bionemo-framework / Git / Diff of /README.md

Models:

Amanda-D/

bionemo-framework

Downloads: 1

Diff of /README.md [b9e282] .. [be1279]

Switch to unified view


# BioNeMo Framework

[![Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU)
[![Docs Build](https://img.shields.io/github/actions/workflow/status/NVIDIA/bionemo-framework/pages/pages-build-deployment?label=docs-build)](https://nvidia.github.io/bionemo-framework)
[![Test Status](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml)
[![Latest Tag](https://img.shields.io/github/v/tag/NVIDIA/bionemo-framework?label=latest-version)](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework/tags)
[![codecov](https://codecov.io/gh/NVIDIA/bionemo-framework/branch/main/graph/badge.svg?token=XqhegdZRqB)](https://codecov.io/gh/NVIDIA/bionemo-framework)

NVIDIA BioNeMo Framework is a is a comprehensive suite of programming tools, libraries, and models designed for computational drug discovery.
It accelerates the most time-consuming and costly stages of building and adapting biomolecular AI models by providing
domain-specific, optimized models and tooling that are easily integrated into GPU-based computational resources for the
fastest performance on the market. You can access BioNeMo Framework as a free community resource here in this repository
or learn more at <https://www.nvidia.com/en-us/clara/bionemo/> about getting an enterprise license for improved
expert-level support.

BioNeMo Framework is part of a larger ecosystem of NVIDIA Biopharma products. Get notified of new releases, bug fixes, critical security updates, and more for biopharma. [Subscribe.](https://www.nvidia.com/en-us/clara/biopharma/product-updates/)

## Structure of the Framework

The `bionemo-framework` is organized into independently installable namespace packages. These are located under the
`sub-packages/` directory. Please refer to [PEP 420 – Implicit Namespace Packages](https://peps.python.org/pep-0420/)
for details.


## Documentation Resources

- **Official Documentation:** For user guides, API references, and troubleshooting, visit our [official documentation](https://docs.nvidia.com/bionemo-framework/latest/).
- **In-Progress Documentation:** To explore the latest features and developments, check the documentation reflecting the current state of the `main` branch [here](https://nvidia.github.io/bionemo-framework/). Note that this may include references to features or APIs that are not yet finalized.

## Getting Started with BioNeMo Framework

Full documentation on using the BioNeMo Framework is provided in our documentation:
<https://docs.nvidia.com/bionemo-framework/latest/user-guide/>. To simplify the integration of optimized third-party dependencies, BioNeMo is primarily distributed as a containerized library. You can download the latest released container for the BioNeMo Framework from
[NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework). To launch a pre-built container, you can use the brev.dev launchable [![ Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU) or execute the following command:

```bash
docker run --rm -it \
  --gpus=all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 \
  nvcr.io/nvidia/clara/bionemo-framework:nightly \
  /bin/bash
```

### Setting up a local development environment

#### Initializing 3rd-party dependencies as git submodules

The NeMo and Megatron-LM dependencies are included as git submodules in bionemo2. The pinned commits for these submodules represent the "last-known-good" versions of these packages
that are confirmed to be working with bionemo2 (and those that are tested in CI).

To initialize these sub-modules when cloning the repo, add the `--recursive` flag to the git clone command:

```bash
git clone --recursive git@github.com:NVIDIA/bionemo-framework.git
cd bionemo-framework
```

To download the pinned versions of these submodules within an existing git repository, run

```bash
git submodule update --init --recursive
```

Different branches of the repo can have different pinned versions of these third-party submodules. Ensure submodules are automatically updated after switching branches or pulling updates by configuring git with:


```bash
git config submodule.recurse true
```

**NOTE**: this setting will not download **new** or remove **old** submodules with the branch's changes.
You will have to run the full `git submodule update --init --recursive` command in these situations.

#### Build the Docker Image Locally


With a locally cloned repository and initialized submodules, build the BioNeMo container using:

```bash
docker buildx build . -t my-container-tag
```


#### VSCode Devcontainer for Interactive Debugging

We distribute a [development container](https://devcontainers.github.io/) configuration for vscode
(`.devcontainer/devcontainer.json`) that simplifies the process of local testing and development. Opening the
bionemo-framework folder with VSCode should prompt you to re-open the folder inside the devcontainer environment.

### NOTE
The first time you launch the devcontainer, it may take a long time to build the image. Building the image locally
(using the command shown above) will ensure that most of the layers are present in the local docker cache.

### Quick Start

See the [tutorials pages](https://docs.nvidia.com/bionemo-framework/latest/user-guide/examples/bionemo-esm2/pretrain/)
for example applications and getting started guides.

	a/README.md		b/README.md
1	# BioNeMo Framework	1	# BioNeMo Framework
2		2
3	[![Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU)	3	[![Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU)
4	[![Docs Build](https://img.shields.io/github/actions/workflow/status/NVIDIA/bionemo-framework/pages/pages-build-deployment?label=docs-build)](https://nvidia.github.io/bionemo-framework)	4	[![Docs Build](https://img.shields.io/github/actions/workflow/status/NVIDIA/bionemo-framework/pages/pages-build-deployment?label=docs-build)](https://nvidia.github.io/bionemo-framework)
5	[![Test Status](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml)	5	[![Test Status](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/NVIDIA/bionemo-framework/actions/workflows/unit-tests.yml)
6	[![Latest Tag](https://img.shields.io/github/v/tag/NVIDIA/bionemo-framework?label=latest-version)](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework/tags)	6	[![Latest Tag](https://img.shields.io/github/v/tag/NVIDIA/bionemo-framework?label=latest-version)](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework/tags)
7	[![codecov](https://codecov.io/gh/NVIDIA/bionemo-framework/branch/main/graph/badge.svg?token=XqhegdZRqB)](https://codecov.io/gh/NVIDIA/bionemo-framework)	7	[![codecov](https://codecov.io/gh/NVIDIA/bionemo-framework/branch/main/graph/badge.svg?token=XqhegdZRqB)](https://codecov.io/gh/NVIDIA/bionemo-framework)
8		8
9	NVIDIA BioNeMo Framework is a is a comprehensive suite of programming tools, libraries, and models designed for computational drug discovery.	9	NVIDIA BioNeMo Framework is a is a comprehensive suite of programming tools, libraries, and models designed for computational drug discovery.
10	It accelerates the most time-consuming and costly stages of building and adapting biomolecular AI models by providing	10	It accelerates the most time-consuming and costly stages of building and adapting biomolecular AI models by providing
11	domain-specific, optimized models and tooling that are easily integrated into GPU-based computational resources for the	11	domain-specific, optimized models and tooling that are easily integrated into GPU-based computational resources for the
12	fastest performance on the market. You can access BioNeMo Framework as a free community resource here in this repository	12	fastest performance on the market. You can access BioNeMo Framework as a free community resource here in this repository
13	or learn more at <https://www.nvidia.com/en-us/clara/bionemo/> about getting an enterprise license for improved	13	or learn more at <https://www.nvidia.com/en-us/clara/bionemo/> about getting an enterprise license for improved
14	expert-level support.	14	expert-level support.
15		15
16	BioNeMo Framework is part of a larger ecosystem of NVIDIA Biopharma products. Get notified of new releases, bug fixes, critical security updates, and more for biopharma. [Subscribe.](https://www.nvidia.com/en-us/clara/biopharma/product-updates/)	16	BioNeMo Framework is part of a larger ecosystem of NVIDIA Biopharma products. Get notified of new releases, bug fixes, critical security updates, and more for biopharma. [Subscribe.](https://www.nvidia.com/en-us/clara/biopharma/product-updates/)
17		17
18	## Structure of the Framework	18	## Structure of the Framework
19		19
20	The `bionemo-framework` is organized into independently installable namespace packages. These are located under the	20	The `bionemo-framework` is organized into independently installable namespace packages. These are located under the
21	`sub-packages/` directory. Please refer to [PEP 420 – Implicit Namespace Packages](https://peps.python.org/pep-0420/)	21	`sub-packages/` directory. Please refer to [PEP 420 – Implicit Namespace Packages](https://peps.python.org/pep-0420/)
22	for details.	22	for details.
23		23
24		24
25	## Documentation Resources	25	## Documentation Resources
26		26
27	- Official Documentation: For user guides, API references, and troubleshooting, visit our [official documentation](https://docs.nvidia.com/bionemo-framework/latest/).	27	- Official Documentation: For user guides, API references, and troubleshooting, visit our [official documentation](https://docs.nvidia.com/bionemo-framework/latest/).
28	- In-Progress Documentation: To explore the latest features and developments, check the documentation reflecting the current state of the `main` branch [here](https://nvidia.github.io/bionemo-framework/). Note that this may include references to features or APIs that are not yet finalized.	28	- In-Progress Documentation: To explore the latest features and developments, check the documentation reflecting the current state of the `main` branch [here](https://nvidia.github.io/bionemo-framework/). Note that this may include references to features or APIs that are not yet finalized.
29		29
30	## Getting Started with BioNeMo Framework	30	## Getting Started with BioNeMo Framework
31		31
32	Full documentation on using the BioNeMo Framework is provided in our documentation:	32	Full documentation on using the BioNeMo Framework is provided in our documentation:
33	<https://docs.nvidia.com/bionemo-framework/latest/user-guide/>. To simplify the integration of optimized third-party dependencies, BioNeMo is primarily distributed as a containerized library. You can download the latest released container for the BioNeMo Framework from	33	<https://docs.nvidia.com/bionemo-framework/latest/user-guide/>. To simplify the integration of optimized third-party dependencies, BioNeMo is primarily distributed as a containerized library. You can download the latest released container for the BioNeMo Framework from
34	[NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework). To launch a pre-built container, you can use the brev.dev launchable [![ Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU) or execute the following command:	34	[NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/containers/bionemo-framework). To launch a pre-built container, you can use the brev.dev launchable [![ Click here to deploy.](https://uohmivykqgnnbiouffke.supabase.co/storage/v1/object/public/landingpage/brevdeploynavy.svg)](https://console.brev.dev/launchable/deploy/now?launchableID=env-2pPDA4sJyTuFf3KsCv5KWRbuVlU) or execute the following command:
35		35
36	```bash	36	```bash
37	docker run --rm -it \	37	docker run --rm -it \
38	--gpus=all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 \	38	--gpus=all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 \
39	nvcr.io/nvidia/clara/bionemo-framework:nightly \	39	nvcr.io/nvidia/clara/bionemo-framework:nightly \
40	/bin/bash	40	/bin/bash
41	```	41	```
42		42
43	### Setting up a local development environment	43	### Setting up a local development environment
44		44
45	#### Initializing 3rd-party dependencies as git submodules	45	#### Initializing 3rd-party dependencies as git submodules
46		46
47	The NeMo and Megatron-LM dependencies are included as git submodules in bionemo2. The pinned commits for these submodules represent the "last-known-good" versions of these packages	47	The NeMo and Megatron-LM dependencies are included as git submodules in bionemo2. The pinned commits for these submodules represent the "last-known-good" versions of these packages
48	that are confirmed to be working with bionemo2 (and those that are tested in CI).	48	that are confirmed to be working with bionemo2 (and those that are tested in CI).
49		49
50	To initialize these sub-modules when cloning the repo, add the `--recursive` flag to the git clone command:	50	To initialize these sub-modules when cloning the repo, add the `--recursive` flag to the git clone command:
51		51
52	```bash	52	```bash
53	git clone --recursive git@github.com:NVIDIA/bionemo-framework.git	53	git clone --recursive git@github.com:NVIDIA/bionemo-framework.git
54	cd bionemo-framework	54	cd bionemo-framework
55	```	55	```
56		56
57	To download the pinned versions of these submodules within an existing git repository, run	57	To download the pinned versions of these submodules within an existing git repository, run
58		58
59	```bash	59	```bash
60	git submodule update --init --recursive	60	git submodule update --init --recursive
61	```	61	```
62		62
63	Different branches of the repo can have different pinned versions of these third-party submodules. Ensure submodules are automatically updated after switching branches or pulling updates by configuring git with:	63	Different branches of the repo can have different pinned versions of these third-party submodules. Ensure submodules are automatically updated after switching branches or pulling updates by configuring git with:
64		64
65		65
66	```bash	66	```bash
67	git config submodule.recurse true	67	git config submodule.recurse true
68	```	68	```
69		69
70	NOTE: this setting will not download new or remove old submodules with the branch's changes.	70	NOTE: this setting will not download new or remove old submodules with the branch's changes.
71	You will have to run the full `git submodule update --init --recursive` command in these situations.	71	You will have to run the full `git submodule update --init --recursive` command in these situations.
72		72
73	#### Build the Docker Image Locally	73	#### Build the Docker Image Locally
74		74
75		75
76	With a locally cloned repository and initialized submodules, build the BioNeMo container using:	76	With a locally cloned repository and initialized submodules, build the BioNeMo container using:
77		77
78	```bash	78	```bash
79	docker buildx build . -t my-container-tag	79	docker buildx build . -t my-container-tag
80	```	80	```
81		81
82		82
83	#### VSCode Devcontainer for Interactive Debugging	83	#### VSCode Devcontainer for Interactive Debugging
84		84
85	We distribute a [development container](https://devcontainers.github.io/) configuration for vscode	85	We distribute a [development container](https://devcontainers.github.io/) configuration for vscode
86	(`.devcontainer/devcontainer.json`) that simplifies the process of local testing and development. Opening the	86	(`.devcontainer/devcontainer.json`) that simplifies the process of local testing and development. Opening the
87	bionemo-framework folder with VSCode should prompt you to re-open the folder inside the devcontainer environment.	87	bionemo-framework folder with VSCode should prompt you to re-open the folder inside the devcontainer environment.
88		88
89	> [!NOTE]	89	### NOTE
90	> The first time you launch the devcontainer, it may take a long time to build the image. Building the image locally	90	The first time you launch the devcontainer, it may take a long time to build the image. Building the image locally
91	> (using the command shown above) will ensure that most of the layers are present in the local docker cache.	91	(using the command shown above) will ensure that most of the layers are present in the local docker cache.
92		92
93	### Quick Start	93	### Quick Start
94		94
95	See the [tutorials pages](https://docs.nvidia.com/bionemo-framework/latest/user-guide/examples/bionemo-esm2/pretrain/)	95	See the [tutorials pages](https://docs.nvidia.com/bionemo-framework/latest/user-guide/examples/bionemo-esm2/pretrain/)
96	for example applications and getting started guides.	96	for example applications and getting started guides.