skills.rest
Estrella-231
Estrella-231COMMUNITY
Explore all skills by this author →
GitHub

esm

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

Updated May 24, 2026
Search Tags:#embeddings#structure prediction#protein design#esm3#function annotation#inverse folding
One-click install
npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill esm-estrella-231
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: esm
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/esm
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill esm-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

ESM helps you generate novel protein sequences, predict structures and functions, and extract embeddings from protein sequences so you can move from hypotheses to testable protein designs faster.

Core Features & Use Cases

  • Multimodal protein generation (ESM3): Create protein sequences from partial prompts, predict 3D structure from sequence, and perform inverse folding to design sequences that fit a target structure.
  • Efficient protein representations (ESM C): Generate high-quality embeddings for similarity search, clustering, and downstream ML feature extraction.
  • Function conditioning and annotation: Generate or condition proteins using function annotations, and predict function-related annotations from sequence.

Use cases: designing fluorescent proteins, building variant libraries for directed evolution, performing structure-based sequence optimization, and clustering large protein datasets using embeddings.

Quick Start

Use the esm skill to generate amino-acid sequence completions by prompting a partially masked sequence with ESM3 and requesting generation on the sequence track.

Frequently Asked Questions about esm

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

FAQPage Schema
How do I generate novel protein sequences from partial prompts?▼

Generate novel protein sequences by prompting ESM3 with partially masked sequences and requesting generation on the sequence track. You must provide ESMProtein inputs paired with track-scoped GenerationConfig to complete the sequence.

Can I perform inverse folding to design sequences for a target 3D structure?▼

Inverse folding is supported directly through ESM3 to design amino acid sequences that fit a target 3D structure. Provide the structural input within an ESMProtein object to generate the matching sequence.

How do I extract protein embeddings for clustering large datasets?▼

Extract efficient protein embeddings for clustering using ESM C encoding and forward passes. You can optionally utilize Forge API clients to perform scalable inference across large protein datasets.

Does ESM3 support function annotation and conditioning?▼

ESM3 supports function annotation by predicting function-related annotations from sequence inputs. You can also condition the generation of novel proteins using specific function annotations within your prompt.

What inputs do I need to predict 3D protein structures with this tool?▼

Predicting 3D protein structures requires ESMProtein inputs combined with track-scoped GenerationConfig. This configuration drives the ESM3 model to generate the structural prediction from your sequence data.

Related Skills

Explore More Education & Research Skills→
silversteinsilverstein
21

esm

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

Community
Advanced
jimmc414jimmc414
557

esm

Generate protein sequences and extract embeddings using ESM3 and ESM C.

Community
Advanced
OwnLabAIOwnLabAI
21

esm

Generate sequences, structures, functions, and embeddings with ESM3 and ESM C via Forge API or locally.

Official
Advanced
mkurmanmkurman
321

esm

Generate protein sequences and structures using ESM3 and ESM C.

Community
Advanced