Benchmarking interpretability of deep learning for predictive genomics: Recall, precision, and variability of feature attribution
Fig 5
Distribution of SNP-wise relative standard deviations (RSD) of attribution magnitudes across ten ensemble members for each algorithm.
For each method, the left (blue) half represents the non-SmoothGrad variant and the right (orange) half represents the SmoothGrad variant. Lower RSD values indicate higher ensemble consistency. Extended upper tails reflect outlier SNPs exhibiting greater attribution variability across models.