OSCR

A neural signature of sleep deprivation in the human brain.

Code ↔ Paper

1 match between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 1 match
  1. [1] § Methods › Classification analysis › Neural signature construction using the discovery dataset ↔ step01_classification_discovery_data.ipynb, lines 40–74 · score 0.60 · cross validation, split, folds, AUC, SVM, kernel

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Jupyter notebook · 91 lines · 2.8 KB · no license · 1 match

  1. # %%
  2. import numpy as np
  3. import pandas as pd
  4. import os
  5. import base_functions as bf
  6. import pickle
  7. from sklearn import svm
  8. from sklearn.model_selection import RepeatedStratifiedKFold, GridSearchCV
  9. from sklearn import metrics
  11. from nilearn import connectome, plotting
  12. import matplotlib.pyplot as plt
  13. %matplotlib inline
  15. # %%
  18. # %%
  19. dtfile = './data/dataset1_connectivity.pkl'
  20. D = pickle.load(open(dtfile, 'rb'))
  21. all_session_subjects = D['all_session_subjects']
  22. all_session_conn_vec = D['all_session_conn_vec']
  23. all_session = D['all_session']
  24. info_DF = D['info_DF']
  26. # %%
  27. care_sess = 0 # focus on the first session, i.e., morning after sleep manipulation
  28. dep_labels = bf.get_subject_info(info_DF, all_session_subjects[care_sess], ['deprive_labels'])
  29. # dep_labels: 0->normal sleep; 1->partial sleep deprivation; 2->sleep deprivation
  30. idx = np.logical_or(dep_labels==0, dep_labels==2)
  31. X = all_session_conn_vec[care_sess][idx]
  32. X = np.arctanh(X) #Fisher r to z
  33. X[np.isnan(X)] = 0
  34. Y = dep_labels[idx]
  35. Y[Y==Y.min()] = 0
  36. Y[Y!=Y.min()] = 1
  37. subjects = all_session_subjects[care_sess]
  38. subjects = [subjects[i] for i,v in enumerate(idx) if v==True]
  40. # %%
  41. rep_num = 10 # repreat cross validation for multiple times
  43. all_scores = np.zeros(rep_num)
  44. all_predict_prob = np.zeros((X.shape[0],rep_num))
  45. all_test_index = []
  46. for irep in range(rep_num):
  47. print(irep)
  48. cvg = RepeatedStratifiedKFold(n_splits=10, n_repeats=1, random_state=irep)
  50. cv_prob_pred = np.zeros_like(Y)
  51. test_index = []
  52. # cross validation
  53. for tridx, tsidx in cvg.split(X, Y):
  54. trX, trY = X[tridx], Y[tridx]
  55. tsX, tsY = X[tsidx], Y[tsidx]
  56. parameters = {'C':np.linspace(0.00001,10000,20)}
  57. clf = GridSearchCV(svm.SVC(kernel='linear', probability=True), parameters, n_jobs=-1)
  59. clf.fit(trX, trY)
  60. prob_pred = clf.decision_function(tsX)
  61. cv_prob_pred[tsidx] = prob_pred
  62. test_index.append(tsidx)
  63. sc = metrics.roc_auc_score(Y, cv_prob_pred)
  65. all_predict_prob[irep] = cv_prob_pred
  66. all_test_index.append(test_index)
  67. all_scores[irep] = sc
  69. pickle.dump({'all_predict_prob':all_predict_prob,
  70. 'all_scores':all_scores,
  71. 'all_test_index':all_test_index,
  72. 'subjects':subjects,
  73. 'Y':Y,},
  74. open(f'./results/accuracy_10-10CV_D1Morning.pkl', 'wb'))
  76. # %%
  77. ## Train model for generalization
  78. parameters = {'C':np.linspace(0.00001,10000,20)}
  79. clf = GridSearchCV(svm.SVC(kernel='linear', probability=True), parameters, n_jobs=-1)
  82. clf.fit(X, Y)
  83. coef_vals = clf.best_estimator_.coef_
  84. patterns = bf.weight_transform(X, coef_vals)
  87. pickle.dump({'clf':clf.best_estimator_,
  88. 'patterns':patterns,
  89. 'coef_vals':coef_vals,
  90. 'subjects':subjects},
  91. open('./Discovery_data_trained_model.pkl', 'wb'))

step01_classification_discovery_data.ipynb at commit fa5ce9b, no license · at the source

Overview

Authors: Zhenfu Wen1,2, Edward F. Pace-Schott3,4, Peter L. Franzen5, Lihan Cui1, Kai Zhang1, Si Gao1, L. Elliot Hong1, Peter Kochunov1, Anne Germain6, Mohammed R. Milad1
ORCID iDs: Kai Zhang, Si Gao, Mohammed R. Milad
  1. Faillace Department of Psychiatry and Behavioral Sciences, McGovern Medical School, University of Texas Health Science Center at Houston,Houston, TX USA
  2. Present Address: Shien-Ming Wu School of Intelligent Engineering, South China University of Technology,Guangzhou, China
  3. Department of Psychiatry, Mass General Brigham Hospital and Harvard Medical School,Charlestown, MA USA
  4. Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital,Charlestown, MA USA
  5. Department of Psychiatry, University of Pittsburgh,Pittsburgh, PA USA
  6. NOCTEM, LLC, Pittsburgh, PA USA
Institutions: The University of Texas Health Science Center at Houston (United States); South China University of Technology (China); Mass General Brigham (United States); Massachusetts General Hospital (United States); University of Pittsburgh (United States)
Journal: Nature communications, volume 17, issue 1, article 8919
Dates: received 16 July 2025; accepted 6 July 2026; published online 22 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41467-026-75661-x · PMID 42637707 · PMCID PMC13503868 · OpenAlex W7170061252
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: human (organism), cognitive (subfield)
Methods: Spectral & time-frequency, Connectivity, Statistics, Machine learning, Preprocessing, fMRI & imaging, Physiology & signal measures
Keywords: Predictive markers, Human behaviour, Sleep deprivation, Cognitive neuroscience
MeSH: Brain*, Sleep Deprivation*, Adult, Brain Mapping, Female, Humans, Machine Learning, Magnetic Resonance Imaging, Male, Neuroimaging, Sleep, Sleep Duration, Young Adult (* major topic)
Topic: Sleep and Work-Related Fatigue (Experimental and Cognitive Psychology, Psychology), according to OpenAlex
Funding: National Institute of Mental Health
Citations: cited by 1 paper (Europe PMC); 86 references in the paper

Abstract

Insufficient sleep disrupts cognitive and emotional functioning, yet the precise neural consequences of sleep loss and their persistence remain unclear. Here, we leverage machine learning and large neuroimaging datasets to identify a candidate neural signature that robustly distinguishes sleep-deprived from well-rested brains. We validate this signature across multiple independent datasets spanning both controlled experimental and real-world settings. The signature not only detects residual neural disturbances following a night of recovery sleep, but also demonstrates sensitivity to partial sleep deprivation. Additionally, it captures natural variations in sleep duration in the general population, independent of experimental manipulation. We further identify distributed connectivity patterns that contribute to the signature, highlighting networks vulnerable to sleep manipulations and those that are resistant or rapidly normalized after recovery sleep. The reliability and generalizability of this neural signature underscore its potential as a biomarker for understanding and monitoring the neural impacts of acute and chronic sleep loss.

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

Repositories

Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.

zhenfu-wen01/sleep_loss_signature

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: fa5ce9b0c149cadc9a7a698c9e7a9b5773995951, 24 June 2026
Languages: Jupyter (5), Python (3)
Size: 16 files, 8 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README, 5 notebooks
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (8 files), pandas (7 files), Matplotlib (6 files), Nilearn (5 files), SciPy (5 files), scikit-learn (3 files), seaborn (3 files), NiBabel (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
9 files
At the source: github.com/zhenfu-wen01/sleep_loss_signature

Zenodo 20822243

License: CC-BY-4.0
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: “Code availability”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (8 files), pandas (7 files), Matplotlib (6 files), Nilearn (5 files), SciPy (5 files), scikit-learn (3 files), seaborn (3 files), NiBabel (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)
  • 27 September 2026: the link answers (HTTP 200)
9 files
At the source: zenodo.org/records/20822243

Code availability

Custom codes to generate the main results are available on GitHub at https://github.com/zhenfu-wen01/sleep_loss_signature and in the Zenodo repository86 (https://zenodo.org/records/20822243).

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

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 16 scripts, each with its path and the digest of its content;
  • 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data availability

The processed data of Dataset 1 are available at https://osf.io/ayj72/. The raw data are not publicly available due to a lack of current institutional authorizations for public data sharing. The raw data could be available upon request and engage in a data-sharing agreement with the institution. Requests for Dataset 1 should be directed to A.G. Dataset 2 is available at https://osf.io/ubhpx/. Dataset 3 is from the Perturbation of the Depression Connectome (PDC) 1.0 data release at https://www.humanconnectome.org/. Dataset 4 is available in OpenNeuro database with accession number ds000201. Dataset 5 is available at NIMH Data Archive through collection ID 2393. Dataset 6 is available from UK Biobank, which can be accessed by applying for access via its Access Management System at https://www.ukbiobank.ac.uk/enable-your-research/apply-for-access. Source data are provided with this paper.

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, 10 authors, 4 keywords, 13 MeSH terms, 1 funder, 86 references.

Cite

This paper

Wen, Z., Pace-Schott, E. F., Franzen, P. L., Cui, L., Zhang, K., Gao, S., Hong, L. E., Kochunov, P., Germain, A., & Milad, M. R. (2026). A neural signature of sleep deprivation in the human brain. Nature communications, 17(1), 8919. https://doi.org/10.1038/s41467-026-75661-x

BibTeX

@article{wen2026neural,
author = {Wen, Zhenfu and Pace-Schott, Edward F. and Franzen, Peter L. and Cui, Lihan and Zhang, Kai and Gao, Si and Hong, L. Elliot and Kochunov, Peter and Germain, Anne and Milad, Mohammed R.},
title = {{A neural signature of sleep deprivation in the human brain}},
journal = {Nature communications},
year = {2026},
month = jul,
volume = {17},
number = {1},
pages = {8919},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/s41467-026-75661-x},
url = {https://doi.org/10.1038/s41467-026-75661-x},
pmid = {42637707},
pmcid = {PMC13503868}
}

RIS

TY - JOUR
AU - Wen, Zhenfu
AU - Pace-Schott, Edward F.
AU - Franzen, Peter L.
AU - Cui, Lihan
AU - Zhang, Kai
AU - Gao, Si
AU - Hong, L. Elliot
AU - Kochunov, Peter
AU - Germain, Anne
AU - Milad, Mohammed R.
TI - A neural signature of sleep deprivation in the human brain
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/07/22
VL - 17
IS - 1
SP - 8919
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/s41467-026-75661-x
UR - https://doi.org/10.1038/s41467-026-75661-x
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41467-026-75661-x",
"type": "article-journal",
"title": "A neural signature of sleep deprivation in the human brain",
"container-title": "Nature communications",
"author": [
{
"family": "Wen",
"given": "Zhenfu"
},
{
"family": "Pace-Schott",
"given": "Edward F."
},
{
"family": "Franzen",
"given": "Peter L."
},
{
"family": "Cui",
"given": "Lihan"
},
{
"family": "Zhang",
"given": "Kai"
},
{
"family": "Gao",
"given": "Si"
},
{
"family": "Hong",
"given": "L. Elliot"
},
{
"family": "Kochunov",
"given": "Peter"
},
{
"family": "Germain",
"given": "Anne"
},
{
"family": "Milad",
"given": "Mohammed R."
}
],
"container-title-short": "Nat Commun",
"volume": "17",
"issue": "1",
"page": "8919",
"DOI": "10.1038/s41467-026-75661-x",
"PMID": "42637707",
"PMCID": "PMC13503868",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41467-026-75661-x",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
22
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

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:10.1162/imag.a.1278 [code]
Young and old adult brains experience opposite effects of acute sleep restriction on the functional connectivity network.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: Nilearn, NiBabel, statsmodels, 5 other tools, 7 references
[2] doi:10.1038/s41514-026-00456-9 [code]
Exploring the link between body physiology and cognition: the role of the brain and aging.
Journal: npj aging
In common: Nilearn, NiBabel, statsmodels, 6 other tools, cognitive, 7 references
[3] doi:10.7554/elife.108109 [code]
Multimodal MRI marker of cognition explains the association between cognition and mental health in the UK Biobank.
Journal: eLife
In common: seaborn, scikit-learn, pandas, 3 other tools, ukbiobank.ac.uk/enable-your-research/apply-for-access, cognitive, 7 references
[4] doi:10.1038/s41562-026-02447-y [code]
Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers.
Journal: Nature human behaviour
In common: 12 references
[5] doi:10.1038/s41467-026-73668-y [code]
Convergent and divergent brain-cognition development in early adolescence.
Journal: Nature communications
In common: Nilearn, NiBabel, seaborn, 5 other tools, 7 references
[6] 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: Nilearn, NiBabel, seaborn, 5 other tools, cognitive, 7 references
[7] doi:10.64898/2026.03.09.710558 [code]
Multi-task fMRI outperforms resting-state fMRI for revealing task-invariant organization of the human brain
Journal: bioRxiv (preprint)
In common: Nilearn, NiBabel, seaborn, 5 other tools, cognitive, 7 references
[8] doi:10.1523/eneuro.0370-25.2026 [code]
Pretraining for Large-Scale Functional Connectome Fingerprinting Supports Generalization and Transfer Learning in Functional Neuroimaging.
Journal: eNeuro
In common: Nilearn, scikit-learn, pandas, 2 other tools, 9 references
[9] doi:10.1038/s44220-026-00680-y [code]
The neuroimaging correlates of depression established across six large-scale population datasets.
Journal: Nature. Mental health
In common: statsmodels, seaborn, scikit-learn, 4 other tools, ukbiobank.ac.uk/enable-your-research/apply-for-access, 5 references
[10] doi:10.1093/sleep/zsag030 [code]
Divergent disruption of brain networks following total and chronic sleep loss: a longitudinal fMRI study.
Journal: Sleep
In common: statsmodels, seaborn, scikit-learn, 4 other tools, 5 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.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

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, reproductions, activity

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.