1
|
Cui W, Long Q, Xiao M, Wang X, Feng G, Li X, Wang P, Zhou Y. Refining computational inference of gene regulatory networks: integrating knockout data within a multi-task framework. Brief Bioinform 2024; 25:bbae361. [PMID: 39082651 PMCID: PMC11289685 DOI: 10.1093/bib/bbae361] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2024] [Revised: 05/09/2024] [Accepted: 07/16/2024] [Indexed: 08/03/2024] Open
Abstract
Constructing accurate gene regulatory network s (GRNs), which reflect the dynamic governing process between genes, is critical to understanding the diverse cellular process and unveiling the complexities in biological systems. With the development of computer sciences, computational-based approaches have been applied to the GRNs inference task. However, current methodologies face challenges in effectively utilizing existing topological information and prior knowledge of gene regulatory relationships, hindering the comprehensive understanding and accurate reconstruction of GRNs. In response, we propose a novel graph neural network (GNN)-based Multi-Task Learning framework for GRN reconstruction, namely MTLGRN. Specifically, we first encode the gene promoter sequences and the gene biological features and concatenate the corresponding feature representations. Then, we construct a multi-task learning framework including GRN reconstruction, Gene knockout predict, and Gene expression matrix reconstruction. With joint training, MTLGRN can optimize the gene latent representations by integrating gene knockout information, promoter characteristics, and other biological attributes. Extensive experimental results demonstrate superior performance compared with state-of-the-art baselines on the GRN reconstruction task, efficiently leveraging biological knowledge and comprehensively understanding the gene regulatory relationships. MTLGRN also pioneered attempts to simulate gene knockouts on bulk data by incorporating gene knockout information.
Collapse
Affiliation(s)
- Wentao Cui
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
| | - Qingqing Long
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
| | - Meng Xiao
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
| | - Xuezhi Wang
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
| | - Guihai Feng
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
- State Key Laboratory of Stem Cell and Reproductive Biology, Institute of Zoology, Chinese Academy of Sciences, 1 Beichen West Road, Chaoyang District, Beijing, 100101, China
| | - Xin Li
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
- State Key Laboratory of Stem Cell and Reproductive Biology, Institute of Zoology, Chinese Academy of Sciences, 1 Beichen West Road, Chaoyang District, Beijing, 100101, China
| | - Pengfei Wang
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
| | - Yuanchun Zhou
- Computer Network Information Center, Chinese Academy of Sciences, CAS Informatization Plaza No. 2 Dong Sheng Nan Lu, Haidian District, Beijing, 100083, China
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Shijingshan District, Beijing, 100049, China
| |
Collapse
|
2
|
Gross B, Dauvin A, Cabeli V, Kmetzsch V, El Khoury J, Dissez G, Ouardini K, Grouard S, Davi A, Loeb R, Esposito C, Hulot L, Ghermi R, Blum M, Darhi Y, Durand EY, Romagnoni A. Robust evaluation of deep learning-based representation methods for survival and gene essentiality prediction on bulk RNA-seq data. Sci Rep 2024; 14:17064. [PMID: 39048590 PMCID: PMC11269749 DOI: 10.1038/s41598-024-67023-8] [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: 04/15/2024] [Accepted: 07/08/2024] [Indexed: 07/27/2024] Open
Abstract
Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions. We demonstrate that baseline methods achieve comparable or superior performance compared to more complex models on survival predictions tasks. DL representation methods, however, are the most efficient to predict the gene essentiality of cell lines. We show that auto-encoders (AE) are consistently improved by techniques such as masking and multi-head training. Our results suggest that the impact of DL representations and of pretraining are highly task- and architecture-dependent, highlighting the need for adopting rigorous evaluation guidelines. These guidelines for robust evaluation are implemented in a pipeline made available to the research community.
Collapse
|
3
|
Vural-Ozdeniz M, Calisir K, Acar R, Yavuz A, Ozgur MM, Dalgıc E, Konu O. CAP-RNAseq: an integrated pipeline for functional annotation and prioritization of co-expression clusters. Brief Bioinform 2024; 25:bbad536. [PMID: 38279653 PMCID: PMC10818169 DOI: 10.1093/bib/bbad536] [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: 10/02/2023] [Revised: 12/04/2023] [Accepted: 12/21/2024] [Indexed: 01/28/2024] Open
Abstract
Cluster analysis is one of the most widely used exploratory methods for visualization and grouping of gene expression patterns across multiple samples or treatment groups. Although several existing online tools can annotate clusters with functional terms, there is no all-in-one webserver to effectively prioritize genes/clusters using gene essentiality as well as congruency of mRNA-protein expression. Hence, we developed CAP-RNAseq that makes possible (1) upload and clustering of bulk RNA-seq data followed by identification, annotation and network visualization of all or selected clusters; and (2) prioritization using DepMap gene essentiality and/or dependency scores as well as the degree of correlation between mRNA and protein levels of genes within an expression cluster. In addition, CAP-RNAseq has an integrated primer design tool for the prioritized genes. Herein, we showed using comparisons with the existing tools and multiple case studies that CAP-RNAseq can uniquely aid in the discovery of co-expression clusters enriched with essential genes and prioritization of novel biomarker genes that exhibit high correlations between their mRNA and protein expression levels. CAP-RNAseq is applicable to RNA-seq data from different contexts including cancer and available at http://konulabapps.bilkent.edu.tr:3838/CAPRNAseq/ and the docker image is downloadable from https://hub.docker.com/r/konulab/caprnaseq.
Collapse
Affiliation(s)
| | - Kubra Calisir
- Department of Molecular Biology and Genetics, Bilkent University, Ankara, Türkiye
| | - Rana Acar
- Department of Molecular Biology and Genetics, Bilkent University, Ankara, Türkiye
| | - Aysenur Yavuz
- Department of Molecular Biology and Genetics, Bilkent University, Ankara, Türkiye
| | - Mustafa M Ozgur
- Department of Molecular Biology and Genetics, Bilkent University, Ankara, Türkiye
| | - Ertugrul Dalgıc
- Department of Medical Biology, School of Medicine, Zonguldak Bülent Ecevit University, Zonguldak, Türkiye
| | - Ozlen Konu
- Department of Neuroscience, Bilkent University, Ankara, Türkiye
- Department of Molecular Biology and Genetics, Bilkent University, Ankara, Türkiye
| |
Collapse
|