Basecamp Research, a biotechnology company that uses artificial intelligence to discover new proteins and help create new medicines, today announced that it has completed a $60 million fundraising round and joined a multi-year collaboration with the Broad Institute of Massachusetts Institute of Technology and Harvard.

The company’s Series B funding round was led by Singular, joined by other investors including S32, Redalpine, True Ventures and Hummingbird Ventures, Roche Vice Chairman André Hoffmann, Royal Philips Chairman Feike Sijbesma and Paul Polman, former CEO of Unilever.

Basecamp has worked to create a large dataset of proteins found in naturewith the vision of creating a knowledge graph that will power AI algorithms to promote the discovery of unexplored drugs and materials. He Does this use what the company calls an “AI-enabled foundational database.”

“We are pushing the boundaries of AI in biological design by doubling down on the fundamental data gap facing the entire biotech industry,” said Dr. Glen Gowers, co-founder and Managing Director of Basecamp Research. “Basecamp Research uses its technology to generate new and deeper insights beyond known biology and to expand every day what we can offer our partners in the biopharmaceutical ecosystem.

Joining the Broad Institute, Basecamp is collaborating with Dr. David R. Liu, Howard Hughes Medical Institute Investigator and Broad Senior Fellow, and the Liu Lab to create new approaches to “programmable genetic medicines.” These drugs could include therapies that interact with biological systems to regulate doses, modify their mode of action, or be designed based on specifically encoded proteins from the genes of a population or disease. The goal is to create treatments for diseases by developing new methods for discovering fusion proteins and other large molecules to produce the next generation of drugs.

Basecamp’s transformation work has already led to the creation of new AI models for the discovery of new protein molecules thanks to its technology. According to the company, although large language models such as ChatGPT have proven useful in helping scientists design and work with protein sequences, they require significant training and conditioning on known protein starter sequences.

To restart this process, the company partnered with Ferruz Laboratory at the Institute of Molecular Biology of Barcelona and announced the release from ZymCtrl in June. The company said it is a next-generation end-to-end protein LLM that provides design capabilities to generate artificial enzymes, a protein that accelerates chemical reactions in living cells. Unlike other LLMs, it requires no starting sequences and can create functioning enzymes that share only 30% resemblance to its training set.

« With ZymCtrl, generate very specific enzymes is as easy as interacting with a chatbot,” said Noelia Ferruz, group leader of the laboratory, a Basecamp partner for over 2 years.

The company also spear BaseFold, a deep learning model designed to predict 3D structures of large, complex proteins more accurately than other models. The company said it created the new model by augmenting AlphaFold2, the industry benchmark for AI-based protein prediction. BaseFold was found to be six times more precise than AlphaFold2 and provides a three-fold improvement in small molecule docking, the company added.

Basecamp said it will use proceeds from the fundraising to scale up its data collection efforts by expanding its core dataset, which already contains 100 times more information on advanced biological systems than public databases. The company also intends to significantly strengthen its research into AI capabilities and focus on a new generation of fundamental models for protein discovery.

Image: Pixabay