bionemo
Skill8 starsChanged 8 months agoMITView on GitHub
Provides NVIDIA BioNeMo patterns for computational biology and AI-driven drug discovery. Applies to tasks involving protein language models (ESM-2), structure prediction (AlphaFold2), protein design (RFdiffusion, ProteinMPNN), molecular generation, NIM microservice deployment, or multi-model biology pipelines.
- Sends data out
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- validate-skillsSkill
- alchemi-toolkit-opsSkill
- autoresearch-setupSkill
- biosimspaceSkill
- cuda-quantumSkill
- cutileSkill
- daskSkill
- flashinferSkill
- materials-projectSkill
- mpiSkill
- nemotronSkill
- omniverse-simreadySkill
- physicsnemoSkill
- polarsSkill
- prime-verifiersSkill
- qiskitSkill
- raySkill
- rdkitSkill
- slurmSkill
- tinkerSkill
- tritonSkill
The file
Files
BioNeMo
Overview
NVIDIA's software ecosystem for building, training, fine-tuning, and deploying AI models for life sciences. BioNeMo Framework provides optimized biomolecular foundation models (ESM-2, AlphaFold2, ProteinMPNN, RFdiffusion) with distributed training support, while BioNeMo NIMs offer production-ready inference microservices with REST API endpoints for scalable deployment.
Quick Pattern
Incorrect — manual protein embedding without framework:
# Raw transformer, no optimization, no pretrained weights
model = TransformerEncoder(...)
embeddings = model(tokenize(sequence))Correct — BioNeMo ESM-2 fine-tuning with pretrained checkpoint:
from bionemo.esm2.model.finetune.finetune_regressor import ESM2FineTuneSeqConfig
from bionemo.core.data.load import load
pretrain_ckpt = load("esm2/650m:2.0")
config = ESM2FineTuneSeqConfig(initial_ckpt_path=str(pretrain_ckpt))
checkpoint, metrics, trainer = train_model(
experiment_name="finetune_regressor",
experiment_dir=Path(results_dir),
config=config,
data_module=data_module,
n_steps_train=50,
)Quick Command
# Pull BioNeMo container
docker pull nvcr.io/nvidia/bionemo/bionemo-framework:latest
# Run container with GPU
docker run --gpus all -it --rm \
-v ${PWD}:/workspace \
nvcr.io/nvidia/bionemo/bionemo-framework:latest bash
# Download ESM-2 checkpoint
python -c "from bionemo.core.data.load import load; load('esm2/650m:2.0')"
# Run ESM-2 inference
infer_esm2 --checkpoint-path /path/to/ckpt \
--data-path data.csv \
--results-path results/
# NIM health check
curl http://localhost:8000/v1/health/ready
# RFdiffusion via NIM
curl -X POST http://localhost:8000/biology/ipd/rfdiffusion/generate \
-H "Content-Type: application/json" \
-d '{"contigs": "A10-100/0 50-150"}'Quick Reference
Supported Models
| Model | Type | Task |
| ESM-2 | Protein language model | Sequence embedding, property prediction |
| AlphaFold2 | Structure prediction | 3D protein folding |
| AlphaFold2-Multimer | Complex prediction | Multi-chain structure |
| ProteinMPNN | Inverse folding | Sequence design from structure |
| RFdiffusion | Generative diffusion | De novo protein structure generation |
| Evo2 | Genomic foundation model | DNA/RNA generation, variant prediction, 1B/7B/40B |
| Geneformer | Single-cell transformer | Cell embeddings, type classification, GRN, 10M/106M |
| AMPLIFY | Protein language model | ESM-2 variant, 120M/350M, modified layers |
| DiffDock | Docking model | Protein-ligand binding |
| MolMIM | Molecular model | Small molecule generation |
NIM Microservice Endpoints
| Service | Endpoint | Method |
| AlphaFold2 | /protein-structure/alphafold2/predict-structure-from-sequence | POST |
| AlphaFold2-Multimer | /protein-structure/alphafold2/multimer/predict-structure-from-sequences | POST |
| RFdiffusion | /biology/ipd/rfdiffusion/generate | POST |
| ProteinMPNN | /biology/ipd/proteinmpnn/predict | POST |
| Health check | /v1/health/ready | GET |
Protein Binder Design Pipeline
Target PDB → AlphaFold2 (structure) → RFdiffusion (binder scaffold)
→ ProteinMPNN (sequence design) → AlphaFold2-Multimer (validation)Key Packages
| Package | Purpose |
bionemo-esm2 | ESM-2 model, training, fine-tuning, inference |
bionemo-core | Shared utilities, data loading, checkpoint management |
bionemo-geneformer | Single-cell transcriptomics |
bionemo-amplify | AMPLIFY protein language model (ESM-2 variant) |
bionemo-evo2 | Evo2 genomic foundation model |
bionemo-moco | Continuous/discrete generative modeling |
bionemo-llm | Shared LLM utilities, BioBERT, training |
bionemo-scdl | Single Cell Data Loader format |
When to Apply
Reference these guidelines when:
- Working with protein language models (ESM-2 embeddings, fine-tuning)
- Predicting protein 3D structures (AlphaFold2)
- Designing novel proteins or binders (RFdiffusion, ProteinMPNN)
- Building drug discovery pipelines
- Deploying biology AI models as microservices (NIM)
- Processing biological sequence data
- Analyzing genomic sequences (DNA/RNA variant effects, generation) with Evo2
- Processing single-cell RNA-seq data (cell type classification, GRN) with Geneformer
- Setting up distributed training infrastructure (NeMo2, Megatron, TransformerEngine)
- Running multi-model biology workflows
Priority-Ordered Guidelines
| Priority | Category | Impact | Prefix |
| 1 | ESM-2 Protein Language | CRITICAL | esm2-* |
| 2 | Structure Prediction | CRITICAL | structure-* |
| 3 | Protein Design | HIGH | protein-* |
| 4 | NIM Microservices | HIGH | nim-* |
| 5 | Evo2 Genomic Model | HIGH | evo2-* |
| 6 | Geneformer Single-Cell | HIGH | geneformer-* |
| 7 | Training Infrastructure | HIGH | training-* |
| 8 | Drug Discovery | MEDIUM | drug-* |
| 9 | Data Preparation | MEDIUM | data-* |
References
Full documentation with code examples in references/:
| File | Impact | Description |
| esm2-protein-language.md | CRITICAL | ESM-2 training, fine-tuning, inference, embeddings |
| structure-prediction.md | CRITICAL | AlphaFold2 folding, MSA, multimer prediction |
| protein-design.md | HIGH | RFdiffusion generation, ProteinMPNN inverse folding |
| nim-microservices.md | HIGH | NIM API endpoints, deployment, health checks |
| drug-discovery.md | MEDIUM | Multi-model pipelines, binder design blueprint |
| evo2-genomic-model.md | HIGH | Evo2 DNA/RNA model, variant prediction, generation |
| geneformer-single-cell.md | HIGH | Geneformer single-cell embeddings, cell type classification |
| training-infrastructure.md | HIGH | Hardware, containers, distributed training, recipes |
| data-preparation.md | MEDIUM | Biological data preprocessing, tokenization, datasets |
Problem -> Skill Mapping
| Problem | Start With |
| Get protein embeddings | esm2-protein-language.md |
| Predict protein structure | structure-prediction.md |
| Design new proteins | protein-design.md |
| Deploy model as API | nim-microservices.md |
| Build drug discovery pipeline | drug-discovery.md |
| Prepare biological data | data-preparation.md |
| Fine-tune ESM-2 | esm2-protein-language.md |
| Validate protein binder | drug-discovery.md |
| Predict variant effects on DNA/RNA | evo2-genomic-model.md |
| Generate DNA/RNA sequences | evo2-genomic-model.md |
| Classify cell types from scRNA-seq | geneformer-single-cell.md |
| Build gene regulatory networks | geneformer-single-cell.md |
| Set up distributed training | training-infrastructure.md |
| Pre-train ESM-2 from scratch | esm2-protein-language.md -> training-infrastructure.md |
| Convert h5ad to SCDL | data-preparation.md |
| Run AlphaFold2 inference | structure-prediction.md -> nim-microservices.md |
Attribution
Based on NVIDIA BioNeMo Framework documentation, bionemo-framework repository, and generative-protein-binder-design blueprint.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

