OSCR

Personalized Network-Guided Neuromodulation Enhances Human Working Memory.

Code ↔ Paper

9 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 9 matches · 8 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § Materials and Methods › Real‐Time Brain State Decoder ↔ wm_decoding/models/task_pred_model.py, the whole file · a weak match · score 0.83 · ADAM optimizer, decay rate, training steps, TensorFlow, minimizing, batch
  2. [2] § Materials and Methods › Brain Image Processing ↔ wm_targeting/step2_register_sbj_vol_to_native.sh, the whole file · a weak match · score 0.80 · native space, MNI space, FSL, fMRIPrep, resampled, preprocessed
  3. [3] § Materials and Methods › Real‐Time Brain State Decoder ↔ wm_decoding/models/task_pred_model.py, the whole file · a weak match · score 0.77 · Softmax cross entropy, layers, hidden, architecture, LSTM, RNNs
  4. [4] § Materials and Methods › Individualized TMS Targeting ↔ wm_targeting/step3_map_sbj_vol_to_surf.m, the whole file · a weak match · score 0.77 · FC map, cortical surface, targeting map, gyrus, peak, candidate
  5. [5] § Materials and Methods › Brain Image Processing ↔ wm_targeting/step1_get_targeting_sbj_vol.m, the whole file · a weak match · score 0.71 · MNI152NLin2009cAsym, fMRIPrep, MNI space, preprocessed, FreeSurfer
  6. [6] § Materials and Methods › MRI Acquisition ↔ lib/freesurfer/matlab/ssbloch.m, the whole file · a weak match · score 0.65 · High resolution, FA, sequence, coil, echo, TE
  7. [7] § Materials and Methods › Brain Image Processing ↔ wm_targeting/step2_register_sbj_vol_to_native.sh, the whole file · a weak match · score 0.61 · ANTs, FSL, fMRIPrep, spaces
  8. [8] § Materials and Methods › Simultaneous TMS/fMRI Session ↔ lib/freesurfer/matlab/read_siemens_header.m, lines 150–209 · score 0.58 · magnetic field, calibrated, strength, coil, connected, positioned
  9. [9] § Materials and Methods › Brain Image Processing ↔ wm_targeting/step1_get_targeting_sbj_vol.m, the whole file · a weak match · score 0.56 · MNI152NLin2009cAsym, fMRIPrep, FreeSurfer, spaces

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 · 53 lines · 2.7 KB · no license · 2 matches

  1. from base.base_model import BaseModel
  2. import tensorflow as tf
  3. from tensorflow.contrib.rnn import LSTMCell
  6. class TaskPredModel(BaseModel):
  7. def __init__(self, config):
  8. super(TaskPredModel, self).__init__(config)
  9. self.build_model()
  10. self.init_saver()
  12. def build_model(self):
  13. self.x = tf.placeholder(tf.float32, shape=[None] + [self.config.step_num,self.config.fea_num])
  14. self.x_ = [tf.squeeze(t, [1]) for t in tf.split(self.x, self.config.step_num, 1)]
  16. self.y = tf.placeholder(tf.float32, shape=[None] + [self.config.step_num,self.config.output_num])
  18. self.seq_len = tf.placeholder(tf.int32, shape=self.config.batch_size)
  19. #self.y_mask = tf.placeholder(tf.float32, shape=[None] + [self.config.step_num,self.config.output_num])
  22. # network_architecture
  23. self._rnn_cell = tf.contrib.rnn.MultiRNNCell([LSTMCell(self.config.hidden_num) for _ in range(self.config.num_hidden_layers)])
  24. self._rnn_cell = tf.contrib.rnn.DropoutWrapper(self._rnn_cell, output_keep_prob=self.config.dropout_keep_rate)
  26. with tf.variable_scope('rnn'):
  27. (self.z_codes, self.z_state) = tf.contrib.rnn.static_rnn(self._rnn_cell, self.x_, dtype=tf.float32, sequence_length=self.seq_len)
  29. with tf.variable_scope('prediction'):
  30. pred_weight_ = tf.Variable(tf.truncated_normal([self.config.hidden_num, self.config.output_num], dtype=tf.float32), name='pred_weight')
  31. pred_bias_ = tf.Variable(tf.constant(0.1, shape=[self.config.output_num], dtype=tf.float32), name='pred_bias')
  33. z_output_ = tf.transpose(tf.stack(self.z_codes), [1, 0, 2])
  34. z_weight_ = tf.tile(tf.expand_dims(pred_weight_, 0), [self.config.batch_size, 1, 1])
  36. self.y_ = tf.matmul(z_output_, z_weight_) + pred_bias_
  37. self.z_output_ = z_output_
  38. self.pred_weight_ = pred_weight_
  39. self.pred_bias_ = pred_bias_
  41. if self.config.is_training:
  42. with tf.name_scope("loss"):
  43. self.loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=self.y, logits=self.y_))
  45. lr = tf.train.exponential_decay(self.config.learning_rate, self.global_step_tensor,
  46. self.config.decay_steps, self.config.decay_rate, staircase=True)
  47. self.optim = tf.train.AdamOptimizer(lr)
  48. self.train_step = self.optim.minimize(self.loss, global_step=self.global_step_tensor)
  51. def init_saver(self):
  52. # here you initalize the tensorflow saver that will be used in saving the checkpoints.
  53. self.saver = tf.train.Saver(max_to_keep=self.config.max_to_keep)

task_pred_model.py at commit 16c5509, no license · at the source

Overview

Authors: Ahsan Khan1,2,3, Hongming Li4,5, Camille Blaine1,2, Julie Grier1,2, Ethan Hammett1,2, Almaris Figueroa‐Gonzalez1,2, Sarai Garcia1,2, Romain Duprat1,2, Justin Reber1,2, Joseph Deluisi4, Christos Davatzikos4,5, Theodore D. Satterthwaite6,7, Yong Fan4,5, Desmond J. Oathes1,2,8,9
ORCID iDs: Ahsan Khan, Desmond J. Oathes
  1. Center For Brain Imaging and Stimulation Department of Psychiatry Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA
  2. Center For Neuromodulation in Depression and Stress Department of Psychiatry Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA
  3. Department of Education and Psychology Academy of Wellness and Human Development Faculty of Arts and Social Sciences Hong Kong Baptist University Kowloon Tong Hong Kong SAR China
  4. Center For Biomedical Image Computing and Analytics Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA
  5. Center for AI and Data Science for Integrated Diagnostics University of Pennsylvania Philadelphia PA USA
  6. Lifespan Informatics & Neuroimaging Center Department of Psychiatry Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA
  7. Lifespan Brain Institute Children's Hospital of Philadelphia University of Pennsylvania Philadelphia Pennsylvania USA
  8. Penn Brain Science Translation Innovation and Modulation Center University of Pennsylvania Philadelphia Pennsylvania USA
  9. Departments of Neuroscience Bioengineering Neurology and Neurosurgery Perelman School of Medicine University of Pennsylvania Philadelphia Pennsylvania USA
Institutions: Hong Kong Baptist University (Hong Kong SAR China); University of Pennsylvania (United States); Children's Hospital of Philadelphia (United States)
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany), volume 13, issue 49, article e23009
Dates: received 12 November 2025; accepted 28 May 2026; published online 12 June 2026; in print September 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1002/advs.202523009 · PMID 42284508 · PMCID PMC13336854 · OpenAlex W7164489481
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: other (modality), human (organism), cognitive (subfield)
Methods: Connectivity, Statistics, Smoothing, state filtering, decompositions, Preprocessing, Machine learning, fMRI & imaging, Single-unit activity, calcium imaging, Physiology & signal measures
Keywords: brain state decoding, functional brain networks, personalized neuromodulation, transcranial magnetic stimulation, working memory
MeSH: Brain*, Memory, Short-Term*, Nerve Net*, Transcranial Magnetic Stimulation*, Adult, Brain Mapping, Cognitive Enhancement, Cross-Over Studies, Female, Humans, Magnetic Resonance Imaging, Male, Young Adult (* major topic)
Topic: Transcranial Magnetic Stimulation Studies (Neurology, Neuroscience), according to OpenAlex
Funding: NIH; HHS | NIH | National Institute of Mental Health (NIMH) (R01 MH120811 to D.J.O. and Y.F); Hart Fund in Cognitive Neuroscience to D.J.O; Penn‐CHOP Lifespan Brain Institute; AE Foundation; Penn AI2D Center
Citations: not cited yet (Europe PMC); 70 references in the paper

Abstract

The next frontier in cognitive neuromodulation is defined by personalized and adaptive protocols, necessitating approaches tailored to individual functional neuroanatomy and brain‐state fluctuations. Here, we introduce an adaptive neuromodulation framework that integrates individualized network targeting with real‐time decoding of brain states to precisely target working memory functional networks. Using concurrent transcranial magnetic stimulation (TMS) and functional magnetic resonance imaging (fMRI), we first mapped participant‐specific networks and identified personalized targets. A real‐time decoder then tracked stimulation‐evoked neural dynamics to empirically determine the optimal frequency (i.e., the best‐performing within a tested set of 5, 10, and 20 Hz) and a corresponding suboptimal frequency for each individual. In a multi‐session crossover study, only the optimal‐frequency stimulation significantly improved working memory, with the decoder's output predicting behavioral gains. A key finding is the substantial inter‐individual variability in the optimal frequency, providing evidence against the notion of a universal “best” frequency. Our results demonstrate that cognitive enhancement is governed by the precise interaction between stimulation target and frequency. This work provides a causal demonstration of personalized, network‐based neuromodulation and offers proof of concept for a generalizable, biomarker‐driven framework, representing a step toward advancing cognitive therapeutics.

Trial Registration: This study is registered at ClinicalTrials.gov (identifier: NCT04402294).

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 9 matches between paragraphs and lines of code.

hmlicas/Collaborative_Brain_Decomposition

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 6f3ad613d065fe592979e1f105065ed22472e999, 15 May 2020
Languages: MATLAB (363), C++ (6), C (2), C/C++ (1)
Size: 399 files, 372 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: FreeSurfer (36 files), Tools for NIfTI and ANALYZE image (MATLAB) (18 files), Image Processing Toolbox (7 files), Statistics and Machine Learning Toolbox (5 files), GIfTI library for MATLAB (2 files), SPM (2 files), cifti-matlab (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
373 files
At the source: github.com/hmlicas/Collaborative_Brain_Decomposition

zaixucui/pncsinglefuncparcel

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: d9cf211985c8b47ffd9fecc4fa0853487c40f604, 10 August 2020
Languages: MATLAB (101), R (45), Python (33)
Size: 190 files, 179 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: ggplot2 (37 files), NumPy (33 files), SciPy (33 files), Statistics and Machine Learning Toolbox (28 files), GIfTI library for MATLAB (21 files), Connectome Workbench (19 files), FreeSurfer (9 files), scikit-learn (4 files), mgcv (3 files), FieldTrip (1 file), FSL (1 file), Matplotlib (1 file), pandas (1 file), seaborn (1 file), statsmodels (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
180 files
At the source: github.com/ZaixuCui/pncSingleFuncParcel/tree/master/Step_2nd_SingleParcellation

hmlicas/Loop_TMS

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 16c5509d26ed67f413fc09fec315be3404fdee47, 26 June 2025
Languages: Python (15), MATLAB (6), Shell (1)
Size: 29 files, 22 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: TensorFlow (9 files), NumPy (6 files), SciPy (4 files), FSL (2 files), FreeSurfer (1 file), GIfTI library for MATLAB (1 file), Tools for NIfTI and ANALYZE image (MATLAB) (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
23 files
At the source: github.com/hmlicas/Loop_TMS

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;
  • 573 scripts, each with its path and the digest of its content;
  • 9 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 Statement

Data supporting the findings of this study are available from the lead contact (D.J.O.) on reasonable request, subject to a data‐use agreement. The code for computing individualized functional networks is available at https://github.com/hmlicas/Collaborative_Brain_Decomposition and https://github.com/ZaixuCui/pncSingleFuncParcel/tree/master/Step_2nd_SingleParcellation. The analysis code for individualized TMS targeting and brain state decoder is available at https://github.com/hmlicas/Loop_TMS.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 14 authors, 5 keywords, 13 MeSH terms, 6 funders, 67 references.

Cite

This paper

Khan, A., Li, H., Blaine, C., Grier, J., Hammett, E., Figueroa‐Gonzalez, A., Garcia, S., Duprat, R., Reber, J., Deluisi, J., Davatzikos, C., Satterthwaite, T. D., Fan, Y., & Oathes, D. J. (2026). Personalized Network-Guided Neuromodulation Enhances Human Working Memory. Advanced science (Weinheim, Baden-Wurttemberg, Germany), 13(49), e23009. https://doi.org/10.1002/advs.202523009

BibTeX

@article{khan2026personalized,
author = {Khan, Ahsan and Li, Hongming and Blaine, Camille and Grier, Julie and Hammett, Ethan and Figueroa‐Gonzalez, Almaris and Garcia, Sarai and Duprat, Romain and Reber, Justin and Deluisi, Joseph and Davatzikos, Christos and Satterthwaite, Theodore D. and Fan, Yong and Oathes, Desmond J.},
title = {{Personalized Network-Guided Neuromodulation Enhances Human Working Memory}},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = jun,
volume = {13},
number = {49},
pages = {e23009},
publisher = {Wiley},
issn = {2198-3844},
doi = {10.1002/advs.202523009},
url = {https://doi.org/10.1002/advs.202523009},
pmid = {42284508},
pmcid = {PMC13336854}
}

RIS

TY - JOUR
AU - Khan, Ahsan
AU - Li, Hongming
AU - Blaine, Camille
AU - Grier, Julie
AU - Hammett, Ethan
AU - Figueroa‐Gonzalez, Almaris
AU - Garcia, Sarai
AU - Duprat, Romain
AU - Reber, Justin
AU - Deluisi, Joseph
AU - Davatzikos, Christos
AU - Satterthwaite, Theodore D.
AU - Fan, Yong
AU - Oathes, Desmond J.
TI - Personalized Network-Guided Neuromodulation Enhances Human Working Memory
T2 - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
J2 - Adv Sci (Weinh)
PY - 2026
DA - 2026/06/12
VL - 13
IS - 49
SP - e23009
SN - 2198-3844
PB - Wiley
DO - 10.1002/advs.202523009
UR - https://doi.org/10.1002/advs.202523009
LA - en
ER -

CSL-JSON

{
"id": "10.1002/advs.202523009",
"type": "article-journal",
"title": "Personalized Network-Guided Neuromodulation Enhances Human Working Memory",
"container-title": "Advanced science (Weinheim, Baden-Wurttemberg, Germany)",
"author": [
{
"family": "Khan",
"given": "Ahsan"
},
{
"family": "Li",
"given": "Hongming"
},
{
"family": "Blaine",
"given": "Camille"
},
{
"family": "Grier",
"given": "Julie"
},
{
"family": "Hammett",
"given": "Ethan"
},
{
"family": "Figueroa‐Gonzalez",
"given": "Almaris"
},
{
"family": "Garcia",
"given": "Sarai"
},
{
"family": "Duprat",
"given": "Romain"
},
{
"family": "Reber",
"given": "Justin"
},
{
"family": "Deluisi",
"given": "Joseph"
},
{
"family": "Davatzikos",
"given": "Christos"
},
{
"family": "Satterthwaite",
"given": "Theodore D."
},
{
"family": "Fan",
"given": "Yong"
},
{
"family": "Oathes",
"given": "Desmond J."
}
],
"container-title-short": "Adv Sci (Weinh)",
"volume": "13",
"issue": "49",
"page": "e23009",
"DOI": "10.1002/advs.202523009",
"PMID": "42284508",
"PMCID": "PMC13336854",
"ISSN": "2198-3844",
"publisher": "Wiley",
"URL": "https://doi.org/10.1002/advs.202523009",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
12
]
]
}
}

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.1222 [code]
Network-based near-scalp personalized brain stimulation targets.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: Connectome Workbench, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 10 other tools, other, 8 references
[2] doi:10.1038/s41467-026-73668-y [code]
Convergent and divergent brain-cognition development in early adolescence.
Journal: Nature communications
In common: Connectome Workbench, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 13 other tools, 6 references
[3] doi:10.1038/s41467-026-71151-2 [code]
Common and distinct neural correlates of social interaction processing and theory of mind in narratives.
Journal: Nature communications
In common: cifti-matlab, Connectome Workbench, GIfTI library for MATLAB, 13 other tools, cognitive, 6 references
[4] doi:10.1016/j.neuron.2026.04.011 [code]
Precision fMRI reveals densely interdigitated network patches with conserved motifs in the lateral prefrontal cortex.
Journal: Neuron
In common: Connectome Workbench, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 10 other tools, 8 references
[5] doi:10.1002/epi.70323 [code]
Individual-specific resting-state networks predict language dominance in drug-resistant epilepsy.
Journal: Epilepsia
In common: Connectome Workbench, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 10 other tools, 5 references
[6] doi:10.21203/rs.3.rs-9326213/v1 [code]
Multi-task fMRI outperforms resting-state fMRI for revealing task-invariant organization of the human brain
Journal: Research Square (preprint)
In common: Connectome Workbench, GIfTI library for MATLAB, FreeSurfer, 9 other tools, cognitive, 7 references
[7] doi:10.1038/s41586-026-10631-3 [code]
A prognostic human brain network for diffuse midline glioma.
Journal: Nature
In common: cifti-matlab, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 13 other tools, 2 references
[8] doi:10.1038/s41467-026-76452-0 [code]
Music evokes shared neural representations of imagined narratives across sensory modalities.
Journal: Nature communications
In common: Connectome Workbench, GIfTI library for MATLAB, Tools for NIfTI and ANALYZE image (MATLAB), 13 other tools, cognitive, 2 references
[9] doi:10.1038/s41467-026-76011-7 [code]
Human cortex organizes dynamic co-fluctuations along the sensorimotor-association axis.
Journal: Nature communications
In common: mgcv, Connectome Workbench, GIfTI library for MATLAB, 10 other tools, 4 references
[10] doi:10.1093/psyrad/kkag013 [code]
Convergent and divergent spatial topographies of individualized brain functional networks and their developmental origins.
Journal: Psychoradiology
In common: cifti-matlab, mgcv, Connectome Workbench, 7 other tools, 7 references

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.