1
|
Yao Z, Li F, Xie W, Chen J, Wu J, Zhan Y, Wu X, Wang Z, Zhang G. DeepSF-4mC: A deep learning model for predicting DNA cytosine 4mC methylation sites leveraging sequence features. Comput Biol Med 2024; 171:108166. [PMID: 38382385 DOI: 10.1016/j.compbiomed.2024.108166] [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: 10/06/2023] [Revised: 02/15/2024] [Accepted: 02/15/2024] [Indexed: 02/23/2024]
Abstract
N4-methylcytosine (4mC) is a DNA modification involving the addition of a methyl group to the fourth nitrogen atom of the cytosine base. This modification may influence gene regulation, providing potential insights into gene control mechanisms. Traditional laboratory methods for detecting 4mC DNA methylation have limitations, but the rise of artificial intelligence has introduced efficient computational strategies for 4mC site prediction. Despite this progress, challenges persist in terms of model performance and interpretability. To tackle these challenges, we propose DeepSF-4mC, a deep learning model specifically designed for predicting DNA cytosine 4mC methylation sites by leveraging sequence features. Our approach incorporates multiple encoding techniques to enhance prediction accuracy, increase model stability, and reduce the computational resources needed. Leveraging transfer learning, we harness existing models to enhance performance through learned representations or fine-tuning. Ensemble learning techniques combine predictions from multiple models, boosting robustness and accuracy. This research contributes to DNA methylation analysis and lays the groundwork for understanding 4mC's multifaceted role in biological processes. The web server for DeepSF-4mC is accessible at: http://deepsf-4mc.top/and the original code can be found at: https://github.com/754131799/DeepSF-4mC.
Collapse
Affiliation(s)
- Zhaomin Yao
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Fei Li
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China
| | - Weiming Xie
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Jiaming Chen
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Jiezhang Wu
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Ying Zhan
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China
| | - Xiaodan Wu
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China
| | - Zhiguo Wang
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China.
| | - Guoxu Zhang
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, 110016, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, 110167, China.
| |
Collapse
|
2
|
Duan M, Wang Y, Zhao D, Liu H, Zhang G, Li K, Zhang H, Huang L, Zhang R, Zhou F. Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis. Brief Bioinform 2023; 24:bbad238. [PMID: 37427963 DOI: 10.1093/bib/bbad238] [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: 04/09/2023] [Revised: 05/29/2023] [Accepted: 06/08/2023] [Indexed: 07/11/2023] Open
Abstract
Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.
Collapse
Affiliation(s)
- Meiyu Duan
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
| | - Yueying Wang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
| | - Dong Zhao
- School of Biology and Engineering, and Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou 550025, China
| | - Hongmei Liu
- School of Biology and Engineering, and Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou 550025, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, China, 130012
| | - Gongyou Zhang
- School of Biology and Engineering, and Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou 550025, China
| | - Kewei Li
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
| | - Haotian Zhang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
| | - Lan Huang
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, China, 130012
| | - Ruochi Zhang
- School of Artificial Intelligence, Jilin University, Changchun, China, 130012
| | - Fengfeng Zhou
- College of Computer Science and Technology, Jilin University, Changchun, Jilin, China, 130012
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, China, 130012
| |
Collapse
|
3
|
Gene expression prediction based on neighbour connection neural network utilizing gene interaction graphs. PLoS One 2023; 18:e0281286. [PMID: 36745614 PMCID: PMC9901809 DOI: 10.1371/journal.pone.0281286] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Accepted: 01/19/2023] [Indexed: 02/07/2023] Open
Abstract
Having observed that gene expressions have a correlation, the Library of Integrated Network-based Cell-Signature program selects 1000 landmark genes to predict the remaining gene expression value. Further works have improved the prediction result by using deep learning models. However, these models ignore the latent structure of genes, limiting the accuracy of the experimental results. We therefore propose a novel neural network named Neighbour Connection Neural Network(NCNN) to utilize the gene interaction graph information. Comparing to the popular GCN model, our model incorperates the graph information in a better manner. We validate our model under two different settings and show that our model promotes prediction accuracy comparing to the other models.
Collapse
|
4
|
Thakur T, Batra I, Luthra M, Vimal S, Dhiman G, Malik A, Shabaz M. Gene Expression-Assisted Cancer Prediction Techniques. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:4242646. [PMID: 34545300 PMCID: PMC8449724 DOI: 10.1155/2021/4242646] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/13/2021] [Accepted: 08/13/2021] [Indexed: 02/07/2023]
Abstract
Cancer is one of the deadliest diseases and with its growing number, its detection and treatment become essential. Researchers have developed various methods based on gene expression. Gene expression is a process that is used to convert deoxyribose nucleic acid (DNA) to ribose nucleic acid (RNA) and then RNA to protein. This protein serves so many purposes, such as creating cells, drugs for cancer, and even hybrid species. As genes carry genetic information from one generation to another, some gene deformity is also transferred to the next generation. Therefore, the deformity needs to be detected. There are many techniques available in the literature to predict cancerous and noncancerous genes from gene expression data. This is an important development from the point of diagnostics and giving a prognosis for the condition. This paper will present a review of some of those techniques from the literature; details about the various datasets on which these techniques are implemented and the advantages and disadvantages.
Collapse
Affiliation(s)
- Tanima Thakur
- School of Computer Science and Engineering, Lovely Professional University, Jalandhar, India
| | - Isha Batra
- School of Computer Science and Engineering, Lovely Professional University, Jalandhar, India
| | | | - Shanmuganathan Vimal
- Department of CSE, Ramco Institute of Technology, Rajapalayam, Tamil Nadu, India
| | - Gaurav Dhiman
- Department of Computer Science, Government Bikram College of Commerce, Patiala, India
| | - Arun Malik
- School of Computer Science and Engineering, Lovely Professional University, Jalandhar, India
| | - Mohammad Shabaz
- Arba Minch University, Arba Minch, Ethiopia
- Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
| |
Collapse
|
5
|
Kunc V, Kléma J. On transformative adaptive activation functions in neural networks for gene expression inference. PLoS One 2021; 16:e0243915. [PMID: 33444316 PMCID: PMC7808640 DOI: 10.1371/journal.pone.0243915] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2020] [Accepted: 12/01/2020] [Indexed: 11/19/2022] Open
Abstract
Gene expression profiling was made more cost-effective by the NIH LINCS program that profiles only ∼1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D-GEX method employs neural networks to infer the entire profile. However, the original D-GEX can be significantly improved. We propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves an average mean absolute error of 0.1340, which is a significant improvement over our reimplementation of the original D-GEX, which achieves an average mean absolute error of 0.1637. The proposed transformative adaptive function enables a significantly more accurate reconstruction of the full gene expression profiles with only a small increase in the complexity of the model and its training procedure compared to other methods.
Collapse
Affiliation(s)
- Vladimír Kunc
- Department of Computer Science, Czech Technical University in Prague, Faculty of Electrical Engineering, Prague, Czech Republic
| | - Jiří Kléma
- Department of Computer Science, Czech Technical University in Prague, Faculty of Electrical Engineering, Prague, Czech Republic
| |
Collapse
|