nf-proteindesign¶

Overview¶

nf-proteindesign is a Nextflow pipeline for high-throughput protein design supporting two generative backends:

• BoltzGen (default) — a flow-matching generative model that uses design YAML specifications
• Proteina-Complexa — an all-atom generative diffusion model that uses pipeline config YAMLs

Design proteins, peptides, and nanobodies to bind various biomolecular targets with a comprehensive suite of downstream analysis modules. Both design backends converge into the same shared downstream pipeline.

Design Backends & Analysis Modules¶

Key Features¶

• Dual Design Backends: Choose BoltzGen (default) or Proteina-Complexa
• :material-parallel: Parallel Processing: Run multiple design specifications simultaneously
• YAML-Based Design: Complete control with custom design specifications
• Comprehensive Analysis: Six optional analysis modules for quality assessment
• Sequence Optimization: ProteinMPNN + Boltz-2 validation workflow
• Container Support: Full Docker and Singularity compatibility
• :material-gpu: GPU Acceleration: Optimized for NVIDIA GPU execution
• Organized Outputs: Structured results with unified reporting

:material-pipeline: Pipeline Workflow¶

graph TB
    A[Samplesheet] --> B{Design Tool?}
    B -->|boltzgen| C[BoltzGen Design<br/>Flow-matching inference]
    B -->|complexa| D[Complexa Design<br/>Diffusion generation]

    C --> E[Budget Designs<br/>PDB Files]
    D --> E

    E --> F{ProteinMPNN<br/>Enabled?}
    F -->|No| Z[Design Outputs Only]
    F -->|Yes| G[Sequence Optimization<br/>Parallel per Design]

    G --> H{Boltz-2<br/>Enabled?}
    H -->|No| Y[MPNN Sequences Only]
    H -->|Yes| I[Prepare Sequences<br/>Split + Target]

    I --> J[Boltz-2 Structure<br/>Prediction]
    J --> K[Boltz-2 Structures<br/>CIF + NPZ]

    K --> L{Analysis<br/>Modules?}
    L -->|IPSAE| M[Interface Scoring]
    L -->|PRODIGY| N[Binding Affinity]
    L -->|Foldseek| O[Structural Search]

    M --> P{Consolidate?}
    N --> P
    O --> P
    P -->|Yes| Q[Unified CSV + HTML<br/>Report]

    Q --> R[Final Results]
    K --> R
    Z --> R
    Y --> R

    style C fill:#1565C0,stroke:#1565C0,color:#fff
    style D fill:#9C27B0,stroke:#9C27B0,color:#fff
    style G fill:#8E24AA,stroke:#8E24AA,color:#fff
    style J fill:#7B1FA2,stroke:#7B1FA2,color:#fff
    style Q fill:#6A1B9A,stroke:#6A1B9A,color:#fff

    classDef note fill:#FFF3E0,stroke:#FF9800,color:#000
    class L note

Quick Start¶

Get started with nf-proteindesign in minutes:

# 1. Install Nextflow (>=23.04.0)
curl -s https://get.nextflow.io | bash

# 2a. Run with BoltzGen (default)
nextflow run seqeralabs/nf-proteindesign \
    -profile docker \
    --input samplesheet.csv \
    --outdir results

# 2b. Or run with Complexa
nextflow run seqeralabs/nf-proteindesign \
    -profile docker \
    --protein_design_tool complexa \
    --input samplesheet_complexa.csv \
    --complexa_ckpt_dir /path/to/checkpoints \
    --outdir results

What Can You Design?¶

The pipeline leverages BoltzGen or Complexa to design:

• Proteins: Full-length protein binders targeting specific interfaces
• Peptides: Short peptide sequences for tight binding
• Nanobodies: Compact antibody fragments for therapeutic applications
• Multi-target Binders: Design to multiple targets simultaneously

All with the flexibility to specify: - Binding site residues - Designed chain type (protein, peptide, nanobody) - Chain length constraints - Custom diffusion parameters

Documentation Structure¶

Computing Requirements¶

Contributing¶

We welcome contributions! The pipeline is designed with modularity and extensibility in mind.

License¶

This project is licensed under the MIT License - see the LICENSE file for details.