Dataset Information

Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment.

ABSTRACT: The tumor microenvironment (TME) profoundly influences tumor progression and affects immunotherapy responses and resistance. Understanding its heterogeneity is the key for developing immunotherapy. However, the available methods can only partially portray the TME heterogeneity with a small number of cell types. Here, we developed a deep learning-based frame with a design visible, DCNet, that embeds the relationships between cells and their marker genes in the neural network, and can infer the cell landscape with more than 400 cell types based on bulk RNA-seq data. DCNet accurately recapitulated the cell landscape of multiple single cell RNA-seq datasets, which showed better robustness and stability. Based on the cell landscape of TCGA patients, which was built with DCNet, the patients were divided into two groups with significant differences in survival time and distinct cell-type populations. DCNet provides a foundation for decoding TME heterogeneity. The source code of DCNet can be found on GitHub: https://github.com/xindd/DCNet.

SUBMITTER: Wang X

PROVIDER: S-EPMC8890395 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment.

Wang Xin X Wang Hongjiu H Liu Dan D Wang Na N He Danni D Wu Zheyu Z Zhu Xu X Wen Xiaoling X Li Xuhua X Li Jin J Wang Zhenzhen Z

Oncoimmunology 20220225 1

The tumor microenvironment (TME) profoundly influences tumor progression and affects immunotherapy responses and resistance. Understanding its heterogeneity is the key for developing immunotherapy. However, the available methods can only partially portray the TME heterogeneity with a small number of cell types. Here, we developed a deep learning-based frame with a design visible, DCNet, that embeds the relationships between cells and their marker genes in the neural network, and can infer the ce ...[more]

PMID: 35251771

Similar Datasets

Project description:BackgroundIn this study, we compared the prognosis, tumor immune microenvironment (TIM), and drug treatment response between left-sided (LCC) and right-sided (RCC) colon cancer to predict outcomes in patients with LCC and RCC.MethodsBased on identified differentially expressed genes and using single-cell RNA sequencing data, we constructed and validated a prognostic model for LCC and RCC patients in the TCGA-COAD cohort and GSE103479 cohort. Moreover, we compared the differences of TIM characteristics and drug treatment response between LCC and RCC patients.ResultsWe constructed and validated a five-gene prognostic model for LCC patients and a four-gene prognostic model for RCC patients, and both showed excellent performance. The RCC patients with higher risk scores were significantly associated with greater metastasis (P = 2.6×10-5), N stage (P = 0.012), advanced pathological stage (P = 1.4×10-4), and more stable microsatellite status (P = 0.007) but not T stage (P = 0.200). For LCC patients, the risk scores were not significantly associated with tumor stage and microsatellite status (P > 0.05). Additionally, immune infiltration by CD8 and regulatory T cells and M0, M1, and M2 macrophages differed significantly between LCC and RCC patients (P < 0.05). APC and TP53 mutations were significantly more common in LCC patients (P < 0.05). In contrast, KRAS, SYNE1, and MUC16 mutations were significantly more common in RCC patients (P < 0.05). In addition, tumor mutation burden values were significantly higher in RCC patients than in LCC patients (P = 5.9×10-8). Moreover, the expression of immune checkpoint targets was significantly higher in RCC patients than in LCC patients (P < 0.05), indicating that RCC patients maybe more sensitive to immunotherapy. However, LCC and RCC patients did not differ significantly in their sensitivity to eight selected chemicals or target drugs (P > 0.05). The average half-maximal inhibitory concentrations for camptothecin, teniposide, vinorelbine, and mitoxantrone were significantly lower in low-risk than in high-risk RCC patients (P < 0.05), indicating that the lower risk score of RCC patients, the more sensitive they were to these four drugs.ConclusionsWe investigated the differences in prognosis, TIM, and drug treatment response between LCC and RCC patients, which may contribute to accurate colon cancer prognosis and treatment of colon cancer.

Dataset Information

Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment.

Publications

Deep learning using bulk RNA-seq data expands cell landscape identification in tumor microenvironment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets