# Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol

arXiv: https://arxiv.org/abs/2602.10152 · HTML: https://mlsanity.com/paper/2602.10152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 52 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Technical Note on Transcription Factor Motif Discovery from Importance Scores (TF-MoDISco) version 0.5.6.5](https://mlsanity.com/paper/1811.00416/) (2018)
- [Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks](https://mlsanity.com/paper/1608.03644/) (2016)
- [Position: Biology is the Challenge Physics-Informed ML Needs to Evolve](https://mlsanity.com/paper/2510.25368/) (2025)
- [siDPT: siRNA Efficacy Prediction via Debiased Preference-Pair Transformer](https://mlsanity.com/paper/2509.15664/) (2025)

## Abstract (arXiv)

Saliency maps are increasingly used as design guidance in siRNA efficacy prediction, yet attribution methods are rarely validated before motivating sequence edits. We introduce a pre-synthesis gate: a protocol for counterfactual sensitivity faithfulness that tests whether mutating high-saliency positions changes model output more than composition-matched controls. Cross-dataset transfer reveals two failure modes that would otherwise go undetected: faithful-but-wrong (saliency valid, predictions fail) and inverted saliency (top-saliency edits less impactful than random). Strikingly, models trained on mRNA-level assays collapse on a luciferase reporter dataset, demonstrating that protocol shifts can silently invalidate deployment. Across four benchmarks, 19/20 fold instances pass; the single failure shows inverted saliency. A biology-informed regularizer (BioPrior) strengthens saliency faithfulness with modest, dataset-dependent predictive trade-offs. Our results establish saliency validation as essential pre-deployment practice for explanation-guided therapeutic design. Code is available at https://github.com/shadi97kh/BioPrior.