Metadata-Version: 2.5
Name: altar-borzoi
Version: 0.3.0
Summary: Borzoi model binding for large-scale Altar variant-gene scoring
Project-URL: Documentation, https://kundajelab.github.io/altar/
Author: Riya Sinha
License-Expression: MIT
License-File: LICENSE
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<0.4,>=0.3.0
Provides-Extra: test
Requires-Dist: pytest-asyncio>=0.24; extra == 'test'
Requires-Dist: pytest>=8; extra == 'test'
Description-Content-Type: text/markdown

# Altar Borzoi binding

`altar-borzoi` is the lightweight control-plane binding for large-scale, gene-specific Borzoi variant
scoring. It registers `BORZOI` in Altar's canonical model-plugin group without installing TensorFlow or the
model's scientific runtime into the framework environment.

One model instance pins the four published human replicate weights, official prediction parameters, the
GTEx RNA target subset, GENCODE 41 gene annotation, selected output tracks, reverse-complement/shift
ensembling, an immutable runtime image, and the hg38 reference identity. Each deterministic outer variant
batch becomes one retryable GPU task. Within that task the runtime loads each replicate exactly once,
streams small ref/alt tensor batches, and averages the official per-replicate scores through a disk-backed
accumulator.

The primary table contains the gene/target pair with the largest absolute `logSED` for each variant. The
`gene_effects` detail table preserves mean `logSED` and `logD2` for every scored `(variant, gene, target)`
tuple. The `altar-borzoi-resources` command fetches and records the published resources. The TensorFlow 2.15
executor lives under `runtimes/borzoi`, and `DEFAULT_IMAGE` pins its published image by digest.
