πŸ“– 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.

NTv3 Paper Summary

✨ Why NTv3?

πŸ€– Models (see collection)

Model Size Pre-training Post-training Tasks
NTv3-8M 8M params MLM ❌ Embeddings, light inference
NTv3-100M 100M params MLM βœ… Tracks, annotation
NTv3-650M 650M params MLM βœ… Tracks, annotation, best accuracy

πŸ““ Tutorial notebooks (browse folder)

πŸ““ Pipeline notebooks (browse folder)

πŸ”— Links

πŸ€– Load a pre-trained model

Here is an example of how to load and use a pre-trained NTv3 model.

from transformers import AutoTokenizer, AutoModelForMaskedLM

model_name = "InstaDeepAI/NTv3_650M_pre"

# Load model and tokenizer
model = AutoModelForMaskedLM.from_pretrained(model_name, trust_remote_code=True)
tok = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

# Tokenize input sequences
batch = tok(["ATCGNATCG", "ACGT"], add_special_tokens=False, padding=True, pad_to_multiple_of=128, return_tensors="pt")

# Run model
out = model(
  **batch,
  output_hidden_states=True,
  output_attentions=True
)

# Print output shapes
print(out.logits.shape)       # (B, L, V = 11)
print(len(out.hidden_states)) # convs + transformers + deconvs
print(len(out.attentions))    # equals transformer layers = 12

Model embeddings can be used for fine-tuning on downstream tasks.

TO DO: add pipeline for fine-tuning on functional tracks or genome annotation.

πŸ’» Use a post-trained model

Here is a quick example of how to use the post-trained NTv3 650M model to predict tracks for a human genomic window.

from transformers import pipeline
import torch

model_name = "InstaDeepAI/NTv3_650M_pos"

ntv3_tracks = pipeline(
    "ntv3-tracks",
    model=model_name,
    trust_remote_code=True,
    device=0 if torch.cuda.is_available() else -1,
)

# Run track prediction
out = ntv3_tracks(
  {
    "chrom": "chr19",
    "start": 6_700_000,
    "end": 6_831_072,
    "species": "human"
  }
)

# Print output shapes
# 7k human tracks over 37.5 % center region of the input sequence
print("bigwig_tracks_logits:", tuple(out.bigwig_tracks_logits.shape))
# Location of 21 genomic elements over 37.5 % center region of the input sequence
print("bed_tracks_logits:", tuple(out.bed_tracks_logits.shape))
# Language model logits for whole sequence over vocabulary
print("language model logits:", tuple(out.mlm_logits.shape))

Predictions can also be plotted for a subset of functional tracks and genomic elements:

tracks_to_plot = {
    "K562 RNA-seq": "ENCSR056HPM",
    "K562 DNAse": "ENCSR921NMD",
    "K562 H3k4me3": "ENCSR000DWD",
    "K562 CTCF": "ENCSR000AKO",
    "HepG2 RNA-seq": "ENCSR561FEE_P",
    "HepG2 DNAse": "ENCSR000EJV",
    "HepG2 H3k4me3": "ENCSR000AMP",
    "HepG2 CTCF": "ENCSR000BIE",
}
elements_to_plot = ["protein_coding_gene", "exon", "intron", "splice_donor", "splice_acceptor"]

out = ntv3_tracks(
    {"chrom": "chr19", "start": 6_700_000, "end": 6_831_072, "species": "human"},
    plot=True,
    tracks_to_plot=tracks_to_plot,
    elements_to_plot=elements_to_plot,
)
Output tracks visualization