# esm | Biohub | Knowledge Base | Instagit

GitHub Stars: 2.6k

Repository: https://github.com/Biohub/esm

---

## Articles

### [How to Integrate ESMC Embeddings with Molecular Dynamics Simulations](/Biohub/esm/how-to-integrate-esmc-embeddings-with-molecular-dynamics-simulations)

Integrate ESM-C embeddings into molecular dynamics simulations. Generate per-residue embeddings, map them to structures, and export for OpenMM or GROMACS restraint weights or collective variables in MD engines.

- Tags: how-to-guide
- Published: 2026-05-30

### [How Biohub Platform Safety Filters Detect Controlled Pathogen Sequences](/Biohub/esm/how-biohub-platform-safety-filters-detect-pathogen-sequences)

Discover how Biohub Platform safety filters detect controlled pathogen sequences using curated blacklists of high-risk entries and regulated keywords to flag potential concerns automatically.

- Tags: deep-dive
- Published: 2026-05-30

### [How to Fine-Tune ESMC Models on Custom Protein Datasets: A Complete Guide](/Biohub/esm/how-to-fine-tune-esmc-models-on-custom-datasets)

Master fine-tuning ESMC models on custom protein datasets. This guide details loading checkpoints, tokenizing sequences, and optimizing loss for advanced protein analysis.

- Tags: how-to-guide
- Published: 2026-05-30

### [How VQVAE Codebook Training Enables Discrete Structure Representation in ESM](/Biohub/esm/how-vqvae-codebook-training-enables-discrete-structure-representation)

Discover how VQVAE codebook training transforms protein structures into discrete tokens for language models. Learn to represent complex biological data efficiently.

- Tags: deep-dive
- Published: 2026-05-30

### [How to Use the Forge API Retry Mechanism for Reliable Batch Inference](/Biohub/esm/how-to-use-forge-api-retry-mechanism-for-batch-inference)

Learn to use the Forge API retry mechanism for reliable batch inference. Process thousands of sequences automatically adapting to API rate limits with tenacity and AIMD rate limiting.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Compute and Visualize Predicted Aligned Error (PAE) Matrices in the ESM Repository](/Biohub/esm/how-predicted-aligned-error-pae-matrices-are-computed-and-visualized)

Learn to compute and visualize predicted aligned error PAE matrices for protein structure. Understand inter-residue distance confidence using novel methods from the Biohub ESM repository.

- Tags: how-to-guide
- Published: 2026-05-30

### [How ESMFold2 Handles DNA and RNA Sequences with Protein Chains](/Biohub/esm/how-esmfold2-handles-dna-rna-with-protein-chains)

Discover how ESMFold2 predicts mixed protein-DNA-RNA complexes. Learn about its type-aware input pipeline for unified token representations and end-to-end structure prediction of heterogeneous assemblies.

- Tags: deep-dive
- Published: 2026-05-30

### [How to Interpret pLDDT Confidence Scores and Predicted Error in ESM‑Fold](/Biohub/esm/how-to-interpret-plddt-confidence-scores-and-predicted-error)

Learn to interpret pLDDT confidence scores and predicted error in ESM Fold. Understand residue uncertainty and model accuracy from Biohub/esm for precise protein structure analysis.

- Tags: deep-dive
- Published: 2026-05-30

### [How the Function Token Decoder Maps InterPro Annotations to Protein Sequences](/Biohub/esm/how-function-token-decoder-maps-interpro-annotations)

Learn how the function token decoder maps InterPro annotations to protein sequences using a compact Transformer stack for efficient per-position classification and contiguous annotation generation.

- Tags: internals
- Published: 2026-05-30

### [How to Load ESMProtein from PDB Files Using from_pdb](/Biohub/esm/how-to-load-esmprotein-from-pdb-files-using-from_pdb)

Easily load ESMProtein from PDB files using ESMProtein.from_pdb() to get sequence coordinates and confidence scores in one line.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Configure LogitsConfig to Return Embeddings for Downstream ML Tasks](/Biohub/esm/how-to-configure-logitsconfig-to-return-embeddings)

Easily configure LogitsConfig to return embeddings for downstream ML tasks by setting sequence and return_embeddings to True in the Biohub esm client. Logits() method extracts dense per-residue embeddings.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Use Guided Generation with PocketConditioning Constraints for Binder Design](/Biohub/esm/how-to-use-guided-generation-with-pocketconditioning-for-binder-design)

Design protein binders with specific pocket contact requirements using Biohub/esm's guided generation and PocketConditioning constraints. Learn this derivative-free decoding engine.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Convert Predicted Structures to mmCIF Format for PDB Deposition with the Biohub/ESM Toolkit](/Biohub/esm/how-to-convert-predicted-structures-to-mmcif-for-pdb-deposition)

Easily convert predicted structures to mmCIF format for PDB deposition using the Biohub/esm toolkit. Export directly with confidence scores embedded for seamless submission.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Handle Multi-Chain Protein Complexes with Chain IDs in ESMProtein](/Biohub/esm/how-to-handle-multi-chain-protein-complexes-with-chain-ids)

Learn to handle multi-chain protein complexes in ESMProtein. Create ProteinChain objects with chain IDs, assemble them into a ProteinComplex, and convert to maintain identifiers for analysis and export.

- Tags: how-to-guide
- Published: 2026-05-30

### [How ESMFold2 Diffusion Sampling Generates Protein Structures](/Biohub/esm/how-esmfold2-diffusion-sampling-generates-structures)

Discover how ESMFold2's diffusion sampling iteratively denoises atom coordinates to generate accurate 3D protein structures. Learn about its noise schedules and masking techniques.

- Tags: deep-dive
- Published: 2026-05-30

### [How to Provide MSA Input to ESMC for Improved Embedding Quality](/Biohub/esm/how-to-provide-msa-input-to-esmc-for-better-embeddings)

Learn how to provide MSA input to ESMC for better protein embeddings. Use the msa parameter in ProteinInput to enhance context aware embeddings with evolutionary data.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Configure SamplingConfig for Iterative Protein Generation in ESM3](/Biohub/esm/how-to-configure-samplingconfig-for-iterative-protein-generation)

Configure SamplingConfig for iterative protein generation with ESM3. Control unmasking schedules and customize temperature, top-p, and invalid IDs for optimal results.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Specify Amino Acid Modifications Using the Modification Dataclass in StructurePredictionInput](/Biohub/esm/how-to-specify-amino-acid-modifications-in-structurepredictioninput)

Learn to specify amino acid modifications accurately for protein structure prediction using the Modification dataclass within StructurePredictionInput. Optimize your ESM framework workflow.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Decompose ESMC Representations with Sparse Autoencoders (SAEs): A Complete Guide](/Biohub/esm/how-to-use-sparse-autoencoders-for-esmc-representation-decomposition)

Decompose ESMC protein embeddings into sparse features using Sparse Autoencoders. Learn how to pass SAEConfig to LogitsConfig and process SAE outputs with helper utilities.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Run ESMFold2 Locally Using Hugging Face with Custom Model Weights](/Biohub/esm/how-to-run-esmfold2-locally-with-huggingface-custom-weights)

Learn to run ESMFold2 locally with Hugging Face. Load pre-trained or custom weights and process inputs for protein structure prediction.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Configure the Biohub Platform API Client with Proper Authentication Tokens](/Biohub/esm/how-to-configure-biohub-platform-api-client-with-authentication-tokens)

Configure the Biohub Platform API client using environment variables, factory function tokens, or Jupyter login. The SDK automatically validates and adds your authentication token for secure API access.

- Tags: how-to-guide
- Published: 2026-05-30

### [How to Extract Hidden States from All ESMC Transformer Layers for Downstream Analysis](/Biohub/esm/how-to-extract-hidden-states-from-all-esmc-transformer-layers-for-downstream-analysis)

Easily extract hidden states from all ESMC transformer layers for downstream analysis. Run a forward pass and access the hidden_states tensor for in-depth protein model insights.

- Tags: how-to-guide
- Published: 2026-05-30