Basecamp Research reveals AI models for programmable gene insertion as Nvidia confirms an investment, signaling a new frontier in gene therapy.
Basecamp Research, a London-based startup applying artificial intelligence to life sciences, has unveiled what it describes as the world’s first AI models for programmable gene insertion. The announcement comes as the company confirmed a strategic investment from Nvidia.
Basecamp Research uses large-scale biodiversity data to design new medicines, building proprietary AI models trained on genomics data collected by its scientists around the world. The newly released family of models is designed to enable precise gene replacement and cellular reprogramming, opening potential new paths for treating cancer and inherited genetic diseases.
“We believe we are at the beginning of a major expansion in what’s possible for patients with cancer and genetic disease,” said John Finn, chief scientific officer at Basecamp Research. “By using AI to design therapeutic enzymes, we aim to accelerate the development of cures for thousands of diseases that are currently untreatable.”
The models are being released alongside a scientific paper co-authored with researchers from Nvidia, Microsoft, and academic institutions. They were unveiled during Nvidia’s presentation at the J.P. Morgan Healthcare Conference in the United States.
Also Read: How Explainable AI Builds Trust in Data Decisions
According to Glen Gowers, Basecamp Research’s chief executive and co-founder, the models cost tens of millions of pounds to develop and were trained using Nvidia’s GPUs. “They are similar in style to GPT-type models,” Gowers said. “In terms of the scale of training data, they are roughly comparable to GPT-4.”
The models are trained to understand the “language” of DNA and evolutionary patterns, allowing them to design programmable therapies across multiple disease types. Gowers said the system can generate peptides that target specific pathogens with reported laboratory accuracy rates of between 97 and 100 percent.
Unlike many consumer-facing AI systems, the models will not be released as a chatbot. Instead, Basecamp Research plans to deploy them in collaboration with pharmaceutical companies to design new therapeutics. Gowers said the approach could overcome key limitations of CRISPR-based techniques, particularly for large genetic edits and insertions.
“What we demonstrate is the ability to make large edits that open the door to tens of thousands of genetic diseases that CRISPR cannot currently address,” he said.
Also Read: The Hybrid Office: Why APAC’s Tech Is Failing Workers
The company also confirmed that it has secured funding from Nvidia’s venture arm, NVentures, in a pre–Series C round, though financial terms were not disclosed.
Basecamp Research was among a group of UK startups highlighted last year by Nvidia CEO Jensen Huang as potential beneficiaries of a £2 billion push to support the British AI ecosystem. Others named at the time included Revolut and Wayve.
To date, Basecamp Research has raised approximately $85 million. Its investors include Singular, True Ventures, Hummingbird Ventures, and Paul Polman, the former chief executive of Unilever.
