# DeepCoDA: personalized interpretability for compositional health data

arXiv: https://arxiv.org/abs/2006.01392 · HTML: https://mlsanity.com/paper/2006.01392/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research](https://mlsanity.com/paper/2508.02621/) (2025)
- [Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome](https://mlsanity.com/paper/2205.09906/) (2022)
- [Instrumental Variable Estimation for Compositional Treatments](https://mlsanity.com/paper/2106.11234/) (2021)
- [Which Question Is Your Attention Metric Answering? Attention Rows as Compositional Data](https://mlsanity.com/paper/2608.14712/) (2026)
- [A Field Guide to Scientific XAI: Transparent and Interpretable Deep Learning for Bioinformatics Research](https://mlsanity.com/paper/2110.08253/) (2021)
- [The Normalized Difference Layer: A Differentiable Spectral Index Formulation for Deep Learning](https://mlsanity.com/paper/2601.06777/) (2026)

## Abstract (arXiv)

Interpretability allows the domain-expert to directly evaluate the model's relevance and reliability, a practice that offers assurance and builds trust. In the healthcare setting, interpretable models should implicate relevant biological mechanisms independent of technical factors like data pre-processing. We define personalized interpretability as a measure of sample-specific feature attribution, and view it as a minimum requirement for a precision health model to justify its conclusions. Some health data, especially those generated by high-throughput sequencing experiments, have nuances that compromise precision health models and their interpretation. These data are compositional, meaning that each feature is conditionally dependent on all other features. We propose the Deep Compositional Data Analysis (DeepCoDA) framework to extend precision health modelling to high-dimensional compositional data, and to provide personalized interpretability through patient-specific weights. Our architecture maintains state-of-the-art performance across 25 real-world data sets, all while producing interpretations that are both personalized and fully coherent for compositional data.