1. Computational and Systems Biology
  2. Genetics and Genomics

Deep learning models predict regulatory variants in pancreatic islets and refine type 2 diabetes association signals

  1. Agata Wesolowska-Andersen
  2. Grace Zhuo Yu
  3. Vibe Nylander
  4. Fernando Abaitua
  5. Matthias Thurner
  6. Jason M Torres
  7. Anubha Mahajan
  8. Anna L Gloyn
  9. Mark I McCarthy  Is a corresponding author
  1. University of Oxford, United Kingdom
  2. Genentech, United States
https://doi.org/10.7554/eLife.51503
Share this article
Cite this article
  1. Agata Wesolowska-Andersen
  2. Grace Zhuo Yu
  3. Vibe Nylander
  4. Fernando Abaitua
  5. Matthias Thurner
  6. Jason M Torres
  7. Anubha Mahajan
  8. Anna L Gloyn
  9. Mark I McCarthy
(2020)
Deep learning models predict regulatory variants in pancreatic islets and refine type 2 diabetes association signals
eLife 9:e51503.
https://doi.org/10.7554/eLife.51503
  2. Download BibTeX
  3. Download .RIS

Abstract

Genome-wide association analyses have uncovered multiple genomic regions associated with T2D, but identification of the causal variants at these remains a challenge. There is growing interest in the potential of deep learning models - which predict epigenome features from DNA sequence - to support inference concerning the regulatory effects of disease-associated variants. Here, we evaluate the advantages of training convolutional neural network (CNN) models on a broad set of epigenomic features collected in a single disease-relevant tissue – pancreatic islets in the case of type 2 diabetes (T2D) - as opposed to models trained on multiple human tissues. We report convergence of CNN-based metrics of regulatory function with conventional approaches to variant prioritization – genetic fine-mapping and regulatory annotation enrichment. We demonstrate that CNN-based analyses can refine association signals at T2D-associated loci and provide experimental validation for one such signal. We anticipate that these approaches will become routine in downstream analyses of GWAS.

Data availability

The datasets analysed during the current study are available in the public repositories under accessions listed in STable 1.

The following previously published data sets were used

Article and author information

Author details

  1. Agata Wesolowska-Andersen

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-8688-2814

  2. Grace Zhuo Yu

    Oxford Centre for Diabetes, Endocrinology and Metabolism, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.

  3. Vibe Nylander

    Oxford Centre for Diabetes, Endocrinology and Metabolism, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.

  4. Fernando Abaitua

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.

  5. Matthias Thurner

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-7329-9769

  6. Jason M Torres

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7537-7035

  7. Anubha Mahajan

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.

  8. Anna L Gloyn

    The Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-1205-1844

  9. Mark I McCarthy

    Department of Human Genetics, Genentech, South San Francisco, United States
    For correspondence
    mark.mccarthy@drl.ox.ac.uk
    Competing interests
    Mark I McCarthy, Senior editor, eLife; has served on advisory panels for Pfizer, NovoNordisk, Zoe Global; has received honoraria from Merck, Pfizer, NovoNordisk and Eli Lilly; has stock options in Zoe Global and has received research funding from Abbvie, Astra Zeneca, Boehringer Ingelheim, Eli Lilly, Janssen, Merck, NovoNordisk, Pfizer, Roche, Sanofi Aventis, Servier & Takeda. As of June 2019, is an employee of Genentech, and holds stock in Roche.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-4393-0510

Funding

Wellcome (099673/Z/12/Z)

  • Matthias Thurner

Horizon 2020 Framework Programme (T2D Systems)

  • Anna L Gloyn

NIH Clinical Center (U01-DK105535)

  • Anna L Gloyn
  • Mark I McCarthy

NIH Clinical Center (U01-DK085545)

  • Anna L Gloyn

National Institute for Health Research (NF-SI-0617-10090)

  • Anna L Gloyn

Wellcome (090532)

  • Mark I McCarthy

Wellcome (106130)

  • Anna L Gloyn
  • Mark I McCarthy

Wellcome (098381)

  • Mark I McCarthy

Wellcome (203141)

  • Anna L Gloyn
  • Mark I McCarthy

Wellcome (212259)

  • Mark I McCarthy

Wellcome (095101)

  • Anna L Gloyn

Wellcome (200837)

  • Anna L Gloyn

Medical Research Council (MR/L020149/1)

  • Anna L Gloyn

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Copyright

© 2020, Wesolowska-Andersen et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 4,137
    views
  • 628
    downloads
  • 27
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Agata Wesolowska-Andersen
  2. Grace Zhuo Yu
  3. Vibe Nylander
  4. Fernando Abaitua
  5. Matthias Thurner
  6. Jason M Torres
  7. Anubha Mahajan
  8. Anna L Gloyn
  9. Mark I McCarthy
(2020)
Deep learning models predict regulatory variants in pancreatic islets and refine type 2 diabetes association signals
eLife 9:e51503.
https://doi.org/10.7554/eLife.51503

Share this article

https://doi.org/10.7554/eLife.51503

Categories and tags

Research organism

Further reading

    1. Cancer Biology
    2. Computational and Systems Biology

    Luminal epithelial cells integrate variable responses to aging into stereotypical changes that underlie breast cancer susceptibility

    Rosalyn W Sayaman, Masaru Miyano ... Mark LaBarge
    Research Article

    Effects from aging in single cells are heterogenous, whereas at the organ- and tissue-levels aging phenotypes tend to appear as stereotypical changes. The mammary epithelium is a bilayer of two major phenotypically and functionally distinct cell lineages: luminal epithelial and myoepithelial cells. Mammary luminal epithelia exhibit substantial stereotypical changes with age that merit attention because these cells are the putative cells-of-origin for breast cancers. We hypothesize that effects from aging that impinge upon maintenance of lineage fidelity increase susceptibility to cancer initiation. We generated and analyzed transcriptomes from primary luminal epithelial and myoepithelial cells from younger <30 (y)ears old and older >55y women. In addition to age-dependent directional changes in gene expression, we observed increased transcriptional variance with age that contributed to genome-wide loss of lineage fidelity. Age-dependent variant responses were common to both lineages, whereas directional changes were almost exclusively detected in luminal epithelia and involved altered regulation of chromatin and genome organizers such as SATB1. Epithelial expression of gap junction protein GJB6 increased with age, and modulation of GJB6 expression in heterochronous co-cultures revealed that it provided a communication conduit from myoepithelial cells that drove directional change in luminal cells. Age-dependent luminal transcriptomes comprised a prominent signal that could be detected in bulk tissue during aging and transition into cancers. A machine learning classifier based on luminal-specific aging distinguished normal from cancer tissue and was highly predictive of breast cancer subtype. We speculate that luminal epithelia are the ultimate site of integration of the variant responses to aging in their surrounding tissue, and that their emergent phenotype both endows cells with the ability to become cancer-cells-of-origin and represents a biosensor that presages cancer susceptibility.

    1. Computational and Systems Biology
    2. Microbiology and Infectious Disease

    An antimicrobial drug recommender system using MALDI-TOF MS and dual-branch neural networks

    Gaetan De Waele, Gerben Menschaert, Willem Waegeman
    Research Article

    Timely and effective use of antimicrobial drugs can improve patient outcomes, as well as help safeguard against resistance development. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is currently routinely used in clinical diagnostics for rapid species identification. Mining additional data from said spectra in the form of antimicrobial resistance (AMR) profiles is, therefore, highly promising. Such AMR profiles could serve as a drop-in solution for drastically improving treatment efficiency, effectiveness, and costs. This study endeavors to develop the first machine learning models capable of predicting AMR profiles for the whole repertoire of species and drugs encountered in clinical microbiology. The resulting models can be interpreted as drug recommender systems for infectious diseases. We find that our dual-branch method delivers considerably higher performance compared to previous approaches. In addition, experiments show that the models can be efficiently fine-tuned to data from other clinical laboratories. MALDI-TOF-based AMR recommender systems can, hence, greatly extend the value of MALDI-TOF MS for clinical diagnostics. All code supporting this study is distributed on PyPI and is packaged at https://github.com/gdewael/maldi-nn.

    1. Computational and Systems Biology
    2. Genetics and Genomics

    Functional characteristics and computational model of abundant hyperactive loci in the human genome

    Sanjarbek Hudaiberdiev, Ivan Ovcharenko
    Research Article

    Enhancers and promoters are classically considered to be bound by a small set of transcription factors (TFs) in a sequence-specific manner. This assumption has come under increasing skepticism as the datasets of ChIP-seq assays of TFs have expanded. In particular, high-occupancy target (HOT) loci attract hundreds of TFs with often no detectable correlation between ChIP-seq peaks and DNA-binding motif presence. Here, we used a set of 1003 TF ChIP-seq datasets (HepG2, K562, H1) to analyze the patterns of ChIP-seq peak co-occurrence in combination with functional genomics datasets. We identified 43,891 HOT loci forming at the promoter (53%) and enhancer (47%) regions. HOT promoters regulate housekeeping genes, whereas HOT enhancers are involved in tissue-specific process regulation. HOT loci form the foundation of human super-enhancers and evolve under strong negative selection, with some of these loci being located in ultraconserved regions. Sequence-based classification analysis of HOT loci suggested that their formation is driven by the sequence features, and the density of mapped ChIP-seq peaks across TF-bound loci correlates with sequence features and the expression level of flanking genes. Based on the affinities to bind to promoters and enhancers we detected five distinct clusters of TFs that form the core of the HOT loci. We report an abundance of HOT loci in the human genome and a commitment of 51% of all TF ChIP-seq binding events to HOT locus formation thus challenging the classical model of enhancer activity and propose a model of HOT locus formation based on the existence of large transcriptional condensates.