Global importance analysis: An interpretability method to quantify importance of genomic features in deep neural networks
Open Access
- 13 May 2021
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 17 (5) , e1008925
Abstract
Deep neural networks have demonstrated improved performance at predicting the sequence specificities of DNA- and RNA-binding proteins compared to previous methods that rely on k-mers and position weight matrices. To gain insights into why a DNN makes a given prediction, model interpretability methods, such as attribution methods, can be employed to identify motif-like representations along a given sequence. Because explanations are given on an individual sequence basis and can vary substantially across sequences, deducing generalizable trends across the dataset and quantifying their effect size remains a challenge. Here we introduce global importance analysis (GIA), a model interpretability method that quantifies the population-level effect size that putative patterns have on model predictions. GIA provides an avenue to quantitatively test hypotheses of putative patterns and their interactions with other patterns, as well as map out specific functions the network has learned. As a case study, we demonstrate the utility of GIA on the computational task of predicting RNA-protein interactions from sequence. We first introduce a convolutional network, we call ResidualBind, and benchmark its performance against previous methods on RNAcompete data. Using GIA, we then demonstrate that in addition to sequence motifs, ResidualBind learns a model that considers the number of motifs, their spacing, and sequence context, such as RNA secondary structure and GC-bias.Keywords
All Related Versions
This publication has 53 references indexed in Scilit:
- Advancing the functional utility of PAR-CLIP by quantifying background binding to mRNAs and lncRNAsGenome Biology, 2014
- Evaluation of methods for modeling transcription factor sequence specificityNature Biotechnology, 2013
- ViennaRNA Package 2.0Algorithms for Molecular Biology, 2011
- iCLIP reveals the function of hnRNP particles in splicing at individual nucleotide resolutionNature Structural & Molecular Biology, 2010
- RNAcontext: A New Method for Learning the Sequence and Structure Binding Preferences of RNA-Binding ProteinsPLOS Computational Biology, 2010
- Transcriptome-wide Identification of RNA-Binding Protein and MicroRNA Target Sites by PAR-CLIPCell, 2010
- Rapid and systematic analysis of the RNA recognition specificities of RNA-binding proteinsNature Biotechnology, 2009
- HITS-CLIP yields genome-wide insights into brain alternative RNA processingNature, 2008
- Statistical mechanical modeling of genome-wide transcription factor occupancy data by MatrixREDUCEBioinformatics, 2006
- The NMR and X-ray Structures of the Saccharomyces cerevisiae Vts1 SAM Domain Define a Surface for the Recognition of RNA HairpinsJournal of Molecular Biology, 2006