Answers are grounded in this paper and cite their sources.
MOTIVATION: As of today, AACR Project GENIE has completed 19 data releases since its launch in 2015. The latest release includes more than 268 000 samples from nearly 250 000 patients, and as of February 2026, over 1730 scientific journal articles have cited Project GENIE data. Despite its scale and scientific impact, programmatic analysis of GENIE data often still requires researchers to work directly with complex flat files and develop custom data integration workflows. RESULTS: Here we present pyGENIE, a Python package that provides a unified API for accessing GENIE flat files, performing clinical and genomic queries, computing tumor mutational burden, and integrating with leading mutational signature analysis tools including SigProfiler and SigMA. Following a data-as-a-service paradigm, pyGENIE returns all results as native pandas DataFrames, enabling seamless integration with machine learning and visualization libraries. Applied to a lung adenocarcinoma (LUAD) case study, pyGENIE reproduces known mutation frequencies, co-mutation patterns, and mutational signatures while reducing the required codebase by approximately an order of magnitude. AVAILABILITY: pyGENIE is freely available at https://github.com/gersteinlab/pyGENIE under the MIT License, archived at https://doi.org/10.5281/zenodo.21981945, and can be installed from PyPI using pip install pygenie-sdk. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
No takes yet. Share an insight, caveat, or question.
Dayan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: