Protein language models through the EvolutionaryScale `esm` Python SDK. Generate and embed sequences with ESM3 (multimodal sequence, structure and function prompting), extract per-residue and mean-pooled embeddings with ESM C, fold sequences with ESMFold2, and run inference locally or against the Forge and Biohub hosted clients. Use this skill for protein representation learning, variant effect and mutational scanning from likelihoods, sequence generation and inpainting, structure prediction from sequence alone, and embedding features for downstream models. Also trigger on esm, ESM3, ESMC, ESM Cambrian, ESMFold2, `from esm.models`, ESMProtein, GenerationConfig, forge.evolutionaryscale.ai, biohub.ai, or ESM_API_KEY.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Protein language models through the EvolutionaryScale `esm` Python SDK. Generate and embed sequences with ESM3 (multimodal sequence, structure and function prompting), extract per-residue and mean-pooled embeddings with ESM C, fold sequences with ESMFold2, and run inference locally or against the Forge and Biohub hosted clients. Use this skill for protein representation learning, variant effect and mutational scanning from likelihoods, sequence generation and inpainting, structure prediction from sequence alone, and embedding features for downstream models. Also trigger on esm, ESM3, ESMC, ESM Cambrian, ESMFold2, `from esm.models`, ESMProtein, GenerationConfig, forge.evolutionaryscale.ai, biohub.ai, or ESM_API_KEY.
license
MIT
compatibility
Requires Python >=3.12,<3.13 and `esm` 3.2.3 from PyPI. Local ESM3-open inference needs a GPU with roughly 16 GB of memory and a gated Hugging Face licence acceptance; hosted inference through Forge or Biohub needs an API key in ESM_API_KEY and no local GPU. ESMFold2 is served through Biohub rather than the local SDK.
allowed-tools
Read Write Edit Bash
metadata
{"version":"1.2","skill-author":"K-Dense Inc."}
ESM: Evolutionary Scale Modeling
Overview
ESM provides protein language models for understanding, generating, and designing proteins. Use this skill for current EvolutionaryScale/Biohub workflows: ESM3 for generative design, ESMC for representation learning and embeddings, hosted Forge/Biohub inference, and ESMFold2 all-atom structure prediction.
Core Capabilities
1. Protein Sequence Generation with ESM3
Generate novel protein sequences with desired properties using multimodal generative modeling.
When to use:
Designing proteins with specific functional properties
Completing partial protein sequences
Generating variants of existing proteins
Creating proteins with desired structural characteristics
Basic usage:
from esm.models.esm3 import ESM3
from esm.sdk.api import ESM3InferenceClient, ESMProtein, GenerationConfig
# Load local open weights after accepting the license on Hugging Face.
model: ESM3InferenceClient = ESM3.from_pretrained("esm3-open").to("cuda")
# Create protein prompt
protein = ESMProtein(sequence="MPRT___KEND") # '_' represents masked positions# Generate completion
protein = model.generate(protein, GenerationConfig(track="sequence", num_steps=8))
print(protein.sequence)
For remote/cloud usage via Forge API:
import os
import esm
from esm.sdk.api import ESMProtein, GenerationConfig
# Same interface as local ESM3; token from ESM_API_KEY (see Authentication)
model = esm.sdk.client("esm3-medium-2024-08", token=os.environ["ESM_API_KEY"])
# Generate
protein = model.generate(protein, GenerationConfig(track="sequence", num_steps=8))
See for detailed ESM3 model specifications, advanced generation configurations, and multimodal prompting examples.
references/esm3-api.md
2. Structure Prediction and Inverse Folding
Use ESM3's structure track for structure prediction from sequence or inverse folding (sequence design from structure).
Structure prediction:
from esm.sdk.api import ESM3InferenceClient, ESMProtein, GenerationConfig
# Predict structure from sequence
protein = ESMProtein(sequence="MPRTKEINDAGLIVHSP...")
protein_with_structure = model.generate(
protein,
GenerationConfig(track="structure", num_steps=protein.sequence.count("_"))
)
# Access predicted structure
coordinates = protein_with_structure.coordinates # 3D coordinates
pdb_string = protein_with_structure.to_pdb()
Inverse folding (sequence from structure):
# Design sequence for a target structure
protein_with_structure = ESMProtein.from_pdb("target_structure.pdb")
protein_with_structure.sequence = None# Remove sequence# Generate sequence that folds to this structure
designed_protein = model.generate(
protein_with_structure,
GenerationConfig(track="sequence", num_steps=50, temperature=0.7)
)
3. Protein Embeddings with ESM C
Generate high-quality embeddings for downstream tasks like function prediction, classification, or similarity analysis.
When to use:
Extracting protein representations for machine learning
Computing sequence similarities
Feature extraction for protein classification
Transfer learning for protein-related tasks
Basic usage:
from esm.models.esmc import ESMC
from esm.sdk.api import ESMProtein, LogitsConfig
# Load ESM C model
model = ESMC.from_pretrained("esmc_300m").to("cuda")
# Get embeddings
protein = ESMProtein(sequence="MPRTKEINDAGLIVHSP...")
protein_tensor = model.encode(protein)
logits_output = model.logits(
protein_tensor,
LogitsConfig(sequence=True, return_embeddings=True),
)
embeddings = logits_output.embeddings
Batch processing:
# Encode multiple proteins
proteins = [
ESMProtein(sequence="MPRTKEIND..."),
ESMProtein(sequence="AGLIVHSPQ..."),
ESMProtein(sequence="KTEFLNDGR...")
]
embeddings_list = [
model.logits(
model.encode(p),
LogitsConfig(sequence=True, return_embeddings=True),
).embeddings
for p in proteins
]
See references/esm-c-api.md for ESM C model details, efficiency comparisons, and advanced embedding strategies.
4. Function Conditioning and Annotation
Use ESM3's function track to generate proteins with specific functional annotations or predict function from sequence.
Function-conditioned generation:
from esm.sdk.api import ESMProtein, FunctionAnnotation, GenerationConfig
# Create protein with desired function
protein = ESMProtein(
sequence="_" * 200, # Generate 200 residue protein
function_annotations=[
FunctionAnnotation(label="fluorescent_protein", start=50, end=150)
]
)
# Generate sequence with specified function
functional_protein = model.generate(
protein,
GenerationConfig(track="sequence", num_steps=200)
)
5. Chain-of-Thought Generation
Iteratively refine protein designs using ESM3's chain-of-thought generation approach.
from esm.sdk.api import GenerationConfig
# Multi-step refinement
protein = ESMProtein(sequence="MPRT" + "_" * 100 + "KEND")
# Step 1: Generate initial structure
config = GenerationConfig(track="structure", num_steps=50)
protein = model.generate(protein, config)
# Step 2: Refine sequence based on structure
config = GenerationConfig(track="sequence", num_steps=50, temperature=0.5)
protein = model.generate(protein, config)
# Step 3: Predict function
config = GenerationConfig(track="function", num_steps=20)
protein = model.generate(protein, config)
6. Batch Processing with Forge API
Process multiple proteins efficiently using Forge's async methods.
import os
import asyncio
import esm
from esm.sdk.api import ESMProtein, GenerationConfig
client = esm.sdk.client("esm3-medium-2024-08", token=os.environ["ESM_API_KEY"])
# Async batch processingasyncdefbatch_generate(proteins_list):
tasks = [
client.async_generate(protein, GenerationConfig(track="sequence"))
for protein in proteins_list
]
returnawait asyncio.gather(*tasks)
# Execute
proteins = [ESMProtein(sequence=f"MPRT{'_' * 50}KEND") for _ inrange(10)]
results = asyncio.run(batch_generate(proteins))
See references/forge-api.md for detailed Forge API documentation, authentication, rate limits, and batch processing patterns.
Model Selection Guide
ESM3 Models (Generative):
esm3-open (1.4B) - Open weights, local usage after accepting the Hugging Face license
esm3-medium-2024-08 (7B) - Best balance of quality and speed (Forge only)
The Forge client ships with the esm package - no extra install for ESM3 or ESMC Forge inference.
Authentication
Forge API access requires an API key. Never hardcode tokens in scripts or commit them to version control.
Check whether ESM_API_KEY is already set in the environment.
If not, check a local .env for ESM_API_KEY only (do not load unrelated secrets).
If still missing, create a key in the Biohub developer console for Biohub APIs or Forge for legacy Forge-hosted ESM3/ESMC access.
import os
token = os.environ["ESM_API_KEY"] # raises KeyError if unset
esm.sdk.client() reads ESM_API_KEY automatically when token is omitted. Keep endpoint URLs fixed to trusted hosts such as https://forge.evolutionaryscale.ai or https://biohub.ai; do not take API hosts from untrusted user input.
Biohub platform: EvolutionaryScale and Forge now surface current hosted models through biohub.ai. SDK class names may still reference "Forge". See references/biohub-platform.md for ESMFold2 and Biohub-specific setup.
Common Workflows
For detailed examples and complete workflows, see references/workflows.md which includes:
Novel GFP design with chain-of-thought
Protein variant generation and screening
Structure-based sequence optimization
Function prediction pipelines
Embedding-based clustering and analysis
References
This skill includes comprehensive reference documentation:
references/esm3-api.md - ESM3 model architecture, API reference, generation parameters, and multimodal prompting
references/esm-c-api.md - ESM C model details, embedding strategies, and performance optimization
references/forge-api.md - Forge platform documentation, authentication, batch processing, and deployment
references/biohub-platform.md - Biohub API migration, ESMFold2 structure prediction, and developer-console auth
references/workflows.md - Complete examples and common workflow patterns
These references contain detailed API specifications, parameter descriptions, and advanced usage patterns. Load them as needed for specific tasks.
Best Practices
For generation tasks:
Start with smaller models for prototyping (esm3-open)
Use temperature parameter to control diversity (0.0 = deterministic, 1.0 = diverse)
Implement iterative refinement with chain-of-thought for complex designs
Validate generated sequences with structure prediction or wet-lab experiments
For embedding tasks:
Batch process sequences when possible for efficiency
Cache embeddings for repeated analyses
Normalize embeddings when computing similarities
Use appropriate model size based on downstream task requirements
For production deployment:
Use Forge API for scalability and latest models
Implement error handling and retry logic for API calls
Monitor token usage and implement rate limiting
Consider AWS SageMaker deployment for dedicated infrastructure
Resources and Documentation
GitHub Repository:https://github.com/Biohub/esm (current ESMC/ESMFold2/Biohub docs; ESM3 docs remain linked from the repository)
Model Weights: Hugging Face EvolutionaryScale and Biohub organizations
Composing with the rest of the bundle
uniprot-rcsb → before: the canonical sequence and any experimental structure. Fold from
sequence only when no structure exists — an experimental structure beats a predicted one.
protein-binder-design → after: ESM embeddings and likelihoods are inputs to binder design and
filtering, not a substitute for BindCraft or RFdiffusion.
antibody-engineering → alongside: general protein language models are weak on antibody CDRs,
which are hypervariable by design and poorly represented in the training distribution. Use IMGT
numbering and antibody-specific tooling there rather than a generic ESM likelihood.
immunogenicity → after: a generated or humanised sequence still needs class II epitope scanning.
A low ESM perplexity says nothing about T-cell epitopes.
boltz / diffdock → after: for a complex, cofolding or docking answers the question ESM does
not — where the ligand goes.
glycoengineering → after: sequon scanning on any designed sequence destined for expression.
adaptyv / tamarind → after: designs are hypotheses until expressed and assayed.
Likelihood is not fitness. A high-likelihood sequence is one the model finds typical of its
training distribution; that correlates with foldability and not at all with the activity you want.
Responsible Use
ESM is designed for beneficial applications in protein engineering, drug discovery, and scientific research. Follow the Responsible Biodesign Framework (https://responsiblebiodesign.ai/) and Biohub Acceptable Use Policy (https://biohub.org/acceptable-use-policy/) when designing novel proteins. Consider biosafety and ethical implications of protein designs before experimental validation.
