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.

[1]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[2]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[3]  Sean R. Eddy,et al.  Representation learning of genomic sequence motifs with convolutional neural networks , 2018, bioRxiv.

[4]  David J. Arenillas,et al.  JASPAR 2016: a major expansion and update of the open-access database of transcription factor binding profiles , 2015, Nucleic Acids Res..

[5]  Scott M. Lundberg,et al.  DeepATAC: A deep-learning method to predict regulatory factor binding activity from ATAC-seq signals , 2017, bioRxiv.

[6]  Anna Shcherbina,et al.  Not Just a Black Box: Learning Important Features Through Propagating Activation Differences , 2016, ArXiv.

[7]  Seyed-Mohsen Moosavi-Dezfooli,et al.  DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaohui S. Xie,et al.  DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences , 2015, bioRxiv.

[9]  David R. Kelley,et al.  Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks , 2015, bioRxiv.

[10]  Jun Zhu,et al.  Boosting Adversarial Attacks with Momentum , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Seyed-Mohsen Moosavi-Dezfooli,et al.  Robustness of classifiers: from adversarial to random noise , 2016, NIPS.

[12]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[13]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[14]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[15]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[16]  Martin Wattenberg,et al.  SmoothGrad: removing noise by adding noise , 2017, ArXiv.

[17]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  O. Troyanskaya,et al.  Predicting effects of noncoding variants with deep learning–based sequence model , 2015, Nature Methods.

[21]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[22]  Sean R. Eddy,et al.  Inferring Sequence-Structure Preferences of RNA-Binding Proteins with Convolutional Residual Networks , 2018, bioRxiv.

[23]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.