Global Importance Analysis: An Interpretability Method to Quantify Importance of Genomic Features in Deep Neural Networks

Koo, Peter, Majdandzic, Antonio, Ploenzke, Matthew, Anand, Praveen, Paul, Steffan (September 2020) Global Importance Analysis: An Interpretability Method to Quantify Importance of Genomic Features in Deep Neural Networks. BioRxiv. (Unpublished)

PDF 2020.Koo.DeepNeuralNetworks.pdf Download (2MB)

Abstract

<h4>ABSTRACT</h4> 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.

Item Type:	Paper
Subjects:	bioinformatics > genomics and proteomics > genetics & nucleic acid processing > genomes bioinformatics > computational biology > algorithms > machine learning
CSHL Authors:	Koo, Peter K Majdandzic, Antonio
Communities:	CSHL labs > Koo Lab
SWORD Depositor:	CSHL Elements
Depositing User:	CSHL Elements
Date:	9 September 2020
Date Deposited:	07 May 2021 20:27
Last Modified:	07 May 2021 20:27
URI:	https://repository.cshl.edu/id/eprint/40066

Actions (login required)

Administrator's edit/view item