An intrinsically interpretable neural network architecture for sequence-to-function learning

Abstract

Sequence-based deep learning approaches have been shown to predict a multitude of functional genomic readouts, including regions of open chromatin and RNA expression of genes. However, a major limitation of current methods is that model interpretation relies on computationally demanding post hoc analyses, and even then, one can often not explain the internal mechanics of highly parameterized models. Here, we introduce a deep learning architecture called totally interpretable sequence-to-function model (tiSFM). tiSFM improves upon the performance of standard multilayer convolutional models while using fewer parameters. Additionally, while tiSFM is itself technically a multilayer neural network, internal model parameters are intrinsically interpretable in terms of relevant sequence motifs.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 01, 2023
Source ID
10.1093/bioinformatics/btad271

Entities

People

  • Ali Tuğrul Balcı
  • Dennis Kostka
  • Maria Chikina
  • Mark Maher Ebeid
  • Panayiotis V Benos

Organizations

  • Defense Advanced Research Projects Agency
  • National Institutes of Health
  • National Science Foundation
  • University of Florida
  • University of Pittsburgh

Tags

Fields of Study

  • Computer science

Readers

  • Molecular Genetics
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks