Revolutionizing Drug Discovery with SwarmOne
SwarmOne has enabled us to create new purpose-built foundational models that are unique to the drug discovery process. Their platform has provided us with a real competitive advantage.
Summary
Numenos leveraged SwarmOne to build groundbreaking AI foundational models, dramatically accelerating the drug discovery process. With SwarmOne, the team was able to launch their service significantly faster compared to traditional AI infrastructure.
Industry: Drug Development
Company Size: Startup
Original GPU Provider: On-premise
The Challenge
Numenos aimed to rethink how AI could be utilized in drug discovery by testing and building an entirely new set of foundational models. This required evaluating 16,000 different model architectures using a non-standard data type—an undertaking that would traditionally demand the setup and configuration of 16,000 GPU instances, a process that would have taken an impractically long time.
“I don’t know how we would have done it without SwarmOne.”
Why SwarmOne?
“We do a lot of experimentation. We needed a way to test thousands of model architectures and then optimize hyperparameters. We reviewed multiple options — SwarmOne was the only platform that met our needs.”
SwarmOne’s autonomous AI training platform stood out for several reasons:
- Fully Automated Training: SwarmOne provisions the necessary hardware and determines the optimal training strategy.
- Seamless Experimentation: Ideal for teams requiring rapid iteration without dealing with infrastructure overhead.
- Scalability: Handles thousands of model architectures effortlessly.
- Code Management: Allows models to be managed like any other software using a Git-based approach.
The Impact
Numenos’ AI models have revolutionized drug discovery by:
- Accelerating Trials: Faster and more accurate trial outcomes.
- Biomarker-Driven Discovery: Enhancing sample prioritization and target identification.
- Increased Efficiency: 10X increase in trial significance and a 80% reduction in trial size.
- Money Saved: $200K-$250K annually, saved by avoiding the need to hire a DevOps engineer and maintaining always-on instances.
By using SwarmOne, Numenos has shifted its focus from infrastructure management to AI innovation. Their unique Causal foundation model continues to uncover data potential, driving transformative results in drug development.
The Future
In October 2024, Numenos secured investment from BC Growth Equity, a Florida-based VC firm supporting early-stage companies with exponential growth potential.
What if your AI models were guaranteed to run seamlessly? SwarmOne eliminates infrastructure headaches, allowing teams to focus solely on model development.
Other Case Studies
