skills.rest
SciMate-AI
SciMate-AIOFFICIAL
Explore all skills by this author →
GitHub

esm

Design proteins and generate embeddings using ESM3 and ESM C.

1|Updated Mar 11, 2026
Search Tags:#embeddings#multimodal#bioinformatics#generation#protein#protein-design#esm3
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill esm-scimate-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/esm
Command: npx skills add https://github.com/SciMate-AI/scicli --skill esm-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Integrates protein-language-model tooling to streamline protein design and embedding workflows using ESM3 and ESM C, reducing setup effort and enabling reproducible experiments.

Core Features & Use Cases

  • Multimodal design and embedding: generate sequences, predict structures, and obtain residue-level embeddings for downstream analyses.
  • Local and cloud options: supports both local model usage and Forge API for scalable inference.
  • Common workflows: design novel proteins, perform inverse folding, and leverage embeddings for ML tasks.

Quick Start

Install the esm package, load a model, and start a simple sequence generation task from a partial protein sequence.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I generate protein embeddings for downstream machine learning tasks?▼

You can generate protein embeddings by loading a model via the esm package and using ESMProtein interfaces to obtain residue-level representations for your sequences. This supports broader sequence-structure-function workflows and ML tasks.

What is the best way to design novel proteins using ESM3?▼

Designing novel proteins with ESM3 involves using the esm package with GenerationConfig to guide sequence generation from a partial protein input. This streamlines multimodal design workflows and enables reproducible experiments.

Can I run ESM3 inverse folding locally or do I need a cloud API?▼

You can perform inverse folding using either local models or the Forge cloud API. The esm package supports both contexts, allowing you to choose local execution or scalable cloud inference based on your resource needs.

Does the esm package support multimodal protein sequence and structure prediction?▼

Yes, the esm package supports multimodal workflows to generate sequences and predict structures. It integrates ESM3 and ESM C to handle combined sequence, structure, and function tasks within Python-based environments.

What are the limitations when using Forge API for protein generation tasks?▼

Protein generation via the Forge API requires Python-based workflows using specific ESMProtein and GenerationConfig interfaces. Users must manage API context limits and ensure reproducible experiments by configuring generation parameters correctly.

Why do I need the ESMProtein and GenerationConfig interfaces for protein design?▼

ESMProtein and GenerationConfig are required to structure inputs and define parameters for protein design tasks. They enable the esm package to process partial sequences and execute reproducible generation workflows across local and Forge API contexts.

Related Skills

Explore More Education & Research Skills→
Hung-3008Hung-3008
1

esm

Design, analyze, and embed proteins with ESM3 and ESM C.

Community
Advanced
biomaps-infrabiomaps-infra

db-alphafold

Retrieve AlphaFold protein structures by UniProt ID and download PDB/mmCIF files.

Official
Intermediate
Estrella-231Estrella-231

esm

Generate protein sequences, predict structures, and extract embeddings with ESM3 and ESM C.

Community
Advanced
hxk622hxk622
8

esm

Generate protein sequences and structures with ESM3 and embeddings with ESM C.

Community
Advanced