> For the complete documentation index, see [llms.txt](https://academy.dnanexus.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.dnanexus.com/public-datasets-on-the-dnanexus-platform/ai-ml-experience-accelerator/nvidia-bionemo-pretrained-model-weights-esm-2-evo-2-geneformer.md).

# NVIDIA BioNeMo pretrained model weights: ESM-2, Evo-2, Geneformer

## Necessary Disclaimers and Legal

The user is responsible for reviewing and complying with the license requirements of the models, notebooks, and data referenced in this documentation.

Users are responsible for the costs associated with analyzing notebooks and its storage in their project spaces. 

Instance type availability and pricing are subject to the contract between the user or the user’s organization and DNAnexus.

## Citations for foundation models

If you use any of the following models in your work, please cite the corresponding publications:

* ESM-2 model:
  * Hugging face: <https://huggingface.co/facebook/esm2_t33_650M_UR50D>&#x20;
  * Paper: <https://www.biorxiv.org/content/10.1101/2022.07.20.500902v2>
* Evo-2 model:
  * Hugging face: <https://huggingface.co/arcinstitute/evo2_7b>
  * Paper: <https://www.biorxiv.org/content/10.1101/2025.02.18.638918v1>&#x20;
* Geneformer:
  * Hugging face: <https://huggingface.co/ctheodoris/Geneformer>&#x20;
  * Paper: <https://www.nature.com/articles/s41586-023-06139-9>&#x20;

## Overview

Foundation models are transforming drug discovery, but deploying them requires specialized infrastructure that most pharma IT organizations cannot provide: large GPU instances, pre-downloaded model weights, and compatible software environments. This accelerator makes foundation models accessible within DNAnexus's secure, compliant environment. On DNAnexus, you can access pre-download model weights of three models: ESM-2,  Evo-2 and Geneformer.

Summary of Models to Access

| Model Family | Domain Focus                | Checkpoint             |
| ------------ | --------------------------- | ---------------------- |
| ESM-2        | Proteins / Amino Acids      | esm2\_t33\_650M\_UR50D |
| Evo 2        | Genomes / DNA               | evo-2-7b               |
| Geneformer   | Transcriptomics (scRNA-seq) | Geneformer             |

These models are packaged into a unified notebook snapshot image "NVIDIA BioNeMo Lite", built on the existing "ML" feature container image with HuggingFace packages and foundation model architectures pre-installed. Three notebooks are provided to showcase and verify the snapshot for each model respectively.

## Using foundation models on DNAnexus

### Copying demo notebooks and model weights into a project

To explore the demo analyses, copy the notebooks and model weights from the public project into your own project space:

1. Create a project for your analyses, billed to your own organization. Tutorials on project setup can be found [here](https://academy.dnanexus.com/overview-of-the-platform/setting-up-a-project).
2. Navigate to the Resources tab, locate the project titled "Public Datasets AWS US (East)," and select the "Foundation\_models" folder.

<figure><img src="/files/jObnrwJ1ZuMsxUvFgZlZ" alt=""><figcaption></figcaption></figure>

3. Select the three notebooks (.ipynb) and models folder.

<figure><img src="/files/PzCjLLQI5kCi9rsRxTnu" alt=""><figcaption></figcaption></figure>

4. Click "Copy" in the top-right menu and select the project created in Step 1.
5. Return to your project space to begin exploring the notebooks.

To run the notebooks, refer to the[ JupyterLab](https://academy.dnanexus.com/interactivecloudcomputing/jupyterlab/introduction) section of the Academy documentation, which includes instructions for the standard environment. We recommend using the prepared snapshot-NVIDIA\_BioNeMo\_Lite-jupyterlab.tar.gz, available in the Notebook\_snapshot folder of the public project.

<figure><img src="/files/pg0bpzpvbjuIABa4No73" alt=""><figcaption></figcaption></figure>

### Running the notebooks

Three notebooks are developed for JupyterLab with Python, R, Stata, ML, Image Processing (version 2.11). When launching JupyterLab, select the ML feature and the snapshot snapshot-NVIDIA\_BioNeMo\_Lite-jupyterlab.tar.gz.

| Notebook                                       | AWS Instance             | Azure Instance              |
| ---------------------------------------------- | ------------------------ | --------------------------- |
| ESM2\_verification\_test\_base-env.ipynb       | mem2\_ssd1\_gpu\_x16     | azure:mem3\_ssd2\_gpu4\_x64 |
| Evo2\_verification\_test\_base-env.ipynb       | mem2\_ssd2\_gpu1\_v2\_x8 | azure:mem3\_ssd2\_gpu4\_x64 |
| Geneformer\_verification\_test\_base-env.ipynb | mem2\_ssd2\_gpu1\_v2\_x8 | azure:mem3\_ssd2\_gpu4\_x64 |

### Steps for launching notebooks

1. Choose a snapshot from Notebook Snapshot folder. Note: the path for this snapshot should be in your own project.&#x20;

<img src="/files/5lMLTdJIMCghpOj0aDtS" alt="" height="350.54700157645823" width="625.011787559918">

2. Choose an instance for the notebook.

<img src="/files/qljyf9931Sf8Zah9t5KN" alt="" height="351.03470200816105" width="624">

3. Set the job name and output destination, then launch the analysis. Note: please change the output location to your project.&#x20;

<img src="/files/dBrd9Lo3Jcc8uAakvtUP" alt="" height="352.08755185031634" width="624">