1
|
Maciejewski E, Horvath S, Ernst J. Cross-species and tissue imputation of species-level DNA methylation samples across mammalian species. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.11.26.568769. [PMID: 38076978 PMCID: PMC10705269 DOI: 10.1101/2023.11.26.568769] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/24/2023]
Abstract
DNA methylation data offers valuable insights into various aspects of mammalian biology. The recent introduction and large-scale application of the mammalian methylation array has significantly expanded the availability of such data across conserved sites in many mammalian species. In our study, we consider 13,245 samples profiled on this array encompassing 348 species and 59 tissues from 746 species-tissue combinations. While having some coverage of many different species and tissue types, this data captures only 3.6% of potential species-tissue combinations. To address this gap, we developed CMImpute (Cross-species Methylation Imputation), a method based on a Conditional Variational Autoencoder, to impute DNA methylation for non-profiled species-tissue combinations. In cross-validation, we demonstrate that CMImpute achieves a strong correlation with actual observed values, surpassing several baseline methods. Using CMImpute we imputed methylation data for 19,786 new species-tissue combinations. We believe that both CMImpute and our imputed data resource will be useful for DNA methylation analyses across a wide range of mammalian species.
Collapse
Affiliation(s)
- Emily Maciejewski
- Computer Science Department, University of California, Los Angeles, Los Angeles, CA 90095, USA
- Department of Biological Chemistry, University of California, Los Angeles, Los Angeles, CA 90095, USA
| | - Steve Horvath
- Dept. of Human Genetics, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90095 USA
- Dept. of Biostatistics, Fielding School of Public Health, University of California Los Angeles, Los Angeles, CA 90095, US
- Altos Labs, Cambridge, UK, WA14 2DT
| | - Jason Ernst
- Computer Science Department, University of California, Los Angeles, Los Angeles, CA 90095, USA
- Department of Biological Chemistry, University of California, Los Angeles, Los Angeles, CA 90095, USA
- Eli and Edythe Broad Center of Regenerative Medicine and Stem Cell Research at University of California, Los Angeles, Los Angeles, CA 90095, USA
- Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA
- Jonsson Comprehensive Cancer Center, University of California, Los Angeles, Los Angeles, CA 90095, USA
- Molecular Biology Institute, University of California, Los Angeles, Los Angeles, CA 90095, USA
| |
Collapse
|
2
|
Yue T, Wang Y, Zhang L, Gu C, Xue H, Wang W, Lyu Q, Dun Y. Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models. Int J Mol Sci 2023; 24:15858. [PMID: 37958843 PMCID: PMC10649223 DOI: 10.3390/ijms242115858] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Revised: 10/24/2023] [Accepted: 10/30/2023] [Indexed: 11/15/2023] Open
Abstract
The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.
Collapse
Affiliation(s)
- Tianwei Yue
- School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA; (Y.W.); (L.Z.); (W.W.)
| | - Yuanxin Wang
- School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA; (Y.W.); (L.Z.); (W.W.)
| | - Longxiang Zhang
- School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA; (Y.W.); (L.Z.); (W.W.)
| | - Chunming Gu
- Department of Biomedical Engineering, School of Medicine, Johns Hopkins University, Baltimore, MD 21218, USA;
| | - Haoru Xue
- The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA;
| | - Wenping Wang
- School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA; (Y.W.); (L.Z.); (W.W.)
| | - Qi Lyu
- Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, MI 48824, USA;
| | - Yujie Dun
- School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China;
| |
Collapse
|
3
|
Choi JM, Park C, Chae H. meth-SemiCancer: a cancer subtype classification framework via semi-supervised learning utilizing DNA methylation profiles. BMC Bioinformatics 2023; 24:168. [PMID: 37101254 PMCID: PMC10131478 DOI: 10.1186/s12859-023-05272-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Accepted: 04/05/2023] [Indexed: 04/28/2023] Open
Abstract
BACKGROUND Identification of the cancer subtype plays a crucial role to provide an accurate diagnosis and proper treatment to improve the clinical outcomes of patients. Recent studies have shown that DNA methylation is one of the key factors for tumorigenesis and tumor growth, where the DNA methylation signatures have the potential to be utilized as cancer subtype-specific markers. However, due to the high dimensionality and the low number of DNA methylome cancer samples with the subtype information, still, to date, a cancer subtype classification method utilizing DNA methylome datasets has not been proposed. RESULTS In this paper, we present meth-SemiCancer, a semi-supervised cancer subtype classification framework based on DNA methylation profiles. The proposed model was first pre-trained based on the methylation datasets with the cancer subtype labels. After that, meth-SemiCancer generated the pseudo-subtypes for the cancer datasets without subtype information based on the model's prediction. Finally, fine-tuning was performed utilizing both the labeled and unlabeled datasets. CONCLUSIONS From the performance comparison with the standard machine learning-based classifiers, meth-SemiCancer achieved the highest average F1-score and Matthews correlation coefficient, outperforming other methods. Fine-tuning the model with the unlabeled patient samples by providing the proper pseudo-subtypes, encouraged meth-SemiCancer to generalize better than the supervised neural network-based subtype classification method. meth-SemiCancer is publicly available at https://github.com/cbi-bioinfo/meth-SemiCancer .
Collapse
Affiliation(s)
- Joung Min Choi
- Department of Computer Science, Virginia Tech, Blacksburg, USA
| | - Chaelin Park
- Division of Computer Science, Sookmyung Women's University, Seoul, Republic of Korea
| | - Heejoon Chae
- Division of Computer Science, Sookmyung Women's University, Seoul, Republic of Korea.
| |
Collapse
|
4
|
Choi Y, Li R, Quon G. siVAE: interpretable deep generative models for single-cell transcriptomes. Genome Biol 2023; 24:29. [PMID: 36803416 PMCID: PMC9940350 DOI: 10.1186/s13059-023-02850-y] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Accepted: 01/06/2023] [Indexed: 02/22/2023] Open
Abstract
Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. We present siVAE, a VAE that is interpretable by design, thereby enhancing downstream analysis tasks. Through interpretation, siVAE also identifies gene modules and hubs without explicit gene network inference. We use siVAE to identify gene modules whose connectivity is associated with diverse phenotypes such as iPSC neuronal differentiation efficiency and dementia, showcasing the wide applicability of interpretable generative models for genomic data analysis.
Collapse
Affiliation(s)
- Yongin Choi
- Graduate Group in Biomedical Engineering, University of California, Davis, Davis, CA, USA
- Genome Center, University of California, Davis, Davis, CA, USA
| | - Ruoxin Li
- Genome Center, University of California, Davis, Davis, CA, USA
- Graduate Group in Biostatistics, University of California, Davis, Davis, CA, USA
| | - Gerald Quon
- Graduate Group in Biomedical Engineering, University of California, Davis, Davis, CA, USA.
- Genome Center, University of California, Davis, Davis, CA, USA.
- Department of Molecular and Cellular Biology, University of California, Davis, Davis, CA, USA.
| |
Collapse
|