrilled to announce that Reticular has officially launched on Y Combinator! After months of hard work and development, we're excited to share our vision for steerable and interpretable AI for protein engineering with the world.

Our Mission

We're giving pharma companies precise control over protein AI models, enabling reliable drug discovery without millions in wasted experiments. By unlocking encoded information in these models through foundational AI interpretability research, we're making steering as easy as prompting ChatGPT.

Our Team

We're Nithin Parsan and John Yang, co-founders of Reticular. We met 7 years ago competing in International Biology and Neuroscience Olympiads and were roommates at MIT for 4 years. Our combined expertise has led to publications in prestigious journals including NeurIPS, Nature, and PLoS ONE.

Our Approach

While protein AI models like AlphaFold have revolutionized drug discovery, they remain black boxes that can waste millions in testing and lack precise control. Rather than relying on trial-and-error, we're leveraging mechanistic interpretability techniques that excel at extracting sparse knowledge from models even with scarce data - the same advances being used in frontier AI labs to steer models like Claude.

For our design partners, we deliver:

  • Direct steering of protein models towards desired properties
  • Interpretable biological features backing every design
  • Efficient exploration of combinatorially massive design spaces with limited data

See Us in Action

Check out our latest research on our website or try our demo at sae.reticular.ai → to see how we're steering Green Fluorescent Protein towards more fluorescent sequences by directly controlling the model's internal knowledge.

Connect With Us

We're looking to connect with:

  • Startups working with biological language models for design partnerships
  • Pharma teams building generative discovery pipelines
  • Researchers working on AI interpretability

Interested in learning more? Support our launch on YC:

Launch YC: Reticular: Steerable and interpretable AI for protein engineering

Or reach out directly through email at contact@reticular.ai.