Deep scSTAR: leveraging deep learning for the extraction and enhancement of phenotype-associated features from single-cell RNA sequencing and spatial transcriptomics data DOI Creative Commons

Lianchong Gao,

Yujun Liu, Jiawei Zou

et al.

Briefings in Bioinformatics, Journal Year: 2025, Volume and Issue: 26(3)

Published: May 1, 2025

Abstract Single-cell sequencing has advanced our understanding of cellular heterogeneity and disease pathology, offering insights into behavior immune mechanisms. However, extracting meaningful phenotype-related features is challenging due to noise, batch effects, irrelevant biological signals. To address this, we introduce Deep scSTAR (DscSTAR), a deep learning-based tool designed enhance phenotype-associated features. DscSTAR identified HSP+ FKBP4+ T cells in CD8+ cells, which linked dysfunction resistance checkpoint blockade non-small cell lung cancer. It also enhanced spatial transcriptomics analysis renal carcinoma, revealing interactions between cancer tumor-associated macrophages that may promote suppression affect outcomes. In hepatocellular it highlighted the role S100A12+ neutrophils cancer-associated fibroblasts forming tumor barriers potentially contributing immunotherapy resistance. These findings demonstrate DscSTAR’s capacity model extract phenotype-specific information, advancing mechanisms therapy

Language: Английский

Pan-cancer T cell atlas links a cellular stress response state to immunotherapy resistance DOI
Yanshuo Chu, Enyu Dai, Yating Li

et al.

Nature Medicine, Journal Year: 2023, Volume and Issue: 29(6), P. 1550 - 1562

Published: May 29, 2023

Language: Английский

Citations

185
Tertiary lymphoid structures and B cells: An intratumoral immunity cycle DOI Creative Commons
Wolf H. Fridman, Maxime Meylan, Guilhem Pupier

et al.

Immunity, Journal Year: 2023, Volume and Issue: 56(10), P. 2254 - 2269

Published: Sept. 11, 2023

Language: Английский

Citations

122
An atlas of epithelial cell states and plasticity in lung adenocarcinoma DOI Creative Commons

Guangchun Han,

Ansam Sinjab, Zahraa Rahal

et al.

Nature, Journal Year: 2024, Volume and Issue: 627(8004), P. 656 - 663

Published: Feb. 28, 2024

Abstract Understanding the cellular processes that underlie early lung adenocarcinoma (LUAD) development is needed to devise intervention strategies 1 . Here we studied 246,102 single epithelial cells from 16 early-stage LUADs and 47 matched normal samples. Epithelial comprised diverse cancer cell states, diversity among was strongly linked LUAD-specific oncogenic drivers. KRAS mutant showed distinct transcriptional features, reduced differentiation low levels of aneuploidy. Non-malignant areas surrounding human LUAD samples were enriched with alveolar intermediate displayed elevated KRT8 expression (termed + (KACs) here), differentiation, increased plasticity driver mutations. Expression profiles KACs in precancer signified poor survival. In mice exposed tobacco carcinogen, emerged before tumours persisted for months after cessation carcinogen exposure. Moreover, they acquired Kras mutations conveyed sensitivity targeted inhibition KAC-enriched organoids derived type 2 (AT2) cells. Last, lineage-labelling AT2 or following exposure are possible intermediates AT2-to-tumour transformation. This study provides new insights into states at root development, such could harbour potential targets prevention intervention.

Language: Английский

Citations

50
Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment DOI Creative Commons
Chaoyi Zhang, Jin Xu,

Rong Tang

et al.

Journal of Hematology & Oncology, Journal Year: 2023, Volume and Issue: 16(1)

Published: Nov. 27, 2023

Research into the potential benefits of artificial intelligence for comprehending intricate biology cancer has grown as a result widespread use deep learning and machine in healthcare sector availability highly specialized datasets. Here, we review new approaches how they are being used oncology. We describe might be detection, prognosis, administration treatments introduce latest large language models such ChatGPT oncology clinics. highlight applications omics data types, offer perspectives on various types combined to create decision-support tools. also evaluate present constraints challenges applying precision Finally, discuss current may surmounted make useful clinical settings future.

Language: Английский

Citations

49
Profiling cell identity and tissue architecture with single-cell and spatial transcriptomics DOI
Gunsagar S. Gulati,

Jeremy Philip D’Silva,

Yunhe Liu

et al.

Nature Reviews Molecular Cell Biology, Journal Year: 2024, Volume and Issue: 26(1), P. 11 - 31

Published: Aug. 21, 2024

Language: Английский

Citations

33
Tertiary lymphoid structural heterogeneity determines tumour immunity and prospects for clinical application DOI Creative Commons
Yuyuan Zhang,

Mengjun Xu,

Yuqing Ren

et al.

Molecular Cancer, Journal Year: 2024, Volume and Issue: 23(1)

Published: April 6, 2024

Abstract Tertiary lymphoid structures (TLS) are clusters of immune cells that resemble and function similarly to secondary organs (SLOs). While TLS is generally associated with an anti-tumour response in most cancer types, it has also been observed act as a pro-tumour response. The heterogeneity largely determined by the composition tumour-infiltrating lymphocytes (TILs) balance cell subsets within tumour-associated (TA-TLS). TA-TLS varying maturity, density, location may have opposing effects on tumour immunity. Higher maturity and/or higher density often favorable clinical outcomes immunotherapeutic response, mainly due crosstalk between different proportions subpopulations TA-TLS. Therefore, can be used marker predict efficacy immunotherapy checkpoint blockade (ICB). Developing efficient imaging induction methods study crucial for enhancing integration techniques biological materials, including nanoprobes hydrogels, alongside artificial intelligence (AI), enables non-invasive vivo visualization TLS. In this review, we explore dynamic interactions among T B phenotypes contribute structural functional diversity TLS, examining both existing emerging induction, focusing immunotherapies biomaterials. We highlight novel therapeutic approaches being explored aim increasing ICB treatment predicting prognosis.

Language: Английский

Citations

26
Spatially exploring RNA biology in archival formalin-fixed paraffin-embedded tissues DOI Creative Commons
Zhiliang Bai, Dingyao Zhang, Yan Gao

et al.

Cell, Journal Year: 2024, Volume and Issue: 187(23), P. 6760 - 6779.e24

Published: Sept. 30, 2024

The capability to spatially explore RNA biology in formalin-fixed paraffin-embedded (FFPE) tissues holds transformative potential for histopathology research. Here, we present pathology-compatible deterministic barcoding tissue (Patho-DBiT) by combining situ polyadenylation and computational innovation spatial whole transcriptome sequencing, tailored probe the diverse species clinically archived FFPE samples. It permits co-profiling of gene expression processing, unveiling region-specific splicing isoforms, high-sensitivity transcriptomic mapping clinical tumor stored 5 years. Furthermore, genome-wide single-nucleotide variants can be captured distinguish malignant subclones from non-malignant cells human lymphomas. Patho-DBiT also maps microRNA regulatory networks dynamics, decoding their roles tumorigenesis. Single-cell level dissects spatiotemporal cellular dynamics driving clonal architecture progression. stands poised as a valuable platform unravel rich aid pathology evaluation.

Language: Английский

Citations

25
Single‐cell RNA‐sequencing and spatial transcriptomic analysis reveal a distinct population of APOE− cells yielding pathological lymph node metastasis in papillary thyroid cancer DOI Creative Commons

Guohui Xiao,

Rongli Xie,

Jianhua Gu

et al.

Clinical and Translational Medicine, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 1, 2025

Language: Английский

Citations

3
Tertiary lymphoid structures and cancer immunotherapy: From bench to bedside DOI Creative Commons
Florent Peyraud, Jean‐Philippe Guégan, Lucile Vanhersecke

et al.

Med, Journal Year: 2025, Volume and Issue: 6(1), P. 100546 - 100546

Published: Jan. 1, 2025

Language: Английский

Citations

2
Leveraging spatial transcriptomics data to recover cell locations in single-cell RNA-seq with CeLEry DOI Creative Commons
Qihuang Zhang, Shunzhou Jiang,

Amelia Schroeder

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 8, 2023

Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular heterogeneity in health and disease. However, the lack physical relationships among dissociated cells limited its applications. To address this issue, we present CeLEry (Cell Location recovEry), a supervised deep learning algorithm that leverages gene expression spatial location learned from transcriptomics to recover origins scRNA-seq. an optional data augmentation procedure via variational autoencoder, which improves method's robustness allows it overcome noise scRNA-seq data. We show can infer at multiple levels, including 2D domain cell, while also providing uncertainty estimates for recovered locations. Our comprehensive benchmarking evaluations on datasets generated brain cancer tissues using Visium, MERSCOPE, MERFISH, Xenium demonstrate reliably information

Language: Английский

Citations

29