OSCR

Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study.

Code ↔ Paper

4 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 4 matches
  1. [1] § Results ↔ Metabolites-Based Classifier for Species-Over 25.ipynb, lines 181–234 · score 0.63 · ROC AUC score, confusion matrices, F1 Score, accuracy, ASD
  2. [2] § Results ↔ Metabolites-Based Classifier for Species-Under 25.ipynb, lines 184–237 · score 0.63 · ROC AUC score, confusion matrices, F1 Score, accuracy, ASD
  3. [3] § Methods ↔ Metabolites-Based Classifier for Species-Over 25.ipynb, lines 181–234 · score 0.62 · ROC AUC score, F1 score, sensitivity, precision, accuracy, classification
  4. [4] § Methods ↔ Metabolites-Based Classifier for Species-Under 25.ipynb, lines 184–237 · score 0.62 · ROC AUC score, F1 score, sensitivity, precision, accuracy, classification

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 · 379 lines · 9.3 KB · MIT · 2 matches

  1. # %%
  2. import pandas as pd
  3. import matplotlib.pyplot as plt
  4. import seaborn as sns
  5. from src.metabolome.metabolome_extractor import MetabolomeExtractor
  7. # %% [markdown]
  8. # # Extract Metabolites
  10. # %%
  11. df = pd.read_csv('data/all_species_asd_epi_health.csv')
  13. # %%
  14. df.head()
  16. # %%
  17. run_ids = list(df.run_id.unique())
  19. # %%
  20. len(run_ids)
  22. # %%
  23. bacteria_files_map = pd.read_csv('data/microbes_files_map_for_gmrepo2.csv')
  24. metabolome_extractor = MetabolomeExtractor(bacteria_files_map)
  26. # %%
  27. bacteria_files_map[bacteria_files_map.name == 'Bacillus atrophaeus']['files'].tolist()
  29. # %%
  30. bacteria_files_map
  32. # %%
  33. all_data = None
  34. index = 0
  35. for run_id in run_ids:
  36. index += 1
  37. print(index, '/', len(run_ids))
  38. temp = df[df.run_id == run_id]
  39. metabolites_df = metabolome_extractor.compute_metabolites_restrictive(temp)
  40. if metabolites_df is None:
  41. continue
  42. metabolites_df['project_id'] = temp.iloc[0].project_id
  43. metabolites_df['run_id'] = temp.iloc[0].run_id
  44. metabolites_df['host_age'] = temp.iloc[0].host_age
  45. metabolites_df['sex'] = temp.iloc[0].sex
  46. metabolites_df['BMI'] = temp.iloc[0].BMI
  47. metabolites_df['country'] = temp.iloc[0].country
  48. metabolites_df['phenotype'] = temp.iloc[0].phenotype
  49. if all_data is None:
  50. all_data = metabolites_df.copy()
  51. else:
  52. all_data = pd.concat([all_data, metabolites_df.copy()])
  56. # %%
  57. temp
  59. # %%
  60. len(all_data.run_id.unique())
  62. # %%
  63. all_data.to_csv('data/all_species_metabolites_asd_epi_health_restrictive.csv', index=False)
  65. # %% [markdown]
  66. # # Pivoting data
  68. # %%
  69. import pandas as pd
  70. import numpy as np
  71. import matplotlib.pyplot as plt
  72. from sklearn.model_selection import train_test_split
  73. from sklearn.ensemble import RandomForestClassifier
  74. from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score
  75. from sklearn.metrics import ConfusionMatrixDisplay
  77. # %%
  78. df = pd.read_csv('data/all_species_metabolites_asd_epi_health_restrictive.csv')
  80. # %%
  81. df.head()
  83. # %%
  84. all_metabolites = list(df.metabolite.unique())
  86. # %%
  87. len(all_metabolites)
  89. # %%
  90. run_ids = list(df.run_id.unique())
  92. # %%
  93. individuals = []
  94. i = 0
  95. for run_id in run_ids:
  96. i += 1
  97. print(i,'/', len(run_ids))
  98. individual = []
  99. temp = df[df.run_id == run_id]
  100. individual.append(temp.iloc[0]['run_id'])
  101. individual.append(temp.iloc[0]['project_id'])
  102. individual.append(temp.iloc[0]['host_age'])
  103. individual.append(temp.iloc[0]['sex'])
  104. individual.append(temp.iloc[0]['BMI'])
  105. individual.append(temp.iloc[0]['country'])
  106. individual.append(temp.iloc[0]['phenotype'])
  107. for metabolite in all_metabolites:
  108. bacter = temp[temp.metabolite == metabolite]
  109. if len(bacter) == 0:
  110. individual.append(0)
  111. else:
  112. individual.append(bacter.iloc[0]['relative_abundance'])
  113. individuals.append(individual)
  114. individual
  116. # %%
  117. columns = ['run_id', 'project_id', 'host_age', 'sex', 'BMI', 'country','phenotype'] + all_metabolites
  118. columns
  120. # %%
  121. final_df = pd.DataFrame(individuals, columns=columns)
  122. final_df.head()
  124. # %%
  125. final_df.to_csv('data/df_metabolites_species_restrictive.csv', index=False)
  127. # %% [markdown]
  128. # # The Classifier
  130. # %%
  131. df = pd.read_csv('data/df_metabolites_species_extensive.csv')
  132. df.head()
  134. # %%
  135. df = df[df.host_age >= 25]
  137. # %%
  138. df.phenotype.unique()
  140. # %%
  141. len(df), len(df[df.phenotype == 'health']), len(df[df.phenotype == 'ASD'])
  143. # %%
  144. df.host_age.hist()
  146. # %%
  147. #df[df.phenotype == 'health'].host_age.hist()
  148. df[df.phenotype == 'ASD'].host_age.hist()
  150. # %%
  151. df.country.hist(xrot=90)
  153. # %%
  154. #df[df.phenotype == 'health'].country.hist(xrot=90)
  155. df[df.phenotype == 'ASD'].country.hist(xrot=90)
  157. # %%
  158. df[df.phenotype == 'ASD'].host_age.hist()
  160. # %%
  161. df[df.phenotype == 'ASD'].country.hist(xrot=90)
  163. # %%
  164. len(df)
  166. # %%
  167. len(df[df.phenotype == 'ASD'])
  169. # %%
  170. n_models = round(len(df[df.phenotype == 'health'])/len(df[df.phenotype == 'ASD']))
  171. n_models
  173. # %%
  174. dfs = []
  175. for i in range(n_models):
  176. dfs.append(pd.concat([df[df.phenotype == 'ASD'], df[df.phenotype == 'health'].sample(len(df[df.phenotype == 'ASD']), random_state=41)]))
  178. # %%
  179. all_metabolites = df.columns[7:]
  181. # %%
  182. feature_importances = []
  183. accuracies = []
  184. specificities = []
  185. sensitivities = []
  186. precisions = []
  187. f1_scores = []
  188. roc_auc_scores = []
  189. all_test = []
  190. all_pred = []
  191. all_probs = []
  192. from statistics import mean
  193. for df in dfs:
  194. X = df[all_metabolites]
  195. y = df.phenotype
  196. X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
  197. clf = RandomForestClassifier(n_estimators=300, max_depth=20, random_state=42)
  198. clf.fit(X_train, y_train)
  199. y_pred = clf.predict(X_test)
  200. y_prob = [ x[0] for x in clf.predict_proba(X_test)]
  201. all_test.extend(y_test)
  202. all_pred.extend(y_pred)
  203. all_probs.extend(y_prob)
  204. tp, fn, fp, tn = confusion_matrix(y_test, y_pred).ravel()
  205. accuracy = (tp+tn)/(tp+fn+fp+tn)
  206. specificity = tn/(tn+fp)
  207. sensitivity = tp/(tp+fn)
  208. precision = tp/(tp+fp)
  209. f1_score = (2*tp)/(2*tp+fp+fn)
  210. roc_auc_score_value = roc_auc_score([int(x) for x in (y_test == 'ASD').tolist()], y_prob)
  211. print('Accuracy:',accuracy, '%')
  212. print('Specificity:',specificity, '%')
  213. print('Sensitivity:',sensitivity, '%')
  214. print('Precision:',precision, '%')
  215. print('F1 Score:',f1_score, '%')
  216. print('ROC AUC score:', roc_auc_score_value)
  217. accuracies.append(accuracy)
  218. specificities.append(specificity)
  219. sensitivities.append(sensitivity)
  220. precisions.append(precision)
  221. f1_scores.append(f1_score)
  222. roc_auc_scores.append(roc_auc_score_value)
  223. importances = clf.feature_importances_
  224. std = np.std([tree.feature_importances_ for tree in clf.estimators_], axis=0)
  225. forest_importances = pd.DataFrame(zip(importances,std), index=all_metabolites, columns=['importance', 'std'])
  226. #forest_importances = forest_importances[forest_importances.importance >= forest_importances.importance.quantile(0.99)]
  227. feature_importances.append(forest_importances)
  228. #sensitivity, specificity, precision, F1-score, ROC-AUC
  229. print("accuracy:", "mean:", mean(accuracies), "std:", np.std(accuracies))
  230. print("specificity:", "mean:", mean(specificities), "std:", np.std(specificities))
  231. print("sensitivity:", "mean:", mean(sensitivities), "std:", np.std(sensitivities))
  232. print("precision:", "mean:", mean(precisions), "std:", np.std(precisions))
  233. print("f1 score:", "mean", mean(f1_scores), "std:", np.std(f1_scores))
  234. print("ROC AUC score:", "mean", mean(roc_auc_scores), "std:", np.std(roc_auc_scores))
  236. # %%
  237. print(classification_report(all_test, all_pred))
  239. # %%
  240. ConfusionMatrixDisplay.from_predictions(all_test, all_pred, normalize='true')
  242. # %%
  243. from sklearn.metrics import roc_curve, roc_auc_score
  244. import matplotlib.pyplot as plt
  246. y_true = [ 1 if x=='ASD' else 0 for x in all_test]
  248. # y_true: true binary labels (0 or 1)
  249. # y_proba: predicted probabilities for the positive class
  250. fpr, tpr, thresholds = roc_curve(y_true, all_probs)
  251. roc_auc = roc_auc_score(y_true, all_probs)
  253. plt.figure()
  254. plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % roc_auc)
  255. plt.plot([0, 1], [0, 1], 'r--') # Diagonal line (random classifier)
  256. plt.xlim([0.0, 1.0])
  257. plt.ylim([0.0, 1.05])
  258. plt.xlabel('False Positive Rate')
  259. plt.ylabel('True Positive Rate')
  260. plt.title('Receiver Operating Characteristic (ROC)')
  261. plt.legend(loc="lower right")
  262. plt.show()
  265. # %%
  266. roc_auc
  268. # %%
  269. df3 = pd.concat(feature_importances)
  270. df3 = df3.groupby(df3.index).mean()
  271. len(df3)
  273. # %%
  274. forest_importances = df3[df3.importance >= df3.importance.quantile(0.95)]
  276. # %%
  277. len(forest_importances)
  279. # %%
  280. print('\n'.join(forest_importances.index.tolist()))
  282. # %%
  283. fig, ax = plt.subplots()
  284. forest_importances.importance.plot.bar(ax=ax, figsize=(15,5))
  285. ax.set_title("Feature importances using MDI")
  286. ax.set_ylabel("Mean decrease in impurity")
  287. fig.tight_layout()
  289. # %%
  290. list(forest_importances.index)
  292. # %% [markdown]
  293. # # Shap Explainer
  295. # %%
  296. feature_importances = []
  297. accuracies = []
  298. from statistics import mean
  299. for df in dfs:
  300. X = df[all_metabolites]
  301. y = df.phenotype
  302. X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
  303. clf = RandomForestClassifier(n_estimators=300, max_depth=20, random_state=0)
  304. clf.fit(X_train, y_train)
  305. y_pred = clf.predict(X_test)
  306. accuracy = sum(y_pred == y_test)/len(y_test)*100
  307. print('Accuracy:',accuracy, '%')
  308. accuracies.append(accuracy)
  309. shap_values = explainer.shap_values(X_test)
  310. feature_importances.append(shap_values)
  311. print("mean accuracy", mean(accuracies), '%')
  313. # %%
  314. feature_importances = np.array(feature_importances)
  316. # %%
  317. shap_values = feature_importances.mean(axis=0)
  319. # %%
  320. shap.summary_plot([shap_values[:,:,0], shap_values[:,:,1]], X_test, max_display=40, plot_type='bar')
  322. # %%
  323. df_important_features = df[list(forest_importances.index) + ['phenotype']].groupby('phenotype').mean()
  325. # %%
  326. df_important_features.head()
  328. # %%
  329. ratios = []
  330. for column in df_important_features.columns:
  331. ratios.append(np.log10(df_important_features.loc['ASD', column]/df_important_features.loc['health', column]))
  333. # %%
  334. df_t = pd.DataFrame(ratios).T
  336. # %%
  337. df_t.columns = df_important_features.columns
  339. # %%
  340. df_t
  342. # %%
  343. ratio = df_t.T
  345. # %%
  346. ratio
  348. # %%
  349. ratio.replace([np.inf, -np.inf], np.nan, inplace=True)
  351. # %%
  352. ratio
  354. # %%
  355. ratio.dropna(how="all", inplace=True)
  357. # %%
  358. ratio
  360. # %%
  361. ratio.columns = ['ratio']
  363. # %%
  364. ratio
  366. # %%
  367. ratio[(ratio.ratio > 0)].plot.bar()
  369. # %%
  370. ratio[(ratio.ratio > 0) & (ratio.ratio < 300)].plot.bar()
  372. # %%
  373. ratio[ratio.ratio < 0].plot.bar()
  375. # %%
  376. ratio.plot.bar(figsize=(15,5))
  378. # %%

Metabolites-Based Classifier for Species-Over 25.ipynb at commit a88e78e, under MIT · at the source

Overview

Authors: Silvia Babolin1, Roberto Enea2, Mariagrazia Cicala3, Daniele Di Giovanni3, Luigi Mazzone1,4, Leonardo Emberti Gialloreti3
  1. Child Neurology and Psychiatry Unit, Department of Wellbeing of Mental and Neurological, Dental and Sensory Organ Health, Policlinico Tor Vergata Hospital, Viale Oxford,00133 Rome, Italy
  2. IMME Research Centre, Via San Francesco d’Assisi 20, 81100 Caserta, Italy
  3. Department of Biomedicine and Prevention, University of Rome Tor Vergata,Via Montpellier 1, 00133 Rome, Italy
  4. Systems Medicine Department, University of Rome Tor Vergata,via Montpellier 1, 00133 Rome, Italy
Institutions: Policlinico Tor Vergata (Italy); University of Rome Tor Vergata (Italy)
Journal: BMC psychiatry, volume 26, issue 1, article 622
Dates: received 15 July 2025; accepted 7 May 2026; published online 8 June 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1186/s12888-026-08178-8 · PMID 42260510 · PMCID PMC13471347 · OpenAlex W7163911025
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: genetics / omics (modality), human (organism), autism (population), clinical / translational (subfield)
Methods: Machine learning, Statistics
Keywords: Autism, Autism spectrum disorder, Gut microbiome, ASD microbiome, Metabolome, ASD biomarker, Machine learning, Brain–gut axis
MeSH: Autism Spectrum Disorder*, Gastrointestinal Microbiome*, Machine Learning*, Biomarkers, Child, Female, Humans, Male, Pilot Projects (* major topic)
Topic: Gut microbiota and health (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Citations: not cited yet (Europe PMC); 97 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 4 matches between paragraphs and lines of code.

dec0der0b/IMPC

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: a88e78ed5649f065bce53f065dae12593c8f7a64, 28 November 2025
Languages: Python (9), Jupyter (3)
Size: 33 files, 12 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, license file, environment (requirements.txt), tests, 3 notebooks
Not found: CITATION.cff, continuous integration, documentation
Tools: pandas (8 files), Matplotlib (3 files), NumPy (3 files), scikit-learn (3 files), seaborn (3 files)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
14 files
At the source: github.com/dec0der0b/IMPC

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;
  • 12 scripts, each with its path and the digest of its content;
  • 4 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

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

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:

  • it points to the authors' code: dec0der0b/IMPC
  • it says that the data are available on request

Read it in the paper: doi.org/10.1186/s12888-026-08178-8.

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, 6 authors, 8 keywords, 9 MeSH terms, 89 references.

Cite

This paper

Babolin, S., Enea, R., Cicala, M., Di Giovanni, D., Mazzone, L., & Emberti Gialloreti, L. (2026). Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study. BMC psychiatry, 26(1), 622. https://doi.org/10.1186/s12888-026-08178-8

BibTeX

@article{babolin2026machine,
author = {Babolin, Silvia and Enea, Roberto and Cicala, Mariagrazia and Di Giovanni, Daniele and Mazzone, Luigi and Emberti Gialloreti, Leonardo},
title = {{Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study}},
journal = {BMC psychiatry},
year = {2026},
month = jun,
volume = {26},
number = {1},
pages = {622},
publisher = {BMC},
issn = {1471-244X},
doi = {10.1186/s12888-026-08178-8},
url = {https://doi.org/10.1186/s12888-026-08178-8},
pmid = {42260510},
pmcid = {PMC13471347}
}

RIS

TY - JOUR
AU - Babolin, Silvia
AU - Enea, Roberto
AU - Cicala, Mariagrazia
AU - Di Giovanni, Daniele
AU - Mazzone, Luigi
AU - Emberti Gialloreti, Leonardo
TI - Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study
T2 - BMC psychiatry
J2 - BMC Psychiatry
PY - 2026
DA - 2026/06/08
VL - 26
IS - 1
SP - 622
SN - 1471-244X
PB - BMC
DO - 10.1186/s12888-026-08178-8
UR - https://doi.org/10.1186/s12888-026-08178-8
LA - en
ER -

CSL-JSON

{
"id": "10.1186/s12888-026-08178-8",
"type": "article-journal",
"title": "Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study",
"container-title": "BMC psychiatry",
"author": [
{
"family": "Babolin",
"given": "Silvia"
},
{
"family": "Enea",
"given": "Roberto"
},
{
"family": "Cicala",
"given": "Mariagrazia"
},
{
"family": "Di Giovanni",
"given": "Daniele"
},
{
"family": "Mazzone",
"given": "Luigi"
},
{
"family": "Emberti Gialloreti",
"given": "Leonardo"
}
],
"container-title-short": "BMC Psychiatry",
"volume": "26",
"issue": "1",
"page": "622",
"DOI": "10.1186/s12888-026-08178-8",
"PMID": "42260510",
"PMCID": "PMC13471347",
"ISSN": "1471-244X",
"publisher": "BMC",
"URL": "https://doi.org/10.1186/s12888-026-08178-8",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
8
]
]
}
}

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:10.1016/j.xcrm.2026.102655 [code]
An integrative multi-omics approach identifies microbiome alterations linked to pathological and behavioral features in autism spectrum disorder.
Journal: Cell reports. Medicine
In common: seaborn, scikit-learn, pandas, 2 other tools, autism, genetics / omics, 2 references
[2] doi:10.3389/fnins.2026.1858005 [code]
Targeted stool metabolomics suggests exploratory catecholamine- and tryptophan-linked metabolic features in autism spectrum disorder.
Journal: Frontiers in neuroscience
In common: autism, clinical / translational, genetics / omics, 4 references
[3] doi:10.3389/fmicb.2026.1811435
Research on the role of gut microbiota metabolites in autism by multi-omics and network pharmacology.
Journal: Frontiers in microbiology
In common: autism, genetics / omics, 4 references
[4] doi:10.1186/s12866-026-05296-x
Gut bacterial characteristics in children with autism spectrum disorder according to symptom severity: a cross-sectional study.
Journal: BMC microbiology
In common: autism, genetics / omics, 4 references
[5] doi:10.3390/nu18152441 [code]
Clinical Improvement and Taxonomic-Functional Gut Microbiome Remodeling After Six Months of Multi-Strain Synbiotic Supplementation in Mexican Children with Autism Spectrum Disorder.
Journal: Nutrients
In common: Matplotlib, NumPy, autism, clinical / translational, 2 references
[6] doi:10.1038/s41380-026-03609-0 [code]
Gut microbiome alterations are sex-dependently associated with brain abnormalities in a mouse model of Neurofibromatosis type I.
Journal: Molecular psychiatry
In common: autism, 3 references
[7] doi:10.3389/fgene.2026.1742595 [code]
An in silico protocol for predicting genetic biomarkers in rare diseases: a case study in sporadic amyotrophic lateral sclerosis.
Journal: Frontiers in genetics
In common: seaborn, scikit-learn, pandas, 2 other tools, clinical / translational, genetics / omics, 1 reference
[8] doi:10.1016/j.ebiom.2026.106291 [code]
Metabolomic signatures of SSRI exposure during neural differentiation and correlation of lysophosphatidylcholines with early symptoms of neurodevelopmental disorders.
Journal: EBioMedicine
In common: genetics / omics, 3 references
[9] doi:10.64898/2026.03.09.710596 [code]
Infant gut microbiomes contribute to metabolic states that impact brain function
Journal: bioRxiv (preprint)
In common: seaborn, scikit-learn, pandas, 2 other tools, 1 reference
[10] doi:10.1093/bib/bbag490 [code]
Systematic benchmarking and optimal strategy selection of cross-species integration methods.
Journal: Briefings in bioinformatics
In common: seaborn, scikit-learn, pandas, 2 other tools, genetics / omics, 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.