METAGENE-1

METAGENE-1 is a metagenomic foundation model designed for pandemic monitoring, trained on over 1.5 trillion base pairs of DNA and RNA sequenced from wastewater. It is specifically optimized to detect anomalies in short metagenomic reads, making it well-suited for tasks like pathogen detection and biosurveillance. The model is the result of a collaboration between researchers at USC, Prime Intellect, and the Nucleic Acid Observatory.
METAGENE-1 works by using a 7-billion-parameter autoregressive transformer language model to analyze metagenomic data. The model is trained on a novel corpus of diverse metagenomic DNA and RNA sequences, which enables it to capture the full distribution of genomic information present across the human microbiome. This approach allows METAGENE-1 to achieve state-of-the-art performance on pathogen detection and metagenomic embedding benchmarks.
Researchers and scientists in the field of public health and genomics can get the most value from METAGENE-1, as it provides a valuable tool for detecting pathogens and monitoring pandemics. The model's capabilities make it an essential resource for those working in biosurveillance and metagenomic anomaly detection.