🧬 NTv3 — Foundation Models for Long-Range Genomics
This Space is the companion hub for NTv3 models: runnable notebooks for inference, fine-tuning, interpretation, and sequence generation.
📖 About NTv3
NTv3 is a multi-species genomic foundation model family that unifies representation learning, functional-track prediction, genome annotation, and controllable sequence generation within a single U-Net-style backbone. It models up to 1 Mb of DNA at single-base resolution, using a conv–Transformer–deconv architecture that efficiently captures both local motifs and long-range regulatory dependencies. NTv3 is first pretrained on ~9T base pairs from the OpenGenome2 corpus spanning >128k species using masked language modeling, and then post-trained with a joint objective on ~16k functional tracks and annotation labels across 24 animal and plant species, enabling state-of-the-art cross-species functional prediction and base-resolution genome annotation.
Beyond prediction, NTv3 can be fine-tuned into a controllable generative model via masked-diffusion language modeling, allowing targeted design of regulatory sequences (for example, enhancers with specified activity and promoter selectivity) that have been validated experimentally.
🤖 Models (see collection)
- 📦 Pretrained checkpoints:
- 🎯 Post-trained checkpoints:
📓 Notebooks (browse folder)
- 🚀 00 — Quickstart inference
- 📊 01 — Tracks prediction
- 🏷️ 02 — Genome annotation / segmentation
- 🎯 03 — Fine-tune on bigwig tracks
- 🔍 04 — Model interpretation
- 🧪 05 — Sequence generation
💻 Model usage
Here is a quick example of how to use the post-trained NTv3 650M model on a human genomic window.
from transformers import AutoConfig
model_name = "InstaDeepAI/NTv3_650M"
# Load track prediction pipeline
cfg = AutoConfig.from_pretrained(model_name, trust_remote_code=True, force_download=True)
pipe = cfg.load_tracks_pipeline(model_name, device="auto") # or "cpu"/"cuda"/"mps"
# Run track prediction
out = pipe(
{
"chrom": "chr19",
"start": 6_700_000,
"end": 6_831_072,
"species": "human"
}
)
print(out.bigwig_tracks_logits.shape) # functional track predictions
print(out.bed_tracks_logits.shape) # genome annotation predictions
print(out.mlm_logits.shape) # MLM logits: (B, L, V = 11)🔗 Links
- 📄 Paper: (add link)
- 💻 JAX model code (GitHub)
- 🏆 NTv3 benchmark leaderboard: (add link)
📄 A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction
