Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DeepSilencer: A Novel Deep Learning Model for Predicting siRNA Knockdown Efficiency
Background: Small interfering RNA (siRNA) is a promising therapeutic agent due to its ability to silence disease-related genes via RNA interference. While traditional machine learning and early deep learning methods have…
Deep LearningMachine Learning Modeling Of SiRNA Structure-Potency Relationship With Applications Against Sars-Cov-2 Spike Gene
The pharmaceutical Research and development (R&D) process is lengthy and costly, taking nearly a decade to bring a new drug to the market. However, advancements in biotechnology, computational methods, and machine learni…
Drug DiscoveryUncertainty-Guided Model Selection for Tabular Foundation Models in Biomolecule Efficacy Prediction
In-context learners like TabPFN are promising for biomolecule efficacy prediction, where established molecular feature sets and relevant experimental results can serve as powerful contextual examples. However, their perf…
MicroRNAs -- targeting and target prediction
MicroRNAs (miRNAs) are a class of small noncoding RNAs that can regulate many genes by base pairing to sites in mRNAs. The functionality of miRNAs overlaps that of short interfering RNAs (siRNAs), and many features of mi…
PredictionHighly Efficient siRNA Delivery from Core-Shell Mesoporous Silica Nanoparticles with Multifunctional Polymer Caps
A new general route for siRNA delivery is presented combining porous core-shell silica nanocarriers with a modularly designed multifunctional block copolymer. Specifically, the internal storage and release of siRNA from …