OSCR

DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification.

Code ↔ Paper

7 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 7 matches · 2 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § Methods › Models training and tuning ↔ 4_models_training.py, lines 49–99 · score 0.87 · multi layer perceptron, logistic regression, decision tree, random forest, model training, Bayes
  2. [2] § Results › Simple ML models can outperform more complex algorithms ↔ 4_models_training.py, lines 49–99 · score 0.70 · multi layer perceptron, logistic regression, Models Training, SVC, score
  3. [3] § Methods › Data characteristics – pancancer classifier ↔ config/api_config.py, the whole file · a weak match · score 0.67 · bone marrow, tumor grade, age, metastatic, platform, diagnosis
  4. [4] § Results › Applicability of pancancer classifier for non-invasive cancer detection ↔ config/api_config.py, the whole file · a weak match · score 0.60 · bone marrow, primary tumor, field, human, metastasis, diagnostics
  5. [5] § Methods › Data characteristics – pancancer classifier ↔ 1_collect_samples.py, lines 142–153 · score 0.56 · acute myeloid leukemia, diagnosis
  6. [6] § Methods › Anomaly detection ↔ 3_build_frames.py, lines 349–381 · score 0.51 · Local Outlier Factor, fitted, LOF, neighbors, training
  7. [7] § Results › Simple ML models can outperform more complex algorithms ↔ 4_models_training.py, lines 21–46 · score 0.50 · balanced accuracy, Model training, outer, folds, inner, BACC

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 · 106 lines · 3.4 KB · MIT · 3 matches

  1. import configparser
  2. from os.path import join, exists
  3. from collections import defaultdict
  5. import joblib
  6. import numpy as np
  7. import pandas as pd
  8. from prefect import flow, task
  10. from sklearn.model_selection import GridSearchCV
  11. from sklearn.model_selection import StratifiedGroupKFold
  12. from sklearn.metrics import balanced_accuracy_score
  14. from src.models import mlp, nb, knn, dct, ext, rf, lr, svc
  17. config = configparser.ConfigParser()
  18. config.read("config/config.ini")
  21. @task(log_prints=True)
  22. def evaluate(X, y, grouping_factor, model, p_grid) -> list:
  23. outer_cv = StratifiedGroupKFold(n_splits=5, shuffle=True, random_state=101)
  24. inner_cv = StratifiedGroupKFold(n_splits=3, shuffle=True, random_state=101)
  25. scoring = []
  27. for cnt, (train_index, test_index) in enumerate(
  28. outer_cv.split(X, y, grouping_factor)
  29. ):
  30. X_train, y_train = X.iloc[train_index], y.iloc[train_index]
  31. X_test, y_test = X.iloc[test_index], y.iloc[test_index]
  32. print(f"Fold {cnt} --> {X_train.shape} - {X_test.shape}")
  34. grid_search = GridSearchCV(
  35. model, p_grid, scoring="balanced_accuracy", cv=inner_cv, n_jobs=3
  36. )
  37. grid_search.fit(X_train, y_train, groups=grouping_factor.iloc[train_index])
  38. print(f"Fold {cnt} --> Best params = {grid_search.best_params_}")
  40. predicted = grid_search.predict(X_test)
  41. bacc = balanced_accuracy_score(y_test, predicted)
  42. print(f"Fold {cnt} --> BACC = {bacc:.2f}")
  43. scoring.append(bacc)
  45. print(f"Average BACC --> {np.mean(scoring):.2f} +- {np.std(scoring):.2f}")
  46. return scoring
  49. @flow(name="Train models", log_prints=True)
  50. def train_models(outcome: str, stats_output: str, mt: str):
  51. X_train = pd.read_parquet(
  52. join(config["DIRECTORY TREE"]["trainData"], "X_cleaned_reduced.parquet")
  53. )
  55. if mt in ["l", "g"]:
  56. print(f"Filtering for {mt} markers")
  57. X_train = X_train[[var for var in X_train.columns if var.endswith(mt)]]
  59. elif mt == "raw":
  60. print(f"Filtering for {mt} markers")
  61. X_train = X_train[[var for var in X_train.columns if (not var.endswith("l")) and (not var.endswith("g"))]]
  63. else:
  64. print(f"Using combined dataset")
  65. mt = "combined"
  67. print(f"Training using {X_train.shape}")
  69. y_train = pd.read_csv(
  70. join(config["DIRECTORY TREE"]["trainData"], "sample_sheet.csv")
  71. ).set_index("Sample_Name")
  72. y_train = y_train.loc[X_train.index, ["case_id", outcome]]
  74. grouping_factor = y_train.case_id
  75. y_train = y_train[outcome]
  77. models = [mlp, lr, nb, knn, dct, ext, rf, svc]
  78. names = [
  79. "Multi-layer Perceptron",
  80. "Logistic Regression",
  81. "Naive Bayes",
  82. "K-Neighbors",
  83. "Decision Tree",
  84. "Extra Trees",
  85. "Random Forest",
  86. "SVC",
  87. ]
  89. scoring = defaultdict(list)
  90. for model, name in zip(models, names):
  91. print(f"Model --> {name}")
  92. model, p_grid = model()
  93. print(f"Parameters grid --> {p_grid}")
  95. scores = evaluate(X_train, y_train, grouping_factor, model, p_grid)
  96. scoring[name].extend(scores)
  98. scoring = pd.DataFrame(scoring)
  99. scoring.to_csv(join(config["FILES"][stats_output], f"scoring_{mt}.csv"))
  102. if __name__ == "__main__":
  103. #train_models("Sample_Group", "models_stats_path", "raw")
  104. #train_models("Sample_Group", "models_stats_path", "l")
  105. #train_models("Sample_Group", "models_stats_path", "g")
  106. train_models("Sample_Group", "models_stats_path", "combined")

4_models_training.py at commit f9e1692, under MIT · at the source

Overview

Authors: Jan Bińkowski1,2, Tomasz K. Wojdacz1,2
  1. Independent Clinical Epigenetics Laboratory, Pomeranian Medical University in Szczecin,Szczecin, Poland
  2. Regional Center for Digital Medicine, Pomeranian Medical University in Szczecin,Aleja Powstańców Wielkopolskich 72, Szczecin, 71-899 Poland
Institutions: Pomeranian Medical University (Poland); University of Szczecin (Poland)
Journal: Genome medicine, volume 18, issue 1, article 66
Dates: received 19 August 2025; accepted 3 April 2026; published online 19 May 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1186/s13073-026-01650-w · PMID 42152108 · PMCID PMC13185202 · OpenAlex W4413992593
Open access: gold, a free copy (OpenAlex)
Preprint: doi:10.21203/rs.3.rs-7408332/v1
Status: code verified
Categories: genetics / omics (modality), human (organism), other condition (population), clinical / translational (subfield)
Methods: Machine learning, Statistics
Keywords: DNA methylation, Machine-learning, Biomarkers, Cancer, Classification
MeSH: Biomarkers, Tumor*, DNA Methylation*, Neoplasms*, Algorithms, Classification Algorithms, Humans, Machine Learning, Prediction Algorithms, Predictive Learning Models (* major topic)
Topic: Cancer Genomics and Diagnostics (Cancer Research, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: Narodowe Centrum Nauki (2021/43/B/NZ2/02979)
Citations: cited by 2 papers (Europe PMC); 86 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.

Repositories

Its files are read in the Code ↔ Paper reader above, with 7 matches between paragraphs and lines of code.

ClinicalEpigeneticsLaboratory/accs-brain-model

License: Apache-2.0
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: ea5171c569734cb34201bc7cd97717c251f9dc65, 30 July 2025
Languages: R (4), Python (2)
Size: 19 files, 6 scripts
Software Heritage: not archived
Found in: “Availability of data and materials”
Holds: README, license file, environment (Dockerfile, requirements.txt)
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: Plotly (3 files), randomForest (2 files), ggplot2 (1 file), NumPy (1 file), pandas (1 file), SciPy (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
8 files
At the source: github.com/ClinicalEpigeneticsLaboratory/accs-brain-model

ClinicalEpigeneticsLaboratory/accs-workflows

License: MIT
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: f9e1692e02b064f370e94b97fdf0de8bc1681c4d, 31 July 2025
Languages: Python (10)
Size: 16 files, 10 scripts
Software Heritage: not archived
Found in: “Availability of data and materials”
Holds: README, license file, environment (poetry.lock, pyproject.toml)
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: pandas (6 files), NumPy (5 files), scikit-learn (5 files), SciPy (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
12 files
At the source: github.com/ClinicalEpigeneticsLaboratory/accs-workflows

Zenodo 19072004

License: CC-BY-4.0
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: “Availability of data and materials”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: pandas (6 files), NumPy (5 files), scikit-learn (5 files), SciPy (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
  • 28 September 2026: the link answers (HTTP 200)
12 files
At the source:

Zenodo 19071942

License: CC-BY-4.0
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Size: 1 file
Software Heritage: not checked
Found in: the references
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: pandas (6 files), NumPy (5 files), scikit-learn (5 files), SciPy (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
  • 28 September 2026: the link answers (HTTP 200)
12 files
At the source:

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:

  • 4 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 36 scripts, each with its path and the digest of its content;
  • 7 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:

Read it in the paper: doi.org/10.1186/s13073-026-01650-w.

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, 2 authors, 5 keywords, 9 MeSH terms, 1 funder, 81 references.

Cite

This paper

Bińkowski, J., & Wojdacz, T. K. (2026). DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification. Genome medicine, 18(1), 66. https://doi.org/10.1186/s13073-026-01650-w

BibTeX

@article{binkowski2026dna,
author = {Bińkowski, Jan and Wojdacz, Tomasz K.},
title = {{DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification}},
journal = {Genome medicine},
year = {2026},
month = may,
volume = {18},
number = {1},
pages = {66},
publisher = {BMC},
issn = {1756-994X},
doi = {10.1186/s13073-026-01650-w},
url = {https://doi.org/10.1186/s13073-026-01650-w},
pmid = {42152108},
pmcid = {PMC13185202}
}

RIS

TY - JOUR
AU - Bińkowski, Jan
AU - Wojdacz, Tomasz K.
TI - DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification
T2 - Genome medicine
J2 - Genome Med
PY - 2026
DA - 2026/05/19
VL - 18
IS - 1
SP - 66
SN - 1756-994X
PB - BMC
DO - 10.1186/s13073-026-01650-w
UR - https://doi.org/10.1186/s13073-026-01650-w
LA - en
ER -

CSL-JSON

{
"id": "10.1186/s13073-026-01650-w",
"type": "article-journal",
"title": "DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification",
"container-title": "Genome medicine",
"author": [
{
"family": "Bińkowski",
"given": "Jan"
},
{
"family": "Wojdacz",
"given": "Tomasz K."
}
],
"container-title-short": "Genome Med",
"volume": "18",
"issue": "1",
"page": "66",
"DOI": "10.1186/s13073-026-01650-w",
"PMID": "42152108",
"PMCID": "PMC13185202",
"ISSN": "1756-994X",
"publisher": "BMC",
"URL": "https://doi.org/10.1186/s13073-026-01650-w",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
19
]
]
}
}

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:10.1093/bioinformatics/btag592 [code]
Network-based stratification of allele-specific expression reveals patient subgroups in Huntington's disease.
Journal: Bioinformatics (Oxford, England)
In common: randomForest, Plotly, ggplot2, 4 other tools, genetics / omics, other condition
[2] doi:10.1038/s41467-026-77170-3 [code]
DNA methylation profiling identifies long-range epigenetic silencing of clustered protocadherins as a key determinant of meningioma progression.
Journal: Nature communications
In common: randomForest, ggplot2, genetics / omics, other condition, 3 references
[3] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: randomForest, Plotly, ggplot2, 4 other tools
[4] doi:10.1038/s41467-026-75723-0 [code]
Spatial transcriptomics reveals distinct cell type dynamics following opioid dependence in female mice with the common human μ-opioid receptor variant Oprm1 A118G.
Journal: Nature communications
In common: randomForest, ggplot2, scikit-learn, 3 other tools, genetics / omics, other condition
[5] doi:10.1016/j.xcrm.2026.102682 [code]
TET CpG sequence-context-specific DNA demethylation shapes progression of IDH-mutant gliomas.
Journal: Cell reports. Medicine
In common: ggplot2, pandas, NumPy, genetics / omics, other condition, 3 references
[6] doi:10.1016/j.isci.2026.115329 [code]
Brain metastases converge on shared geometric architecture and transcriptomic landscape yet remain distinct from gliomas.
Journal: iScience
In common: ggplot2, scikit-learn, pandas, 2 other tools, clinical / translational, genetics / omics, other condition, 1 reference
[7] doi:10.1038/s41514-026-00443-0 [code]
Network-based discovery of regulatory drivers of cognitive decline in alzheimer's disease.
Journal: npj aging
In common: Plotly, ggplot2, scikit-learn, 3 other tools, 1 reference
[8] doi:10.7554/elife.103097 [code]
Canonical neurodevelopmental trajectories of structural and functional manifolds.
Journal: eLife
In common: Plotly, ggplot2, scikit-learn, 3 other tools, 1 reference
[9] doi:10.1038/s41467-026-71719-y [code]
Brain functional-structural gradient coupling reflects development, behavior and genetic influences.
Journal: Nature communications
In common: ggplot2, scikit-learn, pandas, 2 other tools, 2 references
[10] doi:10.34133/csbj.0042 [code]
Using Steady-State Visual Evoked Potentials to Characterize Wide-Ranging Retinopathy Linked to <i>CRB1</i>: Implications for Clinical Trials.
Journal: Computational and structural biotechnology journal
In common: Plotly, ggplot2, scikit-learn, 3 other tools, clinical / translational, other condition

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.