1
|
Yuan Q, Duren Z. Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data. Nat Biotechnol 2024:10.1038/s41587-024-02182-7. [PMID: 38609714 DOI: 10.1038/s41587-024-02182-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Accepted: 02/26/2024] [Indexed: 04/14/2024]
Abstract
Existing methods for gene regulatory network (GRN) inference rely on gene expression data alone or on lower resolution bulk data. Despite the recent integration of chromatin accessibility and RNA sequencing data, learning complex mechanisms from limited independent data points still presents a daunting challenge. Here we present LINGER (Lifelong neural network for gene regulation), a machine-learning method to infer GRNs from single-cell paired gene expression and chromatin accessibility data. LINGER incorporates atlas-scale external bulk data across diverse cellular contexts and prior knowledge of transcription factor motifs as a manifold regularization. LINGER achieves a fourfold to sevenfold relative increase in accuracy over existing methods and reveals a complex regulatory landscape of genome-wide association studies, enabling enhanced interpretation of disease-associated variants and genes. Following the GRN inference from reference single-cell multiome data, LINGER enables the estimation of transcription factor activity solely from bulk or single-cell gene expression data, leveraging the abundance of available gene expression data to identify driver regulators from case-control studies.
Collapse
Affiliation(s)
- Qiuyue Yuan
- Center for Human Genetics, Department of Genetics and Biochemistry, Clemson University, Greenwood, SC, USA
| | - Zhana Duren
- Center for Human Genetics, Department of Genetics and Biochemistry, Clemson University, Greenwood, SC, USA.
| |
Collapse
|
2
|
Liu Y, Darville T, Zheng X, Li Q. Decomposition of variation of mixed variables by a latent mixed Gaussian copula model. Biometrics 2023; 79:1187-1200. [PMID: 35304917 PMCID: PMC10019899 DOI: 10.1111/biom.13660] [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: 07/21/2021] [Accepted: 03/03/2022] [Indexed: 11/27/2022]
Abstract
Many biomedical studies collect data of mixed types of variables from multiple groups of subjects. Some of these studies aim to find the group-specific and the common variation among all these variables. Even though similar problems have been studied by some previous works, their methods mainly rely on the Pearson correlation, which cannot handle mixed data. To address this issue, we propose a latent mixed Gaussian copula (LMGC) model that can quantify the correlations among binary, ordinal, continuous, and truncated variables in a unified framework. We also provide a tool to decompose the variation into the group-specific and the common variation over multiple groups via solving a regularized M-estimation problem. We conduct extensive simulation studies to show the advantage of our proposed method over the Pearson correlation-based methods. We also demonstrate that by jointly solving the M-estimation problem over multiple groups, our method is better than decomposing the variation group by group. We also apply our method to a Chlamydia trachomatis genital tract infection study to demonstrate how it can be used to discover informative biomarkers that differentiate patients.
Collapse
Affiliation(s)
- Yutong Liu
- Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| | - Toni Darville
- Department of Pediatrics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| | - Xiaojing Zheng
- Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
- Department of Pediatrics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| | - Quefeng Li
- Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| |
Collapse
|
3
|
Chowdhury S, Wang R, Yu Q, Huntoon CJ, Karnitz LM, Kaufmann SH, Gygi SP, Birrer MJ, Paulovich AG, Peng J, Wang P. DAGBagM: learning directed acyclic graphs of mixed variables with an application to identify protein biomarkers for treatment response in ovarian cancer. BMC Bioinformatics 2022; 23:321. [PMID: 35931981 PMCID: PMC9354326 DOI: 10.1186/s12859-022-04864-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2022] [Accepted: 07/28/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Applying directed acyclic graph (DAG) models to proteogenomic data has been shown effective for detecting causal biomarkers of complex diseases. However, there remain unsolved challenges in DAG learning to jointly model binary clinical outcome variables and continuous biomarker measurements. RESULTS In this paper, we propose a new tool, DAGBagM, to learn DAGs with both continuous and binary nodes. By using appropriate models, DAGBagM allows for either continuous or binary nodes to be parent or child nodes. It employs a bootstrap aggregating strategy to reduce false positives in edge inference. At the same time, the aggregation procedure provides a flexible framework to robustly incorporate prior information on edges. CONCLUSIONS Through extensive simulation experiments, we demonstrate that DAGBagM has superior performance compared to alternative strategies for modeling mixed types of nodes. In addition, DAGBagM is computationally more efficient than two competing methods. When applying DAGBagM to proteogenomic datasets from ovarian cancer studies, we identify potential protein biomarkers for platinum refractory/resistant response in ovarian cancer. DAGBagM is made available as a github repository at https://github.com/jie108/dagbagM .
Collapse
Affiliation(s)
- Shrabanti Chowdhury
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Ru Wang
- Department of Statistics, University of California, Davis, CA, 95616, USA
| | - Qing Yu
- Department of Cell Biology, Harvard Medical School, Boston, MA, 02115, USA
| | - Catherine J Huntoon
- Division of Oncology Research and Department of Oncology, Mayo Clinic, Rochester, MN, 55905, USA
| | - Larry M Karnitz
- Division of Oncology Research and Department of Oncology, Mayo Clinic, Rochester, MN, 55905, USA
| | - Scott H Kaufmann
- Division of Oncology Research, Mayo Clinic, Rochester, MN, 55905, USA
| | - Steven P Gygi
- Department of Cell Biology, Harvard Medical School, Boston, MA, 02115, USA
| | - Michael J Birrer
- Winthrop P. Rockefeller Cancer Institute, University of Arkansas for Medical Sciences, Little Rock, AR, 72205, USA
| | - Amanda G Paulovich
- Clinical Research Division, Fred Hutchinson Cancer Center, Seattle, WA, 98109, USA
| | - Jie Peng
- Department of Statistics, University of California, Davis, CA, 95616, USA.
| | - Pei Wang
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA.
| |
Collapse
|
4
|
Lu H, Wei Y, Jiang Z, Zhang J, Wang T, Huang S, Zeng P. Integrative eQTL-weighted hierarchical Cox models for SNP-set based time-to-event association studies. J Transl Med 2021; 19:418. [PMID: 34627275 PMCID: PMC8502405 DOI: 10.1186/s12967-021-03090-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2021] [Accepted: 09/26/2021] [Indexed: 01/23/2023] Open
Abstract
BACKGROUND Integrating functional annotations into SNP-set association studies has been proven a powerful analysis strategy. Statistical methods for such integration have been developed for continuous and binary phenotypes; however, the SNP-set integrative approaches for time-to-event or survival outcomes are lacking. METHODS We here propose IEHC, an integrative eQTL (expression quantitative trait loci) hierarchical Cox regression, for SNP-set based survival association analysis by modeling effect sizes of genetic variants as a function of eQTL via a hierarchical manner. Three p-values combination tests are developed to examine the joint effects of eQTL and genetic variants after a novel decorrelated modification of statistics for the two components. An omnibus test (IEHC-ACAT) is further adapted to aggregate the strengths of all available tests. RESULTS Simulations demonstrated that the IEHC joint tests were more powerful if both eQTL and genetic variants contributed to association signal, while IEHC-ACAT was robust and often outperformed other approaches across various simulation scenarios. When applying IEHC to ten TCGA cancers by incorporating eQTL from relevant tissues of GTEx, we revealed that substantial correlations existed between the two types of effect sizes of genetic variants from TCGA and GTEx, and identified 21 (9 unique) cancer-associated genes which would otherwise be missed by approaches not incorporating eQTL. CONCLUSION IEHC represents a flexible, robust, and powerful approach to integrate functional omics information to enhance the power of identifying association signals for the survival risk of complex human cancers.
Collapse
Affiliation(s)
- Haojie Lu
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
| | - Yongyue Wei
- Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, 211166, Jiangsu, China
| | - Zhou Jiang
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
| | - Jinhui Zhang
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
| | - Ting Wang
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
| | - Shuiping Huang
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
- Center for Medical Statistics and Data Analysis, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
- Key Laboratory of Human Genetics and Environmental Medicine, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China
| | - Ping Zeng
- Department of Biostatistics, School of Public Health, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China.
- Center for Medical Statistics and Data Analysis, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China.
- Key Laboratory of Human Genetics and Environmental Medicine, Xuzhou Medical University, Xuzhou, 221004, Jiangsu, China.
| |
Collapse
|
5
|
Picard M, Scott-Boyer MP, Bodein A, Périn O, Droit A. Integration strategies of multi-omics data for machine learning analysis. Comput Struct Biotechnol J 2021; 19:3735-3746. [PMID: 34285775 PMCID: PMC8258788 DOI: 10.1016/j.csbj.2021.06.030] [Citation(s) in RCA: 148] [Impact Index Per Article: 49.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Revised: 06/17/2021] [Accepted: 06/21/2021] [Indexed: 12/25/2022] Open
Abstract
Increased availability of high-throughput technologies has generated an ever-growing number of omics data that seek to portray many different but complementary biological layers including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. New insight from these data have been obtained by machine learning algorithms that have produced diagnostic and classification biomarkers. Most biomarkers obtained to date however only include one omic measurement at a time and thus do not take full advantage of recent multi-omics experiments that now capture the entire complexity of biological systems. Multi-omics data integration strategies are needed to combine the complementary knowledge brought by each omics layer. We have summarized the most recent data integration methods/ frameworks into five different integration strategies: early, mixed, intermediate, late and hierarchical. In this mini-review, we focus on challenges and existing multi-omics integration strategies by paying special attention to machine learning applications.
Collapse
Affiliation(s)
- Milan Picard
- Molecular Medicine Department, CHU de Québec Research Center, Université Laval, Québec, QC, Canada
| | - Marie-Pier Scott-Boyer
- Molecular Medicine Department, CHU de Québec Research Center, Université Laval, Québec, QC, Canada
| | - Antoine Bodein
- Molecular Medicine Department, CHU de Québec Research Center, Université Laval, Québec, QC, Canada
| | - Olivier Périn
- Digital Sciences Department, L'Oréal Advanced Research, Aulnay-sous-bois, France
| | - Arnaud Droit
- Molecular Medicine Department, CHU de Québec Research Center, Université Laval, Québec, QC, Canada
- Corresponding author.
| |
Collapse
|
6
|
Lu J, Wilfred P, Korbie D, Trau M. Regulation of Canonical Oncogenic Signaling Pathways in Cancer via DNA Methylation. Cancers (Basel) 2020; 12:E3199. [PMID: 33143142 PMCID: PMC7692324 DOI: 10.3390/cancers12113199] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2020] [Revised: 10/24/2020] [Accepted: 10/28/2020] [Indexed: 02/07/2023] Open
Abstract
Disruption of signaling pathways that plays a role in the normal development and cellular homeostasis may lead to the dysregulation of cellular signaling and bring about the onset of different diseases, including cancer. In addition to genetic aberrations, DNA methylation also acts as an epigenetic modifier to drive the onset and progression of cancer by mediating the reversible transcription of related genes. Although the role of DNA methylation as an alternative driver of carcinogenesis has been well-established, the global effects of DNA methylation on oncogenic signaling pathways and the presentation of cancer is only emerging. In this article, we introduced a differential methylation parsing pipeline (MethylMine) which mined for epigenetic biomarkers based on feature selection. This pipeline was used to mine for biomarkers, which presented a substantial difference in methylation between the tumor and the matching normal tissue samples. Combined with the Data Integration Analysis for Biomarker discovery (DIABLO) framework for machine learning and multi-omic analysis, we revisited the TCGA DNA methylation and RNA-Seq datasets for breast, colorectal, lung, and prostate cancer, and identified differentially methylated genes within the NRF2-KEAP1/PI3K oncogenic pathway, which regulates the expression of cytoprotective genes, that serve as potential therapeutic targets to treat different cancers.
Collapse
Affiliation(s)
- Jennifer Lu
- Centre for Personalised Nanomedicine, Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia; (J.L.); (P.W.)
- Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia
| | - Premila Wilfred
- Centre for Personalised Nanomedicine, Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia; (J.L.); (P.W.)
- Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia
| | - Darren Korbie
- Centre for Personalised Nanomedicine, Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia; (J.L.); (P.W.)
- Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia
| | - Matt Trau
- Centre for Personalised Nanomedicine, Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia; (J.L.); (P.W.)
- Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, QLD 4072, Australia
- School of Chemistry and Molecular Biosciences, The University of Queensland, St Lucia, QLD 4072, Australia
| |
Collapse
|