Robust Neural Networks are More Interpretable for Genomics
Deep neural networks (DNNs) have been applied to a variety of regulatory genomics tasks. For interpretability, attribution methods are employed to provide importance scores for each nucleotide in a given sequence. However, even with state-of-the-art DNNs, there is no guarantee that these methods can recover interpretable, biological representations. Here we perform systematic experiments on synthetic genomic data to raise awareness of this issue. We find that deeper networks have better generalization performance, but attribution methods recover less interpretable representations. Then, we show training methods promoting robustness - including regularization, injecting random noise into the data, and adversarial training - significantly improve interpretability of DNNs, especially for smaller datasets.