Synthesizing Time-Series Gene Expression Data to Enhance Network Inference Performance Using Autoencoder
Source abstract
Abstract
It is a challenge to infer a gene regulatory network from time-series gene expression data in the systems biology field. A lack of gene expression data samples is a factor limiting the performance of the inference methods. To resolve this problem, we propose a novel autoencoder-based approach that synthesizes virtual gene expression data to be used as input to the inference method. Through intensive experiments, we showed that using synthetic gene expression as input improves the performance of the network inference method compared to that without it. In particular, the performance improvement was stable against the discretization level of gene expression, the number of time steps in the observed gene expression, and the number of genes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gene Regulatory Network Analysis · Bioinformatics and Genomic Networks · Gene expression and cancer classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea
Funding
2024 Research Fund of the University of Ulsan
References (59)
Show source-provided references
1. Malvina, M., and Pancaldi, V. (2023). From time-series transcriptomics to gene regulatory networks: A review on inference methods. PLoS Comput. Biol., 19.10.1371/journal.pcbi.1011254 ↗
2. ARACNE: An Algorithm for the Reconstruction of Gene Regulatory Networks in a Mammalian Cellular Context10.1186/1471-2105-7-S1-S7 ↗
3. MICRAT: A novel algorithm for inferring gene regulatory networks using time series gene expression data10.1186/s12918-018-0635-1 ↗
4. Liang, K., and Wang, X. (2008). Gene regulatory network reconstruction using conditional mutual information. EURASIP J. Bioinform. Syst. Biol., 2008.10.1155/2008/253894 ↗
5. Huynh-Thu, V.A., Irrthum, A., Wehenkel, L., and Geurts, P. (2010). Inferring regulatory networks from expression data using tree-based methods. PLoS ONE, 5.10.1371/journal.pone.0012776 ↗
6. Integrative random forest for gene regulatory network inference10.1093/bioinformatics/btv268 ↗
7. Park, S., Kim, J.M., Shin, W., Han, S.W., Jeon, M., Jang, H.J., Jang, I.S., and Kang, J. (2018). BTNET: Boosted tree-based gene regulatory network inference algorithm using time-course measurement data. BMC Syst. Biol., 12.10.1186/s12918-018-0547-0 ↗
8. Chen, H., Mundra, P.A., Zhao, L.N., Lin, F., and Zheng, J. (2014). Highly sensitive inference of time-delayed gene regulation by network deconvolution. BMC Syst. Biol., 8.10.1186/1752-0509-8-S4-S6 ↗
9. Siegal-Gaskins, D., Ash, J.N., and Crosson, S. (2009). Model-based deconvolution of cell cycle time-series data reveals gene expression details at high resolution. PLoS Comput. Biol., 5.10.1371/journal.pcbi.1000460 ↗
10. A novel constrained genetic algorithm-based Boolean network inference method from steady-state gene expression data10.1093/bioinformatics/btab295 ↗
11. Inference of gene regulatory networks using boolean-network inference methods10.1142/S0219720009004448 ↗
12. Inference of gene regulatory networks based on nonlinear ordinary differential equations10.1093/bioinformatics/btaa032 ↗
13. Large-scale dynamic gene regulatory network inference combining differential equation models with local dynamic Bayesian network analysis10.1093/bioinformatics/btr454 ↗
14. Gene regulatory network inference from sparsely sampled noisy data10.1038/s41467-020-17217-1 ↗
15. Overview of gene regulatory network inference based on differential equation models10.2174/1389203721666200213103350 ↗
16. Thorne, T. (2018). Approximate inference of gene regulatory network models from RNA-Seq time series data. BMC Bioinform., 19.10.1186/s12859-018-2125-2 ↗
17. Autoregressive models for gene regulatory network inference: Sparsity, stability and causality issues10.1016/j.mbs.2013.10.003 ↗
18. Random forests10.1023/A:1010933404324 ↗
19. Murphy, K., and Mian, S. (1999). Modelling Gene Expression Data Using Dynamic Bayesian Networks, Computer Science Division, University of California. Technical Report.
20. Inferring gene networks from time series microarray data using dynamic Bayesian networks10.1093/bib/4.3.228 ↗
21. A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time-course microarray data10.1093/bioinformatics/bth463 ↗
22. Gene expression studies using microarrays: Principles, problems, and prospects10.1152/advan.00043.2002 ↗
23. DEEPFAKE Image Synthesis for Data Augmentation10.1109/ACCESS.2022.3193668 ↗
24. Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J., and Greenspan, H. (2018, January 4–7). Synthetic data augmentation using GAN for improved liver lesion classification. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363576 ↗
25. MinimalGAN: Diverse medical image synthesis for data augmentation using minimal training data10.1007/s10489-022-03609-x ↗
26. Gooya, A., Goksel, O., Oguz, I., and Burgos, N. (2018). Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks. Simulation and Synthesis in Medical Imaging, Springer. SASHIMI 2018; Lecture Notes in Computer Science.10.1007/978-3-030-00536-8 ↗
27. Forestier, G., Petitjean, F., Dau, H.A., Webb, G.I., and Keogh, E. (2017, January 9–12). Generating Synthetic Time Series to Augment Sparse Datasets. Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA.10.1109/ICDM.2017.106 ↗
28. Generating Healthcare Time Series Data for Improving Diagnostic Accuracy of Deep Neural Networks10.1109/TIM.2021.3077049 ↗
29. Leznik, M., Michalsky, P., Willis, P., Schanzel, B., Östberg, P.O., and Domaschka, J. (2021, January 19–23). Multivariate Time Series Synthesis Using Generative Adversarial Networks. Proceedings of the ACM/SPEC International Conference on Performance Engineering, ICPE ’21, New York, NY, USA.10.1145/3427921.3450257 ↗
30. GeneNetWeaver: In silico benchmark generation and performance profiling of network inference methods10.1093/bioinformatics/btr373 ↗
31. DREAM (2010, November 15). Dream: Dialogue for Reverse Engineering Assessments and Methods. Available online: https://gnw.sourceforge.net/dreamchallenge.html.
32. Albert, I., Thakar, J., Li, S., Zhang, R., and Albert, R. (2008). Boolean network simulations for life scientists. Source Code Biol. Med., 3.10.1186/1751-0473-3-16 ↗
33. Modeling and simulation of genetic regulatory systems: A literature review10.1089/10665270252833208 ↗
34. Genetic Network Analyzer: Qualitative simulation of genetic regulatory networks10.1093/bioinformatics/btf851 ↗
35. Artificial gene networks for objective comparison of analysis algorithms10.1093/bioinformatics/btg1069 ↗
36. Van den Bulcke, T., Van Leemput, K., Naudts, B., van Remortel, P., Ma, H., Verschoren, A., De Moor, B., and Marchal, K. (2006). SynTReN: A generator of synthetic gene expression data for design and analysis of structure learning algorithms. BMC Bioinform., 7.10.1186/1471-2105-7-43 ↗
37. Gene expression complex networks: Synthesis, identification, and analysis10.1089/cmb.2010.0118 ↗
38. Generative adversarial networks10.1145/3422622 ↗
39. Arjovsky, M., and Bottou, L. (2017). Towards Principled Methods for Training Generative Adversarial Networks. arXiv.
40. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training GANs. arXiv.
41. Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders
42. Learning a hierarchical representation of the yeast transcriptomic machinery using an autoencoder model10.1186/s12859-015-0852-1 ↗
43. Anh, C.-T., and Kwon, Y.-K. (2023). Mutual Information Based on Multiple Level Discretization Network Inference from Time Series Gene Expression Profiles. Appl. Sci., 13.10.3390/app132111902 ↗
44. Moscana, A., and Monroy, A. (1971). Gene regulation networks: A theory for their structure and global behavior. Current Topics in Developmental Biology 6, Academic Press.
45. Barman, S., and Kwon, Y.-K. (2017). A novel mutual information-based Boolean network inference method from time-series gene expression data. PLoS ONE, 12.10.1371/journal.pone.0171097 ↗
46. LeCun, Y. (1987). Connexionist Learning Models. [Ph.D. Thesis, Sorbonne University—Pierre and Marie Curie Campus].
47. Li, J., Luong, M., and Jurafsky, D. (2015). A Hierarchical Neural Autoencoder for Paragraphs and Documents. arXiv.10.3115/v1/P15-1107 ↗
48. Freitag, M., and Roy, S. (2018). Unsupervised Natural Language Generation with Denoising Autoencoders. arXiv.10.18653/v1/D18-1426 ↗
49. Akram, M.W., Salman, M., Bashir, M.F., Salman, S.M.S., Gadekallu, T.R., and Javed, A.R. (2022). A novel deep auto-encoder based linguistics clustering model for social text. ACM Trans. Asian-Low-Resour. Lang. Inf. Process.10.1145/3527838 ↗
50. Masked Autoencoders in Computer Vision: A Comprehensive Survey10.1109/ACCESS.2023.3323383 ↗
51. Parmar, G., Li, D., Lee, K., and Tu, Z. (2021, January 20–25). Dual contradistinctive generative autoencoder. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00088 ↗
52. Cheng, Z., Sun, H., Takeuchi, M., and Katto, J. (2018, January 24–27). Deep convolutional autoencoder-based lossy image compression. Proceedings of the 2018 Picture Coding Symposium (PCS), San Francisco, CA, USA.10.1109/PCS.2018.8456308 ↗
53. Vachhani, B., Bhat, C., Das, B., and Kopparapu, S.K. (2017). Deep Autoencoder Based Speech Features for Improved Dysarthric Speech Recognition. Interspeech, ISCA.10.21437/Interspeech.2017-1318 ↗
54. Karita, S., Watanabe, S., Iwata, T., Delcroix, M., Ogawa, A., and Nakatani, T. (2019, January 12–17). Semi-supervised end-to-end speech recognition using text-to-speech and autoencoders. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8682890 ↗
55. Géron, A. (2022, October 04). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow; O’Reilly Media; 2022; ISBN 9781098122478. Available online: https://books.google.co.kr/books?id=V5ySEAAAQBAJ.
56. Song, Q., Jin, H., and Hu, X. (2022, June 07). Automated Machine Learning in Action; Manning Publications; 2022; ISBN 9781617298059. Available online: https://www.manning.com/books/automated-machine-learning-in-action.
57. Barabási, A.-L., and Albert, R. (2006). Emergence of Scaling in Random Networks. The Structure and Dynamics of Networks, Princeton University Press.
58. Graph representation learning: A survey10.1017/ATSIP.2020.13 ↗
59. Discovering Consensus Regions for Interpretable Identification of RNA N6-Methyladenosine Modification Sites via Graph Contrastive Clustering10.1109/JBHI.2024.3357979 ↗