Metadata-Version: 2.5
Name: altar
Version: 0.7.0
Summary: Public contracts, orchestration primitives, and conformance suites for genomic variant analysis
Project-URL: Documentation, https://kundajelab.github.io/altar/
Author: Riya Sinha
License-Expression: MIT
License-File: LICENSE
Keywords: bioinformatics,genomics,machine-learning,variant-annotation,variant-effect-prediction
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Typing :: Typed
Requires-Python: >=3.12
Requires-Dist: altar-identity==0.7.0
Requires-Dist: duckdb>=1.0.0
Requires-Dist: intervaltree>=3.1.0
Requires-Dist: ncls>=0.0.70
Requires-Dist: numpy>=1.26
Requires-Dist: pandas>=2.0
Requires-Dist: pyarrow>=17.0.0
Requires-Dist: pydantic>=2
Requires-Dist: pyfaidx>=0.6.1
Requires-Dist: pysam>=0.22.1
Requires-Dist: pytest>=8
Provides-Extra: azure
Requires-Dist: adlfs>=2024.4.1; extra == 'azure'
Requires-Dist: fsspec>=2024.6; extra == 'azure'
Provides-Extra: bigquery
Requires-Dist: google-cloud-bigquery-storage>=2.24; extra == 'bigquery'
Requires-Dist: google-cloud-bigquery[pandas]>=3; extra == 'bigquery'
Provides-Extra: docs
Requires-Dist: mkdocs-material>=9.5; extra == 'docs'
Requires-Dist: mkdocs-redirects<1.2.3,>=1.2.1; extra == 'docs'
Requires-Dist: mkdocs<2,>=1.6; extra == 'docs'
Requires-Dist: mkdocstrings[python]>=0.26; extra == 'docs'
Requires-Dist: ruff; extra == 'docs'
Provides-Extra: fsspec
Requires-Dist: fsspec>=2024.6; extra == 'fsspec'
Provides-Extra: gcs
Requires-Dist: fsspec>=2024.6; extra == 'gcs'
Requires-Dist: gcsfs>=2024.6; extra == 'gcs'
Provides-Extra: hf
Requires-Dist: fsspec>=2024.6; extra == 'hf'
Requires-Dist: huggingface-hub>=0.23; extra == 'hf'
Provides-Extra: http
Requires-Dist: aiohttp>=3.9; extra == 'http'
Requires-Dist: fsspec>=2024.6; extra == 'http'
Provides-Extra: kubernetes
Requires-Dist: kubernetes-asyncio>=29; extra == 'kubernetes'
Provides-Extra: modal
Requires-Dist: modal>=0.64; extra == 'modal'
Provides-Extra: s3
Requires-Dist: fsspec>=2024.6; extra == 's3'
Requires-Dist: s3fs>=2024.6; extra == 's3'
Provides-Extra: test
Requires-Dist: aiohttp>=3.9; extra == 'test'
Requires-Dist: fsspec>=2024.6; extra == 'test'
Requires-Dist: google-cloud-bigquery-storage>=2.24; extra == 'test'
Requires-Dist: google-cloud-bigquery[pandas]>=3; extra == 'test'
Requires-Dist: mypy>=1.11; extra == 'test'
Requires-Dist: pytest-asyncio>=0.24; extra == 'test'
Requires-Dist: pytest-cov; extra == 'test'
Description-Content-Type: text/markdown

# Altar

Altar scores genomic variants with sequence models and annotates them with published evidence, in one run that
writes one table. A run spec names your variants, the models, the annotation sources and where to keep the scores.
Altar runs each model in a container or calls its hosted API, looks up the evidence, and records which model,
settings and dataset release produced every value.

Altar is in beta. Its interfaces are labelled Stable, Provisional or Preview; see
[Maturity labels](https://kundajelab.github.io/altar/reference/maturity/).

![One altar run: a run spec and variants go in; Altar normalizes the variants, scores each model only on variants not already stored, looks each variant up in the annotation sources, and writes one table with provenance.](https://kundajelab.github.io/altar/assets/images/run-overview-light.svg)

## Install

Altar needs Python 3.12 or newer. Install it with the bindings you need. To annotate variants with gnomAD and
ClinVar:

```bash
pip install altar altar-popfreq altar-clinvar
```

Each model and annotation source is a separate binding, such as `altar-legnet` or `altar-conservation`. Cloud storage,
BigQuery and remote execution are extras, such as `pip install "altar[gcs]"`. Model frameworks and weights run in
separate container images. [Install Altar](https://kundajelab.github.io/altar/start/install/) lists every binding
and extra.

## Documentation

The documentation is at <https://kundajelab.github.io/altar/>.

- [Quickstart](https://kundajelab.github.io/altar/quickstart/): annotate a VCF, then score it with LegNet on the CPU
- [Tutorials](https://kundajelab.github.io/altar/start/tutorials/): five notebooks that build one analysis
- [Models and data](https://kundajelab.github.io/altar/integrations/): every model and annotation source
- [Concepts](https://kundajelab.github.io/altar/science/): how a run works, and what the scores, annotations and links mean
- [Use Altar from Python](https://kundajelab.github.io/altar/python/)
- [Extend Altar](https://kundajelab.github.io/altar/extend/): add a model, a dataset, a backend or a store
- [Maturity labels](https://kundajelab.github.io/altar/reference/maturity/): the public modules and the label each
  one carries

## Cite and licence

Cite Altar as [Cite Altar](https://kundajelab.github.io/altar/project/cite/) describes, and cite each model and
dataset you use. Altar is copyright 2026 Riya Sinha and released under the MIT License. Models and datasets carry
their own licences and terms.
