# Semantically Rich Local Dataset Generation for Explainable AI in Genomics

arXiv: https://arxiv.org/abs/2407.02984 · HTML: https://mlsanity.com/paper/2407.02984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 72 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 13 of 13)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Local Rule-Based Explanations of Black Box Decision Systems](https://mlsanity.com/paper/1805.10820/) (2018)
- [Conditioning by adaptive sampling for robust design](https://mlsanity.com/paper/1901.10060/) (2019)
- [Beyond Sparsity: Tree Regularization of Deep Models for Interpretability](https://mlsanity.com/paper/1711.06178/) (2017)
- [AdaLead: A simple and robust adaptive greedy search algorithm for sequence design](https://mlsanity.com/paper/2010.02141/) (2020)
- [Generating and designing DNA with deep generative models](https://mlsanity.com/paper/1712.06148/) (2017)
- [Population-Based Black-Box Optimization for Biological Sequence Design](https://mlsanity.com/paper/2006.03227/) (2020)
- [Fast differentiable DNA and protein sequence optimization for molecular design](https://mlsanity.com/paper/2005.11275/) (2020)
- [Applying Genetic Programming to Improve Interpretability in Machine Learning Models](https://mlsanity.com/paper/2005.09512/) (2020)
- [Data types as a more ergonomic frontend for Grammar-Guided Genetic Programming](https://mlsanity.com/paper/2210.04826/) (2022)

## Abstract (arXiv)

Black box deep learning models trained on genomic sequences excel at predicting the outcomes of different gene regulatory mechanisms. Therefore, interpreting these models may provide novel insights into the underlying biology, supporting downstream biomedical applications. Due to their complexity, interpretable surrogate models can only be built for local explanations (e.g., a single instance). However, accomplishing this requires generating a dataset in the neighborhood of the input, which must maintain syntactic similarity to the original data while introducing semantic variability in the model's predictions. This task is challenging due to the complex sequence-to-function relationship of DNA. We propose using Genetic Programming to generate datasets by evolving perturbations in sequences that contribute to their semantic diversity. Our custom, domain-guided individual representation effectively constrains syntactic similarity, and we provide two alternative fitness functions that promote diversity with no computational effort. Applied to the RNA splicing domain, our approach quickly achieves good diversity and significantly outperforms a random baseline in exploring the search space, as shown by our proof-of-concept, short RNA sequence. Furthermore, we assess its generalizability and demonstrate scalability to larger sequences, resulting in a ~30% improvement over the baseline.