.. GENBoostGPU documentation master file GENBoostGPU =========== **GPU-accelerated elastic net boosting for large-scale methylation and SNP studies.** GENBoostGPU orchestrates feature preprocessing, Optuna-powered hyperparameter search, and elastic net boosting on top of RAPIDS, CuPy, and Dask so you can model thousands of genomic windows in parallel without leaving Python. Key features ------------ * **Adaptive window orchestration** – distribute :mod:`genboostgpu.orchestration` jobs across one or many GPUs with auto-tuned ``max_in_flight`` concurrency. * **Automated SNP curation** – zero-variance filtering, missing data imputation, and LD clumping in :mod:`genboostgpu.snp_processing`. * **Elastic net boosting core** – reproducible variance decomposition and ridge refits from :mod:`genboostgpu.enet_boosting`. * **Flexible I/O** – load PLINK data, CuPy arrays, or parquet outputs with :mod:`genboostgpu.data_io`. * **Tuning toolbox** – global and per-window hyperparameter utilities in :mod:`genboostgpu.tuning`, including cohort-wide Optuna refits. * **Reproducibility guardrails** – documented seeding, metadata capture, and structured logging patterns for consistent reruns. Supported platforms ------------------- GENBoostGPU targets Linux with NVIDIA GPUs (Ampere or newer) and CUDA 12.x. Multi-GPU orchestration requires RAPIDS ``cudf/cuML`` 25.8 and ``dask-cuda`` 25.8 or newer. Development and documentation can be performed on CPU-only machines by installing the mock/documentation requirements. Get started ----------- * :doc:`quickstart` – minimal pipeline example with saved outputs. * :doc:`installation` – environment setup for CPU docs versus GPU production. * :doc:`user-guide/index` – deep dives on data formats, workflow, tuning, scaling, and reproducibility. * :doc:`tutorials/index` – walkthroughs based on the scripts in ``examples/``. * :doc:`api/index` – autogenerated API reference. * :doc:`troubleshooting` – common fixes for CUDA, RAPIDS, and Dask issues. * :doc:`contributing` – guidelines for development, style, and tests. * :doc:`changelog` – highlights from each release. .. toctree:: :maxdepth: 2 :caption: Contents quickstart installation user-guide/index tutorials/index api/index troubleshooting contributing changelog Citation -------- If you use GENBoostGPU in academic or industrial work, please cite: .. epigraph:: Alexis Bennett and Kynon J.M. Benjamin. *GENBoostGPU: GPU-accelerated elastic net boosting for large-scale epigenomics.* DOI: `10.5281/zenodo.17238798 `_. Indices and tables ------------------ * :ref:`genindex` * :ref:`modindex` * :ref:`search`