Gkmexplain: Fast and Accurate Interpretation of Nonlinear Gapped k-mer SVMs Using Integrated Gradients

Abstract

Support VectorMachines with gapped k-mer kernels (gkm-SVMs) have been used to learn predictive models of regulatory DNA sequence. However, interpreting predictive sequence patterns learned by gkm-SVMs can be challenging. Existing interpretation methods such as deltaSVM, in-silico mutagenesis (ISM), or SHAP either do not scale well or make limiting assumptions about the model that can produce misleading results when the gkm kernel is combined with nonlinear kernels. Here, we propose gkmexplain: a novel approach inspired by the method of Integrated Gradients for interpreting gkm-SVM models. Using simulated regulatory DNA sequences, we show that gkmexplain identifies predictive patterns with high accuracy while avoiding pitfalls of deltaSVM and ISM and being orders of magnitude more computationally efficient than SHAP. We use a novel motif discovery method called TF-MoDISco to recover consolidated TF motifs from gkm-SVM models of in vivo TF binding by aggregating predictive patterns identified by gkmexplain. Finally, we find that mutation impact scores derived through gkmexplain using gkm-SVM models of chromatin accessibility in lymphoblastoid cell-lines consistently outperform deltaSVM and ISM at identifying regulatory genetic variants (dsQTLs). Code and example notebooks replicating the workflow are available at https://github.com/kundajelab/gkmexplain. Explanatory videos available at http://bit.ly/gkmexplainvids.

Explainable machine learning in deployment

“…For example, one research scientist noted that, "Many [financial institutions] use kernel-based methods on tabular data. " As a result, there is a desire to translate explainability techniques for kernel support vector machines in genomics [58] to models trained on tabular data.…”

Predicting mean ribosome load for 5’UTR of any length using deep learning

“…This method yields more interpretable results than individually visualizing convolutional filters, as such filters often learn distributed representations of sequence features. More detail can be found in the respective paper and in Shrikumar et al [ 53 ] and Avsec et al [ 54 ].…”

Explainable Machine Learning in Deployment

“…For example, one research scientist noted that, "Many [financial institutions] use kernel-based methods on tabular data. " As a result, there is a desire to translate explainability techniques for kernel support vector machines for genomics [54] to models trained on tabular data.…”