esm

Generate protein sequences and embeddings with ESM3 and ESM C.

1|Updated Jan 14, 2026

Search Tags:#embeddings #bioinformatics #protein engineering #esm #protein design #generative models

Ready to run

npx skills add https://github.com/Sologa/codex-pipeline --skill esm-sologa

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/Sologa/codex-pipeline/tree/main/.codex/skills/esm
Command: npx skills add https://github.com/Sologa/codex-pipeline --skill esm-sologa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit for working with advanced protein language models, enabling complex tasks like protein design, sequence generation, structure prediction, and function annotation.

Core Features & Use Cases

Generative Protein Design (ESM3): Design novel protein sequences and structures, predict protein functions, and perform inverse folding.
Protein Embeddings (ESM C): Generate high-quality embeddings for downstream machine learning tasks like classification and similarity analysis.
Use Case: Design a novel enzyme with a specific catalytic activity by providing functional constraints and desired structural properties.

Quick Start

Use the esm skill to generate a protein sequence based on a partial input sequence.

Frequently Asked Questions about esm

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

FAQPage Schema

How do I design a novel protein sequence using a partial input?▼

Design a novel protein sequence by inputting partial sequences and functional constraints into the ESM3 generative model, which outputs complete sequences and predicted structures.

Can I generate protein embeddings for downstream machine learning tasks?▼

Generate high-quality protein embeddings using ESM C for downstream machine learning tasks such as sequence classification and similarity analysis.

What is inverse folding in protein engineering and how does this toolkit support it?▼

Inverse folding predicts an amino acid sequence that folds into a given 3D structure. This toolkit supports inverse folding alongside structure prediction and function annotation via the ESM3 model.

Does the protein design toolkit support cloud-based API inference for large-scale tasks?▼

Yes, the toolkit supports cloud-based Forge API for scalable inference alongside local model usage, accommodating large-scale protein engineering tasks.

What's the best way to predict protein functions and structures from a novel sequence?▼

Use ESM3 for structure prediction and function annotation, enabling you to evaluate novel sequences against desired catalytic activities and structural properties.

Do I need local computational resources to run generative protein models?▼

No, local resources are not strictly required because the toolkit supports cloud-based Forge API for scalable inference, though local model usage is also supported.