Discovering and deciphering relationships across disparate data modalities
Abstract
Understanding the relationships between different properties of data, such as whether a genome or connectome has information about disease status, is increasingly important. While existing approaches can test whether two properties are related, they may require unfeasibly large sample sizes and often are not interpretable. Our approach, 'Multiscale Graph Correlation' (MGC), is a dependence test that juxtaposes disparate data science techniques, including k-nearest neighbors, kernel methods, and multiscale analysis. Other methods may require double or triple the number of samples to achieve the same statistical power as MGC in a benchmark suite including high-dimensional and nonlinear relationships, with dimensionality ranging from 1 to 1000. Moreover, MGC uniquely characterizes the latent geometry underlying the relationship, while maintaining computational efficiency. In real data, including brain imaging and cancer genetics, MGC detects the presence of a dependency and provides guidance for the next experiments to conduct.
Data availability
To facilitate reproducibility, we make all datasets available from: https://github.com/neurodata/MGC-paper/tree/master/Data/Preprocessed
Article and author information
Author details
Funding
Child Mind Institute Endeavor Scientist Program
- Joshua T Vogelstein
National Science Foundation
- Joshua T Vogelstein
Defense Advanced Research Projects Agency
- Joshua T Vogelstein
Office of Naval Research
- Joshua T Vogelstein
Air Force Office of Scientific Research
- Joshua T Vogelstein
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Dane Taylor, University of Buffalo, United States
Version history
- Received: September 3, 2018
- Accepted: January 14, 2019
- Accepted Manuscript published: January 15, 2019 (version 1)
- Version of Record published: February 22, 2019 (version 2)
Copyright
© 2019, Vogelstein 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
-
- 3,501
- views
-
- 418
- downloads
-
- 16
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
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)
Further reading
-
- Computational and Systems Biology
The reconstruction of complete microbial metabolic pathways using ‘omics data from environmental samples remains challenging. Computational pipelines for pathway reconstruction that utilize machine learning methods to predict the presence or absence of KEGG modules in incomplete genomes are lacking. Here, we present MetaPathPredict, a software tool that incorporates machine learning models to predict the presence of complete KEGG modules within bacterial genomic datasets. Using gene annotation data and information from the KEGG module database, MetaPathPredict employs deep learning models to predict the presence of KEGG modules in a genome. MetaPathPredict can be used as a command line tool or as a Python module, and both options are designed to be run locally or on a compute cluster. Benchmarks show that MetaPathPredict makes robust predictions of KEGG module presence within highly incomplete genomes.
-
- Computational and Systems Biology
- Evolutionary Biology
As the genome encodes the information crucial for cell growth, a sizeable genomic deficiency often causes a significant decrease in growth fitness. Whether and how the decreased growth fitness caused by genome reduction could be compensated by evolution was investigated here. Experimental evolution with an Escherichia coli strain carrying a reduced genome was conducted in multiple lineages for approximately 1000 generations. The growth rate, which largely declined due to genome reduction, was considerably recovered, associated with the improved carrying capacity. Genome mutations accumulated during evolution were significantly varied across the evolutionary lineages and were randomly localized on the reduced genome. Transcriptome reorganization showed a common evolutionary direction and conserved the chromosomal periodicity, regardless of highly diversified gene categories, regulons, and pathways enriched in the differentially expressed genes. Genome mutations and transcriptome reorganization caused by evolution, which were found to be dissimilar to those caused by genome reduction, must have followed divergent mechanisms in individual evolutionary lineages. Gene network reconstruction successfully identified three gene modules functionally differentiated, which were responsible for the evolutionary changes of the reduced genome in growth fitness, genome mutation, and gene expression, respectively. The diversity in evolutionary approaches improved the growth fitness associated with the homeostatic transcriptome architecture as if the evolutionary compensation for genome reduction was like all roads leading to Rome.