Skip to main content

Interpretable Deep Learning

This Genome Biology special issue is guest edited by Peter Koo of Cold Spring Harbor Laboratory, Sara Mostafavi of the University of Washington, and Asa Ben-Hur of Colorado State University.

Deep learning models have demonstrated a powerful ability to accurately model various genomics data. However, their impact on biology depends on the ability to interpret the models and discover new findings. We would like to invite submissions that focus on this aspect of deep learning:  new methods for making interpretable predictions for genomics data or studies that demonstrate the ability of these architectures to make novel biological discoveries. 

Genome Biology highlights timely advances in interpretable deep learning with applications in genomics.

  1. The binding of transcription factors at proximal promoters and distal enhancers is central to gene regulation. Identifying regulatory motifs and quantifying their impact on expression remains challenging. Usin...

    Authors: Jacob Hepkema, Nicholas Keone Lee, Benjamin J. Stewart, Siwat Ruangroengkulrith, Varodom Charoensawan, Menna R. Clatworthy and Martin Hemberg
    Citation: Genome Biology 2023 24:189
  2. Deep learning models such as convolutional neural networks (CNNs) excel in genomic tasks but lack interpretability. We introduce ExplaiNN, which combines the expressiveness of CNNs with the interpretability of...

    Authors: Gherman Novakovsky, Oriol Fornes, Manu Saraswat, Sara Mostafavi and Wyeth W. Wasserman
    Citation: Genome Biology 2023 24:154
  3. Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and or even capture differences among training cell types. We ...

    Authors: Rui Yang, Arnav Das, Vianne R. Gao, Alireza Karbalayghareh, William S. Noble, Jeffrey A. Bilmes and Christina S. Leslie
    Citation: Genome Biology 2023 24:134

    The Author Correction to this article has been published in Genome Biology 2024 25:132

  4. DNA double-strand breaks (DSBs) are among the most deleterious DNA lesions, and they can cause cancer if improperly repaired. Recent chromosome conformation capture techniques, such as Hi-C, have enabled the i...

    Authors: Yu Sun, Xiang Xu, Lin Lin, Kang Xu, Yang Zheng, Chao Ren, Huan Tao, Xu Wang, Huan Zhao, Weiwei Tu, Xuemei Bai, Junting Wang, Qiya Huang, Yaru Li, Hebing Chen, Hao Li…
    Citation: Genome Biology 2023 24:90
  5. As interest in using unsupervised deep learning models to analyze gene expression data has grown, an increasing number of methods have been developed to make these models more interpretable. These methods can ...

    Authors: Joseph D. Janizek, Anna Spiro, Safiye Celik, Ben W. Blue, John C. Russell, Ting-I Lee, Matt Kaeberlin and Su-In Lee
    Citation: Genome Biology 2023 24:81
  6. Alternative splicing is a widespread regulatory phenomenon that enables a single gene to produce multiple transcripts. Among the different types of alternative splicing, intron retention is one of the least ex...

    Authors: Fahad Ullah, Saira Jabeen, Maayan Salton, Anireddy S. N. Reddy and Asa Ben-Hur
    Citation: Genome Biology 2023 24:53
  7. Studies have shown a link between colorectal cancer (CRC) and gut microbiome compositions. In these studies, machine learning is used to infer CRC biomarkers using global explanation methods. While these metho...

    Authors: Ryza Rynazal, Kota Fujisawa, Hirotsugu Shiroma, Felix Salim, Sayaka Mizutani, Satoshi Shiba, Shinichi Yachida and Takuji Yamada
    Citation: Genome Biology 2023 24:21
  8. In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only. Benchmarking comparisons...

    Authors: Junru Jin, Yingying Yu, Ruheng Wang, Xin Zeng, Chao Pang, Yi Jiang, Zhongshen Li, Yutong Dai, Ran Su, Quan Zou, Kenta Nakai and Leyi Wei
    Citation: Genome Biology 2022 23:219