OSCR

Spatial pattern-driven interpretable model and biological correlates in brain glioblastoma-lymphoma differentiation.

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. [1] § STAR★Methods › Method details › Radiomics and spatial feature extraction ↔ neuroHarmonize/harmonizationApply.py, lines 10–116 · score 0.69 · neuroCombat, spline, harmonisation, covariates, training, variable
  2. [2] § STAR★Methods › Method details › Radiomics and spatial feature extraction ↔ neuroHarmonize/harmonizationLearn.py, lines 10–78 · score 0.65 · neuroCombat, harmonisation, adjustment, covariates, variable, batch

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 · 257 lines · 9.4 KB · MIT · 1 match

  1. import os
  2. import pickle
  3. import numpy as np
  4. import pandas as pd
  5. import nibabel as nib
  6. from statsmodels.gam.api import BSplines
  7. from neuroCombat.neuroCombat import make_design_matrix, adjust_data_final
  8. import copy
  10. def harmonizationApply(data, covars, model, return_stand_mean=False):
  11. """
  12. Applies harmonization model with neuroCombat functions to new data.
  14. Arguments
  15. ---------
  16. data : a numpy array
  17. data to harmonize with ComBat, dimensions are N_samples x N_features
  19. covars : a pandas DataFrame
  20. contains covariates to control for during harmonization
  21. all covariates must be encoded numerically (no categorical variables)
  22. must contain a single column "SITE" with site labels for ComBat
  23. dimensions are N_samples x (N_covariates + 1)
  25. model : a dictionary of model parameters
  26. the output of a call to harmonizationLearn()
  28. Returns
  29. -------
  31. bayes_data : a numpy array
  32. harmonized data, dimensions are N_samples x N_features
  34. """
  35. # transpose data as per ComBat convention
  36. data = data.T
  37. # prep covariate data
  38. batch_col = covars.columns.get_loc('SITE')
  39. isTrainSite = covars['SITE'].isin(model['SITE_labels'])
  40. cat_cols = []
  41. num_cols = [covars.columns.get_loc(c) for c in covars.columns if c!='SITE']
  42. covars = np.array(covars, dtype='object')
  44. if "ref_level" in model["info_dict"]:
  45. ref_level = model["info_dict"]["ref_level"]
  46. else:
  47. ref_level = None
  49. # load the smoothing model
  50. smooth_model = model['smooth_model']
  51. smooth_cols = smooth_model['smooth_cols']
  53. ### additional setup code from neuroCombat implementation:
  54. # convert training SITEs in batch col to integers
  55. site_dict = dict(zip(model['SITE_labels'], np.arange(len(model['SITE_labels']))))
  56. covars[:,batch_col] = np.vectorize(site_dict.get)(covars[:,batch_col],-1)
  58. # compute samples_per_batch for training data
  59. sample_per_batch = [np.sum(covars[:,batch_col]==i) for i in list(site_dict.values())]
  60. sample_per_batch = np.asarray(sample_per_batch)
  62. # create dictionary that stores batch info
  63. batch_levels = np.unique(list(site_dict.values()),return_counts=False)
  64. info_dict = {
  65. 'batch_levels': batch_levels.astype('int'),
  66. 'n_batch': len(batch_levels),
  67. 'n_sample': int(covars.shape[0]),
  68. 'sample_per_batch': sample_per_batch.astype('int'),
  69. 'batch_info': [list(np.where(covars[:,batch_col]==idx)[0]) for idx in batch_levels],
  70. 'ref_level': ref_level
  71. }
  72. covars[~isTrainSite, batch_col] = 0
  73. covars[:,batch_col] = covars[:,batch_col].astype(int)
  74. ###
  75. # isolate array of data in training site
  76. # apply ComBat without re-learning model parameters
  77. design = make_design_matrix(covars, batch_col, cat_cols, num_cols, ref_level)
  78. design[~isTrainSite,0:len(model['SITE_labels'])] = np.nan
  79. ### additional setup if smoothing is performed
  80. if smooth_model['perform_smoothing']:
  81. # create cubic spline basis for smooth terms
  82. X_spline = covars[:, smooth_cols].astype(float)
  83. bs_basis = smooth_model['bsplines_constructor'].transform(X_spline)
  84. # construct formula and dataframe required for gam
  85. formula = 'y ~ '
  86. df_gam = {}
  87. for b in batch_levels:
  88. formula = formula + 'x' + str(b) + ' + '
  89. df_gam['x' + str(b)] = design[:, b]
  90. for c in num_cols:
  91. if c not in smooth_cols:
  92. formula = formula + 'c' + str(c) + ' + '
  93. df_gam['c' + str(c)] = covars[:, c].astype(float)
  94. formula = formula[:-2] + '- 1'
  95. df_gam = pd.DataFrame(df_gam)
  96. # for matrix operations, a modified design matrix is required
  97. design = np.concatenate((df_gam, bs_basis), axis=1)
  99. ###
  100. s_data, stand_mean, var_pooled, mod_mean = applyStandardizationAcrossFeatures(data, design, info_dict, model)
  101. if sum(isTrainSite)==0:
  102. bayes_data = np.full(s_data.shape,np.nan)
  103. else:
  104. bayes_data = adjust_data_final(s_data, design, model['gamma_star'], model['delta_star'],
  105. stand_mean, mod_mean, var_pooled, info_dict, data)
  106. bayes_data[:,~isTrainSite] = np.nan
  108. # transpose data to return to original shape
  109. stand_mean = stand_mean.T
  110. bayes_data = bayes_data.T
  112. #return either bayes_data or both
  113. if return_stand_mean:
  114. return bayes_data, stand_mean
  115. else:
  116. return bayes_data
  119. def applyStandardizationAcrossFeatures(X, design, info_dict, model):
  120. """
  121. The original neuroCombat function standardize_across_features plus
  122. necessary modifications.
  124. This function will apply a pre-trained harmonization model to new data.
  125. """
  127. n_batch = info_dict['n_batch']
  128. n_sample = info_dict['n_sample']
  129. sample_per_batch = info_dict['sample_per_batch']
  131. B_hat = model['B_hat']
  132. stand_mean = model['stand_mean'][:, [0]]
  133. var_pooled = model['var_pooled']
  135. # new code in neuroCombat to compute model mean
  136. if design is not None:
  137. tmp = copy.deepcopy(design)
  138. tmp[:,range(0,n_batch)] = 0
  139. mod_mean = np.transpose(np.dot(tmp, B_hat))
  141. s_data = ((X- stand_mean - mod_mean) / np.dot(np.sqrt(var_pooled), np.ones((1, n_sample))))
  143. return s_data, stand_mean, var_pooled, mod_mean
  145. def applyModelOne(data, covars, model, return_stand_mean=False):
  146. """
  147. Utility function to apply model to one data point.
  148. """
  149. if data.shape[0]>1:
  150. raise ValueError('Argument `data` contains more than one sample!')
  151. if covars.shape[0]>1:
  152. raise ValueError('Argument `covars` contains more than one sample!')
  153. if model['smooth_model']['perform_smoothing']:
  154. raise NotImplementedError(
  155. '[neuroHarmonize] applyModelOne does not support models trained with '
  156. 'smooth_terms. Use flattenNIFTIs + harmonizationApply instead.')
  157. # transpose data as per ComBat convention
  158. X = data.T
  159. # prep covariate data
  160. batch_labels = model['SITE_labels']
  161. batch_i = covars.SITE.to_numpy()[0]
  162. isTrainSite = covars['SITE'].isin(model['SITE_labels'])
  164. if batch_i not in batch_labels:
  165. # raise ValueError('Site Label "%s" not in the training set. Check `covars` argument.' % batch_i)
  166. batch_level_i = np.array([0])
  167. else:
  168. batch_level_i = np.argwhere(batch_i==batch_labels)[0]
  170. if "ref_level" in model["info_dict"]:
  171. ref_level = model["info_dict"]["ref_level"]
  172. else:
  173. ref_level = None
  175. batch_col = covars.columns.get_loc('SITE')
  176. cat_cols = []
  177. num_cols = [covars.columns.get_loc(c) for c in covars.columns if c!='SITE']
  178. covars = np.array(covars, dtype='object')
  180. # convert batch col to integer
  181. covars[:,batch_col] = np.unique(covars[:,batch_col],return_inverse=True)[-1]
  183. # apply design matrix construction (needs to be modified)
  184. # design_i = make_design_matrix(covars, batch_col, cat_cols, num_cols)
  185. design_i = make_design_matrix(covars, batch_col, cat_cols, num_cols, ref_level)
  187. # encode batches as in larger dataset
  188. design_i_batch = np.zeros((1, len(batch_labels)))
  189. design_i_batch[:, batch_level_i] = 1
  190. design_i = np.concatenate((design_i_batch, design_i[:, 1:]), axis=1)
  192. design_i[~isTrainSite,0:len(model['SITE_labels'])] = np.nan
  194. # additional setup with batch info
  195. n_sample = 1
  196. sample_per_batch = 1
  197. D = design_i
  198. n_batch = len(batch_labels)
  199. j = batch_level_i[0]
  201. B_hat = model['B_hat']
  202. stand_mean = model['stand_mean'][:, [0]]
  203. var_pooled = model['var_pooled']
  205. # new code in neuroCombat to compute model mean
  206. if design_i is not None:
  207. tmp = copy.deepcopy(design_i)
  208. tmp[:,range(0,n_batch)] = 0
  209. mod_mean = np.transpose(np.dot(tmp, B_hat))
  211. s_data = (X- stand_mean - mod_mean) / np.dot(np.sqrt(var_pooled), np.ones((1, n_sample)))
  213. if sum(isTrainSite)==0:
  214. bayesdata = np.full(s_data.shape,np.nan)
  215. else:
  216. # adjust_data_final
  217. batch_design = D[:,:n_batch]
  219. bayesdata = s_data
  220. gamma_star = np.array(model['gamma_star'])
  221. delta_star = np.array(model['delta_star'])
  223. dsq = np.sqrt(delta_star[j, :])
  224. dsq = dsq.reshape((len(dsq), 1))
  225. denom = np.dot(dsq, np.ones((1, sample_per_batch)))
  226. numer = np.array(bayesdata - np.dot(batch_design, gamma_star).T)
  228. bayesdata = numer / denom
  230. vpsq = np.sqrt(var_pooled).reshape((len(var_pooled), 1))
  231. bayesdata = bayesdata * np.dot(vpsq, np.ones((1, n_sample))) + stand_mean + mod_mean
  233. # preserve original data for reference batch (mirrors adjust_data_final)
  234. if ref_level is not None and batch_level_i[0] == ref_level:
  235. bayesdata = X
  237. # return either bayesdata or both
  238. if return_stand_mean:
  239. # Return the complete reference (stand_mean + mod_mean) for NIFTI output
  240. reference_mean = stand_mean + mod_mean
  241. return bayesdata.T, reference_mean.T
  242. else:
  243. return bayesdata.T
  244. # return bayesdata.T
  246. def loadHarmonizationModel(file_name):
  247. """
  248. For loading model contents, this function will load a model specified
  249. by file_name using the pickle package.
  250. """
  251. if not os.path.exists(file_name):
  252. raise ValueError('Model file does not exist: %s. Did you run `saveHarmonizationModel`?' % file_name)
  253. in_file = open(file_name,'rb')
  254. model = pickle.load(in_file)
  255. in_file.close()
  257. return model

harmonizationApply.py at commit 89ef77f, under MIT · at the source

Overview

Authors: Yi Wang1,2, Haohui Chen3, Kaiyan Su1, Jianrui Li4, Tianliang Zhan5,4, Lingyu Kong6, Qiang Xu4, Gaoping Liu7, Xiaorui Su8, Wei You6, Jianguo Xia2, Ji Zhang2, Weizhong Tian2, Wei Liao9, Qiang Yue8, Bing Zhang7, Weihua Liao6, Wei Xing10, Dante Mantini11, Guangming Lu4, Zhiqiang Zhang1,4,3, Multi-Centre Cooperative Clinical Study Group for “Lesion-Phenotype Brain Mapping in Brain Tumours”
ORCID iDs: Zhiqiang Zhang
  1. Department of Radiology, Jinling Clinical Medical College, Nanjing Medical University, Nanjing 210002, China
  2. Department of Radiology, The Affiliated Taizhou People’s Hospital of Nanjing Medical University, Taizhou School of Clinical Medicine, Nanjing Medical University, Taizhou 225300, China
  3. Department of Radiology, Jinling Clinical Medical College, Nanjing University of Chinese Medicine, Nanjing 210002, China
  4. Department of Radiology, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing 210002, China
  5. Department of Radiology, General Hospital of Center Theater of PLA, Wuhan 430070, China
  6. Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, China
  7. Department of Radiology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing 210008, China
  8. Department of Radiology, West China Hospital of Sichuan University, Chengdu 610041, China
  9. The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China
  10. Department of Radiology, Third Affiliated Hospital of Soochow University, Changzhou 213003, China
  11. Movement Control and Neuroplasticity Research Group, Biomedical Sciences, KU Leuven, 3001 Leuven, Belgium
Institutions: Taizhou People's Hospital (China); Nanjing Medical University (China); Nanjing University of Chinese Medicine (China); Nanjing General Hospital of Nanjing Military Command (China); Nanjing University (China); Chinese People's Liberation Army (China); General Hospital of Central Theater Command; Central South University (China); Xiangya Hospital Central South University (China); Nanjing Drum Tower Hospital (China); West China Hospital of Sichuan University (China); University of Electronic Science and Technology of China (China); Soochow University (China); KU Leuven (Belgium)
Journal: iScience, volume 29, issue 9, article 117281
Dates: received 12 January 2026; accepted 5 August 2026; published online 21 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1016/j.isci.2026.117281 · PMID 42668694 · PMCID PMC13524760 · OpenAlex W7203882140
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: genetics / omics (modality), human (organism), other condition (population)
Methods: Connectivity, Statistics, Smoothing, state filtering, decompositions, Machine learning, Preprocessing, Graphs
Keywords: glioblastoma, primary central nervous system lymphoma, tumor probabilistic maps, spatial radiomics, transcriptomics
Topic: Radiomics and Machine Learning in Medical Imaging (Radiology, Nuclear Medicine and Imaging, Medicine), according to OpenAlex
Funding: National Natural Science Foundation of China (82127806, 2018YFA0701703); Nanjing Medical University; National Key Research and Development Program of China (2018YFA0701703, 82127806)
Citations: not cited yet (Europe PMC); 58 references in the paper

Abstract

Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) often exhibit overlapping appearances on routine MRI, complicating pre-treatment diagnosis. In 1,109 patients from five centers, we constructed standard-space tumor probabilistic maps and derived atlas-anchored spatial features to augment conventional radiomics. The spatial radiomics classifier outperformed radiomics alone (external test area under the ROC curve [AUC], 0.98) with acceptable calibration and decision curve benefit, and SHapley Additive exPlanations (SHAP)-enabled anatomy-grounded interpretation. Aligning tumor localization with the Allen Human Brain Atlas and a normative functional connectome linked GBM-enriched territories to developmental-oncogenic programs and network hubness, whereas PCNSL-enriched territories showed immune-inflammatory/proliferative programs, and associations with network hubness did not survive spatial-autocorrelation correction. These results provide shareable reference maps and an interpretable, multicenter-generalizing tool for GBM-PCNSL differentiation, while offering biological context for diagnosis-specific location susceptibility.

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

Repositories

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

JLhos-fmri/SPLSM_version1.0

License: GPL-3.0
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 7ec072a17c4804036eea90f163f075289d755038, 4 August 2023
Languages: MATLAB (57)
Size: 109 files, 57 scripts
Software Heritage: not archived
Found in: “Data and code availability”
Holds: README, license file
Not found: CITATION.cff, environment file, tests, continuous integration, documentation
Tools: SPM (10 files), Image Processing Toolbox (9 files), Statistics and Machine Learning Toolbox (4 files)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
59 files
At the source: github.com/JLhos-fmri/SPLSM_version1.0

JLhos-fmri/ClinicalFrequencyAnalysisToolkit

License: GPL-3.0
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 8fcc568032378fc1709f4a01bfe7fae6bc99b025, 29 July 2022
Languages: MATLAB (23)
Size: 76 files, 23 scripts
Software Heritage: not archived
Found in: “Data and code availability”
Holds: license file
Not found: README, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: SPM (9 files), Image Processing Toolbox (1 file), Statistics and Machine Learning Toolbox (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
24 files
At the source: github.com/JLhos-fmri/ClinicalFrequencyAnalysisToolkit

rpomponio/neuroHarmonize

License: MIT
State: the link answers, verified on 26 September 2026
Evidence: files inventoried
Commit: 89ef77fa44c7c5f11113e22f766cc66a9776af71, 13 September 2026
Languages: Python (10)
Size: 24 files, 10 scripts
Software Heritage: not archived
Found in: “Data and code availability”
Holds: README, license file, environment (pyproject.toml, setup.py), tests, continuous integration
Not found: CITATION.cff, documentation
Tools: NumPy (8 files), pandas (7 files), neuroHarmonize (4 files), NiBabel (4 files), neuroCombat (3 files), statsmodels (3 files)
Availability: 1 check, the latest on 26 September 2026: the link answers
  • 26 September 2026: the link answers
12 files
At the source: github.com/rpomponio/neuroHarmonize

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:

  • 3 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 90 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

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

Data and code availability

Data supporting the findings are provided within the article and its supplemental information. Raw center-specific MRI scans cannot be made publicly available because of ethics committee/IRB restrictions and patient privacy considerations. De-identified derived data generated in this study, including lesion masks, feature matrices, tumor probability maps, and model-output files, are available from the corresponding author upon reasonable request and completion of a data-use agreement. Publicly available group-level resources used for biological contextualization include the AHBA microarray dataset (https://human.brain-map.org/static/download) and the UK Biobank group-ICA resting-state dataset (access subject to UK Biobank terms; https://www.fmrib.ox.ac.uk/ukbiobank/).

The Standard sPace Lesion-Symptom Mapping (SPLSM) pipeline (version 1.0 beta), developed by our team and openly available at https://github.com/JLhos-fmri/SPLSM_version1.0, was used for MNI normalization, generation of tumor probabilistic maps, voxel-wise q-statistics, and atlas-anchored spatial feature extraction. The JHU-189 atlas used to derive the 189 atlas-anchored spatial features is implemented within the Clinical Frequency Analysis Toolkit and is available at https://github.com/JLhos-fmri/ClinicalFrequencyAnalysisToolkit. Radiomics feature extraction used PyRadiomics v3.0.1 (https://pyradiomics.readthedocs.io/), batch harmonization used neuroHarmonize v2.4.5 (https://github.com/rpomponio/neuroHarmonize), and additional tools included SPM12 (https://www.fil.ion.ucl.ac.uk/spm/), abagen (https://github.com/rmarkello/abagen), and the Brain Connectivity Toolbox (https://sites.google.com/site/bctnet/).

This study did not generate microarray or RNA-seq datasets, and no standalone software package was generated.

Any additional information required to reanalyze the data reported in this paper is available from the lead contact upon reasonable request.

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 2, 28 September 2026

  • Authors: added Zhiqiang Zhang (0000-0002-3993-7330); removed Zhiqiang Zhang
  • Funding: added National Natural Science Foundation of China: 82127806, 2018YFA0701703; Nanjing Medical University; National Key Research and Development Program of China: 2018YFA0701703, 82127806

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 22 authors, 5 keywords, 58 references.

Cite

This paper

Wang, Y., Chen, H., Su, K., Li, J., Zhan, T., Kong, L., Xu, Q., Liu, G., Su, X., You, W., Xia, J., Zhang, J., Tian, W., Liao, W., Yue, Q., Zhang, B., Liao, W., Xing, W., Mantini, D., . . . Multi-Centre Cooperative Clinical Study Group for “Lesion-Phenotype Brain Mapping in Brain Tumours”. (2026). Spatial pattern-driven interpretable model and biological correlates in brain glioblastoma-lymphoma differentiation. iScience, 29(9), 117281. https://doi.org/10.1016/j.isci.2026.117281

BibTeX

@article{wang2026spatial,
author = {Wang, Yi and Chen, Haohui and Su, Kaiyan and Li, Jianrui and Zhan, Tianliang and Kong, Lingyu and Xu, Qiang and Liu, Gaoping and Su, Xiaorui and You, Wei and Xia, Jianguo and Zhang, Ji and Tian, Weizhong and Liao, Wei and Yue, Qiang and Zhang, Bing and Liao, Weihua and Xing, Wei and Mantini, Dante and Lu, Guangming and Zhang, Zhiqiang and {Multi-Centre Cooperative Clinical Study Group for “Lesion-Phenotype Brain Mapping in Brain Tumours”}},
title = {{Spatial pattern-driven interpretable model and biological correlates in brain glioblastoma-lymphoma differentiation}},
journal = {iScience},
year = {2026},
month = aug,
volume = {29},
number = {9},
pages = {117281},
publisher = {Elsevier},
issn = {2589-0042},
doi = {10.1016/j.isci.2026.117281},
url = {https://doi.org/10.1016/j.isci.2026.117281},
pmid = {42668694},
pmcid = {PMC13524760}
}

RIS

TY - JOUR
AU - Wang, Yi
AU - Chen, Haohui
AU - Su, Kaiyan
AU - Li, Jianrui
AU - Zhan, Tianliang
AU - Kong, Lingyu
AU - Xu, Qiang
AU - Liu, Gaoping
AU - Su, Xiaorui
AU - You, Wei
AU - Xia, Jianguo
AU - Zhang, Ji
AU - Tian, Weizhong
AU - Liao, Wei
AU - Yue, Qiang
AU - Zhang, Bing
AU - Liao, Weihua
AU - Xing, Wei
AU - Mantini, Dante
AU - Lu, Guangming
AU - Zhang, Zhiqiang
AU - Multi-Centre Cooperative Clinical Study Group for “Lesion-Phenotype Brain Mapping in Brain Tumours”
TI - Spatial pattern-driven interpretable model and biological correlates in brain glioblastoma-lymphoma differentiation
T2 - iScience
J2 - iScience
PY - 2026
DA - 2026/08/21
VL - 29
IS - 9
SP - 117281
SN - 2589-0042
PB - Elsevier
DO - 10.1016/j.isci.2026.117281
UR - https://doi.org/10.1016/j.isci.2026.117281
LA - en
ER -

CSL-JSON

{
"id": "10.1016/j.isci.2026.117281",
"type": "article-journal",
"title": "Spatial pattern-driven interpretable model and biological correlates in brain glioblastoma-lymphoma differentiation",
"container-title": "iScience",
"author": [
{
"family": "Wang",
"given": "Yi"
},
{
"family": "Chen",
"given": "Haohui"
},
{
"family": "Su",
"given": "Kaiyan"
},
{
"family": "Li",
"given": "Jianrui"
},
{
"family": "Zhan",
"given": "Tianliang"
},
{
"family": "Kong",
"given": "Lingyu"
},
{
"family": "Xu",
"given": "Qiang"
},
{
"family": "Liu",
"given": "Gaoping"
},
{
"family": "Su",
"given": "Xiaorui"
},
{
"family": "You",
"given": "Wei"
},
{
"family": "Xia",
"given": "Jianguo"
},
{
"family": "Zhang",
"given": "Ji"
},
{
"family": "Tian",
"given": "Weizhong"
},
{
"family": "Liao",
"given": "Wei"
},
{
"family": "Yue",
"given": "Qiang"
},
{
"family": "Zhang",
"given": "Bing"
},
{
"family": "Liao",
"given": "Weihua"
},
{
"family": "Xing",
"given": "Wei"
},
{
"family": "Mantini",
"given": "Dante"
},
{
"family": "Lu",
"given": "Guangming"
},
{
"family": "Zhang",
"given": "Zhiqiang"
},
{
"literal": "Multi-Centre Cooperative Clinical Study Group for “Lesion-Phenotype Brain Mapping in Brain Tumours”"
}
],
"container-title-short": "iScience",
"volume": "29",
"issue": "9",
"page": "117281",
"DOI": "10.1016/j.isci.2026.117281",
"PMID": "42668694",
"PMCID": "PMC13524760",
"ISSN": "2589-0042",
"publisher": "Elsevier",
"URL": "https://doi.org/10.1016/j.isci.2026.117281",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
21
]
]
}
}

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/s41586-026-10631-3 [code]
A prognostic human brain network for diffuse midline glioma.
Journal: Nature
In common: SPM, Image Processing Toolbox, NiBabel, 3 other tools, other condition, 4 references
[2] doi:10.1038/s41598-026-56688-y [code]
On the value of radiomics in addition to clinical measures in emotional conflict fMRI for predicting sertraline response in major depressive disorder.
Journal: Scientific reports
In common: neuroHarmonize, SPM, NiBabel, 3 other tools, 2 references
[3] doi:10.1038/s41398-026-04426-3 [code]
Resting-state brain age is associated with cognitive and sensorimotor abnormalities in schizophrenia spectrum disorders: a validation & longitudinal study.
Journal: Translational psychiatry
In common: neuroHarmonize, neuroCombat, NiBabel, 3 other tools, 1 reference
[4] doi:10.1038/s41467-026-73072-6 [code]
Mapping the spatiotemporal continuum of structural connectivity development across the human connectome in youth.
Journal: Nature communications
In common: neuroHarmonize, neuroCombat, NiBabel, 3 other tools, 1 reference
[5] doi:10.1038/s41467-026-74153-2 [code]
Regional, functional and transcriptomic decoding of multidimensional brain structure alterations in obsessive-compulsive disorder.
Journal: Nature communications
In common: neuroCombat, SPM, NiBabel, 3 other tools, genetics / omics, other condition, 1 reference
[6] doi:10.1371/journal.pone.0343722 [code]
Comprehensive methodology for sample enrichment in EEG biomarker studies for Alzheimer's risk classification.
Journal: PloS one
In common: neuroHarmonize, neuroCombat, statsmodels, 2 other tools, 1 reference
[7] doi:10.1038/s41398-026-03965-z [code]
Disentangling individual heterogeneity reveals robust network and molecular signatures of major depressive disorder with suicidal ideation.
Journal: Translational psychiatry
In common: SPM, NiBabel, statsmodels, 3 other tools, genetics / omics, 2 references
[8] doi:10.1016/j.nicl.2026.104012 [code]
Structural-functional multilayer brain network properties and outcome of combined repetitive transcranial magnetic stimulation and psychotherapy for obsessive-compulsive disorder.
Journal: NeuroImage. Clinical
In common: SPM, Image Processing Toolbox, NiBabel, 4 other tools, other condition, 1 reference
[9] doi:10.1038/s41593-026-02359-0 [code]
The cross-site reproducibility of MRI morphometric phenotypes in psychiatric disorders.
Journal: Nature neuroscience
In common: neuroCombat, SPM, Image Processing Toolbox, 4 other tools
[10] doi:10.1371/journal.pbio.3003856 [code]
Aging and metabolism contribute separately to brain-body health.
Journal: PLoS biology
In common: SPM, Image Processing Toolbox, NiBabel, 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.