agentleFS
dtunaidtunai/agent-skills-for-compute/skills/bionemo/SKILL.md

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

The file

Files
SKILL.md

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

ModelTypeTask
ESM-2Protein language modelSequence embedding, property prediction
AlphaFold2Structure prediction3D protein folding
AlphaFold2-MultimerComplex predictionMulti-chain structure
ProteinMPNNInverse foldingSequence design from structure
RFdiffusionGenerative diffusionDe novo protein structure generation
Evo2Genomic foundation modelDNA/RNA generation, variant prediction, 1B/7B/40B
GeneformerSingle-cell transformerCell embeddings, type classification, GRN, 10M/106M
AMPLIFYProtein language modelESM-2 variant, 120M/350M, modified layers
DiffDockDocking modelProtein-ligand binding
MolMIMMolecular modelSmall molecule generation

NIM Microservice Endpoints

ServiceEndpointMethod
AlphaFold2/protein-structure/alphafold2/predict-structure-from-sequencePOST
AlphaFold2-Multimer/protein-structure/alphafold2/multimer/predict-structure-from-sequencesPOST
RFdiffusion/biology/ipd/rfdiffusion/generatePOST
ProteinMPNN/biology/ipd/proteinmpnn/predictPOST
Health check/v1/health/readyGET

Protein Binder Design Pipeline

Target PDB → AlphaFold2 (structure) → RFdiffusion (binder scaffold)
  → ProteinMPNN (sequence design) → AlphaFold2-Multimer (validation)

Key Packages

PackagePurpose
bionemo-esm2ESM-2 model, training, fine-tuning, inference
bionemo-coreShared utilities, data loading, checkpoint management
bionemo-geneformerSingle-cell transcriptomics
bionemo-amplifyAMPLIFY protein language model (ESM-2 variant)
bionemo-evo2Evo2 genomic foundation model
bionemo-mocoContinuous/discrete generative modeling
bionemo-llmShared LLM utilities, BioBERT, training
bionemo-scdlSingle 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

PriorityCategoryImpactPrefix
1ESM-2 Protein LanguageCRITICALesm2-*
2Structure PredictionCRITICALstructure-*
3Protein DesignHIGHprotein-*
4NIM MicroservicesHIGHnim-*
5Evo2 Genomic ModelHIGHevo2-*
6Geneformer Single-CellHIGHgeneformer-*
7Training InfrastructureHIGHtraining-*
8Drug DiscoveryMEDIUMdrug-*
9Data PreparationMEDIUMdata-*

References

Full documentation with code examples in references/:

FileImpactDescription
esm2-protein-language.mdCRITICALESM-2 training, fine-tuning, inference, embeddings
structure-prediction.mdCRITICALAlphaFold2 folding, MSA, multimer prediction
protein-design.mdHIGHRFdiffusion generation, ProteinMPNN inverse folding
nim-microservices.mdHIGHNIM API endpoints, deployment, health checks
drug-discovery.mdMEDIUMMulti-model pipelines, binder design blueprint
evo2-genomic-model.mdHIGHEvo2 DNA/RNA model, variant prediction, generation
geneformer-single-cell.mdHIGHGeneformer single-cell embeddings, cell type classification
training-infrastructure.mdHIGHHardware, containers, distributed training, recipes
data-preparation.mdMEDIUMBiological data preprocessing, tokenization, datasets

Problem -> Skill Mapping

ProblemStart With
Get protein embeddingsesm2-protein-language.md
Predict protein structurestructure-prediction.md
Design new proteinsprotein-design.md
Deploy model as APInim-microservices.md
Build drug discovery pipelinedrug-discovery.md
Prepare biological datadata-preparation.md
Fine-tune ESM-2esm2-protein-language.md
Validate protein binderdrug-discovery.md
Predict variant effects on DNA/RNAevo2-genomic-model.md
Generate DNA/RNA sequencesevo2-genomic-model.md
Classify cell types from scRNA-seqgeneformer-single-cell.md
Build gene regulatory networksgeneformer-single-cell.md
Set up distributed trainingtraining-infrastructure.md
Pre-train ESM-2 from scratchesm2-protein-language.md -> training-infrastructure.md
Convert h5ad to SCDLdata-preparation.md
Run AlphaFold2 inferencestructure-prediction.md -> nim-microservices.md

Attribution

Based on NVIDIA BioNeMo Framework documentation, bionemo-framework repository, and generative-protein-binder-design blueprint.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.