OSCR

Long-term exposure to polystyrene microplastics exacerbates seizure symptoms via lipid metabolic disruption and ferroptosis: insights from multi-omics analyses.

Code ↔ Paper

2 matches 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 2 matches · 1 of them tie a paragraph to a whole file, not to given lines: a weak match, whose lines are not tinted
  1. [1] § Results › Microplastic exposure induces lipid metabolic disturbance, triggering ferroptosis and exacerbating seizure severity ↔ Machine learning.py, lines 36–47 · score 0.68 · logistic regression, Gradient Boosting, machine learning, probability, models
  2. [2] § Results › Microplastic exposure induces lipid metabolic disturbance, triggering ferroptosis and exacerbating seizure severity ↔ Brouta feacture selection.R, the whole file · a weak match · score 0.57 · Boruta algorithm, feature selection, clinical, Width

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

Python · 243 lines · 7.9 KB · no license · 1 match

  1. # Import required libraries
  2. import os
  3. import pandas as pd
  4. import numpy as np
  5. import xgboost as xgb
  6. import matplotlib.pyplot as plt
  7. from sklearn.linear_model import LogisticRegression
  8. from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, AdaBoostClassifier
  9. from sklearn.neighbors import KNeighborsClassifier
  10. from sklearn.neural_network import MLPClassifier
  11. from sklearn.tree import DecisionTreeClassifier
  12. from sklearn.svm import SVC
  13. from sklearn.metrics import roc_auc_score, accuracy_score, roc_curve, precision_recall_curve, auc
  14. from sklearn.preprocessing import OneHotEncoder, StandardScaler
  15. from sklearn.compose import ColumnTransformer
  16. from sklearn.pipeline import Pipeline
  17. from sklearn.impute import SimpleImputer
  19. # Set working directory and read data
  20. os.chdir("Your own path")
  21. data = pd.read_csv("Your own CSV")
  22. target_column = 'Group'
  23. data[target_column] = data[target_column].astype('category')
  25. # Split features and target
  26. X = data.drop(columns=target_column)
  27. y = data[target_column]
  29. # Define preprocessor for numerical features
  30. preprocessor = ColumnTransformer(
  31. transformers=[
  32. ('num', SimpleImputer(strategy='median'), X.columns)
  33. ]
  34. )
  36. # Define dictionary of models to be evaluated
  37. models = {
  38. 'Logistic Regression': LogisticRegression(max_iter=10000, solver='liblinear'),
  39. 'Random Forest': RandomForestClassifier(random_state=121),
  40. 'AdaBoost': AdaBoostClassifier(random_state=121),
  41. 'GradientBoosting': GradientBoostingClassifier(random_state=121),
  42. 'XGBoost': xgb.XGBClassifier(use_label_encoder=False, eval_metric='logloss', seed=121),
  43. 'KNN': KNeighborsClassifier(),
  44. 'MLP': MLPClassifier(max_iter=2000, random_state=121),
  45. 'Decision Tree': DecisionTreeClassifier(random_state=121),
  46. 'SVM': SVC(probability=True, random_state=121)
  47. }
  49. # Set color cycle for plotting
  50. colors = plt.cm.Set3(np.linspace(0, 1, len(models)))
  52. # Initialize dictionaries to store results and predictions
  53. results = {}
  54. predictions = {}
  56. # Train models and collect predictions
  57. for (name, model), color in zip(models.items(), colors):
  58. # Create pipeline with preprocessing and model
  59. pipeline = Pipeline(steps=[('preprocessor', preprocessor),
  60. ('scaler', StandardScaler()),
  61. ('classifier', model)])
  63. # Fit model and get predictions
  64. pipeline.fit(X, y)
  65. y_pred = pipeline.predict_proba(X)[:, 1]
  66. predictions[name] = y_pred
  68. # Calculate performance metrics
  69. results[name] = {
  70. 'auc': roc_auc_score(y, y_pred),
  71. 'acc': accuracy_score(y, pipeline.predict(X))
  72. }
  74. # Plot ROC curve
  75. plt.figure(figsize=(10, 8))
  76. for (name, y_pred), color in zip(predictions.items(), colors):
  77. fpr, tpr, _ = roc_curve(y, y_pred)
  78. roc_auc = auc(fpr, tpr)
  79. plt.plot(fpr, tpr, color=color, label=f'{name} (AUC = {roc_auc:.2f})')
  81. plt.plot([0, 1], [0, 1], 'k--')
  82. plt.xlim([0.0, 1.0])
  83. plt.ylim([0.0, 1.05])
  84. plt.xlabel('False Positive Rate')
  85. plt.ylabel('True Positive Rate')
  86. plt.title('ROC Curve')
  87. plt.legend(loc='lower right')
  88. plt.grid(True)
  89. plt.show()
  91. # Plot Precision-Recall curve
  92. plt.figure(figsize=(10, 8))
  93. for (name, y_pred), color in zip(predictions.items(), colors):
  94. precision, recall, _ = precision_recall_curve(y, y_pred)
  95. prc_auc = auc(recall, precision)
  96. plt.plot(recall, precision, color=color, label=f'{name} (AUC = {prc_auc:.2f})')
  98. plt.xlim([0.0, 1.0])
  99. plt.ylim([0.0, 1.05])
  100. plt.xlabel('Recall')
  101. plt.ylabel('Precision')
  102. plt.title('Precision-Recall Curve')
  103. plt.legend(loc='lower left')
  104. plt.grid(True)
  105. plt.show()
  107. # Define function for Decision Curve Analysis
  108. def calculate_net_benefit(y_true, y_pred_proba, threshold):
  109. """
  110. Calculate net benefit for a given threshold
  111. Args:
  112. y_true: True labels
  113. y_pred_proba: Predicted probabilities
  114. threshold: Decision threshold
  115. Returns:
  116. Net benefit value
  117. """
  118. y_pred = (y_pred_proba >= threshold).astype(int)
  119. TP = np.sum((y_true == 1) & (y_pred == 1))
  120. FP = np.sum((y_true == 0) & (y_pred == 1))
  121. n = len(y_true)
  123. if TP + FP == 0:
  124. return 0
  126. net_benefit = (TP/n) - (FP/n) * (threshold/(1-threshold))
  127. return net_benefit
  129. def plot_dca_curve(y_true, predictions_dict, thresholds=np.arange(0, 1.01, 0.01),
  130. title="Decision Curve Analysis", colors=None):
  131. """
  132. Plot Decision Curve Analysis
  133. Args:
  134. y_true: True labels
  135. predictions_dict: Dictionary of model predictions
  136. thresholds: Array of threshold values
  137. title: Plot title
  138. colors: Color scheme for plotting
  139. """
  140. y_true_num = pd.get_dummies(y_true).iloc[:, 1].values
  142. plt.figure(figsize=(10, 8))
  144. if colors is None:
  145. colors = plt.cm.Set3(np.linspace(0, 1, len(predictions_dict)))
  147. # Calculate and plot "treat all" net benefit
  148. all_treat = [np.mean(y_true_num) - threshold/(1-threshold)*(1-np.mean(y_true_num))
  149. for threshold in thresholds]
  150. plt.plot(thresholds, all_treat, 'k--', label='Treat All')
  152. # Plot "treat none" baseline
  153. plt.plot(thresholds, np.zeros_like(thresholds), 'k-', label='Treat None')
  155. # Calculate and plot net benefit for each model
  156. for (name, y_pred), color in zip(predictions_dict.items(), colors):
  157. net_benefits = []
  158. for threshold in thresholds:
  159. nb = calculate_net_benefit(y_true_num, y_pred, threshold)
  160. net_benefits.append(nb)
  161. plt.plot(thresholds, net_benefits, color=color, label=name)
  163. plt.xlim(0, 1)
  164. plt.ylim(-0.05, max(all_treat) + 0.1)
  165. plt.xlabel('Threshold Probability')
  166. plt.ylabel('Net Benefit')
  167. plt.title(title)
  168. plt.legend(loc='lower left')
  169. plt.grid(True)
  171. return plt.gcf()
  173. # Plot DCA curve
  174. dca = plot_dca_curve(y, predictions)
  175. plt.show()
  177. # Calculate and display comprehensive metrics
  178. from sklearn.metrics import precision_score, recall_score, f1_score
  180. metrics = {}
  181. for name, model in models.items():
  182. pipeline = Pipeline(steps=[('preprocessor', preprocessor),
  183. ('scaler', StandardScaler()),
  184. ('classifier', model)])
  186. pipeline.fit(X, y)
  187. y_pred_class = pipeline.predict(X)
  188. y_pred_prob = pipeline.predict_proba(X)[:, 1]
  190. metrics[name] = {
  191. 'Accuracy': accuracy_score(y, y_pred_class),
  192. 'Precision': precision_score(y, y_pred_class),
  193. 'Recall': recall_score(y, y_pred_class),
  194. 'F1-score': f1_score(y, y_pred_class),
  195. 'ROC-AUC': roc_auc_score(y, y_pred_prob)
  196. }
  198. # Create and display metrics DataFrame
  199. metrics_df = pd.DataFrame(metrics).T
  200. print("\nModel Performance Metrics:")
  201. print(metrics_df.round(3))
  203. # Save results to CSV
  204. metrics_df.to_csv('model_metrics.csv')
  206. # Plot radar charts for each metric
  207. metrics_list = ['Accuracy', 'Precision', 'Recall', 'F1-score', 'ROC-AUC']
  208. model_names = list(models.keys())
  209. angles = np.linspace(0, 2*np.pi, len(model_names), endpoint=False)
  210. angles = np.concatenate((angles, [angles[0]]))
  211. model_names_plot = np.concatenate((model_names, [model_names[0]]))
  213. def add_value_labels(ax, angles, values):
  214. """
  215. Add value labels to radar chart
  216. """
  217. for angle, value in zip(angles[:-1], values[:-1]):
  218. ha = 'left' if 0 <= angle <= np.pi else 'right'
  219. offset = 0.1 if 0 <= angle <= np.pi else -0.1
  220. ax.text(angle, value + 0.05, f'{value:.3f}',
  221. ha=ha, va='center')
  223. # Plot radar chart for each metric
  224. for metric in metrics_list:
  225. plt.figure(figsize=(10, 8))
  226. ax = plt.subplot(111, projection='polar')
  228. values = [metrics[model][metric] for model in model_names]
  229. values = np.concatenate((values, [values[0]]))
  231. ax.plot(angles, values, 'o-', linewidth=2, label=metric)
  232. ax.fill(angles, values, alpha=0.25)
  234. add_value_labels(ax, angles, values)
  236. ax.set_xticks(angles[:-1])
  237. ax.set_xticklabels(model_names, fontsize=10)
  238. ax.set_ylim(0, 1)
  239. ax.set_title(f'{metric} Performance')
  240. ax.grid(True)
  242. plt.tight_layout()
  243. plt.show()

Machine learning.py at commit 5f464c1, no license · at the source

Overview

Authors: Yueying Liu1, Ruijin Xie1, Wenjing Zhao2, Hua Xu1, Jianrui Dou3, Xue Xiao1, Yufan Luo1, Heng Zhang4, Peiweng Wang5, Wei Xiao1, Xiao Tong1, Shengjie Xu1, Dongqin Wu1, Xianhui Deng6, Yu Wu5, Chenyu Sun7,8,9, Shudong Hu4
  1. Department of Pediatrics, Affiliated Hospital of Jiangnan University, Wuxi, China
  2. Yangzhou Key Laboratory of Anesthesiology, Northern Jiangsu People’s Hospital Affiliated to Yangzhou University, Yangzhou, China
  3. Center for Disease Control and Prevention of Yangzhou, Yangzhou, China
  4. Department of Radiology, Affiliated Hospital of Jiangnan University, Wuxi, China
  5. Lab of Modern Environmental Toxicology, Public Health and Preventive Medicine, Wuxi School of Medicine, Jiangnan University, Wuxi, China
  6. Department of Neonatology, Jiangyin People’s Hospital of Nantong University, Wuxi, China
  7. Division of Public Health, Infectious Diseases, and Occupational Medicine, Mayo Clinic, Rochester, USA
  8. Mayo Clinic School of Graduate Medical Education, Mayo Clinic College of Medicine and Science, Rochester, USA
  9. School of Public Health, University of Minnesota-Twin Cities, Minneapolis, USA
Institutions: Wuxi Fourth People's Hospital (China); Northern Jiangsu People's Hospital (China); Yangzhou University (China); Jiangnan University (China); Nantong University (China); Jiangyin People's Hospital (China); University of Minnesota (United States); Mayo Clinic (United States)
Journal: Journal of nanobiotechnology, volume 24, issue 1, article 743
Dates: received 29 September 2025; accepted 19 May 2026; published online 29 May 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1186/s12951-026-04599-5 · PMID 42216007 · PMCID PMC13464342 · OpenAlex W7162757203
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: genetics / omics (modality), human (organism), mouse (organism), epilepsy (population), cellular / molecular (subfield)
Methods: Statistics
Keywords: Microplastics, Neurotoxicity, Seizures, Inflammation, Ferroptosis
MeSH: Ferroptosis*, Lipid Metabolism*, Microplastics*, Polystyrenes*, Seizures*, Animals, Humans, Male, Mice, Multiomics, Oxidative Stress (* major topic)
Topic: Microplastics and Plastic Pollution (Pollution, Environmental Science), according to OpenAlex
Funding: Jiangsu Traditional Chinese Medicine (PDJH2024027); National Natural Science Foundation of China (82371462)
Citations: not cited yet (Europe PMC); 56 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 2 matches between paragraphs and lines of code.

PediatricLab-Jiangnan/Airborne-singlecell-bulk

License: none: the authors keep all their rights
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: 5f464c17f45dcc8131c25993a5317516a43784c0, 21 April 2025
Languages: R (9), Python (1)
Size: 13 files, 10 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: tidyverse (6 files), ggplot2 (3 files), clusterProfiler (2 files), Seurat (2 files), car (1 file), data.table (1 file), ggpubr (1 file), Harmony (1 file), Matplotlib (1 file), NumPy (1 file), pandas (1 file), patchwork (1 file), rstatix (1 file), scikit-learn (1 file), XGBoost (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
11 files
At the source: github.com/PediatricLab-Jiangnan/Airborne-singlecell-bulk

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;
  • 10 scripts, each with its path and the digest of its content;
  • 2 matches 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

Code and data availability statement

The paper has a code and data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1186/s12951-026-04599-5.

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, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 17 authors, 5 keywords, 11 MeSH terms, 2 funders, 55 references.

Cite

This paper

Liu, Y., Xie, R., Zhao, W., Xu, H., Dou, J., Xiao, X., Luo, Y., Zhang, H., Wang, P., Xiao, W., Tong, X., Xu, S., Wu, D., Deng, X., Wu, Y., Sun, C., & Hu, S. (2026). Long-term exposure to polystyrene microplastics exacerbates seizure symptoms via lipid metabolic disruption and ferroptosis: insights from multi-omics analyses. Journal of nanobiotechnology, 24(1), 743. https://doi.org/10.1186/s12951-026-04599-5

BibTeX

@article{liu2026long,
author = {Liu, Yueying and Xie, Ruijin and Zhao, Wenjing and Xu, Hua and Dou, Jianrui and Xiao, Xue and Luo, Yufan and Zhang, Heng and Wang, Peiweng and Xiao, Wei and Tong, Xiao and Xu, Shengjie and Wu, Dongqin and Deng, Xianhui and Wu, Yu and Sun, Chenyu and Hu, Shudong},
title = {{Long-term exposure to polystyrene microplastics exacerbates seizure symptoms via lipid metabolic disruption and ferroptosis: insights from multi-omics analyses}},
journal = {Journal of nanobiotechnology},
year = {2026},
month = may,
volume = {24},
number = {1},
pages = {743},
publisher = {BMC},
issn = {1477-3155},
doi = {10.1186/s12951-026-04599-5},
url = {https://doi.org/10.1186/s12951-026-04599-5},
pmid = {42216007},
pmcid = {PMC13464342}
}

RIS

TY - JOUR
AU - Liu, Yueying
AU - Xie, Ruijin
AU - Zhao, Wenjing
AU - Xu, Hua
AU - Dou, Jianrui
AU - Xiao, Xue
AU - Luo, Yufan
AU - Zhang, Heng
AU - Wang, Peiweng
AU - Xiao, Wei
AU - Tong, Xiao
AU - Xu, Shengjie
AU - Wu, Dongqin
AU - Deng, Xianhui
AU - Wu, Yu
AU - Sun, Chenyu
AU - Hu, Shudong
TI - Long-term exposure to polystyrene microplastics exacerbates seizure symptoms via lipid metabolic disruption and ferroptosis: insights from multi-omics analyses
T2 - Journal of nanobiotechnology
J2 - J Nanobiotechnology
PY - 2026
DA - 2026/05/29
VL - 24
IS - 1
SP - 743
SN - 1477-3155
PB - BMC
DO - 10.1186/s12951-026-04599-5
UR - https://doi.org/10.1186/s12951-026-04599-5
LA - en
ER -

CSL-JSON

{
"id": "10.1186/s12951-026-04599-5",
"type": "article-journal",
"title": "Long-term exposure to polystyrene microplastics exacerbates seizure symptoms via lipid metabolic disruption and ferroptosis: insights from multi-omics analyses",
"container-title": "Journal of nanobiotechnology",
"author": [
{
"family": "Liu",
"given": "Yueying"
},
{
"family": "Xie",
"given": "Ruijin"
},
{
"family": "Zhao",
"given": "Wenjing"
},
{
"family": "Xu",
"given": "Hua"
},
{
"family": "Dou",
"given": "Jianrui"
},
{
"family": "Xiao",
"given": "Xue"
},
{
"family": "Luo",
"given": "Yufan"
},
{
"family": "Zhang",
"given": "Heng"
},
{
"family": "Wang",
"given": "Peiweng"
},
{
"family": "Xiao",
"given": "Wei"
},
{
"family": "Tong",
"given": "Xiao"
},
{
"family": "Xu",
"given": "Shengjie"
},
{
"family": "Wu",
"given": "Dongqin"
},
{
"family": "Deng",
"given": "Xianhui"
},
{
"family": "Wu",
"given": "Yu"
},
{
"family": "Sun",
"given": "Chenyu"
},
{
"family": "Hu",
"given": "Shudong"
}
],
"container-title-short": "J Nanobiotechnology",
"volume": "24",
"issue": "1",
"page": "743",
"DOI": "10.1186/s12951-026-04599-5",
"PMID": "42216007",
"PMCID": "PMC13464342",
"ISSN": "1477-3155",
"publisher": "BMC",
"URL": "https://doi.org/10.1186/s12951-026-04599-5",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
29
]
]
}
}

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:10.1002/imt2.70163 [code]
Spatial multi-omics unveils sphingolipid metabolic reprogramming within the retinal pathological niche.
Journal: iMeta
In common: Harmony, rstatix, clusterProfiler, 10 other tools, genetics / omics, mouse, cellular / molecular
[2] doi:10.1038/s41586-026-10214-2 [code]
Multidimensional profiling of heterogeneity in supratentorial ependymomas.
Journal: Nature
In common: Harmony, car, clusterProfiler, 10 other tools, genetics / omics, mouse
[3] doi:10.1016/j.xcrm.2026.102766 [code]
A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.
Journal: Cell reports. Medicine
In common: Harmony, car, clusterProfiler, 10 other tools, genetics / omics, cellular / molecular
[4] doi:10.1016/j.cell.2026.05.026 [code]
The critical role of the endogenous immune compartment after CAR T cell therapy in recurrent GBM.
Journal: Cell
In common: Harmony, rstatix, clusterProfiler, 10 other tools, genetics / omics
[5] doi:10.1038/s41586-026-10629-x [code]
Whole-genome duplication shaped cell-type evolution in the vertebrate brain.
Journal: Nature
In common: Harmony, rstatix, clusterProfiler, 9 other tools, genetics / omics, mouse, cellular / molecular
[6] doi:10.1038/s41398-026-04200-5 [code]
Postmortem brain single-nucleus and bulk gene expression analyses identify shared and distinct abnormalities in bipolar disorder and major depressive disorder.
Journal: Translational psychiatry
In common: Harmony, XGBoost, rstatix, 8 other tools, genetics / omics, cellular / molecular
[7] doi:10.1186/s13073-026-01704-z [code]
Gene expression profiling enables refined parcellation of cortical layers in the heterogeneous human cerebral cortex.
Journal: Genome medicine
In common: Harmony, XGBoost, Seurat, 9 other tools, genetics / omics, mouse, cellular / molecular
[8] doi:10.3390/toxics14050443 [code]
6PPDQ Exposure Exacerbates Seizure-Induced Neuronal Damage via the TP53/Nrf2 Axis: An Integrated Strategy Combining Network Toxicology and Experimental Validation.
Journal: Toxics
In common: XGBoost, ggplot2, scikit-learn, 3 other tools, epilepsy, cellular / molecular, 5 references
[9] doi:10.1126/sciadv.aeg3223 [code]
The extreme diversity of retinal amacrine cells has deep evolutionary roots.
Journal: Science advances
In common: XGBoost, rstatix, clusterProfiler, 9 other tools, genetics / omics, cellular / molecular
[10] doi:10.1038/s41593-026-02300-5 [code]
Integrated single-cell and spatial transcriptomic profiling in ALS uncovers peripheral-to-central immune infiltration and reprogramming.
Journal: Nature neuroscience
In common: Harmony, car, Seurat, 9 other tools, genetics / omics, cellular / molecular

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.