Skip to main content


Front. Neurosci., 06 December 2023
Sec. Brain Imaging Methods
This article is part of the Research Topic Modern Statistical Learning Strategies in Imaging Genetics - Volume II View all 5 articles

Editorial: Modern statistical learning strategies in imaging genetics, volume II

  • 1Department of Statistics, Florida State University, Tallahassee, FL, United States
  • 2Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA, United States
  • 3Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, AB, Canada

As an emerging interdisciplinary study, imaging genetics mainly focuses on using brain imaging techniques to identify and characterize the effects of genetic variations on brain function or structure in order to better understand their impact on behavior and different disease, such as Attention-deficit/hyperactivity disorder (ADHD) (Klein et al., 2017), Autism (Nisar and Haris, 2023), Parkinson's disease (Kim et al., 2017), Alzheimer's disease (Huang et al., 2017), and among others. Although many biomedical studies, such as the Alzheimer's disease neuroimaging initiative (ADNI) study (Mueller et al., 2005), Human Connectome Project (HCP) (Van Essen et al., 2013), and UK BioBank (UKBB) study (Sudlow et al., 2015), are being conducted to collect massive datasets with volumes of imaging [like structural magnetic resonance imaging (MRI), functional MRI, diffusion MRI, and positron emission tomography (PET)], genetic, neurocognitive, and clinical information from increasingly large cohorts, it is still challenging for existing statistical learning approaches to integrate these rich and diverse multi-modal datasets (Huang et al., 2022). These challenges are usually caused by (i) the high-dimensionality of genotype information and the unknown dependencies between them; (ii) the high-dimensionality and irregularity of imaging phenotypes (Liu et al., 2023); and (iii) imaging heterogeneities due to differences in study design, protocol, environment, population, or other hidden confounders (Huang and Zhu, 2022). For example, existing statistical learning methods using regional-wised summary statistics as imaging phenotypes may not account for the spatial configurations of imaging voxels and are sensitive to the choice of region of interest (ROI) atlas, which may cause a loss of prediction accuracy and even lead to inconsistent results. As a follow-up to our first volume on this topic (Huang et al., 2022), this Research Topic includes a group of papers specifically leveraging these massive biomedical datasets to develop new learning approaches in imaging genetics and uncover novel clinical findings.

Integrating transcriptomic data with imaging genetics allows researchers to explore the underlying genetic mechanisms that influence variations seen in medical imaging. It can help in identifying how gene expression patterns relate to differences observed in brain structure, function, or other physiological aspects visualized through imaging techniques. Liu Y. et al. developed an integrative Bayesian scalar-on-image regression model for predicting cognitive outcomes in Alzheimer's disease by integrating voxel-level cortical thickness measurements derived from T1-weighted MRI along with transcriptomics (gene expression) features. Compared to the genetic variants, i.e., single nucleotide polymorphisms (SNPs), the dependencies of high-dimensional and collinear genetic features are well preserved in the transcriptomic information and successfully characterized by a graph Laplacian structure. In addition, the spatial orientation of the voxels in the brain image was captured via a tensor representation for the imaging coefficients, which can uncover patterns and relationships that may be missed by voxel-wise or ROI-based analysis.

The brain activation phenotype in imaging genetics refers to the observable characteristics or patterns of brain activity that are studied in conjunction with genetic variations. It can help in understanding how genetic differences among individuals might influence or correlate with specific patterns of brain activation as observed through various imaging techniques. Jin et al. introduced a Bayesian hierarchical model for detecting influential genetic variants and consistent activation regions using the PET and SNP data from subjects in the ADNI study. They found that their approach can jointly estimate the brain activation regions after accounting for external sources of clinical factors and genetic variation. In particular, it detected important genetic and demographic factors associated with activation intensities inside activation regions. Through applying the proposed method to the AD study, they discovered some important loci correlated to AD-related brain activation regions, which deserved further biological investigations.

Finally, studying resting-state functional connectivity (rs-FC) has become a crucial area of research in the context of psychological diseases or disorders. Liu X. et al. collected resting-state functional MRI data from 31 psychological erectile dysfunction (pED) patients and 31 healthy controls (HCs) and derived the rs-FC to explore the abnormalities of brain function, as well as their relationships with sexual behavior and emotion in pED patients. Altered brain function was found in the medial superior frontal gyrus and caudate-putamen of pED patients, which were associated with sexual function and psychological condition. In addition, Li et al. conducted an image-based meta-analysis to evaluate the effect of different seed selection on rs-FC. They found that the overlap of meta-analytic maps across different seeds' ROIs within the default mode network is relatively low, which means the choice of seed may significantly affect the connectivity results.

Taken together, the studies in this Research Topic include several advanced statistical learning approaches in imaging genetics, and exemplify the potential impact of applying these methods to better understand the roles of brain imaging data and genetic information in mental health and disease.

Author contributions

CH: Writing—original draft. RL: Writing—original draft. BZ: Writing—review & editing. LK: Writing—review & editing.


The author(s) declare that no financial support was received for the research, authorship, and/or publication of this article.

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher's note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.


Huang, C., Liu, R., Zhao, B., and Kong, L. (2022). Editorial: Modern statistical learning strategies in imaging genetics. Front. Neurosci. 16, 957304. doi: 10.3389/fnins.2022.957304

PubMed Abstract | CrossRef Full Text | Google Scholar

Huang, C., Thompson, P., Wang, Y., Yu, Y., Zhang, J., Kong, D., et al. (2017). FGWAS: functional genome wide association analysis. Neuroimage 159, 107–121. doi: 10.1016/j.neuroimage.2017.07.030

PubMed Abstract | CrossRef Full Text | Google Scholar

Huang, C., and Zhu, H. (2022). Functional hybrid factor regression model for handling heterogeneity in imaging studies. Biometrika 109, 1133–1148. doi: 10.1093/biomet/asac007

PubMed Abstract | CrossRef Full Text | Google Scholar

Kim, M., Kim, J., Lee, S.-H., and Park, H. (2017). Imaging genetics approach to Parkinson's disease and its correlation with clinical score. Sci. Rep. 7, 46700. doi: 10.1038/srep46700

PubMed Abstract | CrossRef Full Text | Google Scholar

Klein, M., Onnink, M., van Donkelaar, M., Wolfers, T., Harich, B., Shi, Y., et al. (2017). Brain imaging genetics in ADHD and beyond-mapping pathways from gene to disorder at different levels of complexity. Neurosci. Biobehav. Rev. 80, 115–155. doi: 10.1016/j.neubiorev.2017.01.013

PubMed Abstract | CrossRef Full Text | Google Scholar

Liu, R., Li, M., and Dunson, D. B. (2023). PPA: principal parcellation analysis for brain connectomes and multiple traits. Neuroimage 276, 120214. doi: 10.1016/j.neuroimage.2023.120214

PubMed Abstract | CrossRef Full Text | Google Scholar

Mueller, S. G., Weiner, M. W., Thal, L. J., Petersen, R. C., Jack, C., Jagust, W., et al. (2005). The Alzheimer's disease neuroimaging initiative. Neuroimaging Clin. N. Am. 15, 869–877. doi: 10.1016/j.nic.2005.09.008

CrossRef Full Text | Google Scholar

Nisar, S., and Haris, M. (2023). Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder. Mol. Psychiatry 1–14. doi: 10.1038/s41380-023-02060-9

PubMed Abstract | CrossRef Full Text | Google Scholar

Sudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., et al. (2015). UK BioBank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med. 12, e1001779. doi: 10.1371/journal.pmed.1001779

PubMed Abstract | CrossRef Full Text | Google Scholar

Van Essen, D. C., Smith, S. M., Barch, D. M., Behrens, T. E., Yacoub, E., Ugurbil, K., et al. (2013). The Wu-Minn human connectome project: an overview. Neuroimage 80, 62–79. doi: 10.1016/j.neuroimage.2013.05.041

PubMed Abstract | CrossRef Full Text | Google Scholar

Keywords: statistical learning, imaging genetic, functional connectivity, transcriptomic, association analysis

Citation: Huang C, Liu R, Zhao B and Kong L (2023) Editorial: Modern statistical learning strategies in imaging genetics, volume II. Front. Neurosci. 17:1337411. doi: 10.3389/fnins.2023.1337411

Received: 13 November 2023; Accepted: 20 November 2023;
Published: 06 December 2023.

Edited and reviewed by: Vince D. Calhoun, Georgia State University, United States

Copyright © 2023 Huang, Liu, Zhao and Kong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Chao Huang,

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.