1. Computational and Systems Biology
  2. Genetics and Genomics

Rapid, reference-free human genotype imputation with denoising autoencoders

  1. Raquel Dias
  2. Doug Evans
  3. Shang-Fu Chen
  4. Kai-Yu Chen
  5. Salvatore Loguercio
  6. Leslie Chan
  7. Ali Torkamani  Is a corresponding author
  1. University of Florida, United States
  2. Scripps Research Institute, United States
https://doi.org/10.7554/eLife.75600
Share this article
Cite this article
  1. Raquel Dias
  2. Doug Evans
  3. Shang-Fu Chen
  4. Kai-Yu Chen
  5. Salvatore Loguercio
  6. Leslie Chan
  7. Ali Torkamani
(2022)
Rapid, reference-free human genotype imputation with denoising autoencoders
eLife 11:e75600.
https://doi.org/10.7554/eLife.75600
  2. Download BibTeX
  3. Download .RIS

Abstract

Genotype imputation is a foundational tool for population genetics. Standard statistical imputation approaches rely on the co-location of large whole-genome sequencing-based reference panels, powerful computing environments, and potentially sensitive genetic study data. This results in computational resource and privacy-risk barriers to access to cutting-edge imputation techniques. Moreover, the accuracy of current statistical approaches is known to degrade in regions of low and complex linkage disequilibrium. Artificial neural network-based imputation approaches may overcome these limitations by encoding complex genotype relationships in easily portable inference models. Here we demonstrate an autoencoder-based approach for genotype imputation, using a large, commonly used reference panel, and spanning the entirety of human chromosome 22. Our autoencoder-based genotype imputation strategy achieved superior imputation accuracy across the allele-frequency spectrum and across genomes of diverse ancestry, while delivering at least 4-fold faster inference run time relative to standard imputation tools.

Data availability

The data that support the findings of this study are available from dbGAP and European Genome-phenome Archive (EGA), but restrictions apply to the availability of these data, which were used under ethics approval for the current study, and so are not openly available to the public. The computational pipeline for autoencoder training and validation is available at https://github.com/TorkamaniLab/Imputation_Autoencoder/tree/master/autoencoder_tuning_pipeline. The python script for calculating imputation accuracy is available at https://github.com/TorkamaniLab/imputation_accuracy_calculator. Instructions on how to access the unique information on the parameters and hyperparameters of each one of the 256 autoencoders is shared through our source code repository at https://github.com/TorkamaniLab/imputator_inference. We also shared the pre-trained autoencoders and instructions on how to use them for imputation at https://github.com/TorkamaniLab/imputator_inference.Imputation data format. The imputation results are exported in variant calling format (VCF) containing the imputed genotypes and imputation quality scores in the form of class probabilities for each one of the three possible genotypes (homozygous reference, heterozygous, and homozygous alternate allele). The probabilities can be used for quality control of the imputation results.

The following previously published data sets were used

Article and author information

Author details

  1. Raquel Dias

    Department of Microbiology and Cell Science, University of Florida, Gainesville, United States
    Competing interests
    The authors declare that no competing interests exist.

  2. Doug Evans

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    Competing interests
    The authors declare that no competing interests exist.

  3. Shang-Fu Chen

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    Competing interests
    The authors declare that no competing interests exist.

  4. Kai-Yu Chen

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    Competing interests
    The authors declare that no competing interests exist.

  5. Salvatore Loguercio

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    Competing interests
    The authors declare that no competing interests exist.

  6. Leslie Chan

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    Competing interests
    The authors declare that no competing interests exist.

  7. Ali Torkamani

    Scripps Research Translational Institute, Scripps Research Institute, La Jolla, United States
    For correspondence
    atorkama@scripps.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-0232-8053

Funding

National Institutes of Health (R01HG010881)

  • Raquel Dias
  • Doug Evans
  • Shang-Fu Chen
  • Kai-Yu Chen
  • Salvatore Loguercio
  • Ali Torkamani

National Institutes of Health (KL2TR002552)

  • Raquel Dias

National Institutes of Health (U24TR002306)

  • Doug Evans
  • Shang-Fu Chen
  • Kai-Yu Chen
  • Ali Torkamani

National Institutes of Health (UL1TR002550)

  • Doug Evans
  • Shang-Fu Chen
  • Kai-Yu Chen
  • Ali Torkamani

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

Copyright

© 2022, Dias 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

  • 2,444
    views
  • 279
    downloads
  • 8
    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. Raquel Dias
  2. Doug Evans
  3. Shang-Fu Chen
  4. Kai-Yu Chen
  5. Salvatore Loguercio
  6. Leslie Chan
  7. Ali Torkamani
(2022)
Rapid, reference-free human genotype imputation with denoising autoencoders
eLife 11:e75600.
https://doi.org/10.7554/eLife.75600

Share this article

https://doi.org/10.7554/eLife.75600

Categories and tags

Research organism

Further reading

    1. Computational and Systems Biology
    2. Developmental Biology

    Dynamic readout of the Hh gradient in the Drosophila wing disc reveals pattern-specific tradeoffs between robustness and precision

    Rosalío Reyes, Arthur D Lander, Marcos Nahmad
    Research Article Updated

    Understanding the principles underlying the design of robust, yet flexible patterning systems is a key problem in developmental biology. In the Drosophila wing, Hedgehog (Hh) signaling determines patterning outputs using dynamical properties of the Hh gradient. In particular, the pattern of collier (col) is established by the steady-state Hh gradient, whereas the pattern of decapentaplegic (dpp), is established by a transient gradient of Hh known as the Hh overshoot. Here, we use mathematical modeling to suggest that this dynamical interpretation of the Hh gradient results in specific robustness and precision properties. For instance, the location of the anterior border of col, which is subject to self-enhanced ligand degradation is more robustly specified than that of dpp to changes in morphogen dosage, and we provide experimental evidence of this prediction. However, the anterior border of dpp expression pattern, which is established by the overshoot gradient is much more precise to what would be expected by the steady-state gradient. Therefore, the dynamical interpretation of Hh signaling offers tradeoffs between robustness and precision to establish tunable patterning properties in a target-specific manner.

    1. Computational and Systems Biology
    2. Neuroscience

    Estradiol elicits distinct firing patterns in arcuate nucleus kisspeptin neurons of females through altering ion channel conductances

    Jian Qiu, Margaritis Voliotis ... Martin J Kelly
    Research Article

    Hypothalamic kisspeptin (Kiss1) neurons are vital for pubertal development and reproduction. Arcuate nucleus Kiss1 (Kiss1ARH) neurons are responsible for the pulsatile release of gonadotropin-releasing hormone (GnRH). In females, the behavior of Kiss1ARH neurons, expressing Kiss1, neurokinin B (NKB), and dynorphin (Dyn), varies throughout the ovarian cycle. Studies indicate that 17β-estradiol (E2) reduces peptide expression but increases Slc17a6 (Vglut2) mRNA and glutamate neurotransmission in these neurons, suggesting a shift from peptidergic to glutamatergic signaling. To investigate this shift, we combined transcriptomics, electrophysiology, and mathematical modeling. Our results demonstrate that E2 treatment upregulates the mRNA expression of voltage-activated calcium channels, elevating the whole-cell calcium current that contributes to high-frequency burst firing. Additionally, E2 treatment decreased the mRNA levels of canonical transient receptor potential (TPRC) 5 and G protein-coupled K+ (GIRK) channels. When Trpc5 channels in Kiss1ARH neurons were deleted using CRISPR/SaCas9, the slow excitatory postsynaptic potential was eliminated. Our data enabled us to formulate a biophysically realistic mathematical model of Kiss1ARH neurons, suggesting that E2 modifies ionic conductances in these neurons, enabling the transition from high-frequency synchronous firing through NKB-driven activation of TRPC5 channels to a short bursting mode facilitating glutamate release. In a low E2 milieu, synchronous firing of Kiss1ARH neurons drives pulsatile release of GnRH, while the transition to burst firing with high, preovulatory levels of E2 would facilitate the GnRH surge through its glutamatergic synaptic connection to preoptic Kiss1 neurons.

    1. Computational and Systems Biology

    Emergence of power-law distributions in protein-protein interaction networks through study bias

    David B Blumenthal, Marta Lucchetta ... Martin H Schaefer
    Research Article

    Degree distributions in protein-protein interaction (PPI) networks are believed to follow a power law (PL). However, technical and study bias affect the experimental procedures for detecting PPIs. For instance, cancer-associated proteins have received disproportional attention. Moreover, bait proteins in large-scale experiments tend to have many false-positive interaction partners. Studying the degree distributions of thousands of PPI networks of controlled provenance, we address the question if PL distributions in observed PPI networks could be explained by these biases alone. Our findings are supported by mathematical models and extensive simulations and indicate that study bias and technical bias suffice to produce the observed PL distribution. It is, hence, problematic to derive hypotheses about the topology of the true biological interactome from the PL distributions in observed PPI networks. Our study casts doubt on the use of the PL property of biological networks as a modeling assumption or quality criterion in network biology.