OSCR

ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states.

Code ↔ Paper

6 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 6 matches · 3 of them tie a paragraph to a whole file without given lines: weak matches, whose lines are not tinted
  1. [1] § Materials and methods › ADInteractome: gene interactions discovery from neural interaction states › Formulating neural interaction states from neural networks ↔ transformer/celluformer.py, the whole file · a weak match · score 0.70 · binary classification, classify cells, expressed gene, vocabulary, dimensional, embedding · Report a mismatch
  2. [2] § Results › Neural interaction states reflect Alzheimer's disease-associated gene–gene interactions ↔ evaluation/plot_reference_bubble.py, lines 36 to 83 · score 0.64 · BioGRID, CS CORE, CelluFormer, Pearson, NES, filtered · Report a mismatch
  3. [3] § Materials and methods › Virtual knock-out knock-in experiment for evaluating the hypothesis generated by ADInteractome ↔ transformer/celluformer.py, the whole file · a weak match · score 0.60 · binary classification, attention heads, genes expressed, Celluformer, layers, seq · Report a mismatch
  4. [4] § Results › Neural interaction states reflect Alzheimer's disease-associated gene–gene interactions ↔ co-expression/pearson_correlation/pearson_correlation.bash, the whole file · a weak match · score 0.59 · Pearson correlation, co expression, Python, trained, cell · Report a mismatch
  5. [5] § Materials and methods › ADInteractome: gene interactions discovery from neural interaction states › Enrichment analysis of ranked gene–gene interactions ↔ evaluation/gsea_random.py, lines 110 to 140 · score 0.56 · normalized enrichment score, BioGRID, NES · Report a mismatch
  6. [6] § Materials and methods › ADInteractome: gene interactions discovery from neural interaction states › Enrichment analysis of ranked gene–gene interactions ↔ transformer/main.py, lines 34 to 39 · score 0.52 · L6 CT, SEA AD, Car3, NP, Chandelier, L5 · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 55 lines · 2 KB · no license · 2 matches

  1. """CelluFormer model for single-cell gene expression classification."""
  3. import torch.nn as nn
  6. class CelluFormer(nn.Module):
  7. """Transformer-based model for classifying cells from sparse gene expression data.
  9. The model embeds variable-length gene sequences (non-zero expressed genes),
  10. scales embeddings by expression values, processes them through a transformer
  11. encoder, and classifies via mean-pooled representations.
  13. Args:
  14. num_genes: Total number of genes in the vocabulary.
  15. embedding_dim: Dimension of gene embeddings.
  16. dim_feedforward: Hidden dimension of the transformer feedforward network.
  17. head: Number of attention heads.
  18. depth: Number of transformer encoder layers.
  19. dropout: Dropout probability.
  20. """
  22. def __init__(self, num_genes, embedding_dim=128, dim_feedforward=512, head=8, depth=4, dropout=.1):
  23. super(CelluFormer, self).__init__()
  24. self.emb = nn.Embedding(num_genes+1, embedding_dim, padding_idx=0)
  25. nn.init.uniform_(self.emb.weight, a=-1.0/num_genes, b=1.0/num_genes)
  26. self.emb.weight.data[0].fill_(0)
  28. self.encoder_layer = nn.TransformerEncoderLayer(
  29. d_model=embedding_dim,
  30. nhead=head,
  31. batch_first=True,
  32. dropout=dropout,
  33. dim_feedforward=dim_feedforward
  34. )
  35. self.encoder = nn.TransformerEncoder(self.encoder_layer, num_layers=depth)
  37. self.output = nn.Linear(embedding_dim, 2)
  39. def forward(self, seq, vals):
  40. """Forward pass.
  42. Args:
  43. seq: Gene index sequences of shape (batch_size, seq_len).
  44. Indices are 1-based (0 is padding).
  45. vals: Expression values of shape (batch_size, seq_len).
  47. Returns:
  48. Logits of shape (batch_size, 2) for binary classification.
  49. """
  50. x = self.emb(seq)
  51. x = x * vals.unsqueeze(2)
  52. x = self.encoder(x)
  53. x_pooled = x.mean(dim=1)
  55. return self.output(x_pooled)

celluformer.py at commit 4344f0e, no license · at the source

Overview

Authors: Yifan Wu1, Neha Maurya2, Yuntao Yang3, Wenbo Chen2, Guanchu Wang4, Zirui Liu5, Xia Hu6, W Jim Zheng2, Zhaozhuo Xu7
ORCID iDs: Yifan Wu, Neha Maurya, Yuntao Yang, Wenbo Chen, Guanchu Wang, Zirui Liu, Xia Hu, W Jim Zheng, Zhaozhuo Xu
  1. College of Science and Engineering, University of Minnesota Twin Cities, Mayo D528, 420 Delaware St SE, Minneapolis, MN 55455, United States
  2. McWilliams School of Biomedical Informatics, UTHealth Houston, 7000 Fannin St, Suite 600, Houston, TX 77030, United States
  3. MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX 77030, United States
  4. Department of Computer Science, University of North Carolina at Charlotte, Woodward Hall, 9201 University City Blvd, Charlotte, NC 28223, United States
  5. Department of Computer Science & Engineering, University of Minnesota Twin Cities, 4-192 Keller Hall, 200 Union Street SE, Minneapolis, MN 55455, United States
  6. Department of Computer Science, Rice University, Duncan Hall 3122, 6100 Main Street, Houston, TX 77005, United States
  7. School of Computing, Stevens Institute of Technology, Gateway Center North, 1 Castle Point Terrace, Hoboken, NJ 07030, United States
Institutions: University of Minnesota (United States); The University of Texas Health Science Center at Houston (United States); The University of Texas MD Anderson Cancer Center (United States); University of North Carolina at Charlotte (United States); Rice University (United States); Stevens Institute of Technology (United States)
Journal: Briefings in bioinformatics, volume 27, issue 6, article bbag601
Dates: received 20 January 2026; accepted 24 September 2026; published online 2 November 2026; in print November 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1093/bib/bbag601 · PMID 42969854 · PMCID PMC13725928 · OpenAlex W7225089996
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: genetics / omics (modality), human (organism), Alzheimer's / dementia (population), cellular / molecular (subfield)
Methods: Statistics, Machine learning, Connectivity
Keywords: gene interactions, Alzheimer’s disease, neural interaction states
MeSH: Alzheimer Disease*, Cell Nucleus*, Epistasis, Genetic*, Gene Regulatory Networks*, Neural Networks, Computer*, RNA-Seq*, Brain, Humans, RNA, Small Nuclear, Sequence Analysis, RNA, Single-Cell Gene Expression Analysis (* major topic)
Journal subjects: Problem Solving Protocol
Topic: Single-cell and spatial transcriptomics (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: National Science Foundation (2451398, 2450524); national institutes of health (1UL1TR003167, 1UM1TR004906-01, 1R01AG066749, 1U24MH130988-01, 5R56AG069880-02); U.S. Department of Defense (W81XWH-22-1-0164, 1R01AR081280-01A1, 5R01AG074283-04); Cancer Prevention and Research Institute of Texas (RP170668); Cancer Prevention & Research Institute of Texas (CPRIT) (RP210045, RP260802)
Citations: not cited yet (Europe PMC); 56 references in the paper

Abstract

Alzheimer’s disease (AD) is a prevalent neurodegenerative disorder characterized by amyloid β plaques and tau tangles, yet its molecular mechanisms remain elusive. Advances in single-nucleus RNA sequencing (snRNA-seq) have provided profound insights into the cellular heterogeneity of AD-associated brains. In this study, we introduce ADInteractome, an interpretable artificial intelligence framework designed to discover gene interactions associated with AD directly from the internal state of neural networks trained on the snRNA-seq data of brain cells. The method is based on the intuition that if a neural network can accurately classify cells from AD and non-AD donors based on their snRNA-seq data, then its internal interaction states, reflecting interaction patterns within the gene expression data, are informative for identifying biologically meaningful gene interactions. Applied to a large-scale snRNA-seq dataset from the Seattle Alzheimer’s Disease Brain Cell Atlas, ADInteractome reveals cell-type-specific and AD-associated gene circuits supported by existing literature. The results were further supported by our virtual knock-out and knock-in experiments, a novel concept to probe our findings through a data-driven approach. Compared with traditional co-expression network methods, it achieves stronger enrichment for known AD-associated gene interactions and uncovers novel interaction patterns. These findings highlight the potential of interpretable AI approaches for elucidating complex molecular interactions in neurodegenerative disease.

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 6 matches between paragraphs and lines of code.

Evan810828/ADInteractome

License: none: the authors keep all their rights
State: the link answers, verified on 3 November 2026
Evidence: files inventoried
Commit: 4344f0e906ac4a585e449032b7687676dee8970f, 2 November 2026
Languages: Python (42), Shell (6)
Size: 73 files, 48 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: PyTorch (28 files), NumPy (23 files), pandas (16 files), Scanpy (15 files), scikit-learn (10 files), anndata (8 files), Matplotlib (6 files), SciPy (4 files), h5py (1 file), seaborn (1 file), Hugging Face Transformers (1 file)
Availability: 1 check, the latest on 3 November 2026: the link answers
  • 3 November 2026: the link answers
49 files
At the source: github.com/Evan810828/ADInteractome

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;
  • 48 scripts, each with its path and the digest of its content;
  • 6 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 SEA-AD snRNA-seq data analyzed in this study are publicly available at the https://sea-ad-single-cell-profiling.s3.amazonaws.com/index.html#MTG/RNAseq/previous_objects/. Detailed descriptions of the model architectures and dataset configurations are provided in the Supplementary Information. The ADInteractome source code, environment specification, and usage instructions are publicly available at https://github.com/Evan810828/ADInteractome.

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, 3 November 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 9 authors, 3 keywords, 11 MeSH terms, 5 funders, 49 references.

Cite

This paper

Wu, Y., Maurya, N., Yang, Y., Chen, W., Wang, G., Liu, Z., Hu, X., Zheng, W. J., & Xu, Z. (2026). ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states. Briefings in bioinformatics, 27(6), bbag601. https://doi.org/10.1093/bib/bbag601

BibTeX

@article{wu2026adinteractome,
author = {Wu, Yifan and Maurya, Neha and Yang, Yuntao and Chen, Wenbo and Wang, Guanchu and Liu, Zirui and Hu, Xia and Zheng, W Jim and Xu, Zhaozhuo},
title = {{ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states}},
journal = {Briefings in bioinformatics},
year = {2026},
month = nov,
volume = {27},
number = {6},
pages = {bbag601},
publisher = {Oxford University Press},
issn = {1467-5463},
doi = {10.1093/bib/bbag601},
url = {https://doi.org/10.1093/bib/bbag601},
pmid = {42969854},
pmcid = {PMC13725928}
}

RIS

TY - JOUR
AU - Wu, Yifan
AU - Maurya, Neha
AU - Yang, Yuntao
AU - Chen, Wenbo
AU - Wang, Guanchu
AU - Liu, Zirui
AU - Hu, Xia
AU - Zheng, W Jim
AU - Xu, Zhaozhuo
TI - ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states
T2 - Briefings in bioinformatics
J2 - Brief Bioinform
PY - 2026
DA - 2026/11/01
VL - 27
IS - 6
SP - bbag601
SN - 1467-5463
PB - Oxford University Press
DO - 10.1093/bib/bbag601
UR - https://doi.org/10.1093/bib/bbag601
LA - en
ER -

CSL-JSON

{
"id": "10.1093/bib/bbag601",
"type": "article-journal",
"title": "ADInteractome: discovering Alzheimer's disease-associated gene interactions from single-nucleus RNA-seq data through neural interaction states",
"container-title": "Briefings in bioinformatics",
"author": [
{
"family": "Wu",
"given": "Yifan"
},
{
"family": "Maurya",
"given": "Neha"
},
{
"family": "Yang",
"given": "Yuntao"
},
{
"family": "Chen",
"given": "Wenbo"
},
{
"family": "Wang",
"given": "Guanchu"
},
{
"family": "Liu",
"given": "Zirui"
},
{
"family": "Hu",
"given": "Xia"
},
{
"family": "Zheng",
"given": "W Jim"
},
{
"family": "Xu",
"given": "Zhaozhuo"
}
],
"container-title-short": "Brief Bioinform",
"volume": "27",
"issue": "6",
"page": "bbag601",
"DOI": "10.1093/bib/bbag601",
"PMID": "42969854",
"PMCID": "PMC13725928",
"ISSN": "1467-5463",
"publisher": "Oxford University Press",
"URL": "https://doi.org/10.1093/bib/bbag601",
"language": "en",
"issued": {
"date-parts": [
[
2026,
11,
1
]
]
}
}

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:10.1186/s12864-026-12965-8 [code]
Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction.
Journal: BMC genomics
In common: Hugging Face Transformers, anndata, Scanpy, 8 other tools, cellular / molecular, 2 references
[2] doi:10.1093/nar/gkag706 [code]
scDifformer: diffusion-based post-training for virtual cell modeling across large-scale single-cell data.
Journal: Nucleic acids research
In common: anndata, Scanpy, h5py, 7 other tools, 3 references
[3] doi:10.1038/s41467-026-68920-4 [code]
Molecular signatures of resilience to Alzheimer's disease in neocortical layer 4 neurons.
Journal: Nature communications
In common: anndata, Scanpy, PyTorch, 6 other tools, Alzheimer's / dementia, cellular / molecular, 3 references
[4] doi:10.1093/bib/bbag259 [code]
PVAED: prior-guided variational autoencoders with diffusion denoising for interpretable single-cell representation learning.
Journal: Briefings in bioinformatics
In common: anndata, Scanpy, PyTorch, 5 other tools, genetics / omics, 3 references
[5] doi:10.1038/s41467-024-53971-2 [code]
scPair: Boosting single cell multimodal analysis by leveraging implicit feature selection and single cell atlases.
Journal: Nature communications
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 3 references
[6] doi:10.1038/s41467-024-50608-2 [code]
Whole brain alignment of spatial transcriptomics between humans and mice with BrainAlign.
Journal: Nature communications
In common: anndata, Scanpy, h5py, 7 other tools, genetics / omics, 2 references
[7] doi:10.1186/s12967-025-07245-0 [code]
SpateCV: cross-modality alignment regularization of cell types improves spatial gene imputation for spatial transcriptomics.
Journal: Journal of translational medicine
In common: anndata, Scanpy, h5py, 7 other tools, genetics / omics, cellular / molecular, 2 references
[8] doi:10.1016/j.xgen.2024.100581 [code]
SIMS: A deep-learning label transfer tool for single-cell RNA sequencing analysis.
Journal: Cell genomics
In common: anndata, Scanpy, h5py, 7 other tools, genetics / omics, 2 references
[9] doi:10.1038/s41467-023-38121-4 [code]
Reconstruction of the cell pseudo-space from single-cell RNA sequencing data with scSpace.
Journal: Nature communications
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, cellular / molecular, 3 references
[10] doi:10.1186/s13073-026-01598-x [code]
Exploring phenotype-related single-cells through attention-enhanced representation learning.
Journal: Genome medicine
In common: anndata, Scanpy, PyTorch, 6 other tools, cellular / molecular, 2 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.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.1093/bib/bbag601.svg)](https://openscicode.org/badge/doi/10.1093/bib/bbag601)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1093/bib/bbag601.svg
   :target: https://openscicode.org/badge/doi/10.1093/bib/bbag601
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1093/bib/bbag601"><img src="https://openscicode.org/badge/doi/10.1093/bib/bbag601.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge 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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.