A groundbreaking initiative promises to revolutionize our understanding of biodiversity and its applications—and it’s powered by Microsoft and NVIDIA. Meet Basecamp Research.
The Basecamp Research team is on a mission to digitize nature, transforming biological material into data to unlock the secrets of the natural world. This ambitious project aims to bridge the gap between biotechnology and biodiversity, creating the world’s largest and fastest growing database of biological protein sequences, containing more than 9.8 billion new sequences and more than one million newly discovered species—expanding the known tree of life by more than tenfold compared to all public databases combined.
This scale is not just a scientific milestone—it’s a breakthrough that enables researchers to model evolution itself, providing a window into how life on Earth has adapted and diversified over billions of years.
When you look at a spoonful of soil, there could be as many living things in that spoonful of soil as there are humans on the planet.
—Marlon Clark, Collaboration and Innovation Lead, Basecamp Research
Basecamp Research is not just building a longer list of catalogued species, but creating a database of a completely different scale and complexity. This comprehensive dataset empowers advanced AI models to uncover the rules and mechanisms of evolution, identify novel proteins and pathways, and design new biological solutions for challenges in medicine, sustainability, and beyond.
Evolution is the most powerful force in biology, and by understanding how nature uses it to solve problems, we can’t underestimate the impact this will have on advances in biology.
—John Finn, Chief Scientific Officer, Basecamp Research
As part of the Microsoft for Startups and NVIDIA Inception program, Basecamp Research has the tools and resources needed to unlock the secrets of biodiversity and drive innovation in biotechnology. By combining Azure’s scalable cloud foundation with NVIDIA’s full-stack AI innovation, Basecamp Research is paving the way for a new era of biological discovery and inspiring others to explore the incredible potential of nature. Microsoft and NVIDIA power Basecamp Research’s AI models to process and analyze data at increased speeds, further accelerating their research and enabling them to tackle complex biological challenges.
The startup ’s focus is on converting biological material into data through DNA sequencing, a process that reveals the intricate details of the organisms that inhabit our planet. This data is then used to build a comprehensive database of more than 10 billion novel protein sequences that not only catalogs the diversity of life but also is training a new family of foundation models, leveraging insights into how these organisms function and interact with their environment—laying the foundation to inspire new innovations in biotechnology.
We’re not just using our database to start identifying novel proteins we can use. But we’re using the AI models we’re building actually to help us start evolving those proteins to have the features we want without doing millions of variants.
—John Finn, Chief Scientific Officer, Basecamp Research
Microsoft and NVIDIA: Powering the next leap in biological discovery
Basecamp Research’s mission is powered by a unique combination of Microsoft Azure and the full stack NVIDIA AI platform. Together, these technologies provide the scalable infrastructure, advanced AI tools, and accelerated computing needed to process and analyze the world’s largest and most diverse biological dataset.
By leveraging the power of Azure’s cloud services, Basecamp Research can process and analyze vast amounts of biological data efficiently and effectively. The scalability and flexibility of Azure allow the team to handle the massive datasets generated from DNA sequencing and other biological analyses.
One of the key advantages of Azure is its ability to support high-performance computing (HPC) workloads accelerated by NVIDIA. This is crucial for Basecamp Research, as their work involves complex computational tasks that require significant processing power. Azure’s HPC capabilities enable the team to run large-scale simulations and analyses, accelerating their research and discovery processes.
Additionally, AI and machine learning tools from Azure and NVIDIA are instrumental in helping Basecamp Research derive meaningful insights from their data. By leveraging Azure Machine Learning and NVIDIA BioNeMo framework, the team can build, train, and deploy sophisticated AI models that can predict and identify patterns in biological data. This allows them to uncover new biological insights and develop innovative solutions inspired by nature.
Making learnings accessible
The Basecamp Research team is also committed to ensuring that the benefits of their work are shared with the communities they collaborate with. They enhance local capacity by building labs, sharing data, and training scientists, and they pass revenue back to these communities when their data leads to commercial success.
From the work they do, to the technology they choose, the Basecamp Research project is a testament to the power of collaboration and innovation. By breaking through the “data wall” that has limited progress in the life sciences, Basecamp’s database empowers generative biology—using AI to design, generate, and annotate proteins, pathways, and therapeutics with a level of accuracy and creativity that was previously impossible
At its heart, Basecamp Research as a company is built on this idea that biology has the answers and the process of evolution has led to this really, truly remarkable complex system that shouldn’t work and yet, and yet it does. Fundamentally, we’re so reliant on biodiversity and being able to study it and understand it is one of the most important things that you can do.
—Phoebe Oldach, Vice President Data Growth, Basecamp Research
To delve deeper into this fascinating journey and witness the groundbreaking work of the Basecamp Research team, watch the full-length video. For other intriguing applications of Microsoft and NVIDIA technology, follow the Catalyst series.
