A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements

  1. Calvin M Schmidt
  2. Christina D Smolke  Is a corresponding author
  1. Stanford University, United States

Abstract

Ribozyme switches are a class of RNA-encoded genetic switch that support conditional regulation of gene expression across diverse organisms. An improved elucidation of the relationships between sequence, structure, and activity can improve our capacity for de novo rational design of ribozyme switches. Here, we generated data on the activity of hundreds of thousands of ribozyme sequences. Using automated structural analysis and machine learning, we leveraged these large datasets to develop predictive models that estimate the in vivo gene-regulatory activity of a ribozyme sequence. These models supported the de novo design of ribozyme libraries with low mean basal gene-regulatory activities and new ribozyme switches that exhibit changes in gene-regulatory activity in the presence of a target ligand, producing functional switches for four out of five aptamers. Our work examines how biases in the model and the dataset that affect prediction accuracy can arise and demonstrates that machine learning can be applied to RNA sequences to predict gene-regulatory activity, providing the basis for design tools for functional RNAs.

Data availability

All data generated or analyzed during this study and including in the manuscript and supporting file. Source data files are provided where appropriate.

The following previously published data sets were used

Article and author information

Author details

  1. Calvin M Schmidt

    Bioengineering, Stanford University, Stanford, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Christina D Smolke

    Bioengineering, Stanford University, Stanford, United States
    For correspondence
    csmolke@stanford.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-5449-8495

Funding

National Institutes of Health (R01 GM086663)

  • Christina D Smolke

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

Reviewing Editor

  1. Detlef Weigel, Max Planck Institute for Developmental Biology, Germany

Version history

  1. Received: June 5, 2020
  2. Accepted: April 15, 2021
  3. Accepted Manuscript published: April 16, 2021 (version 1)
  4. Version of Record published: May 17, 2021 (version 2)

Copyright

© 2021, Schmidt & Smolke

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

  • 1,838
    views
  • 269
    downloads
  • 7
    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. Calvin M Schmidt
  2. Christina D Smolke
(2021)
A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
eLife 10:e59697.
https://doi.org/10.7554/eLife.59697

Share this article

https://doi.org/10.7554/eLife.59697

Further reading

    1. Computational and Systems Biology
    2. Medicine
    Seo-Gyeong Bae, Guo Nan Yin ... Jihwan Park
    Research Article

    Erectile dysfunction (ED) affects a significant proportion of men aged 40–70 and is caused by cavernous tissue dysfunction. Presently, the most common treatment for ED is phosphodiesterase 5 inhibitors; however, this is less effective in patients with severe vascular disease such as diabetic ED. Therefore, there is a need for development of new treatment, which requires a better understanding of the cavernous microenvironment and cell-cell communications under diabetic condition. Pericytes are vital in penile erection; however, their dysfunction due to diabetes remains unclear. In this study, we performed single-cell RNA sequencing to understand the cellular landscape of cavernous tissues and cell type-specific transcriptional changes in diabetic ED. We found a decreased expression of genes associated with collagen or extracellular matrix organization and angiogenesis in diabetic fibroblasts, chondrocytes, myofibroblasts, valve-related lymphatic endothelial cells, and pericytes. Moreover, the newly identified pericyte-specific marker, Limb Bud-Heart (Lbh), in mouse and human cavernous tissues, clearly distinguishing pericytes from smooth muscle cells. Cell-cell interaction analysis revealed that pericytes are involved in angiogenesis, adhesion, and migration by communicating with other cell types in the corpus cavernosum; however, these interactions were highly reduced under diabetic conditions. Lbh expression is low in diabetic pericytes, and overexpression of LBH prevents erectile function by regulating neurovascular regeneration. Furthermore, the LBH-interacting proteins (Crystallin Alpha B and Vimentin) were identified in mouse cavernous pericytes through LC-MS/MS analysis, indicating that their interactions were critical for maintaining pericyte function. Thus, our study reveals novel targets and insights into the pathogenesis of ED in patients with diabetes.

    1. Computational and Systems Biology
    Rebecca A Deek, Siyuan Ma ... Hongzhe Li
    Review Article

    Large-scale microbiome studies are progressively utilizing multiomics designs, which include the collection of microbiome samples together with host genomics and metabolomics data. Despite the increasing number of data sources, there remains a bottleneck in understanding the relationships between different data modalities due to the limited number of statistical and computational methods for analyzing such data. Furthermore, little is known about the portability of general methods to the metagenomic setting and few specialized techniques have been developed. In this review, we summarize and implement some of the commonly used methods. We apply these methods to real data sets where shotgun metagenomic sequencing and metabolomics data are available for microbiome multiomics data integration analysis. We compare results across methods, highlight strengths and limitations of each, and discuss areas where statistical and computational innovation is needed.