OSCR

NeuroStream: an interactive platform for exploratory visualization and harmonization of multicohort brain MRI data.

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] § 3 Results › 3.1 Performance and usability ↔ deta.py, lines 75–134 · score 0.64 · log transformation, intracranial volume, log1p, ComBat, score, ICV
  2. [2] § 3 Results › 3.1 Performance and usability ↔ app.py, lines 25–82 · score 0.61 · log transformation, intracranial volume, log1p, score, Selection, ComBat
  3. [3] § 2 Methods › 2.3 Data handling and preprocessing ↔ deta.py, lines 75–134 · score 0.52 · Log transformation, log1p, score
  4. [4] § 2 Methods › 2.3 Data handling and preprocessing ↔ app.py, lines 25–82 · score 0.52 · Log transformation, log1p, score, preprocessing

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 · 152 lines · 5 KB · no license · 2 matches

  1. import os
  2. import numpy as np
  3. import pandas as pd
  4. import streamlit as st
  6. from sklearn.preprocessing import (
  7. OneHotEncoder,
  8. PowerTransformer,
  9. StandardScaler
  10. )
  11. from pycombat import Combat
  12. from PIL.Image import open
  14. path='./assets'
  16. ind=[
  17. 'C_ID','epid','session_id','R_ID','session','ck_dcode','AS_DATA_CLASS','AS_EDATE'
  18. ]
  20. exotic=["cretn_tr1","cretn_tr2"]
  21. grouper="cohort"
  23. @st.cache_data
  24. def read(deta_path=path) -> pd.DataFrame:
  25. deta_files = [q.path for q in os.scandir(deta_path) if q.name.endswith(".f")]
  26. if not deta_files:
  27. raise FileNotFoundError("No .f files found in assets directory.")
  28. df = pd.concat([pd.read_feather(p) for p in deta_files], axis=0)
  30. cols_to_drop = [c for c in ind if c in df.columns]
  31. if cols_to_drop:
  32. df = df.drop(columns=cols_to_drop)
  33. return df
  35. @st.cache_data
  36. def get_col(deta) -> tuple:
  37. deta_site = deta.loc[:, grouper].unique()
  39. deta_cov_col = [q for q in deta.columns if q.startswith('cov_') or q.lower() == 'age']
  40. deta_contigous_col = deta.select_dtypes(include=[float, int]).columns.to_list()
  42. deta_vol_col = [
  43. q for q in deta_contigous_col
  44. if str(q)[-1].isnumeric() and q not in exotic and q not in deta_cov_col
  45. ]
  47. deta_categorical_col = [
  48. c for c in deta.columns
  49. if c not in deta_vol_col and c.lower() != 'age' and c.lower() != 'cov_age'
  50. ]
  52. if grouper not in deta_categorical_col:
  53. deta_categorical_col.append(grouper)
  55. return deta_site, deta_categorical_col, deta_contigous_col, deta_vol_col
  57. @st.cache_data
  58. def get_var(deta=None) -> tuple:
  59. if deta is None:
  60. deta = read()
  61. deta.index = range(deta.shape[0])
  62. site, cat, cont, vol = get_col(deta)
  63. return deta, site, cat, cont, vol
  65. @st.cache_data
  66. def safe_log1p(df: pd.DataFrame, cols, eps=1e-6, do_zscore=False):
  67. X = df.loc[:, cols].to_numpy(dtype=float)
  68. mins = X.min(axis=0)
  69. shift = np.where(mins <= 0, -mins + eps, 0.0)
  70. X_log = np.log1p(X + shift)
  71. if do_zscore:
  72. X_log = StandardScaler().fit_transform(X_log)
  73. return pd.DataFrame(X_log, columns=cols)
  75. @st.cache_data
  76. def transform(
  77. deta: pd.DataFrame,
  78. how: str,
  79. deta_contigous_col: list,
  80. deta_vol_col: list,
  81. covariates: list = None
  82. ) -> pd.DataFrame:
  83. final = deta.copy()
  85. if how == "Log Transform (log1p)":
  86. final[deta_vol_col] = np.log1p(deta[deta_vol_col])
  87. elif how == "Log Transform + Z-score":
  88. logged = np.log1p(deta[deta_vol_col])
  89. final[deta_vol_col] = pd.DataFrame(
  90. StandardScaler().fit_transform(logged),
  91. columns=deta_vol_col,
  92. index=deta.index
  93. )
  94. elif how == "Scale (Z-score)":
  95. final[deta_vol_col] = pd.DataFrame(
  96. StandardScaler().fit_transform(deta[deta_vol_col]),
  97. columns=deta_vol_col,
  98. index=deta.index
  99. )
  100. elif "Combat" in how:
  101. if not covariates:
  102. Xc = None
  103. else:
  104. cov_t_list = []
  105. for col in covariates:
  106. if deta[col].dtype in ['int64', 'int32'] or deta[col].nunique() < 10:
  107. coder = OneHotEncoder(sparse_output=False, drop='first')
  108. encoded = coder.fit_transform(deta[[col]])
  109. cov_t_list.append(encoded)
  110. else:
  111. pt = PowerTransformer()
  112. scaled = pt.fit_transform(deta[[col]].astype(float))
  113. cov_t_list.append(scaled)
  114. Xc = np.concatenate(cov_t_list, axis=1).astype("f4") if cov_t_list else None
  116. stabiliser = Combat()
  117. X = deta.loc[:, deta_vol_col].to_numpy(dtype=float)
  118. Xb = deta.loc[:, grouper].to_numpy(dtype="U16")
  120. Xt = PowerTransformer().fit_transform(X)
  121. Xts = stabiliser.fit_transform(Xt, Xb, None, Xc)
  123. final[deta_vol_col] = Xts
  125. elif how == "divided by intracranial volume":
  126. icv_cols = [c for c in deta.columns if "icv" in c.lower()]
  127. if not icv_cols:
  128. raise ValueError("ICV column not found")
  129. icv_col = icv_cols[0]
  130. vol_no_icv = [c for c in deta_vol_col if c != icv_col]
  131. final[vol_no_icv] = deta.loc[:, vol_no_icv].div(deta[icv_col], axis=0)
  133. final.index = deta.index
  134. return final
  136. @st.cache_data
  137. def get_noe_image(deta_path=path)->dict:
  138. return {q.name.replace('.png',''):open(q.path) for q in os.scandir(deta_path) if q.name.endswith('.png')}
  141. @st.cache_data
  142. def trim(deta, deta_vol_col, gizun=.001) -> pd.DataFrame:
  143. final = deta.copy()
  144. deta_vol_col = [q for q in final.columns if q in deta_vol_col]
  146. for col in deta_vol_col:
  147. lower = final[col].quantile(gizun)
  148. upper = final[col].quantile(1 - gizun)
  150. final.loc[(final[col] < lower) | (final[col] > upper), col] = np.nan
  152. return final.dropna(subset=deta_vol_col)

deta.py at commit 1874414, no license · at the source

Overview

Authors: Myeongji Cho1, Byung Soo Park1, Hye Ryeong Nam1, Jae Pil Jeon2, Sang Cheol Kim1
ORCID iDs: Myeongji Cho, Sang Cheol Kim
  1. Division of Healthcare and Artificial Intelligence, Department of Precision Medicine, National Institute of Health, Korea Disease Control and Prevention Agency, Cheongju-si 28159, Republic of Korea
  2. Department of Precision Medicine, National Institute of Health, Korea Disease Control and Prevention Agency, Cheongju-si 28159, Republic of Korea
Institutions: Korea National Institute of Health (South Korea); Korea Disease Control and Prevention Agency (South Korea)
Journal: Bioinformatics advances, volume 6, issue 1, article vbag117
Dates: received 28 January 2026; accepted 20 April 2026; published online 26 April 2026
Type: Brief report · Language: English
License: CC BY
Identifiers: DOI 10.1093/bioadv/vbag117 · PMID 42109578 · PMCID PMC13152653 · OpenAlex W7156091540
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), methods / tools (subfield)
Methods: Statistics, Smoothing, state filtering, decompositions, Preprocessing, fMRI & imaging
Journal subjects: Application Note, Data Visualization
Topic: Functional Brain Connectivity Studies (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: National Institute of Health (NIH) (2024-NI-010–02)
Citations: not cited yet (Europe PMC); 7 references in the paper

Abstract

Motivation: Large-scale neuroimaging studies increasingly integrate brain MRI data from multiple cohorts and acquisition sites. Exploratory visualization and harmonization are essential for identifying batch effects, assessing preprocessing strategies, and preserving biologically meaningful variation. However, existing tools are often cohort-specific, rely on static visualizations, or separate harmonization from data exploration.

Results: We present NeuroStream, an interactive application for real-time visualization and harmonization of multicohort brain MRI quantitative data. Built using the Streamlit framework, NeuroStream enables the exploration of quantitative imaging features derived from structural MRI along with demographic and clinical variables. The platform supports preprocessing and harmonization options, including log transformation, intracranial volume normalization, and ComBat-based batch correction, which can be compared interactively using dynamic visualizations. NeuroStream provides principal component analysis, distributional plots, and group comparison statistics. In addition, the platform supports covariate-adjusted regression-based evaluation of site effects and residual diagnostics, enabling quantitative and visual assessment of cohort-related variability across preprocessing settings. All visualizations presented in this manuscript were generated using transformed example datasets designed to illustrate the functionality of the platform, rather than to report original subject-level measurements, while NeuroStream itself supports direct analysis of user-provided tabular data. Using transformed example datasets derived from BICWALZS and KoGES multicohort MRI data, we demonstrate intuitive inspection of batch-related variance and harmonization outcomes without custom scripting.

Availability and implementation: NeuroStream is implemented in Python and freely available at https://github.com/NIHxAI/NeuroStream.

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 4 matches between paragraphs and lines of code.

NIHxAI/NeuroStream

License: none: the authors keep all their rights
State: the link answers, verified on 30 September 2026
Evidence: files inventoried
Commit: 187441493b919f2f13243b250c08ca070d6d14f7, 16 March 2026
Languages: Python (3)
Size: 25 files, 3 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, environment (requirements.txt)
Not found: license file, CITATION.cff, tests, continuous integration, documentation
Tools: pandas (3 files), NumPy (2 files), scikit-learn (2 files), Matplotlib (1 file), Pillow (1 file), Pingouin (1 file), Plotly (1 file), SciPy (1 file), seaborn (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 30 September 2026: the link answers
  • 30 September 2026: the link answers
4 files
At the source: github.com/NIHxAI/NeuroStream

Availability and implementation

NeuroStream is implemented in Python and freely available at https://github.com/NIHxAI/NeuroStream.

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:

  • 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;
  • 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.

Data availability

The NeuroStream source code and documentation are publicly available at: https://github.com/NIHxAI/NeuroStream.

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, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 1 funder, 6 references.

Cite

This paper

Cho, M., Park, B. S., Nam, H. R., Jeon, J. P., & Kim, S. C. (2026). NeuroStream: an interactive platform for exploratory visualization and harmonization of multicohort brain MRI data. Bioinformatics advances, 6(1), vbag117. https://doi.org/10.1093/bioadv/vbag117

BibTeX

@article{cho2026neurostream,
author = {Cho, Myeongji and Park, Byung Soo and Nam, Hye Ryeong and Jeon, Jae Pil and Kim, Sang Cheol},
title = {{NeuroStream: an interactive platform for exploratory visualization and harmonization of multicohort brain MRI data}},
journal = {Bioinformatics advances},
year = {2026},
month = apr,
volume = {6},
number = {1},
pages = {vbag117},
publisher = {Oxford University Press},
issn = {2635-0041},
doi = {10.1093/bioadv/vbag117},
url = {https://doi.org/10.1093/bioadv/vbag117},
pmid = {42109578},
pmcid = {PMC13152653}
}

RIS

TY - JOUR
AU - Cho, Myeongji
AU - Park, Byung Soo
AU - Nam, Hye Ryeong
AU - Jeon, Jae Pil
AU - Kim, Sang Cheol
TI - NeuroStream: an interactive platform for exploratory visualization and harmonization of multicohort brain MRI data
T2 - Bioinformatics advances
J2 - Bioinform Adv
PY - 2026
DA - 2026/04/26
VL - 6
IS - 1
SP - vbag117
SN - 2635-0041
PB - Oxford University Press
DO - 10.1093/bioadv/vbag117
UR - https://doi.org/10.1093/bioadv/vbag117
LA - en
ER -

CSL-JSON

{
"id": "10.1093/bioadv/vbag117",
"type": "article-journal",
"title": "NeuroStream: an interactive platform for exploratory visualization and harmonization of multicohort brain MRI data",
"container-title": "Bioinformatics advances",
"author": [
{
"family": "Cho",
"given": "Myeongji"
},
{
"family": "Park",
"given": "Byung Soo"
},
{
"family": "Nam",
"given": "Hye Ryeong"
},
{
"family": "Jeon",
"given": "Jae Pil"
},
{
"family": "Kim",
"given": "Sang Cheol"
}
],
"container-title-short": "Bioinform Adv",
"volume": "6",
"issue": "1",
"page": "vbag117",
"DOI": "10.1093/bioadv/vbag117",
"PMID": "42109578",
"PMCID": "PMC13152653",
"ISSN": "2635-0041",
"publisher": "Oxford University Press",
"URL": "https://doi.org/10.1093/bioadv/vbag117",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
26
]
]
}
}

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.1269 [code]
From early to contemporary normative modeling: Mapping individual differences in neurophysiological signals.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: Pingouin, Plotly, statsmodels, 6 other tools, 2 references
[2] doi:10.1002/alz.71649 [code]
Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: Pingouin, Plotly, Pillow, 7 other tools, structural MRI / diffusion
[3] doi:10.1016/j.isci.2026.116825 [code]
Social hierarchy shapes behavioral and transcriptional responses to chronic stress and ketamine in male mice.
Journal: iScience
In common: Pingouin, Plotly, Pillow, 7 other tools
[4] doi:10.1523/eneuro.0041-26.2026 [code]
Ocular Speech Tracking Persists in Blindness, but Its Dynamics and Oculo-Cerebral Connectivity Depend on Visual Status.
Journal: eNeuro
In common: Pingouin, Plotly, Pillow, 7 other tools
[5] doi:10.7554/elife.103097 [code]
Canonical neurodevelopmental trajectories of structural and functional manifolds.
Journal: eLife
In common: Pingouin, Plotly, statsmodels, 4 other tools, structural MRI / diffusion, 2 references
[6] doi:10.1371/journal.pmed.1004809 [code]
Brain morphology in Anorexia Nervosa and its subtypes: A multi-cohort study of individual participant data.
Journal: PLoS medicine
In common: Plotly, Pillow, statsmodels, 6 other tools, structural MRI / diffusion, 1 reference
[7] doi:10.1038/s41467-026-74462-6 [code]
Neural similarity between choice options predicts group-level context effects.
Journal: Nature communications
In common: Pingouin, Pillow, statsmodels, 6 other tools, 1 reference
[8] doi:10.1038/s41598-026-48496-1 [code]
A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points.
Journal: Scientific reports
In common: Plotly, Pillow, statsmodels, 6 other tools, methods / tools, structural MRI / diffusion
[9] doi:10.1002/ana.78203 [code]
AI-Driven Mapping of Seizure Spread Patterns.
Journal: Annals of neurology
In common: Pingouin, Pillow, statsmodels, 6 other tools, structural MRI / diffusion
[10] doi:10.1186/s13059-026-04125-8 [code]
MLMarker: a machine learning framework for tissue inference and biomarker discovery.
Journal: Genome biology
In common: Plotly, Pillow, statsmodels, 6 other tools, methods / tools

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.