OSCR

Neuronal silence as a predictive biomarker and target for epileptic seizures suppression.

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] § Results › Random neuronal network ↔ Random Forest/RF_code.ipynb, lines 45–69 · score 0.54 · absolute error, Random Forest, Pearson, trained, predicting, model

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 · 102 lines · 3.3 KB · no license · 1 match

  1. # %%
  2. import pandas as pd
  3. import statistics
  4. import math
  5. from scipy import stats
  6. import numpy as np
  7. from collections import Counter
  8. import seaborn as sns
  9. import matplotlib.pyplot as plt
  10. import matplotlib as mpl
  11. import random
  12. import pylab as rcParams
  13. from statsmodels.tsa.seasonal import seasonal_decompose
  14. from pandas.plotting import register_matplotlib_converters
  15. from sklearn.model_selection import train_test_split
  16. from sklearn.ensemble import RandomForestRegressor
  17. from sklearn.preprocessing import RobustScaler
  18. from sklearn.metrics import mean_squared_error
  19. from sklearn.metrics import r2_score
  20. import warnings
  21. warnings.filterwarnings("ignore")
  23. # %%
  24. # loading the Mean silence time with its delays and R
  25. df_T = pd.read_csv("Mean_Silence_Time_gsyn0.001811.csv") # this dataframe contains the complete time series that we used to train the RF in the paper. It is possible to use the others time series as well
  26. df = pd.read_csv("Mean_Silence_Time_gsyn0.001825.csv") # this dataframe contains the complete time series
  28. # %%
  29. plt.figure(figsize=(20, 8))
  31. plt.suptitle('Complete Time Series of R(t) and <T>', fontsize=16)
  33. plt.subplot(2, 1, 1)
  34. plt.plot(df['time']/1000, df['R'], label='R(t)', c='red')
  35. plt.xlim(0,1000)
  36. plt.xlabel('Time (s)', fontsize=14)
  37. plt.ylabel('R(t)', fontsize=14)
  39. plt.subplot(2, 1, 2)
  40. plt.plot(df['time']/1000, df['T'], label='<T>', c='green')
  41. plt.xlim(0,1000)
  42. plt.xlabel('Time (s)', fontsize=14)
  43. plt.ylabel('<T> (ms)', fontsize=14)
  45. # %%
  46. from sklearn.model_selection import train_test_split
  47. from sklearn.metrics import mean_absolute_error
  49. ######### Here we are training the Random Forest model ##############
  51. #y: target
  52. #X: Characteristics
  54. X= df_T.drop(['time'], axis=1)
  55. X= X.drop(['R'], axis=1)
  56. y = df_T['R']
  58. X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=18)
  60. rf = RandomForestRegressor(criterion='absolute_error',n_estimators = 200, max_features = 0.2, max_depth = 30, bootstrap=True, random_state = 18).fit(X_train, y_train)
  61. prediction_train = rf.predict(X_train)
  62. prediction_test = rf.predict(X_test)
  65. absolute_error = mean_absolute_error(y_test, prediction_test)
  66. r = pearsonr(y_test, prediction_test)
  67. r2 = r2_score(y_test, prediction_test)
  68. print("Evaluation of the model on the test set:")
  69. print("Absolute error = %.3f, PearsonR = %.3f, R2 = %.3f" % (np.mean(absolute_error), r[0], r2))
  72. # %%
  73. #once the model is trained, we can use it to predict the whole time series. We can also do the prediction of different time series with different parameters
  74. # to change the time series to try it out we have to change the dataframe df
  76. df = pd.read_csv("Mean_Silence_Time_gsyn0.001825.csv")
  78. X = df.drop(['time'], axis=1)
  79. X = X.drop(['R'], axis=1)
  80. y = df['R']
  82. prediction = rf.predict(X)
  84. absolute_error = mean_absolute_error(y, prediction)
  85. r = pearsonr(y, prediction)
  86. r2 = r2_score(y, prediction)
  88. print("Using the complete time series:")
  89. print("Absolute error = %.3f, PearsonR = %.3f, R2 = %.3f" % (np.mean(absolute_error), r[0], r2))
  91. # %%
  92. plt.figure(figsize=(20, 8))
  94. plt.subplot(2, 1, 1)
  95. plt.plot(df['time']/1000, df['R'], label='R(t)', c='red')
  96. plt.xlabel('Time (s)', fontsize=14)
  97. plt.ylabel('R(t)', fontsize=14)
  99. plt.subplot(2, 1, 2)
  100. plt.plot(df['time']/1000, prediction, label='R_pred', c='black')
  101. plt.xlabel('Time (s)', fontsize=14)
  102. plt.ylabel('R_pred', fontsize=14)

RF_code.ipynb at commit 2b49c0a, no license · at the source

Overview

Authors: Diogo L. M. Souza1, Lucas E. Bentivoglio1, Enrique C. Gabrick2, Paulo R. Protachevicz1,3, Iberê L. Caldas2, Kelly C. Iarosz1,2, Salvador Dura-Bernal4,5, Antonio M. Batista1,6, Fernando S. Borges1,4,7
ORCID iDs: Diogo L. M. Souza
  1. Graduate Program in Sciences, State University of Ponta Grossa,Ponta Grossa, Paraná Brazil
  2. Institute of Physics, University of São Paulo,São Paulo, Brazil
  3. Graduate Program in Electrical Engineering and Industrial Informatics, Federal University of Technology of Paraná,Curitiba, Paraná Brazil
  4. Department of Physiology and Pharmacology, State University of New York Downstate Health Sciences University,New York, NY USA
  5. Center for Biomedical Imaging and Neuromodulation, The Nathan S. Kline Institute for Psychiatric Research,New York, USA
  6. Department of Mathematics and Statistics, State University of Ponta Grossa,Ponta Grossa, Paraná Brazil
  7. Center for Mathematics, Computation, and Cognition, Federal University of ABC,São Bernardo do Campo, São Paulo Brazil
Institutions: Universidade Estadual de Ponta Grossa (Brazil); Universidade de São Paulo (Brazil); Universidade Tecnológica Federal do Paraná (Brazil); State University of New York (United States); Nathan Kline Institute for Psychiatric Research (United States); Universidade Federal do ABC (Brazil)
Journal: Scientific reports, volume 16, issue 1, article 16732
Dates: received 1 November 2025; accepted 9 March 2026; published online 9 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41598-026-44063-w · PMID 41957397 · PMCID PMC13223270 · OpenAlex W7152719840
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: EEG (modality), human (organism), epilepsy (population), clinical / translational (subfield)
Methods: Single-unit activity, calcium imaging
Keywords: Epilepsy, Seizure prediction, Seizure Suppression, Intermittent synchronization, Biomarkers, Neurology, Neuroscience
MeSH: Epilepsy*, Neurons*, Seizures*, Biomarkers, Computer Simulation, Electroencephalography, Humans, Models, Neurological (* major topic)
Topic: Functional Brain Connectivity Studies (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (88887.991936/2024–00); Conselho Nacional de Desenvolvimento Científico e Tecnológico (315299/2025–8); Fundação de Amparo à Pesquisa do Estado de São Paulo (2025/02318-5); NIH (U24EB028998)
Citations: cited by 1 paper (Europe PMC); 76 references in the paper

Abstract

Epilepsy is a prevalent neurological disorder marked by abnormal synchronized neuronal firing, which can often lead to long-term cognitive and physical impairments. In this work, we introduce a reliable biomarker for seizure prediction. Through simulations of a conductance-based neuronal network model that reproduces spontaneous seizure-like events, we identify that slow potassium channels play an important role in seizure generation. Our key finding is the consistent presence of a prolonged period of neuronal silence that precedes the seizure onset, establishing it as a physiologically relevant biomarker for seizure prediction. Notably, this silence is also identified in human electrophysiological data, confirming its physiological and clinical relevance. Based on this biomarker, we develop a targeted suppression strategy that, in our simulations, significantly shortens long seizure duration by up to 93%. Our results establish the network silence as a predictive and clinically translatable biomarker for seizure dynamics, opening new avenues for improved forecasting and personalized neuromodulation therapies in epilepsy.

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

Repository

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

DiogoLeonai/Neuronal-silence-as-an-epileptic-seizure-biomarker

License: none: the authors keep all their rights
State: the link answers, verified on 29 September 2026
Evidence: files inventoried
Commit: 2b49c0abd5716644bab18f16213c85a556f0faf3, 14 April 2026
Languages: Jupyter (2), C (1)
Size: 8 files, 3 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, 2 notebooks
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: Matplotlib (2 files), NumPy (2 files), pandas (2 files), scikit-learn (1 file), SciPy (1 file), seaborn (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 29 September 2026: the link answers
  • 29 September 2026: the link answers
4 files
At the source: github.com/DiogoLeonai/Neuronal-silence-as-an-epileptic-seizure-biomarker

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

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:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 3 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 codes generated and analyzed during the current study are available in the GitHub repository (https://github.com/DiogoLeonai/Neuronal-silence-as-an-epileptic-seizure-biomarker) (https://github.com/DiogoLeonai/Neuronal-silence-as-an-epileptic-seizure-biomarker). The datasets analyzed in this study were originally collected and published by Elahian et al.40 and are publicly available in the Zenodo repository (https://doi.org/10.5281/zenodo.836286)48 (https://doi.org/10.5281/zenodo.836286).

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, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 9 authors, 7 keywords, 8 MeSH terms, 4 funders, 67 references.

Cite

This paper

Souza, D. L. M., Bentivoglio, L. E., Gabrick, E. C., Protachevicz, P. R., Caldas, I. L., Iarosz, K. C., Dura-Bernal, S., Batista, A. M., & Borges, F. S. (2026). Neuronal silence as a predictive biomarker and target for epileptic seizures suppression. Scientific reports, 16(1), 16732. https://doi.org/10.1038/s41598-026-44063-w

BibTeX

@article{souza2026neuronal,
author = {Souza, Diogo L. M. and Bentivoglio, Lucas E. and Gabrick, Enrique C. and Protachevicz, Paulo R. and Caldas, Iberê L. and Iarosz, Kelly C. and Dura-Bernal, Salvador and Batista, Antonio M. and Borges, Fernando S.},
title = {{Neuronal silence as a predictive biomarker and target for epileptic seizures suppression}},
journal = {Scientific reports},
year = {2026},
month = apr,
volume = {16},
number = {1},
pages = {16732},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-44063-w},
url = {https://doi.org/10.1038/s41598-026-44063-w},
pmid = {41957397},
pmcid = {PMC13223270}
}

RIS

TY - JOUR
AU - Souza, Diogo L. M.
AU - Bentivoglio, Lucas E.
AU - Gabrick, Enrique C.
AU - Protachevicz, Paulo R.
AU - Caldas, Iberê L.
AU - Iarosz, Kelly C.
AU - Dura-Bernal, Salvador
AU - Batista, Antonio M.
AU - Borges, Fernando S.
TI - Neuronal silence as a predictive biomarker and target for epileptic seizures suppression
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/04/09
VL - 16
IS - 1
SP - 16732
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-44063-w
UR - https://doi.org/10.1038/s41598-026-44063-w
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-44063-w",
"type": "article-journal",
"title": "Neuronal silence as a predictive biomarker and target for epileptic seizures suppression",
"container-title": "Scientific reports",
"author": [
{
"family": "Souza",
"given": "Diogo L. M."
},
{
"family": "Bentivoglio",
"given": "Lucas E."
},
{
"family": "Gabrick",
"given": "Enrique C."
},
{
"family": "Protachevicz",
"given": "Paulo R."
},
{
"family": "Caldas",
"given": "Iberê L."
},
{
"family": "Iarosz",
"given": "Kelly C."
},
{
"family": "Dura-Bernal",
"given": "Salvador"
},
{
"family": "Batista",
"given": "Antonio M."
},
{
"family": "Borges",
"given": "Fernando S."
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "16732",
"DOI": "10.1038/s41598-026-44063-w",
"PMID": "41957397",
"PMCID": "PMC13223270",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-44063-w",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
9
]
]
}
}

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:10.1038/s41598-026-43151-1 [code]
Stabilizing fractional dynamical networks suppresses epileptic seizures.
Journal: Scientific reports
In common: statsmodels, seaborn, scikit-learn, 4 other tools, epilepsy, EEG, 3 references
[2] doi:10.1038/s41593-026-02258-4 [code]
Laminar organization of cellular microcircuits modulating human interictal epileptiform discharges.
Journal: Nature neuroscience
In common: statsmodels, seaborn, scikit-learn, 4 other tools, epilepsy, EEG, 2 references
[3] doi:10.1016/j.neurot.2026.e01031
Single-neuron responses to neurostimulation: Insights for epilepsy.
Journal: Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics
In common: epilepsy, clinical / translational, 4 references
[4] doi:10.1016/j.ebiom.2026.106362 [code]
Neuron-derived neurotrophic factor-positive interneurons: a cellular target for anti-seizure therapies.
Journal: EBioMedicine
In common: scikit-learn, pandas, SciPy, 2 other tools, epilepsy, 2 references
[5] doi:10.1093/braincomms/fcag088 [code]
Dual mechanism of anti-seizure medications in controlling seizure activity.
Journal: Brain communications
In common: statsmodels, seaborn, pandas, 3 other tools, epilepsy, 1 reference
[6] doi:10.1038/s41593-026-02376-z [code]
A framework for comparative analysis of human and mouse cortical neuron dendrites in corresponding brain regions.
Journal: Nature neuroscience
In common: statsmodels, seaborn, scikit-learn, 4 other tools, 1 reference
[7] doi:10.1007/s00234-026-04103-8 [code]
Enhanced detection of subtle cortical abnormalities in focal epilepsy using 7 T MRI surface-based models and graph neural networks.
Journal: Neuroradiology
In common: statsmodels, seaborn, scikit-learn, 4 other tools, epilepsy, EEG
[8] doi:10.1002/ana.78203 [code]
AI-Driven Mapping of Seizure Spread Patterns.
Journal: Annals of neurology
In common: statsmodels, seaborn, scikit-learn, 4 other tools, epilepsy, EEG
[9] doi:10.1002/epi4.70336 [code]
Quantifying extra-lesional interhemispheric cortical asymmetry in focal cortical dysplasia type II.
Journal: Epilepsia open
In common: statsmodels, seaborn, scikit-learn, 4 other tools, epilepsy, clinical / translational
[10] doi:10.1371/journal.pcbi.1014657 [code]
Population morphology implies a common developmental blueprint for Drosophila motion detectors.
Journal: PLoS computational biology
In common: statsmodels, seaborn, scikit-learn, 4 other tools, 1 reference

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.