# allenai/scispacy

A full spaCy pipeline and models for scientific/biomedical documents.

Repository: https://github.com/allenai/scispacy
Canonical: https://ross.abutalabs.com/products/scispacy
Homepage: https://allenai.github.io/scispacy/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: scientific-documents, spacy, custom-pipes, nlp, biomedical, bioinformatics
Last push: 2025-12-04T07:49:16+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 26, longevity 100
- inputs: {"age_days": 2900, "days_push": 272, "days_rel": 336, "gap_med": 169.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1988, forks 256 (observed 2026-08-28T04:06:02.884532+00:00)

## What it is
scispaCy is a Python library providing full spaCy pipelines, models, and custom pipes for processing scientific, biomedical, and clinical text. It includes a custom tokenizer, POS tagger, syntactic parser, entity span detection, and NER models trained on corpora like CRAFT, JNLPBA, and BC5CDR.

## Use cases
- extract named entities like diseases and chemicals from biomedical papers
- parse and POS-tag clinical notes with spaCy
- tokenize scientific text with domain-specific rules
- identify genes, proteins, and cell types in PubMed abstracts
- build a biomedical text mining pipeline in Python

## When to choose
- you need spaCy-compatible NLP models tailored to biomedical or clinical text
- you want pretrained NER for entities like genes, diseases, chemicals, or cell lines
- you need a scientific tokenizer and parser that outperforms generic spaCy models on biomedical data

## When to avoid
- your text is general-domain news or web content where standard spaCy models suffice
- you need state-of-the-art transformer-based biomedical NLP beyond what these models provide
- you are not working in the Python/spaCy ecosystem

## Facets
- artifact type: library
- maturity: active
- function: nlp, parser, machine-learning
- domain: bioinformatics, healthcare
- platform: python
- tags: spacy, biomedical-text, ner, scientific-documents, tokenization, natural-language-processing

## Member repositories
- allenai/scispacy (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:02.884532+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 2026-08-30T03:02:58.172979+00:00, confidence not recorded.
  - readme: https://github.com/allenai/scispacy (fetched 2026-08-28T04:06:02.884532+00:00, sha e6a36497b980)
  - homepage: https://allenai.github.io/scispacy/ (fetched 2026-08-29T10:42:39.729967+00:00, sha 5c352c8dd968)
  - registry_pypi: https://pypi.org/pypi/scispacy/json (fetched 2026-08-29T10:42:39.739458+00:00, sha a5cf1af1566a)
- Data as of 2026-08-30T08:39:29.467469+00:00.