# Biohub/esm

Repository: https://github.com/Biohub/esm
Canonical: https://ross.abutalabs.com/products/biohub-esm
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2026-08-25T22:04:31+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 52, longevity 57
- inputs: {"age_days": 799, "days_push": 8, "days_rel": 323, "gap_med": 21.5, "n_releases_24m": 13}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2927, forks 381 (observed 2026-08-28T04:07:30.385861+00:00)

## What it is
A Python library and model release providing ESMC protein language models, ESMFold2 structure prediction, and the ESM Atlas of 6.8 billion proteins. It enables protein representation, structure prediction, and de novo protein/binder design from sequences.

## Use cases
- predict protein 3D structure from a single amino acid sequence
- generate protein sequence embeddings for downstream ML tasks
- design de novo minibinders or antibody-derived scFvs against a target
- predict protein-protein and antibody-antigen complex structures
- explore interpretable features of protein biology via sparse autoencoders
- run fast single-sequence protein folding

## When to choose
- you need state-of-the-art protein structure prediction or folding throughput
- you want embeddings from a frontier protein language model
- you are doing computational protein design or binder discovery

## When to avoid
- you need a lightweight model for CPU-only or low-resource environments
- your task is unrelated to protein sequences or structures
- you require a permissive open-source license (license is non-standard)

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference
- domain: bioinformatics, machine-learning, deep-learning
- platform: python
- tags: protein-language-model, protein-structure-prediction, protein-design, esm, computational-biology, binder-design, sparse-autoencoders, natural-language-processing

## Member repositories
- Biohub/esm (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.385861+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:33:35.136136+00:00, confidence not recorded.
  - readme: https://github.com/Biohub/esm (fetched 2026-08-28T04:07:30.385861+00:00, sha 786f403bcd7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.