@inproceedings{6489e1b77d734e728a836f8abc14ab5d,
title = "GCVAE: A graph conditional variational autoencoder for feature dependency guided synthetic metabolomic data generation",
abstract = "Metabolomics benefits biomarker discovery and other applications, but publicly available metabolomic data is very limited. Synthetic metabolomic data can aid novel research paradigms. Due to curse of dimensionality, real metabolomic data are often incompatible with major generative approaches such as conditional variational autoencoder (CVAE) and conditional generative adversarial network (CGAN). We present a novel graph conditional variational autoencoder (GCVAE) to exploit feature dependency graphs - capturing relationships in real data - to restrict the exponential space of feature combinations by aligning learned distributions with the graph, which benefits small training data. We evaluate GCVAE for synthetic metabolomic data generation from 4 aspects - fidelity, correlation, utility, and privacy. We show that GCVAE often generates higher quality synthetic data than CVAE and/or CGAN. We show that GCVAE can further improve synthetic data by utilizing domain knowledge on metabolic reactions. Overall, our results show that the feature dependency-guided GCVAE is a promising approach for generating synthetic metabolomic data from limited real data.",
keywords = "correlation graph, domain knowledge, graph conditional variational autoencoder, knowledge graph, metabolomics, synthetic data",
author = "Kowshika Sarker and Chengxiang Zhai",
note = "This work is partially supported by Personalized Nutrition Initiative at University of Illinois at Urbana-Champaign via a seed grant. We thank the anonymous reviewers for constructive feedback.; 16th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2025 ; Conference date: 12-10-2025 Through 15-10-2025",
year = "2025",
month = dec,
day = "10",
doi = "10.1145/3765612.3767249",
language = "English (US)",
series = "BCB 2025 - Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",
publisher = "Association for Computing Machinery",
booktitle = "BCB 2025 - Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",
address = "United States",
}