EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Benchmarking interpretability of deep learning for predictive genomics: Recall, precision, and variability of feature attribution

Justin Reynolds iD, Chongle Pan iD

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1013784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Justin Reynolds und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Gallogly College of Engineering, University of Oklahoma, Norman, Oklahoma, United States of America. Hauptthemen laut MEDLINE: Deep Learning, Genomics. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCCIH NIH HHS, University of Oklahoma, National Center for Complementary and Integrative Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep neural networks can model the nonlinear architecture of polygenic traits, yet the reliability of attribution methods to identify the genetic variants driving model predictions remains uncertain. We introduce a benchmarking framework that quantifies three aspects of interpretability: attribution recall, attribution precision, and stability, and apply it to deep learning models trained on UK Biobank genotypes for standing height prediction. After quality control, feed-forward neural networks were trained on more than half a million autosomal variants from approximately 300 thousand participants and evaluated using four attribution algorithms (Saliency, Gradient SHAP, DeepLIFT, Integrated Gradients) with and without SmoothGrad noise averaging. Attribution recall was assessed using synthetic spike-in variants with known additive, dominant, recessive, and epistatic effects, enabling direct measurement of sensitivity to diverse genetic architectures. Attribution precision estimated specificity using an equal number of null decoy variants that preserved allele structure while disrupting genotype-phenotype correspondence. Stability was measured by the consistency of variant-level attributions across an ensemble of independently trained models. SmoothGrad increased average recall across effect types by approximately 0.16 at the top 1% of the most highly attributed variants and improved average precision by about 0.06 at the same threshold, while stability remained comparable with median relative standard deviations of 0.4 to 0.5 across methods. Among the evaluated attribution methods, Saliency achieved the highest composite score, indicating that its simple gradient formulation provided the best overall balance of recall, precision, and stability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGenomicsHumansBenchmarkingAlgorithmsComputational BiologyGenotypeNeural Networks, ComputerModels, GeneticPhenotypeMultifactorial InheritanceGenetic VariationReproducibility of Results

Autor:innen und Institutionen

  • School of Computer Science, Gallogly College of Engineering, University of Oklahoma, Norman, Oklahoma, United States of America.

ORCID-Profile: Justin Reynolds, Chongle Pan

Förderung

  • NCCIH NIH HHS
  • University of Oklahoma
  • National Center for Complementary and Integrative Health
  • National Institute of General Medical Sciences

Zitieren

APA

Reynolds, J., & Pan, C. (2025). Benchmarking interpretability of deep learning for predictive genomics: Recall, precision, and variability of feature attribution. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013784

Vancouver

Reynolds J, Pan C. Benchmarking interpretability of deep learning for predictive genomics: Recall, precision, and variability of feature attribution. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1013784

BibTeX
@article{Reynolds2025,
  author = {Reynolds, Justin and Pan, Chongle},
  title = {Benchmarking interpretability of deep learning for predictive genomics: Recall, precision, and variability of feature attribution},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1013784}
}
Kostenlos starten →