README.md

---
license: mit
base_model:
- RaphaelMourad/Mistral-DNA-v1-422M-hg38
tags:
- genomics
- virus
library_name: transformers
paper:
  title: 'Vir2vec: A Genome-Wide Viral Embedding'
  url: https://www.biorxiv.org/content/10.64898/2025.12.12.693901v1
pipeline_tag: feature-extraction
---

# Vir2vec: A Genome-Wide Viral Embedding

## Model description
[Vir2vec](https://www.biorxiv.org/content/10.64898/2025.12.12.693901v1) is a viral genomic language model (gLM) designed to produce fixed-length, genome-level embeddings that can be fine-tuned across downstream tasks such as viral discrimination, host-range prediction, and variant typing. For more details and training scripts check [GitHub](https://github.com/pabloarozarena/Vir2vec)

## Intended use
Vir2vec embeddings are intended for tasks including (but not limited to):

- Virus vs non-virus genome/read discrimination
- DNA vs RNA virus classification
- Host-range prediction
- Intra-genus separation (e.g., HIV-1 vs HIV-2)
- Variant/subtype typing (e.g., SARS-CoV-2 lineages)
- Phenotypic signal detection (e.g., tissue tropism proxies)

## Model sizes
All Vir2vec model scales produce fixed-length **4,096-dimensional genome-level embeddings** via max-pooled vocabulary logits:

- **422M** (`main` branch)
- **138M** (`revision="138M"`)
- **17M** (`revision="17M"`)

## How to use
### Load from Hugging Face
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("pabloarozarenad/Vir2vec", trust_remote_code=True) # Add revision=138M or revision=17M to change model size. 422M is default.
model = AutoModelForCausalLM.from_pretrained("pabloarozarenad/Vir2vec", trust_remote_code=True) # Add revision=138M or revision=17M to change model size. 422M is default.
model.eval()
```

### Compute embeddings
```python
dna = "ACGTAGCATCGCGATGACTGCATCACT"
inputs = tokenizer(dna, return_tensors="pt")

with torch.no_grad():
    # Forward pass to obtain vocabulary logits [batch, seq_len, 4096]
    outputs = model(**inputs)
    logits = outputs.logits

    # Max-pool logits over token positions -> 4,096-dimensional embedding
    embedding = torch.max(logits, dim=1).values[0]

print(embedding.shape)  # torch.Size([4096])
```

## Access
Vir2vec can be loaded upon request, subject to providing an institutional email address, a brief description of the intended use, and the associated IRB protocol number. For more info contact pablo.arozarenadonel01@universitadipavia.it