Learning interpretable compositional features associated with continuous covariates
- 1Johns Hopkins Bloomberg School of Public Health
Abstract
Compositional variation as a function of continuous covariates, such as time, presents challenges for learning interpretable features and accounting for their construction in subsequent inference. Motivated by temporal change in isoform usage in genomics, we introduce IsoVita, a statistical framework integrating covariate-informed balance learning designed for compositional data with complementary tests for abrupt and gradual compositional variation. IsoVita estimates a dominant covariate-dependent direction in the log-ratio coordinates and approximates it as a log ratio of their geometric mean proportions between two learned component groups, linking statistical evidence to explicit component membership. Change point and spline tests evaluate this interpretable feature, while a selection-aware permutation procedure repeats feature construction and testing under each permutation. In transcript-level simulations, IsoVita maintained low empirical false discovery proportions with power to detect differences and change point accuracy improving as temporal signals strengthened. However, the performance depended on trajectory shape and study design. Applications to two human brain bulk RNA-sequencing datasets identified widespread temporal variation in isoform composition while retaining transcript-level interpretability. IsoVita integrates interpretable compositional feature learning with inference along continuous covariates, with potential applications beyond transcriptomics. IsoVita is available as a PyPI package (https://pypi.org/project/isovita).
Related
- Discovering compositional, interpretable structure in social behavior
- Interpretable Multiomics Machine Learning Identifies GSDMB-Associated Epigenetic Repression and Reduced Immune Activity in Metastatic Colorectal Cancer
- Learning Options for Compositional Motor Control with Adapter Banks
- Interpretable Machine Learning Links Group-Specific Plasma Proteomics to Regional Structural Neuroimaging in Alzheimer's Disease
- Learning interpretable kinetic models for biomolecular interaction networks
BibTeX
@misc{chen2026learning,
title = {{Learning interpretable compositional features associated with continuous covariates}},
author = {X. Chen and S. C. Hicks},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.04.764349},
url = {https://www.biorxiv.org/content/10.64898/2026.11.04.764349v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Learning interpretable compositional features associated with continuous covariates
AU - X. Chen
AU - S. C. Hicks
PY - 2026
DA - 2026/11/04
PB - bioRxiv
DO - 10.64898/2026.11.04.764349
UR - https://www.biorxiv.org/content/10.64898/2026.11.04.764349v1
AB - Compositional variation as a function of continuous covariates, such as time, presents challenges for learning interpretable features and accounting for their construction in subsequent inference. Motivated by temporal change in isoform usage in genomics, we introduce IsoVita, a statistical framework integrating covariate-informed balance learning designed for compositional data with complementary tests for abrupt and gradual compositional variation. IsoVita estimates a dominant covariate-dependent direction in the log-ratio coordinates and approximates it as a log ratio of their geometric mean proportions between two learned component groups, linking statistical evidence to explicit component membership. Change point and spline tests evaluate this interpretable feature, while a selection-aware permutation procedure repeats feature construction and testing under each permutation. In transcript-level simulations, IsoVita maintained low empirical false discovery proportions with power to detect differences and change point accuracy improving as temporal signals strengthened. However, the performance depended on trajectory shape and study design. Applications to two human brain bulk RNA-sequencing datasets identified widespread temporal variation in isoform composition while retaining transcript-level interpretability. IsoVita integrates interpretable compositional feature learning with inference along continuous covariates, with potential applications beyond transcriptomics. IsoVita is available as a PyPI package (https://pypi.org/project/isovita).
ER -