Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912947098353664 |
|---|---|
| author | Khodagholi, Zahra Yousefi, Niloofar |
| author_facet | Khodagholi, Zahra Yousefi, Niloofar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10152 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol Khodagholi, Zahra Yousefi, Niloofar Genomics Machine Learning 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. |
| title | Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol |
| topic | Genomics Machine Learning |
| url | https://arxiv.org/abs/2602.10152 |