1
|
Zhao X, Chen Z, Wang H, Sun H. Occlusion enhanced pan-cancer classification via deep learning. BMC Bioinformatics 2024; 25:260. [PMID: 39118043 PMCID: PMC11308240 DOI: 10.1186/s12859-024-05870-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Accepted: 07/12/2024] [Indexed: 08/10/2024] Open
Abstract
Quantitative measurement of RNA expression levels through RNA-Seq is an ideal replacement for conventional cancer diagnosis via microscope examination. Currently, cancer-related RNA-Seq studies focus on two aspects: classifying the status and tissue of origin of a sample and discovering marker genes. Existing studies typically identify marker genes by statistically comparing healthy and cancer samples. However, this approach overlooks marker genes with low expression level differences and may be influenced by experimental results. This paper introduces "GENESO," a novel framework for pan-cancer classification and marker gene discovery using the occlusion method in conjunction with deep learning. we first trained a baseline deep LSTM neural network capable of distinguishing the origins and statuses of samples utilizing RNA-Seq data. Then, we propose a novel marker gene discovery method called "Symmetrical Occlusion (SO)". It collaborates with the baseline LSTM network, mimicking the "gain of function" and "loss of function" of genes to evaluate their importance in pan-cancer classification quantitatively. By identifying the genes of utmost importance, we then isolate them to train new neural networks, resulting in higher-performance LSTM models that utilize only a reduced set of highly relevant genes. The baseline neural network achieves an impressive validation accuracy of 96.59% in pan-cancer classification. With the help of SO, the accuracy of the second network reaches 98.30%, while using 67% fewer genes. Notably, our method excels in identifying marker genes that are not differentially expressed. Moreover, we assessed the feasibility of our method using single-cell RNA-Seq data, employing known marker genes as a validation test.
Collapse
Grants
- 14106521 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14100620 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14105823 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14115319 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 2141109 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 2141157 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 2141261 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14105123 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14103522 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14120420 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
- 14120619 General Research Funds (GRF) from the Research Grants Council (RGC), University Grants Committee of the Hong Kong Special Administrative Region, China.
Collapse
Affiliation(s)
- Xing Zhao
- Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, People's Republic of China
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen, Guangdong, People's Republic of China
| | - Zigui Chen
- Department of Microbiology, The Chinese University of Hong Kong, Hong Kong, People's Republic of China
| | - Huating Wang
- Department of Orthopaedics and Traumatology, Li Ka Shing Institute of Health Sciences, The Chinese University of Hong Kong, Hong Kong, People's Republic of China
| | - Hao Sun
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen, Guangdong, People's Republic of China.
- Department of Chemical Pathology, Li Ka Shing Institute of Health Sciences, The Chinese University of Hong Kong, Hong Kong, People's Republic of China.
| |
Collapse
|
2
|
Hu D, Zhang Z, Liu X, Wu Y, An Y, Wang W, Yang M, Pan Y, Qiao K, Du C, Zhao Y, Li Y, Bao J, Qin T, Pan Y, Xia Z, Zhao X, Sun K. Generalizable transcriptome-based tumor malignant level evaluation and molecular subtyping towards precision oncology. J Transl Med 2024; 22:512. [PMID: 38807223 PMCID: PMC11134716 DOI: 10.1186/s12967-024-05326-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2024] [Accepted: 05/19/2024] [Indexed: 05/30/2024] Open
Abstract
In cancer treatment, therapeutic strategies that integrate tumor-specific characteristics (i.e., precision oncology) are widely implemented to provide clinical benefits for cancer patients. Here, through in-depth integration of tumor transcriptome and patients' prognoses across cancers, we investigated dysregulated and prognosis-associated genes and catalogued such important genes in a cancer type-dependent manner. Utilizing the expression matrices of these genes, we built models to quantitatively evaluate the malignant levels of tumors across cancers, which could add value to the clinical staging system for improved prediction of patients' survival. Furthermore, we performed a transcriptome-based molecular subtyping on hepatocellular carcinoma, which revealed three subtypes with significantly diversified clinical outcomes, mutation landscapes, immune microenvironment, and dysregulated pathways. As tumor transcriptome was commonly profiled in clinical practice with low experimental complexity and cost, this work proposed easy-to-perform approaches for practical clinical promotion towards better healthcare and precision oncology of cancer patients.
Collapse
Affiliation(s)
- Dingxue Hu
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
- Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230027, China
| | - Ziteng Zhang
- Hepato-Biliary Surgery Division, The Second Affiliated Hospital, Shenzhen Third People's Hospital, Southern University of Science and Technology, Shenzhen, 518100, China
| | - Xiaoyi Liu
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
| | - Youchun Wu
- Hepato-Biliary Surgery Division, The Second Affiliated Hospital, Shenzhen Third People's Hospital, Southern University of Science and Technology, Shenzhen, 518100, China
| | - Yunyun An
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
| | - Wanqiu Wang
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
- Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230027, China
| | - Mengqi Yang
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
| | - Yuqi Pan
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
- Department of Biology, Southern University of Science and Technology, Shenzhen, 518055, China
| | - Kun Qiao
- Thoracic Surgical Department, Shenzhen Third People's Hospital, The Second Affiliated Hospital, Southern University of Science and Technology, Shenzhen, 518100, China
| | - Changzheng Du
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China
- Department of Biochemistry, School of Medicine, Southern University of Science and Technology, Shenzhen, 518055, China
- Beijing Tsinghua Changgung Hospital, Tsinghua University School of Medicine, Beijing, 102218, China
| | - Yu Zhao
- Molecular Cancer Research Center, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, 518107, China
| | - Yan Li
- Department of Biology, Southern University of Science and Technology, Shenzhen, 518055, China
- Integrative Microecology Clinical Center, Shenzhen Key Laboratory of Gastrointestinal Microbiota and Disease, Shenzhen Clinical Research Center for Digestive Disease, Shenzhen Technology Research Center of Gut Microbiota Transplantation, Shenzhen Hospital, Southern Medical University, Shenzhen, 510086, China
| | - Jianqiang Bao
- Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230027, China
| | - Tao Qin
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Medical Research Center, Sun Yat- Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China
| | - Yue Pan
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Medical Research Center, Sun Yat- Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China
| | - Zhaohua Xia
- Thoracic Surgical Department, Shenzhen Third People's Hospital, The Second Affiliated Hospital, Southern University of Science and Technology, Shenzhen, 518100, China.
| | - Xin Zhao
- Hepato-Biliary Surgery Division, The Second Affiliated Hospital, Shenzhen Third People's Hospital, Southern University of Science and Technology, Shenzhen, 518100, China.
| | - Kun Sun
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, 518132, China.
| |
Collapse
|
3
|
Li LS, Guo XY, Sun K. Recent advances in blood-based and artificial intelligence-enhanced approaches for gastrointestinal cancer diagnosis. World J Gastroenterol 2021; 27:5666-5681. [PMID: 34629793 PMCID: PMC8473600 DOI: 10.3748/wjg.v27.i34.5666] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/27/2021] [Revised: 05/14/2021] [Accepted: 08/03/2021] [Indexed: 02/06/2023] Open
Abstract
Gastrointestinal (GI) cancers are among the most common cancer types and leading causes of cancer-related deaths worldwide. There is a tremendous clinical need for effective early diagnosis for better healthcare of GI cancer patients. In this article, we provide a short overview of the recent advances in GI cancer diagnosis. In the first part, we discuss the applications of blood-based biomarkers, such as plasma circulating cell-free DNA, circulating tumor cells, extracellular vesicles, and circulating cell-free RNA, for cancer liquid biopsies. In the second part, we review the current trends of artificial intelligence (AI) for pathology image and tissue biopsy analysis for GI cancer, as well as deep learning-based approaches for purity assessment of tissue biopsies. We further provide our opinions on the future directions in blood-based and AI-enhanced approaches for GI cancer diagnosis, and we think that these fields will have more intensive integrations with clinical needs in the near future.
Collapse
Affiliation(s)
- Li-Shi Li
- School of Chemical Biology and Biotechnology, Shenzhen Graduate School, Peking University, Shenzhen 518055, Guangdong Province, China
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen 518132, Guangdong Province, China
| | - Xiang-Yu Guo
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen 518132, Guangdong Province, China
| | - Kun Sun
- Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen 518132, Guangdong Province, China
- BGI-Shenzhen, Shenzhen 518083, Guangdong Province, China
| |
Collapse
|