Donate

Publication

Similarity-driven multi-view embeddings from high-dimensional biomedical data

Citation:
Nature Computational Science. 2021; 1: 143–152 https://doi.org/10.1038/s43588-021-00029-8
Authored By:
Avants, B.B., Tustison, N.J. & Stone, J.R
Abstract:
Diverse, high-dimensional modalities collected in large cohorts present new opportunities for the formulation and testing of integrative scientific hypotheses. Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR contributes an objective function to identify joint signal regularization based on sparse matrices representing prior within-modality relationships and an implementation that permits application to joint reduction of large data matrices. We demonstrate that SiMLR outperlforms closely related methods on supervised learning problems in simulation data, a multi-omics cancer survival prediction dataset and multiple modality neuroimaging datasets. Taken together, this collection of results shows that SiMLR may be applied to joint signal estimation from disparate modalities and may yield practically useful results in a variety of application domains.
Published in:
Nature Computational Science
View article

More Publications

August 1, 2023

Journal of Psychopharmacology

Improving Translational Relevance in Preclinical Psychopharmacology (iTRIPP)

View
July 6, 2023

Gerontology and Geriatric Medicine

Caring for Dementia Caregivers: Understanding Caregiver Stress During the COVID-19 Pandemic

View
May 19, 2023

Nature Reviews Neurology

Global synergistic actions to improve brain health for human development

View
April 20, 2023

Nature Mental Health

Machine learning-based identification of a psychotherapy-predictive electroencephalographic signature in PTSD

View
February 21, 2023

Translational Psychiatry

Screening for PTSD and TBI in Veterans using Routine Clinical Laboratory Blood Tests

View
February 13, 2023

Frontiers in Aging Neuroscience

Machine learning within the Parkinson’s progression markers initiative: Review of the current state of affairs

View
View All

Cohen Veterans Bioscience is a non-profit 501(c)(3) biomedical research and technology organization dedicated to advancing brain health by fast-tracking precision diagnostics and tailored therapeutics.

Cohen Veterans Bioscience is a non-profit 501(c)(3) biomedical research and technology organization dedicated to advancing brain health by fast-tracking precision diagnostics and tailored therapeutics.

©2023 Cohen Veterans Bioscience |  Privacy Policy | Terms of Use

Newsletter
Donate