GEO series

Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions [DECAMP cohort]

GSE300258 Homo sapiens (human) RNA-seq (gene expression) 70 samples Submitted 2026/05/27 Platform GPL18573Platform GPL16791

At a glance

RNA-seq (gene expression) · human · 70 samples

What it is: RNA-seq (gene expression)Gene activity measured by sequencing. The summary does not mention single-cell work, so this is most likely bulk: one average per sample, the usual starting point for comparing groups.
Organism: Homo sapiens (human)
Samples: 70 samples: 70 samples, each with a distinct title — no replicated groupsGroups are read from the sample names, not from the paper. Check the list below.
Data you can get: A processed table (series matrix) and supplementary files from NCBI; the raw sequencing reads from ENA. Which of these hold counts depends on the study, so check the file list.
Paper: Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesionsGenome medicine · 2026

Summary (written by the submitters)

Background: Molecular and cellular alterations to the normal pseudostratified columnar bronchial epithelium results in the development of bronchial premalignant lesions representing a spectrum of histology from normal to hyperplasia, metaplasia, dysplasia (mild, moderate, and severe), carcinoma in situ and invasive carcinoma. Several studies have identified molecular alterations associated with lesion histology and progression.

Read the full summary ↓

The broad and continuous spectrum of histologic and molecular changes makes reproducible stratification of lesions across multiple studies challenging. Methods: We proposed a transformer-based framework that flexibly utilizes transcriptomic and histologic patterns to distinguish lesions with bronchial dysplasia or worse from normal, hyperplasia, and metaplasia. We leveraged H&E whole slide images (WSIs) of endobronchial biopsies and bulk gene expression data (GE) derived from endobronchial biopsies and brushings from previously published studies and on-going lung precancer atlas efforts obtained from patients at high-risk for lung cancer. Results: On an external testing dataset of WSIs, the model trained on WSIs plus GE achieved an area under the ROC curve (AUROC) of 0.884±0.040 compared to 0.829±0.046 for the model trained on WSIs alone. On external testing datasets of GE, the model trained on WSIs plus GE achieved an AUROC of 0.857±0.033 versus 0.713±0.098 for a model trained on GE alone. Based on these results, we leveraged data across 4 studies to train a flexible fusion model that allows one or both data modalities (WSIs and GE) to be used in training. The model achieved an AUROC of 0.906±0.034 on external testing WSIs data and 0.870±0.023 on external testing GE data. Despite model training on a binary label, model probabilities were associated with histologic grade and the model identified gene expression alterations associated with bronchial dysplasia across multiple studies. Conclusions: Our multimodal transformer outperformed models trained on a single data modality and enabled the inclusion of samples with one or both modalities during training and/or testing. It increases the flexibility, scalability, and real-world applicability of disease severity assessment that better risk stratifies bronchial premalignant lesions even when only routine histology data is accessible.

Published in

Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions

Xu L, Kefella Y, Zhang Y et al. · Genome medicine 2026 · PMID 41952176 · doi:10.1186/s13073-026-01636-8

This dataset

Open GSE300258 in finder → Find more human RNA-seq datasets →

Download · which file do I need?

Direct links to NCBI and ENA, no account and no request form. Pick by what you want to do: take the small processed table to look, the supplementary files to re-analyse, or the original raw data to start over.

1 · Just have a look

Processed table

The series matrix: one table of values per sample as the submitters processed it. The smallest download, and it opens in Excel or R. Start here to see what the data look like.

Series matrix ↓

2 · Re-analyse it

Supplementary files

The count tables and other files the authors uploaded. Take only the samples you need, or the whole study as GSE300258_RAW.tar (it can run to tens of gigabytes).

All supplementary files ↗ Whole study · RAW.tar ↓

3 · Start from the raw reads

Raw sequencing reads

The original FASTQ files, straight from the sequencer, held at ENA. Large, and you align them yourself, so only choose this if you need to re-process the study from scratch.

Raw reads on ENA ↗

What the files usually look like: For RNA-seq the counts are usually a table among the supplementary files (look for 'counts', 'expression', 'FPKM' or 'TPM' in the file name). The series matrix of a sequencing study is sometimes nearly empty.

Also filed as BioProject PRJNA1279974. Searching any of these in the dataset finder brings you back here.

NCBI GEO page ↗ Paper (PMID 41952176) ↗

Study design

70 samples, each with a distinct title — no replicated groups

Any grouping that defines a comparison lives in the sample characteristics, which GEO records separately from the titles.

How we read this: Read from 70 sample titles: 70 distinct titles with little repetition. These groups are guessed from the sample names, not taken from the paper, so check them against the sample list below before relying on them.

Samples in this study

GSM9056556 4202-002-67
GSM9056557 4202-003-67
GSM9056558 4202-004-67
GSM9056559 4202-006-67
GSM9056560 4202-011-67
GSM9056561 4202-012-67
GSM9056562 4202-013-67
GSM9056563 4202-030-67
GSM9056564 4202-033-67
GSM9056565 4438-002-69
GSM9056566 4438-003-69
GSM9056567 4438-005-67
GSM9056568 4438-007-67
GSM9056569 4438-011-67
GSM9056570 4438-026-67
GSM9056571 4438-032-67
GSM9056572 4438-042-67
GSM9056573 4438-082-67
GSM9056574 4714-001-67
GSM9056575 4714-018-67
GSM9056576 4714-020-67
GSM9056577 4790-002-67
GSM9056578 4790-003-67
GSM9056579 4790-004-67
GSM9056580 4790-005-67
GSM9056581 4790-011-67
GSM9056582 4790-012-67
GSM9056583 4790-013-67
GSM9056584 4790-014-67
GSM9056585 4790-015-67
GSM9056586 4790-016-67
GSM9056587 4790-021-67
GSM9056588 4790-022-67
GSM9056589 4790-026-67
GSM9056590 4790-034-67
GSM9056591 4791-002-69
GSM9056592 4791-007-67
GSM9056593 4791-011-67
GSM9056594 4793-030-67
GSM9056595 4793-038-67

+ 30 more — browse all 70 samples with per-sample file links →

Datasets on a similar topic

GSE320389 Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions 215 samples shares attention-based, premalignant, pathology, learning, squamous, lesions, images
GSE320381 Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions [HTAN cohort] 145 samples shares attention-based, premalignant, pathology, learning, squamous, lesions, images
GSE319666 Archetype analysis of lung adenocarcinoma premalignancy links heterogeneity in premalignant lesions to diverging features of invasive disease 177 samples shares premalignant, lesions
GSE196711 Immune profiling of premalignant lesions in patients with Peutz-Jeghers Syndrome 29 samples shares premalignant, lesions
GSE134520 Dissecting the single-cell transcriptome network underlying gastric premalignant lesions and early gastric cancer [10x genomics] 13 samples shares premalignant, lesions
GSE153960 Truncated stathmin-2 is a marker of TDP-43 pathology in frontotemporal dementia 1838 samples shares pathology
GSE324265 Contribution of cytotoxic CD8 T cells, neutrophils and type 1 interferon signaling to hyperinflammatory pathology in HIV associated TB meningitis [RNA-Seq] 125 samples shares pathology
GSE240766 SARS-CoV-2 infection of human pluripotent stem cell-derived vascular cells reveals smooth muscle cells as key mediators of vascular pathology during infection 101 samples shares pathology

Search all human RNA-seq datasets in GEO →

Share this dataset

Metadata from NCBI GEO, cached and refreshed periodically — the NCBI page above is authoritative. Downloads link straight to NCBI/ENA; nothing is proxied through BioTransfer.