Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Latent space-based network analysis for brain–behavior linking in neuroimaging

Nature Methods volume 23, pages 225–235 (2026)Cite this article

Subjects

Abstract

We propose a latent space-based statistical network analysis (LatentSNA) method that implements network science in a generative Bayesian framework, preserves neurologically meaningful brain topology and improves statistical power for imaging biomarker detection. LatentSNA (1) addresses the lack of power and inflated type II errors in current analytic approaches when detecting imaging biomarkers, (2) allows unbiased estimation of the influence of biomarkers on behavioral variants, (3) quantifies uncertainty and evaluates the likelihood of estimated biomarker effects against chance and (4) improves brain–behavior prediction in new samples as well as the clinical utility of neuroimaging findings. LatentSNA is broadly applicable across multiple imaging modalities and outcome measures in developing, aging and transdiagnostic cohorts, totaling 8,003 to 11,861 participants. LatentSNA achieves substantial accuracy gains (averaging 110–150%) and replicability improvements (averaging 153%) over existing approaches in moderate to large datasets. As a result, LatentSNA elucidates how network topology is implicated in brain–behavior relationships.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Schematic diagram of LatentSNA.
Fig. 2: LatentSNA improves statistical power for biomarker detection.
Fig. 3: LatentSNA shows substantially improved predictive performance over existing approaches.
Fig. 4: Reproducibility analysis of CPM and LatentSNA methods across different behaviors, fMRI conditions and datasets.
Fig. 5: Large-scale disruptions of multiple functional systems are consistently found with internalizing psychopathology across cognitive conditions.
Fig. 6: LatentSNA identifies biologically meaningful imaging biomarkers with strong anatomical associations.

Similar content being viewed by others

Data availability

The individual-level imaging and behavior data used in the present study are available from four publicly accessible data resources: ABCD (https://abcdstudy.org/), HCP (https://www.humanconnectome.org/), A4 (https://www.a4studydata.org) and ADNI (https://adni.loni.usc.edu). Transdiagnostic data are available via the NDA website (https://nda.nih.gov/).

Code availability

The estimation algorithm for this paper was implemented in R. The code is available at https://github.com/selenashuowang/latentSNA with a tutorial. The code is released under the MIT License. In this GitHub repository, we have provided instructions for installation (specifying prerequisite packages), explanations of outputs and a sample toy example with evaluations.

References

  1. Barabási, A. Network science. Philos. Trans. A Math. Phys. Eng Sci 371, 20120375 (2013).

    PubMed  Google Scholar 

  2. Sweet, T. & Wang, S. Network science in psychology. Psychol. Methods https://doi.org/10.1037/met0000745 (2025).

    Article  PubMed  Google Scholar 

  3. Wang, S. et al. Establishing group-level brain structural connectivity incorporating anatomical knowledge under latent space modeling. Med. Image Anal. 99, 103309 (2025).

    PubMed  Google Scholar 

  4. Satterthwaite, T. D. et al. Common and dissociable dysfunction of the reward system in bipolar and unipolar depression. Neuropsychopharmacology 40, 2258–2268 (2015).

    PubMed  PubMed Central  Google Scholar 

  5. Shen, X. et al. Using connectome-based predictive modeling to predict individual behavior from brain connectivity. Nat. Protoc. 12, 506–518 (2017).

    PubMed  PubMed Central  Google Scholar 

  6. Gao, S., Greene, A. S., Constable, R. T. & Scheinost, D. Combining multiple connectomes improves predictive modeling of phenotypic measures. Neuroimage 201, 116038 (2019).

    PubMed  Google Scholar 

  7. Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J. & Scholkopf, B. Support vector machines. IEEE Intell. Syst. 13, 18–28 (1998).

    Google Scholar 

  8. Belgiu, M. & Drăguţ, L. Random forest in remote sensing: a review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 114, 24–31 (2016).

    Google Scholar 

  9. Albawi, S., Mohammed, T. A. & Al-Zawi, S. Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET) 1–6 (IEEE, 2017).

  10. Bullmore, E. & Sporns, O. Complex brain networks: graph theoretical analysis of structural and functional systems. Nat. Rev. Neurosci. 10, 186–198 (2009).

    PubMed  Google Scholar 

  11. Dobra, A., Hans, C., Jones, B., Nevins, J. R., Yao, G. & West, M. Sparse graphical models for exploring gene expression data. J. Multivar. Anal. 90, 196–212 (2004).

    Google Scholar 

  12. Friedman, N., Linial, M., Nachman, I. & Pe’er, D. Using Bayesian networks to analyze expression data. In Proc. 4th Annual International Conference on Computational Molecular Biology 127–135 (ACM, 2000).

  13. Ni, Y., Baladandayuthapani, V., Vannucci, M. & Stingo, F. C. Bayesian graphical models for modern biological applications. Stat. Methods Appt. 31, 197–225 (2022).

    PubMed  Google Scholar 

  14. Ni, Y., Stingo, F. C. & Baladandayuthapani, V. Bayesian graphical regression. J. Am. Stat. Assoc. 114, 184–197 (2019).

    PubMed  Google Scholar 

  15. Wang, S. Recent integrations of latent variable network modeling with psychometric models. Front. Psychol. 12, 773289 (2021).

    PubMed  PubMed Central  Google Scholar 

  16. Wang, S. & Edgerton, J. Resilience to stress in bipartite networks: application to the Islamic State recruitment network. J. Complex Netw. 10, cnac017 (2022).

    Google Scholar 

  17. Di Fatta, D., Caputo, F., Evangelista, F. & Dominici, G. Small world theory and the World Wide Web: linking small world properties and website centrality. Int. J. Mark. Bus. Syst. 2, 126–140 (2016).

    Google Scholar 

  18. Bassett, D. S. & Bullmore, E. D. Small-world brain networks. Neuroscientist 12, 512–523 (2006).

    PubMed  Google Scholar 

  19. Petersen, R. C. et al. Alzheimer’s Disease Neuroimaging Initiative (ADNI) clinical characterization. Neurology 74, 201–209 (2010).

    PubMed  PubMed Central  Google Scholar 

  20. Sperling, R. A. et al. The A4 study: stopping AD before symptoms begin?. Sci. Transl. Med. 6, 228fs13 (2014).

    PubMed  PubMed Central  Google Scholar 

  21. Bookheimer, S. Y. et al. The Lifespan Human Connectome Project in Aging: an overview. Neuroimage 185, 335–348 (2019).

    PubMed  Google Scholar 

  22. Casey, B. J. et al. The Adolescent Brain Cognitive Development (ABCD) study: imaging acquisition across 21 sites. Dev. Cogn. Neurosci. 32, 43–54 (2018).

    PubMed  PubMed Central  Google Scholar 

  23. Greene, A. S. et al. Brain–phenotype models fail for individuals who defy sample stereotypes. Nature 609, 109–118 (2022).

    PubMed  PubMed Central  Google Scholar 

  24. Relión, J. D. A., Kessler, D., Levina, E. & Taylor, S. F. Network classification with applications to brain connectomics. Ann. Appl. Stat. 13, 1648–1677 (2019).

    Google Scholar 

  25. Zhang, Z., Allen, G. I., Zhu, H. & Dunson, D. Tensor network factorizations: relationships between brain structural connectomes and traits. Neuroimage 197, 330–343 (2019).

    PubMed  Google Scholar 

  26. Krueger, R. F. & Markon, K. E. Understanding psychopathology: melding behavior genetics, personality, and quantitative psychology to develop an empirically based model. Curr. Dir. Psychol. Sci. 15, 113–117 (2006).

    PubMed  PubMed Central  Google Scholar 

  27. Sawai, H. Exploring a new small-world network for real-world applications. In Networked Digital Technologies: 4th International Conference, NDT 2012, Dubai, UAE, April 24–26, 2012. Proceedings, Part I 4 (ed. Benlamri, R.) 90–101 (Springer, 2012).

  28. Zhao, Y., Li, T. & Zhu, H. Bayesian sparse heritability analysis with high-dimensional neuroimaging phenotypes. Biostatistics 23, 467–484 (2022).

    PubMed  Google Scholar 

  29. Zhang, X., Hulvershorn, L. A., Constable, T., Zhao, Y. & Wang, S. Cost efficiency of fMRI studies using resting-state vs. task-based functional connectivity. Hum. Brain Mapp. 46, e70260 (2025).

    PubMed  PubMed Central  Google Scholar 

  30. Chen, S. et al. Identifying covariate-related subnetworks for whole-brain connectome analysis. Biostatistics 25, 541–558 (2024).

  31. Kolb, B. & Whishaw, I. Q. Brain plasticity and behavior. Annu. Rev. Psychol. 49, 43–64 (1998).

    PubMed  Google Scholar 

  32. Chahal, R., Gotlib, I. H. & Guyer, A. E. Research review: brain network connectivity and the heterogeneity of depression in adolescence—a precision mental health perspective. J. Child Psychol. Psychiatry 61, 1282–1298 (2020).

    PubMed  PubMed Central  Google Scholar 

  33. Breiman, L. Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat. Sci. 16, 199–231 (2001).

    Google Scholar 

  34. Wang, S., Wu, H. & Pek, J. Performance of alternative regression weights in the context of prediction versus inference. Multivar. Behav. Res. 57, 163 (2022).

    Google Scholar 

  35. Tibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. B Stat. Methodol. 58, 267–288 (1996).

    Google Scholar 

  36. Wasserman, S. et al. Social Network Analysis: Methods and Applications (Cambridge Univ. Press, 1994).

  37. Heider, F. Social perception and phenomenal causality. Psychol. Rev. 51, 358–374 (1944).

    Google Scholar 

  38. Hoff, P. D. Bilinear mixed-effects models for dyadic data. J. Am. Stat. Assoc. 100, 286–295 (2005).

    Google Scholar 

  39. Hoff, P. D. Modeling homophily and stochastic equivalence in symmetric relational data. Adv. Neural Inf. Process. Syst. 20, 657–664 (2008).

    Google Scholar 

  40. Sosa, J. & Buitrago, L. A review of latent space models for social networks. Rev. Colomb. Estad. 44, 171–200 (2021).

    Google Scholar 

  41. Calhoun, V. D. & Sui, J. Multimodal fusion of brain imaging data: a key to finding the missing link(s) in complex mental illness. Biol. Psychiatry Cogn. Neurosci. Neuroimaging 1, 230–244 (2016).

    PubMed  PubMed Central  Google Scholar 

  42. Wu, J., Li, J., Eickhoff, S. B., Scheinost, D. & Genon, S. The challenges and prospects of brain-based prediction of behaviour. Nat. Hum. Behav. 7, 1255–1264 (2023).

    PubMed  Google Scholar 

  43. Stavropoulos, I. et al. Increased hair cortisol and antecedent somatic complaints in children with a first epileptic seizure. Epilepsy Behav. 68, 146–152 (2017).

    PubMed  Google Scholar 

  44. Shen, X., Papademetris, X. & Constable, R. T. Graph-theory based parcellation of functional subunits in the brain from resting-state fMRI data. Neuroimage 50, 1027–1035 (2010).

    PubMed  Google Scholar 

  45. Gelman, A., Carlin, J. B., Stern, H. S. & Rubin, D. B. Bayesian Data Analysis (Chapman and Hall/CRC, 1995).

  46. Price, J. L. & Drevets, W. C. Neural circuits underlying the pathophysiology of mood disorders. Trends Cogn. Sci. 16, 61–71 (2012).

    PubMed  Google Scholar 

  47. Chen, J. et al. Shared and unique brain network features predict cognitive, personality, and mental health scores in the ABCD study. Nat. Commun. 13, 2217 (2022).

    PubMed  PubMed Central  Google Scholar 

  48. Cole, M. W., Bassett, D. S., Power, J. D., Braver, T. S. & Petersen, S. E. Intrinsic and task-evoked network architectures of the human brain. Neuron 83, 238–251 (2014).

    PubMed  PubMed Central  Google Scholar 

  49. Guell, X., Gabrieli, J. D. E. & Schmahmann, J. D. Triple representation of language, working memory, social and emotion processing in the cerebellum: convergent evidence from task and seed-based resting-state fMRI analyses in a single large cohort. Neuroimage 172, 437–449 (2018).

    PubMed  Google Scholar 

  50. Liu, Z. et al. Decreased regional homogeneity in insula and cerebellum: a resting-state fMRI study in patients with major depression and subjects at high risk for major depression. Psychiatry Res. Neuroimaging 182, 211–215 (2010).

    Google Scholar 

  51. Zhuo, C. et al. Altered resting-state functional connectivity of the cerebellum in schizophrenia. Brain Imaging Behav. 12, 383–389 (2018).

    PubMed  Google Scholar 

  52. D’Agostino, R. B. Transformation to normality of the null distribution of g1. Biometrika 57, 679–681 (1970).

  53. Anscombe, F. J. & Glynn, W. J. Distribution of the kurtosis statistic b2 for normal samples. Biometrika 70, 227–234 (1983).

    Google Scholar 

  54. Nigam, S. et al. Rich-club organization in effective connectivity among cortical neurons. J. Neurosci. 36, 670–684 (2016).

    PubMed  PubMed Central  Google Scholar 

  55. Guimerà, R., Díaz-Guilera, A., Vega-Redondo, F., Cabrales, A. & Arenas, A. Optimal network topologies for local search with congestion. Phys. Rev. Lett. 89, 248701 (2002).

    PubMed  Google Scholar 

  56. Madore, K. P. & Wagner, A. D. Multicosts of multitasking. Cerebrum 2019, cer-04-19 (2019).

  57. Gollini, I. & Murphy, T. B. Joint modeling of multiple network views. J. Comput. Graph. Stat. 25, 246–265 (2016).

    Google Scholar 

  58. Salter-Townshend, M. & McCormick, T. H. Latent space models for multiview network data. Ann. Appl. Stat. 11, 1217–1244 (2017).

    PubMed  PubMed Central  Google Scholar 

  59. Wang, L., Durante, D., Jung, R. E. & Dunson, D. B. Bayesian network–response regression. Bioinformatics 33, 1859–1866 (2017).

    PubMed  Google Scholar 

  60. Morris, E. L., He, K. & Kang, J. Scalar on network regression via boosting. Ann. Appl. Stat. 16, 2755–2773 (2022).

    PubMed  PubMed Central  Google Scholar 

  61. Fischer, G. H. & Molenaar, I. W. (eds) Rasch Models: Foundations, Recent Developments, and Applications (Springer, 2012).

  62. Joshi, A. et al. Unified framework for development, deployment and robust testing of neuroimaging algorithms. Neuroinformatics 9, 69–84 (2011).

    PubMed  PubMed Central  Google Scholar 

  63. Greene, A. S., Gao, S., Scheinost, D. & Constable, R. T. Task-induced brain state manipulation improves prediction of individual traits. Nat. Commun. 9, 2807 (2018).

    PubMed  PubMed Central  Google Scholar 

  64. Horien, C., Shen, X., Scheinost, D. & Constable, R. T. The individual functional connectome is unique and stable over months to years. Neuroimage 189, 676–687 (2019).

    PubMed  Google Scholar 

  65. Shen, X., Tokoglu, F., Papademetris, X. & Constable, R. T. Groupwise whole-brain parcellation from resting-state fMRI data for network node identification. Neuroimage 82, 403–415 (2013).

    PubMed  Google Scholar 

  66. Manjón, J. V. et al. Diffusion weighted image denoising using overcomplete local PCA. PLoS ONE 8, e73021 (2013).

  67. Moore, C. & Sciacca, F. Fiber assignment by continuous tracking algorithm (FACT). Radiopaedia https://doi.org/10.53347/rid-72014 (2019).

  68. Jenkinson, M., Beckmann, C. F., Behrens, T. E. J., Woolrich, M. W. & Smith, S. M. FSL. Neuroimage 62, 782–790 (2012).

    PubMed  Google Scholar 

  69. Cammoun, L. et al. Mapping the human connectome at multiple scales with diffusion spectrum MRI. J. Neurosci. Methods 203, 386–397 (2012).

    PubMed  Google Scholar 

  70. Yan, J. et al. Brain-wide structural connectivity alterations under the control of Alzheimer risk genes. Int. J. Comput. Biol. Drug Des. 13, 58–70 (2020).

    PubMed  PubMed Central  Google Scholar 

  71. Tourbier, S. et al. Connectome Mapper 3: a flexible and open-source pipeline software for multiscale multimodal human connectome mapping. J. Open Source Softw. 7, 4248 (2022).

    Google Scholar 

  72. Gorgolewski, K. et al. Nipype: a flexible, lightweight and extensible neuroimaging data processing framework in Python. Front. Neuroinform. 5, 13 (2011).

    PubMed  PubMed Central  Google Scholar 

  73. Cox, R. W. AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. Comput. Biomed. Res. 29, 162–173 (1996).

    PubMed  Google Scholar 

  74. Jenkinson, M. & Smith, S. A global optimisation method for robust affine registration of brain images. Med. Image Anal. 5, 143–156 (2001).

    PubMed  Google Scholar 

  75. Kueper, J. K., Speechley, M. & Montero-Odasso, M. The Alzheimer’s Disease Assessment Scale–Cognitive Subscale (ADAS-Cog): modifications and responsiveness in pre-dementia populations. a narrative review. J. Alzheimers Dis. 63, 423–444 (2018).

    PubMed  PubMed Central  Google Scholar 

  76. Farias, S. T. et al. The measurement of everyday cognition (ECog): scale development and psychometric properties. Neuropsychology 22, 531–544 (2008).

    PubMed  PubMed Central  Google Scholar 

  77. Lutkenhoff, E. S. et al. Optimized brain extraction for pathological brains (optiBET). PloS ONE 9, e115551 (2014).

    PubMed  PubMed Central  Google Scholar 

  78. Greve, D. N. et al. Cortical surface-based analysis reduces bias and variance in kinetic modeling of brain PET data. Neuroimage 92, 225–236 (2014).

    PubMed  Google Scholar 

  79. Desikan, R. S. et al. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 31, 968–980 (2006).

    PubMed  Google Scholar 

  80. Donohue, M. C. et al. The Preclinical Alzheimer Cognitive Composite: measuring amyloid-related decline. JAMA Neurol. 71, 961–970 (2014).

    PubMed  PubMed Central  Google Scholar 

  81. Papp, K. V. et al. The Computerized Cognitive Composite (c3) in A4, an Alzheimer’s disease secondary prevention trial. J. Prev. Alzheimers Dis. 8, 59–67 (2021).

    PubMed  Google Scholar 

  82. Weintraub, S. et al. Cognition assessment using the NIH Toolbox. Neurology 80, S54–S64 (2013).

    PubMed  PubMed Central  Google Scholar 

  83. NIH Toolbox Scoring and Interpretation Guide (NIH, 2022); https://www.epicrehab.com/epic/documents/crc/crc-201307-nih-toolbox-scoring-and-interpretation-manual%209-27-12.pdf

  84. Derogatis, L. R. & Melisaratos, N. The brief symptom inventory: an introductory report. Psychol. Med. 13, 595–605 (1983).

    PubMed  Google Scholar 

  85. Zhang, J., Sun, W. W. & Li, L. Generalized connectivity matrix response regression with applications in brain connectivity studies. J. Comput. Graph. Stat. 32, 252–262 (2023).

    PubMed  Google Scholar 

  86. Wang, S., Paul, S. & De Boeck, P. Joint latent space model for social networks with multivariate attributes. Psychometrika 88, 1197–1227 (2023).

    PubMed  Google Scholar 

  87. Leonard, T. & Hsu, J. S. J. Bayesian inference for a covariance matrix. Ann. Stat. 20, 1669–1696 (1992).

    Google Scholar 

  88. Zhang, Z. A note on Wishart and inverse Wishart priors for covariance matrix. J. Behav. Data Sci. 1, 119–126 (2021).

    Google Scholar 

  89. Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33, 1–22 (2010).

    PubMed  PubMed Central  Google Scholar 

  90. González, I., Déjean, S., Martin, P. G. P. & Baccini, A. CCA: an R package to extend canonical correlation analysis. J. Stat. Softw. 23, 1–14 (2008).

    Google Scholar 

  91. Aine, C. et al. Multimodal neuroimaging in schizophrenia: description and dissemination. Neuroinformatics 15, 343–364 (2017).

    PubMed  PubMed Central  Google Scholar 

  92. Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A. & Leisch, F. e1071: misc functions of the Department of Statistics, Probability Theory Group (formerly: E1071), TU Wien. https://CRAN.R-project.org/package=e1071 (2023).

  93. Wright, M. N. & Ziegler, A. ranger: a fast implementation of random forests for high dimensional data in C++ and R. J. Stat. Softw. 77, 1–17 (2017).

    Google Scholar 

  94. Falbel, D. & Luraschi, J. torch: tensors and neural networks with ‘GPU’ acceleration. https://CRAN.R-project.org/package=torch (2023).

  95. Achard, S., Salvador, R., Whitcher, B., Suckling, J. & Bullmore, E. A resilient, low-frequency, small-world human brain functional network with highly connected association cortical hubs. J. Neurosci. 26, 63–72 (2006).

    PubMed  PubMed Central  Google Scholar 

  96. Paquette, M., Girard, G., Chamberland, M. & Descoteaux, M. ‘Noise’ in diffusion tractography connectomes is not additive. In ISMRM 24th Annual Meeting (ISMR, 2016).

  97. Newman, M. E. J. Scientific collaboration networks. II. Shortest paths, weighted networks, and centrality. Phys. Rev. E Stat. Nonlin. Soft Matter Phys. 64, 016132 (2001).

    PubMed  Google Scholar 

  98. Freeman, L. C. Centrality in social networks: conceptual clarification. Soc. Netw. 1, 238–263 (1979).

    Google Scholar 

  99. Freeman, L. C. A set of measures of centrality based on betweenness. Sociometry 40, 35–41 (1977).

    Google Scholar 

  100. Brandes, U. A faster algorithm for betweenness centrality. J. Math. Sociol. 25, 163–177 (2001).

    Google Scholar 

  101. Burt, R. S. in The New Economic Sociology: A Reader (ed. Dobbin, F.) 325–348 (Princeton Univ. Press, 2004).

Download references

Acknowledgements

S.W. was partially supported by the Alzheimer’s Disease Data Initiative from the 2025 William H. Gates Sr Fellowship and NIH grant P30 AG072976. Y.Z. was partially supported by NIH grants R01AG068191, RF1AG081413, R01EB034720, P30AG072976 and P30AG021342. We thank the individuals represented in the ADNI (https://adni.loni.usc.edu), A4 (https://www.a4studydata.org), ABCD (https://nda.nih.gov/abcd), HCP (https://db.humanconnectome.org) and transdiagnostic studies for their participation and the research teams for their work in collecting, processing and disseminating these datasets for analysis. Some data collection and sharing for this project was funded by the ADNI (NIH grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). The A4 study is a secondary prevention trial in preclinical Alzheimer’s disease, aiming to slow cognitive decline associated with brain Aβ accumulation in clinically typical older individuals. Some data used in the preparation of this article were obtained from the ABCD study, held in the National Institute of Mental Health Data Archive (https://nda.nih.gov). HCP data were provided by the HCP WU-Minn Consortium (principal investigators D. Van Essen and K. Ugurbil; 1U54MH091657) funded by the 16 NIH institutes and centers that support the NIH Blueprint for Neuroscience Research and the McDonnell Center for Systems Neuroscience at Washington University. The transdiagnostic study was supported by the National Institute of Mental Health (R01MH123245 and R01MH120080).

Author information

Authors and Affiliations

  1. Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, IN, USA

    Selena Wang

  2. Department of Biostatistics, Yale University, New Haven, CT, USA

    Xinzhi Zhang, Wanwan Xu, Xinyuan Tian & Yize Zhao

  3. Department of Statistics, Texas A&M University, College Station, TX, USA

    Yunhe Liu

Authors
  1. Selena Wang
    View author publications

    Search author on:PubMed Google Scholar

  2. Xinzhi Zhang
    View author publications

    Search author on:PubMed Google Scholar

  3. Yunhe Liu
    View author publications

    Search author on:PubMed Google Scholar

  4. Wanwan Xu
    View author publications

    Search author on:PubMed Google Scholar

  5. Xinyuan Tian
    View author publications

    Search author on:PubMed Google Scholar

  6. Yize Zhao
    View author publications

    Search author on:PubMed Google Scholar

Contributions

S.W. and Y.Z. designed the study; S.W. and Y.L. performed the simulation; S.W., W.X., X.T. and X.Z. analyzed data; S.W. wrote the paper; and all authors have given comments and edits. All authors contributed to the interpretation of results, discussion and paper revision.

Corresponding authors

Correspondence to Selena Wang or Yize Zhao.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Methods thanks Chao Huang, Pew-Thian Yap and Aiying Zhang for their contribution to the peer review of this work. Peer reviewer reports are available. Primary Handling Editor: Nina Vogt, in collaboration with the Nature Methods team.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Functional architectures of internalizing psychopathology are driven by the core actors of the connectivity network.

(A) The strength of each brain region in MOT based on the latent network (left) and the observed network (right) for an average participant during MID condition. Regions identified to play a significant role in explaining individual differences in internalizing behaviors are colored as green, and non-significant regions are colored as red. (B) The location and connectivity networks of an imaging biomarker (top) versus a null effect (bottom) with no identifiable contribution to internalizing. The 3D brain plots show the front (top left), back (top right), right (bottom left) and left (bottom right) views. (C) The circle plots of the connectivity edges associated with the imaging biomarker (top) and the null effect (bottom). In B and C, red line indicates positive connectivity edges, and blue line indicates negative connectivity edges.

Extended Data Fig. 2 Internalizing psychopathology in children are attributable to star-like functional networks.

Latent internalizing networks (left) against CPM networks (right) for an average participant in each functional system during MID task. Node positions of the latent networks are then determined using the fruchterman-reingold force-directed graph layout algorithm. The nodes are fixed in the same positions when plotting the internalizing connectivity edges identified via CPM. We also show the corresponding (whole) latent networks, with both significant and non-significant connectivity edges, estimated via LatentSNA, as well as the average observed networks. MF: Medial-Frontal, FP: Fronto-parietal, DMN: Default Mode, MOT: Motor, VI: Visual I, VII: Visual II, VAs: Visual Association, LIM: Limbic, BG: Basal Ganglia, CBL: Cerebellum. Blue represents the positive connectivity edges, and red represents negative edges.

Supplementary information

Supplementary Information

Supplementary Figs. 1–8 and Tables 1–3.

Reporting Summary

Peer Review File

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, S., Zhang, X., Liu, Y. et al. Latent space-based network analysis for brain–behavior linking in neuroimaging. Nat Methods 23, 225–235 (2026). https://doi.org/10.1038/s41592-025-02896-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41592-025-02896-9

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing