Introducing METAGENE-1🧬, an open-source 7B-parameter metagenomics foundation model pretrained on 1.5 trillion base pairs. Built for pandemic monitoring, pathogen detection, and biosurveillance, with SOTA results across many genomics tasks. 🧵1/ - ThreadSky

oliu-io.bsky.social • 51 days ago

Introducing METAGENE-1🧬, an open-source 7B-parameter metagenomics foundation model pretrained on 1.5 trillion base pairs. Built for pandemic monitoring, pathogen detection, and biosurveillance, with SOTA results across many genomics tasks.
🧵1/

Comments

oliu-io.bsky.social•51 days ago

Why is METAGENE-1 special? 🤔We trained it on wastewater metagenomics, capturing the human-adjacent microbiome across the US for the past 12 months. This unlocks powerful capabilities for early pathogen detection and microbial ecosystems understanding. 🌱🦠
🌐Website: https://metagene.ai/
🧵2/

oliu-io.bsky.social•51 days ago

📊The data behind METAGENE-1:
- Brand-new dataset collected with experts from Southern California & Missouri
- 1.5 trillion base pairs from diverse wastewater samples
- Short reads (100–300 BPs), deep sequencing at scale
- Byte-Pair Encoding customized for genomic sequences
🧵3/

oliu-io.bsky.social•51 days ago

The METAGENE-1 model is 7B parameter Llama-style transformer 🦙, pretrained and optimized for anomaly detection, embedding, and multi-species genomics. Fully compatible with 🤗Hugging Face (https://huggingface.co/metagene-ai) – ready to use like any of your favorite LLMs!
🧵4/

oliu-io.bsky.social•51 days ago

📈METAGENE-1 achieves state-of-the-art results in:
- Pathogen detection
- Genomic embedding benchmarks
- Generalization to multi-species tasks
It already shows promise in public health and biosurveillance, and we are collaborating with experts to unlock its full impact.
🧵5/

oliu-io.bsky.social•51 days ago

🛡Tailored for detection, not design. We scoped METAGENE-1 to minimize risks while maximizing potential for public health and biosurveillance. Responsible open-sourcing matters. With open weights, we aim to drive progress in interpretability and safe genomics research.
🧵6/

oliu-io.bsky.social•51 days ago

We’re sharing METAGENE-1’s:
📄Paper: https://metagene.ai/metagene-1-paper.pdf
🌐Website: https://metagene.ai
🤗Model weights: https://huggingface.co/metagene-ai
🧵7/

oneai8.bsky.social•50 days ago

Awesome👍👍👍

Comments

Posting Rules

Reply