Targeting Complex Diseases with AI

How Genesis Therapeutics Scaled AI-Driven Drug Discovery with Lambda

Challenge

Overcoming Compute Limits in Molecular AI

Genesis had already made significant progress in AI-driven small molecule drug discovery, across several internal oncology and immunology drug programs. Yet, as their research expanded to harder-to-drug targets and more intricate protein-ligand structures, the sheer computational demand began to surpass their available resources.

Key Challenges:

• As datasets grew, model training times increased from weeks to months, impacting Genesis' ability to quickly iterate and refine their research.
• Even with high-end GPUs, slow network speeds prevented efficient utilization of hardware resources.

“We hit a natural limit where training models took months. We needed results in a week or less to maintain the pace of our research.”
—Wojtek Swiderski, Director of Software Engineering, Genesis Therapeutics

• Their existing computational resources weren’t suited to larger datasets, which are important for new, more complex protein targets.
• Genesis needed a scalable, high-performance AI cloud that could keep up with the demands of AI-driven drug discovery.

Solution

Accelerating AI Drug Discovery at Scale with Lambda

To process billions of molecular candidates and simulate complex protein binding at scale, Genesis needed an infrastructure partner that could keep pace with their cutting-edge AI models.

Using Lambda’s 1-Click Clusters, Genesis could quickly spin up powerful NVIDIA H100 GPU clusters to train their next-gen models—all without long-term contracts or infrastructure overhead.

How Lambda Helped:

• 3X Faster Training Times
  By leveraging Lambda’s high-performance NVIDIA GPU clusters and NVIDIA Quantum-2 InfiniBand networking, Genesis reduced model training times from months to just a week, enabling faster iteration and discovery.

• Flexible Scaling Without Lock-In → Lambda’s 1-Click Cluster (1CC)

  “Not only does Lambda solve problems, but they explain their solutions in a way that helps us improve our internal processes. It’s been an invaluable learning experience.”

• Expert AI Support
  —Wojtek Swiderski

Results

Faster AI Breakthroughs & Scalable Drug Discovery

With Lambda, Genesis unlocked the computational power needed to take their research to the next level without all of the hassle and complexity of typical GPU infrastructures.

Key Outcomes:

• Genesis can now process larger datasets and train more advanced models, accelerating research on proteins once considered undruggable.
• Higher computational power enables more precise simulations, enhancing drug discovery potential.

What’s Next?

Genesis is continuing to enhance their models, creating the most advanced molecular AI platform in the field. With Lambda’s scalable compute power, they’re pushing the boundaries of AI-driven drug discovery.

“This field is so complex that AI might understand it better than humans. Our challenge is to build models that can take us beyond our current limits —Lambda is helping us get there.”
—Wojtek Swiderski