Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI.

Overview

1. Department of Mathematics and Women’s Cancer, University College London, London WC1E 6BT, UK
2. Institute of Biogerontology, Lobachevsky State University, Nizhny Novgorod 603022, Russia
3. Institute for Cognitive Neuroscience, University Higher School of Economics, Moscow 101000, Russia; (D.V.)
4. Academician A.P. Nesterov Department of Ophthalmology of the Institute of Clinical Medicine, Pirogov Russian National Research Medical University, Moscow 117437, Russia
5. Centre for Cancer Screening, Prevention and Early Diagnosis, Wolfson Institute of Population Health, Queen Mary University of London, London EC1M 6BQ, UK
6. Department of Paediatrics and Paediatric Infectious Diseases, Institute of Child’s Health, I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow 119991, Russia

Abstract

Background/Objectives: Synolitic graphs (SGs) were developed for task-based fMRI, where edge weights encode the discriminative power of pairwise regional features; whether similar information can be recovered from resting-state data was untested. We benchmarked SGs for autism spectrum disorder (ASD) classification using the multisite ABIDE-I dataset (871 subjects: 403 subjects with ASD, 468 typical controls; 17 sites; CC200 atlas). Methods: Using 5-fold cross-validation with 10 repeats and balanced accuracy as the primary metric, we compared SGs with eight baselines including correlation matrices, tangent space connectivity, elastic net logistic regression, SVM, and XGBoost. Results: The vectorised correlation matrix achieved 67.9% balanced accuracy (AUC = 0.743), the combined model 68.0% (AUC = 0.744), and SGs 57.0% (AUC = 0.598). SGs performed above chance (permutation p = 0.001), but their performance was not significantly different from that of direct logistic regression (Nadeau–Bengio p = 0.82). After covariate residualisation, correlation-based methods retained 66.9–67.1% balanced accuracy, while SGs achieved 55.6%. Leave-one-site-out validation yielded 66.0–66.2% for correlation-based models and 55.0% for SGs, with similar declines of approximately 2 percentage points from standard cross-validation. SG-derived ROI rankings were unstable, and ADOS severity prediction among 193 ASD participants was underpowered and inconclusive. Conclusions: Conventional connectivity representations substantially outperformed SGs for resting-state ASD classification, contrasting with previously reported task-fMRI advantages. No evaluated method achieved performance suitable for stand-alone clinical screening or diagnosis; this study should therefore be interpreted as a methodological benchmark rather than a validation of a clinically deployable tool.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

ABIDE-I raw imaging and phenotypic data are publicly available from the International Neuroimaging Data-sharing Initiative (INDI) 1000 Functional Connectomes Project at http://fcon_1000.projects.nitrc.org/indi/abide/abide_I.html (accessed on 11 July 2026). C-PAC-preprocessed derivatives (filt_noglobal strategy, CC200 parcellation) are available from the Preprocessed Connectomes Project at http://preprocessed-connectomes-project.org/abide/cpac.html (accessed on 11 July 2026), also mirrored on NITRC and as a public Amazon Web Services S3 bucket, as described by Craddock et al. [10]. All ABIDE-I data are fully anonymised and contain no protected health information, in accordance with HIPAA guidelines and 1000 Functional Connectomes Project/INDI data-sharing protocols; consequently, no separate data use agreement is required, although users must register with NITRC and the 1000 Functional Connectomes Project to obtain access. The original data collection, including clinical/diagnostic assessment, was approved and conducted by the institutional review boards and clinical teams at each of the 17 contributing acquisition sites, as described by the ABIDE consortium [3]. Raw ABIDE-I data are distributed under a Creative Commons Attribution-NonCommercial-ShareAlike licence and the C-PAC-preprocessed derivatives under a permissive BSD-style licence; our use of both datasets for non-commercial academic research complies with these terms. Analysis code is available from the authors upon reasonable request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 7 authors, 7 keywords, 1 funder, 21 references.

Cite

This paper

Zaikin, A., Vlasenko, D., Zakharov, D., Oganezova, J. G., Krivonosov, M. I., Ivanchenko, M., & Blyuss, O. (2026). Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI. Diagnostics (Basel, Switzerland), 16(17), 2746. https://doi.org/10.3390/diagnostics16172746

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41593-026-02287-z [code]

Autism subtypes identified using cross-species functional connectivity analyses.

Journal: Nature neuroscience

In common: autism, fMRI, 4 references

[2] doi:10.1038/s44220-026-00656-y [code]

Multiscale heterogeneity of atypical functional connectivity in autism.

Journal: Nature. Mental health

In common: autism, fMRI, 4 references

[3] doi:10.1016/j.patter.2026.101560 [code]

Automating region selection with genetic algorithms for energy landscape analyses of brain dynamics.

Journal: Patterns (New York, N.Y.)

In common: autism, fMRI, methods / tools, 3 references

[4] doi:10.1016/j.bpsgos.2026.100787 [code]

Dynamic Functional Synchronization Profiles in Autism Differ by Spatial Scale and Along Hierarchical Cortical Gradients.

Journal: Biological psychiatry global open science

In common: autism, fMRI, 3 references

[5] doi:10.1002/hbm.70559 [code]

Replicability of Functional Brain Networks: A Study Through the Lens of Seven Resting-State Networks.

Journal: Human brain mapping

In common: fMRI, 3 references

[6] doi:10.3389/fncom.2026.1851416

AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis.

Journal: Frontiers in computational neuroscience

In common: autism, 2 references

[7] doi:10.21203/rs.3.rs-9326213/v1 [code]

Multi-task fMRI outperforms resting-state fMRI for revealing task-invariant organization of the human brain

Journal: Research Square (preprint)

In common: fMRI, 3 references

[8] doi:10.3390/diagnostics16101478

Autistic vs. Control Differences in MRI Scan Quality Across ABIDE-II Sites.

Journal: Diagnostics (Basel, Switzerland)

In common: autism, methods / tools, 2 references

[9] doi:10.1002/aur.70243

Autism and Cortical Thickness Deviation From Neurotypical Controls: Evidence for a Spatial Association With Serotonin Receptors.

Journal: Autism research : official journal of the International Society for Autism Research

In common: autism, 2 references

[10] doi:10.1038/s44220-026-00623-7 [code]

Optimizing functional connectivity scanning conditions for predicting autistic traits.

Journal: Nature. Mental health

In common: autism, 2 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.