1
|
Ye X, Shang Y, Shi T, Zhang W, Sakurai T. Multi-omics clustering for cancer subtyping based on latent subspace learning. Comput Biol Med 2023; 164:107223. [PMID: 37490833 DOI: 10.1016/j.compbiomed.2023.107223] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2023] [Revised: 06/07/2023] [Accepted: 06/30/2023] [Indexed: 07/27/2023]
Abstract
The increased availability of high-throughput technologies has enabled biomedical researchers to learn about disease etiology across multiple omics layers, which shows promise for improving cancer subtype identification. Many computational methods have been developed to perform clustering on multi-omics data, however, only a few of them are applicable for partial multi-omics in which some samples lack data in some types of omics. In this study, we propose a novel multi-omics clustering method based on latent sub-space learning (MCLS), which can deal with the missing multi-omics for clustering. We utilize the data with complete omics to construct a latent subspace using PCA-based feature extraction and singular value decomposition (SVD). The data with incomplete multi-omics are then projected to the latent subspace, and spectral clustering is performed to find the clusters. The proposed MCLS method is evaluated on seven different cancer datasets on three levels of omics in both full and partial cases compared to several state-of-the-art methods. The experimental results show that the proposed MCLS method is more efficient and effective than the compared methods for cancer subtype identification in multi-omics data analysis, which provides important references to a comprehensive understanding of cancer and biological mechanisms. AVAILABILITY: The proposed method can be freely accessible at https://github.com/ShangCS/MCLS.
Collapse
Affiliation(s)
- Xiucai Ye
- Department of Computer Science, University of Tsukuba, Tsukuba, 3058577, Japan; Tsukuba Life Science Innovation Program, University of Tsukuba, Tsukuba, 3058577, Japan.
| | - Yifan Shang
- Department of Computer Science, University of Tsukuba, Tsukuba, 3058577, Japan
| | - Tianyi Shi
- Tsukuba Life Science Innovation Program, University of Tsukuba, Tsukuba, 3058577, Japan
| | - Weihang Zhang
- Department of Computer Science, University of Tsukuba, Tsukuba, 3058577, Japan
| | - Tetsuya Sakurai
- Department of Computer Science, University of Tsukuba, Tsukuba, 3058577, Japan; Tsukuba Life Science Innovation Program, University of Tsukuba, Tsukuba, 3058577, Japan
| |
Collapse
|
2
|
Ye X, Shi T, Cui Y, Sakurai T. Interactive gene identification for cancer subtyping based on multi-omics clustering. Methods 2023; 211:61-67. [PMID: 36804215 DOI: 10.1016/j.ymeth.2023.02.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Revised: 02/06/2023] [Accepted: 02/12/2023] [Indexed: 02/17/2023] Open
Abstract
Recent advances in multi-omics databases offer the opportunity to explore complex systems of cancers across hierarchical biological levels. Some methods have been proposed to identify the genes that play a vital role in disease development by integrating multi-omics. However, the existing methods identify the related genes separately, neglecting the gene interactions that are related to the multigenic disease. In this study, we develop a learning framework to identify the interactive genes based on multi-omics data including gene expression. Firstly, we integrate different omics based on their similarities and apply spectral clustering for cancer subtype identification. Then, a gene co-expression network is construct for each cancer subtype. Finally, we detect the interactive genes in the co-expression network by learning the dense subgraphs based on the L1 prosperities of eigenvectors in the modularity matrix. We apply the proposed learning framework on a multi-omics cancer dataset to identify the interactive genes for each cancer subtype. The detected genes are examined by DAVID and KEGG tools for systematic gene ontology enrichment analysis. The analysis results show that the detected genes have relationships to cancer development and the genes in different cancer subtypes are related to different biological processes and pathways, which are expected to yield important references for understanding tumor heterogeneity and improving patient survival.
Collapse
Affiliation(s)
- Xiucai Ye
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan.
| | - Tianyi Shi
- Tsukuba Life Science Innovation Program, University of Tsukuba, Tsukuba 3058577, Japan
| | - Yaxuan Cui
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan
| | - Tetsuya Sakurai
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan; Tsukuba Life Science Innovation Program, University of Tsukuba, Tsukuba 3058577, Japan
| |
Collapse
|
3
|
Wei L, Ye X, Sakurai T, Mu Z, Wei L. ToxIBTL: prediction of peptide toxicity based on information bottleneck and transfer learning. Bioinformatics 2022; 38:1514-1524. [PMID: 34999757 DOI: 10.1093/bioinformatics/btac006] [Citation(s) in RCA: 40] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2021] [Revised: 11/29/2021] [Accepted: 01/04/2022] [Indexed: 02/03/2023] Open
Abstract
MOTIVATION Recently, peptides have emerged as a promising class of pharmaceuticals for various diseases treatment poised between traditional small molecule drugs and therapeutic proteins. However, one of the key bottlenecks preventing them from therapeutic peptides is their toxicity toward human cells, and few available algorithms for predicting toxicity are specially designed for short-length peptides. RESULTS We present ToxIBTL, a novel deep learning framework by utilizing the information bottleneck principle and transfer learning to predict the toxicity of peptides as well as proteins. Specifically, we use evolutionary information and physicochemical properties of peptide sequences and integrate the information bottleneck principle into a feature representation learning scheme, by which relevant information is retained and the redundant information is minimized in the obtained features. Moreover, transfer learning is introduced to transfer the common knowledge contained in proteins to peptides, which aims to improve the feature representation capability. Extensive experimental results demonstrate that ToxIBTL not only achieves a higher prediction performance than state-of-the-art methods on the peptide dataset, but also has a competitive performance on the protein dataset. Furthermore, a user-friendly online web server is established as the implementation of the proposed ToxIBTL. AVAILABILITY AND IMPLEMENTATION The proposed ToxIBTL and data can be freely accessible at http://server.wei-group.net/ToxIBTL. Our source code is available at https://github.com/WLYLab/ToxIBTL. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Lesong Wei
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan
| | - Xiucai Ye
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan
| | - Tetsuya Sakurai
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan
| | - Zengchao Mu
- School of Mathematics and Statistics, Shandong University, Weihai, China
| | - Leyi Wei
- School of Software, Shandong University, Jinan, China
| |
Collapse
|
4
|
Sekula M, Gaskins J, Datta S. Single-Cell Differential Network Analysis with Sparse Bayesian Factor Models. Front Genet 2022; 12:810816. [PMID: 35186014 PMCID: PMC8855158 DOI: 10.3389/fgene.2021.810816] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2021] [Accepted: 12/21/2021] [Indexed: 11/13/2022] Open
Abstract
Differential network analysis plays an important role in learning how gene interactions change under different biological conditions, and the high resolution of single-cell RNA (scRNA-seq) sequencing provides new opportunities to explore these changing gene-gene interactions. Here, we present a sparse hierarchical Bayesian factor model to identify differences across network structures from different biological conditions in scRNA-seq data. Our methodology utilizes latent factors to impact gene expression values for each cell to help account for zero-inflation, increased cell-to-cell variability, and overdispersion that are unique characteristics of scRNA-seq data. Condition-dependent parameters determine which latent factors are activated in a gene, which allows for not only the calculation of gene-gene co-expression within each group but also the calculation of the co-expression differences between groups. We highlight our methodology’s performance in detecting differential gene-gene associations across groups by analyzing simulated datasets and a SARS-CoV-2 case study dataset.
Collapse
Affiliation(s)
- Michael Sekula
- Department of Bioinformatics and Biostatistics, University of Louisville, Louisville, KY, United States
| | - Jeremy Gaskins
- Department of Bioinformatics and Biostatistics, University of Louisville, Louisville, KY, United States
| | - Susmita Datta
- Department of Biostatistics, University of Florida, Gainesville, FL, United States
- *Correspondence: Susmita Datta,
| |
Collapse
|
5
|
Yu CY, Mitrofanova A. Mechanism-Centric Approaches for Biomarker Detection and Precision Therapeutics in Cancer. Front Genet 2021; 12:687813. [PMID: 34408770 PMCID: PMC8365516 DOI: 10.3389/fgene.2021.687813] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Accepted: 06/28/2021] [Indexed: 12/18/2022] Open
Abstract
Biomarker discovery is at the heart of personalized treatment planning and cancer precision therapeutics, encompassing disease classification and prognosis, prediction of treatment response, and therapeutic targeting. However, many biomarkers represent passenger rather than driver alterations, limiting their utilization as functional units for therapeutic targeting. We suggest that identification of driver biomarkers through mechanism-centric approaches, which take into account upstream and downstream regulatory mechanisms, is fundamental to the discovery of functionally meaningful markers. Here, we examine computational approaches that identify mechanism-centric biomarkers elucidated from gene co-expression networks, regulatory networks (e.g., transcriptional regulation), protein-protein interaction (PPI) networks, and molecular pathways. We discuss their objectives, advantages over gene-centric approaches, and known limitations. Future directions highlight the importance of input and model interpretability, method and data integration, and the role of recently introduced technological advantages, such as single-cell sequencing, which are central for effective biomarker discovery and time-cautious precision therapeutics.
Collapse
Affiliation(s)
- Christina Y. Yu
- Department of Biomedical and Health Informatics, School of Health Professions, Rutgers, The State University of New Jersey, Newark, NJ, United States
| | - Antonina Mitrofanova
- Department of Biomedical and Health Informatics, School of Health Professions, Rutgers, The State University of New Jersey, Newark, NJ, United States
- Rutgers Cancer Institute of New Jersey, Rutgers, The State University of New Jersey, New Brunswick, NJ, United States
| |
Collapse
|
6
|
Wei L, Ye X, Xue Y, Sakurai T, Wei L. ATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism. Brief Bioinform 2021; 22:6209691. [PMID: 33822870 DOI: 10.1093/bib/bbab041] [Citation(s) in RCA: 32] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/11/2021] [Accepted: 01/28/2021] [Indexed: 12/13/2022] Open
Abstract
MOTIVATION Peptides have recently emerged as promising therapeutic agents against various diseases. For both research and safety regulation purposes, it is of high importance to develop computational methods to accurately predict the potential toxicity of peptides within the vast number of candidate peptides. RESULTS In this study, we proposed ATSE, a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural networks and attention mechanism. More specifically, it consists of four modules: (i) a sequence processing module for converting peptide sequences to molecular graphs and evolutionary profiles, (ii) a feature extraction module designed to learn discriminative features from graph structural information and evolutionary information, (iii) an attention module employed to optimize the features and (iv) an output module determining a peptide as toxic or non-toxic, using optimized features from the attention module. CONCLUSION Comparative studies demonstrate that the proposed ATSE significantly outperforms all other competing methods. We found that structural information is complementary to the evolutionary information, effectively improving the predictive performance. Importantly, the data-driven features learned by ATSE can be interpreted and visualized, providing additional information for further analysis. Moreover, we present a user-friendly online computational platform that implements the proposed ATSE, which is now available at http://server.malab.cn/ATSE. We expect that it can be a powerful and useful tool for researchers of interest.
Collapse
Affiliation(s)
- Lesong Wei
- Department of Computer Science, University of Tsukuba, Tsukuba, Japan, 3058577
| | - Xiucai Ye
- Department of Computer Science, University of Tsukuba, Tsukuba, Japan, 3058577
| | - Yuyang Xue
- Department of Computer Science, University of Tsukuba, Tsukuba, Japan, 3058577
| | - Tetsuya Sakurai
- Department of Computer Science, University of Tsukuba, Tsukuba, Japan, 3058577
| | - Leyi Wei
- School of Software, Shandong University, Jinan, China
| |
Collapse
|
7
|
Hu Y, Li B, Chen F, Qu K. Single-cell data clustering based on sparse optimization and low-rank matrix factorization. G3-GENES GENOMES GENETICS 2021; 11:6205713. [PMID: 33787873 PMCID: PMC8495739 DOI: 10.1093/g3journal/jkab098] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Accepted: 03/20/2021] [Indexed: 12/05/2022]
Abstract
Unsupervised clustering is a fundamental step of single-cell RNA-sequencing (scRNA-seq) data analysis. This issue has inspired several clustering methods to classify cells in scRNA-seq data. However, accurate prediction of the cell clusters remains a substantial challenge. In this study, we propose a new algorithm for scRNA-seq data clustering based on Sparse Optimization and low-rank matrix factorization (scSO). We applied our scSO algorithm to analyze multiple benchmark datasets and showed that the cluster number predicted by scSO was close to the number of reference cell types and that most cells were correctly classified. Our scSO algorithm is available at https://github.com/QuKunLab/scSO. Overall, this study demonstrates a potent cell clustering approach that can help researchers distinguish cell types in single- scRNA-seq data.
Collapse
Affiliation(s)
- Yinlei Hu
- School of Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui, China, 230021
| | - Bin Li
- Department of Oncology, The First Affiliated Hospital of USTC, Division of Molecular Medicine, Hefei National Laboratory for Physical Sciences at Microscale, School of Basic Medical Sciences, Division of Life Sciences and Medicine, University of Science and Technology of China, 230021 Hefei, Anhui, China
| | - Falai Chen
- School of Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui, China, 230021.,School of Data Science, University of Science and Technology of China, 230026 Hefei, Anhui, China
| | - Kun Qu
- Department of Oncology, The First Affiliated Hospital of USTC, Division of Molecular Medicine, Hefei National Laboratory for Physical Sciences at Microscale, School of Basic Medical Sciences, Division of Life Sciences and Medicine, University of Science and Technology of China, 230021 Hefei, Anhui, China.,CAS Center for Excellence in Molecular Cell Sciences, the CAS Key Laboratory of Innate Immunity and Chronic Disease, University of Science and Technology of China, 230027 Hefei, Anhui, China.,School of Data Science, University of Science and Technology of China, 230026 Hefei, Anhui, China
| |
Collapse
|
8
|
Cui F, Zou Q. Biocomputing and Synthetic Biology in Cells: Cells Special Issue. Cells 2020; 9:cells9112459. [PMID: 33187277 PMCID: PMC7697410 DOI: 10.3390/cells9112459] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2020] [Accepted: 11/10/2020] [Indexed: 11/16/2022] Open
Affiliation(s)
- Feifei Cui
- Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China;
| | - Quan Zou
- Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China;
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
- Hainan Key Laboratory for Computational Science and Application, Hainan Normal University, Haikou 570206, China
- Correspondence:
| |
Collapse
|