skills.rest
NVIDIA-BioNeMo
NVIDIA-BioNeMoOFFICIAL
Explore all skills by this author →
WebsiteGitHub

rfdiffusion-nim

Generate protein backbone structures with RFDiffusion NIM via hosted or local Docker inference.

413|62|Updated Jun 23, 2026
Search Tags:#biotech#pdb#generative#protein#nim#rfdiffusion
One-click install
npx skills add https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit --skill rfdiffusion-nim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rfdiffusion-nim
Source: https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/plugins/bionemo-agent-toolkit/skills/rfdiffusion-nim
Command: npx skills add https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit --skill rfdiffusion-nim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes references (resource) components.

What problem does it solve?

This Skill automates the complex process of generating de novo protein backbones, motif scaffolds, and binder designs, removing the need for manual structural modeling and local infrastructure management.

Core Features & Use Cases

  • De Novo Design: Generate novel protein backbones from scratch based on length constraints.
  • Motif Scaffolding: Preserve functional loops or motifs while generating a surrounding protein structure.
  • Binder Design: Create protein binders specifically optimized to target hotspots on a known protein structure.
  • Use Case: A researcher can use this to generate a library of potential binder backbones for a specific viral protein target, which are then passed to ProteinMPNN for sequence design.

Quick Start

Use the rfdiffusion-nim skill to generate a 100-residue de novo protein backbone using the hosted NVIDIA API.

Frequently Asked Questions about rfdiffusion-nim

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate de novo protein backbones using the RFDiffusion NIM?▼

To generate de novo protein backbones, use the rfdiffusion-nim skill with the hosted NVIDIA API endpoint, specifying your desired length constraints to produce novel structural scaffolds.

What is motif scaffolding and how does it work for protein design?▼

Motif scaffolding preserves functional loops or motifs while generating a surrounding protein structure, allowing you to maintain critical binding interfaces within a newly designed backbone.

Do I need NGC API credentials to design protein binders with this tool?▼

Yes, valid NGC API credentials are required to access the hosted NVIDIA API endpoints for generating protein binders optimized to target specific hotspots on known structures.

Can I run RFDiffusion locally using Docker for high-throughput structural biology?▼

Yes, the skill supports local Docker-based inference as an alternative to the hosted NVIDIA API, enabling high-throughput structural biology workflows without relying on remote endpoints.

How do I define structural constraints when designing custom protein backbones?▼

Structural constraints and design modes are defined using the contigs DSL, which allows you to specify precise parameters for de novo design, motif scaffolding, and binder development.

What's the best way to design protein binders for a specific viral protein target?▼

Use the binder design mode to create protein binders optimized for target hotspots on a known structure, then pass the generated backbone library to ProteinMPNN for sequence design.

Related Skills

Explore More Education & Research Skills→
NVIDIA-BioNeMoNVIDIA-BioNeMo
413

openfold2-nim

Predict monomer protein structures from amino-acid sequences via OpenFold2 NIM microservices.

Official
Advanced
mims-harvardmims-harvard
1.6k

tooluniverse-protein-therapeutic-design

Design protein therapeutics with RFdiffusion, ProteinMPNN, and ESMFold validation.

Official
Advanced
K-Dense-AIK-Dense-AI
33.0k

alphafold-database

Retrieve AlphaFold-predicted protein structures and confidence metrics by UniProt IDs.

Official
Intermediate
zongtingweizongtingwei
25

rfdiffusion

Generate de novo protein backbones with a diffusion-based generative model.

Community
Advanced