mbSparse: an autoencoder-based imputation method to address sparsity in microbiome data.
The involvement of gut microbiota in host physiological activities is crucial, yet the high sparsity of microbiome data, marked by numerous zeros in count matrices, presents huge analytical challenges
APA
Qi C, Cai Y, et al. (2025). mbSparse: an autoencoder-based imputation method to address sparsity in microbiome data.. Gut microbes, 17(1), 2552347. https://doi.org/10.1080/19490976.2025.2552347
MLA
Qi C, et al.. "mbSparse: an autoencoder-based imputation method to address sparsity in microbiome data.." Gut microbes, vol. 17, no. 1, 2025, pp. 2552347.
PMID
40888610
Abstract
The involvement of gut microbiota in host physiological activities is crucial, yet the high sparsity of microbiome data, marked by numerous zeros in count matrices, presents huge analytical challenges. To overcome this, we developed mbSparse, an imputation algorithm that leverages deep learning rather than traditional predefined count distributions. Utilizing a feature autoencoder for learning sample representations and a conditional variational autoencoder (CVAE) for data reconstruction, mbSparse effectively integrates these processes to enhance imputation. Our results demonstrate that mbSparse achieves exceptional accuracy, with mean squared error reductions of up to 4.1 compared to existing microbiome methods, even amid outlier samples and varying sequencing depths. In colorectal cancer analysis, mbSparse increases the detection of validated disease-associated taxa from 7 to 27, while predictive accuracy improves, as evidenced by area under the precision-recall area under the curve values rising from 0.85 to 0.93. Additionally, mbSparse addresses non-biological zeros by restoring over 88% of removed counts and achieving a Pearson correlation of 0.9354 at a 10% removal rate, preserving essential taxonomic relationships. Finally, our exploration of mbSparse variants reveals that the CVAE is critical for enhancing accuracy, providing valuable insights for further optimizing microbiome data imputation techniques.
MeSH Terms
Humans; Gastrointestinal Microbiome; Colorectal Neoplasms; Algorithms; Bacteria; Deep Learning; Computational Biology; Autoencoder
같은 제1저자의 인용 많은 논문 (3)
- Characterization of Cell-Surface Interactions of Ligands Using F NMR and DNP Hyperpolarization.
- Safety and Efficacy of CT041 in Patients With Refractory Metastatic Pancreatic Cancer: A Pooled Analysis of Two Early-Phase Trials.
- Delineating the underlying molecular mechanisms and key genes involved in metastasis of colorectal cancer via bioinformatics analysis.