Astromech, an AI startup developing predictive models for biological evolution and change, has raised $20 million in new funding at a $3.8 billion valuation.
The round was led by biotech investor Bob Nelsen, with participation from Peak 6, NeoGenesis Capital, Builders VC, and CAZ Investments. The latest financing brings Astromech’s total capital raised to $60 million and nearly doubles the company’s valuation from its previous financing in March.
Building AI Models to Forecast Biology
Founded by Ben Lamm and George Church, Astromech was spun out of Colossal Biosciences and is developing AI models designed to predict how biological systems may change over time.
The company’s platform combines genomic, evolutionary, and functional data to identify patterns associated with biological resilience, vulnerability, and adaptation.
Astromech aims to forecast biological trajectories and identify potential vulnerabilities before they become major problems. Potential applications include disease prevention, drug resistance, biosecurity, agriculture, food security, and conservation.
Using Evolutionary History as a Training Signal
Astromech’s approach uses billions of years of evolutionary history as a source of data for its AI models.
The platform combines genomic information from living and extinct species with evolutionary relationships and functional data covering biological traits, gene expression, and responses to environmental conditions.
Its models are designed to analyze not only how genomes differ between species, but also when those differences emerged, how regulatory systems changed, and how those changes affected biological functions.
The company is also developing methods to reconstruct ancestral regulatory states, including changes in gene expression and chromatin accessibility, rather than focusing solely on ancestral genetic sequences.
Longevity as an Initial Test Case
Astromech is using longevity and biological resilience as an early demonstration of its technology.
The company is studying evolutionary outliers such as Asian elephants, bowhead whales, Brandt’s bats, and Tasmanian devils to understand genetic and regulatory mechanisms associated with cancer resistance, longevity, and adaptation.
Its initial longevity demonstration maps 46 longevity-associated genes across a time-calibrated tree of life, allowing researchers to examine how genes linked to longevity and cellular and genomic maintenance have evolved across species.
By comparing species with unusual biological characteristics, Astromech aims to identify mechanisms that could generate new hypotheses for human health and aging research.
Expanding Comparative Genomic Data
Astromech plans to use the new funding to expand its research team, add more species to its functional genomic datasets, and scale the infrastructure used to train its models.
The company has access to genomic resources developed through Colossal, including data from living and extinct species, ancient DNA capabilities, and computational biology infrastructure.
Astromech is also developing technology for faster genome-scale analysis. The company says its learned tree-inference method has reconstructed phylogenetic trees approximately 100 times faster than conventional maximum-likelihood approaches in internal benchmarks while maintaining comparable topology accuracy.
Applications Across Health, Agriculture and Biosecurity
Astromech’s technology could eventually be applied across multiple areas of biology.
Potential applications include predicting pathogen susceptibility, drug resistance, disease progression, genetic bottlenecks, ecosystem risks, agricultural vulnerabilities, and responses to environmental change.
The company is pursuing a common biological intelligence platform that can be adapted to different species, traits, and industries rather than building separate AI models for each application.
Astromech says its unified modeling engine and longevity explorer are already operational across genomes, genes, traits, and evolutionary groups. The company plans to begin forecasting pilots with partners in health and biosecurity to prospectively test its predictions.
With its latest financing, Astromech is seeking to move from analyzing biological history to forecasting biological change, with the longer-term goal of building a biological intelligence platform capable of identifying important changes and vulnerabilities before they occur.
