skip to main content

This content will become publicly available on April 1, 2023

Title: Interpretable deep generative models for genomics
Deep neural networks implementing generative models for dimensionality reduction have been extensively used for the visualization and analysis of genomic data. One of their key limitations is lack of interpretability: it is challenging to quantitatively identify which input features are used to construct the embedding dimensions, thus preventing insight into why cells are organized in a particular data visualization, for example. Here we present a scalable, interpretable variational autoencoder (siVAE) that is interpretable by design: it learns feature embeddings that guide the interpretation of the cell embeddings in a manner analogous to factor loadings of factor analysis. siVAE is as powerful and nearly as fast to train as the standard VAE but achieves full interpretability of the embedding dimensions. Using siVAE, we exploit a number of connections between dimensionality reduction and gene network inference to identify gene neighborhoods and gene hubs, without the explicit need for gene network inference. We observe a systematic difference in the gene neighborhoods identified by dimensionality reduction methods and gene network inference algorithms in general, suggesting they provide complementary information about the underlying structure of the gene co-expression network. Finally, we apply siVAE to implicitly learn gene networks for individual iPSC lines and uncover a more » correlation between neuronal differentiation efficiency and loss of co-expression of several mitochondrial complexes, including NADH dehydrogenase, cytochrome C oxidase, and cytochrome b. « less
Authors:
; ;
Award ID(s):
1846559
Publication Date:
NSF-PAR ID:
10327264
Journal Name:
bioRxiv
ISSN:
2692-8205
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Motivation

    Gene regulatory networks (GRNs) of the same organism can be different under different conditions, although the overall network structure may be similar. Understanding the difference in GRNs under different conditions is important to understand condition-specific gene regulation. When gene expression and other relevant data under two different conditions are available, they can be used by an existing network inference algorithm to estimate two GRNs separately, and then to identify the difference between the two GRNs. However, such an approach does not exploit the similarity in two GRNs, and may sacrifice inference accuracy.

    Results

    In this paper, we model GRNs withmore »the structural equation model (SEM) that can integrate gene expression and genetic perturbation data, and develop an algorithm named fused sparse SEM (FSSEM), to jointly infer GRNs under two conditions, and then to identify difference of the two GRNs. Computer simulations demonstrate that the FSSEM algorithm outperforms the approaches that estimate two GRNs separately. Analysis of a dataset of lung cancer and another dataset of gastric cancer with FSSEM inferred differential GRNs in cancer versus normal tissues, whose genes with largest network degrees have been reported to be implicated in tumorigenesis. The FSSEM algorithm provides a valuable tool for joint inference of two GRNs and identification of the differential GRN under two conditions.

    Availability and implementation

    The R package fssemR implementing the FSSEM algorithm is available at https://github.com/Ivis4ml/fssemR.git. It is also available on CRAN.

    Supplementary information

    Supplementary data are available at Bioinformatics online.

    « less
  2. Nie, Qing (Ed.)
    The analysis of single-cell genomics data presents several statistical challenges, and extensive efforts have been made to produce methods for the analysis of this data that impute missing values, address sampling issues and quantify and correct for noise. In spite of such efforts, no consensus on best practices has been established and all current approaches vary substantially based on the available data and empirical tests. The k-Nearest Neighbor Graph (kNN-G) is often used to infer the identities of, and relationships between, cells and is the basis of many widely used dimensionality-reduction and projection methods. The kNN-G has also been themore »basis for imputation methods using, e.g ., neighbor averaging and graph diffusion. However, due to the lack of an agreed-upon optimal objective function for choosing hyperparameters, these methods tend to oversmooth data, thereby resulting in a loss of information with regard to cell identity and the specific gene-to-gene patterns underlying regulatory mechanisms. In this paper, we investigate the tuning of kNN- and diffusion-based denoising methods with a novel non-stochastic method for optimally preserving biologically relevant informative variance in single-cell data. The framework, Denoising Expression data with a Weighted Affinity Kernel and Self-Supervision (DEWÄKSS), uses a self-supervised technique to tune its parameters. We demonstrate that denoising with optimal parameters selected by our objective function (i) is robust to preprocessing methods using data from established benchmarks, (ii) disentangles cellular identity and maintains robust clusters over dimension-reduction methods, (iii) maintains variance along several expression dimensions, unlike previous heuristic-based methods that tend to oversmooth data variance, and (iv) rarely involves diffusion but rather uses a fixed weighted kNN graph for denoising. Together, these findings provide a new understanding of kNN- and diffusion-based denoising methods. Code and example data for DEWÄKSS is available at https://gitlab.com/Xparx/dewakss/-/tree/Tjarnberg2020branch .« less
  3. Mathelier, Anthony (Ed.)
    Abstract Motivation Single-cell transcriptomics profiling technologies enable genome-wide gene expression measurements in individual cells but can currently only provide a static snapshot of cellular transcriptional states. RNA velocity analysis can help infer cell state changes using such single-cell transcriptomics data. To interpret these cell state changes inferred from RNA velocity analysis as part of underlying cellular trajectories, current approaches rely on visualization with principal components, t-distributed stochastic neighbor embedding and other 2D embeddings derived from the observed single-cell transcriptional states. However, these 2D embeddings can yield different representations of the underlying cellular trajectories, hindering the interpretation of cell state changes.more »Results We developed VeloViz to create RNA velocity-informed 2D and 3D embeddings from single-cell transcriptomics data. Using both real and simulated data, we demonstrate that VeloViz embeddings are able to capture underlying cellular trajectories across diverse trajectory topologies, even when intermediate cell states may be missing. By considering the predicted future transcriptional states from RNA velocity analysis, VeloViz can help visualize a more reliable representation of underlying cellular trajectories. Availability and implementation Source code is available on GitHub (https://github.com/JEFworks-Lab/veloviz) and Bioconductor (https://bioconductor.org/packages/veloviz) with additional tutorials at https://JEF.works/veloviz/. Datasets used can be found on Zenodo (https://doi.org/10.5281/zenodo.4632471). Supplementary information Supplementary data are available at Bioinformatics online.« less
  4. Finding the network biomarkers of cancers and the analysis of cancer driving genes that are involved in these biomarkers are essential for understanding the dynamics of cancer. Clusters of genes in co-expression networks are commonly known as functional units. This work is based on the hypothesis that the dense clusters or communities in the gene co-expression networks of cancer patients may represent functional units regarding cancer initiation and progression. In this study, RNA-seq gene expression data of three cancers - Breast Invasive Carcinoma (BRCA), Colorectal Adenocarcinoma (COAD) and Glioblastoma Multiforme (GBM) - from The Cancer Genome Atlas (TCGA) are usedmore »to construct gene co-expression networks using Pearson Correlation. Six well-known community detection algorithms are applied on these networks to identify communities with five or more genes. A permutation test is performed to further mine the communities that are conserved in other cancers, thus calling them conserved communities. Then survival analysis is performed on clinical data of three cancers using the conserved community genes as prognostic co-variates. The communities that could distinguish the cancer patients between high- and low-risk groups are considered as cancer biomarkers. In the present study, 16 such network biomarkers are discovered.« less
  5. Electronic health records (EHRs) have been heavily used in modern healthcare systems for recording patients' admission information to health facilities. Many data-driven approaches employ temporal features in EHR for predicting specific diseases, readmission times, and diagnoses of patients. However, most existing predictive models cannot fully utilize EHR data, due to an inherent lack of labels in supervised training for some temporal events. Moreover, it is hard for the existing methods to simultaneously provide generic and personalized interpretability. To address these challenges, we propose Sherbet, a self-supervised graph learning framework with hyperbolic embeddings for temporal health event prediction. We first proposemore »a hyperbolic embedding method with information flow to pretrain medical code representations in a hierarchical structure. We incorporate these pretrained representations into a graph neural network (GNN) to detect disease complications and design a multilevel attention method to compute the contributions of particular diseases and admissions, thus enhancing personalized interpretability. We present a new hierarchy-enhanced historical prediction proxy task in our self-supervised learning framework to fully utilize EHR data and exploit medical domain knowledge. We conduct a comprehensive set of experiments on widely used publicly available EHR datasets to verify the effectiveness of our model. Our results demonstrate the proposed model's strengths in both predictive tasks and interpretable abilities.« less