DeepIMB: Imputation of non-biological zero counts in microbiome data
Genes & Genomics · 2026
DOI: 10.1007/s13258-025-01693-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genes & Genomics, 2026. Verfasst von Hanbyul Song und 2 weiteren Autor:innen. Beteiligte Einrichtung: Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, 08826, Republic of Korea. Hauptthemen laut MEDLINE: Microbiota, Deep Learning. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
BACKGROUND: The high prevalence of non-biological zero counts, arising from low sequencing depth and sampling variation, presents a significant challenge in microbiome data analysis. These zeros can distort taxon abundance distributions and hinder the identification of true biological signals, complicating downstream analyses. OBJECTIVE: To address the challenges of non-biological zeros in microbiome datasets, we propose DeepIMB, a deep learning-based imputation method for microbiome data, specifically designed to accurately identify and impute non-biological zero counts while preserving biological integrity. METHODS: DeepIMB operates in two main phases. First, it identifies non-biological zeros using a gamma-normal mixture model applied to the normalized, log-transformed taxon count matrix. Second, it imputes these zeros with a deep neural network model that integrates diverse sources of information, including taxon abundances, sample covariates, and phylogenetic distances, thereby learning complex, nonlinear relationships within microbiome data. RESULTS: By leveraging integrated information from multiple data types, DeepIMB accurately imputes non-biological zeros while preserving true biological signals. In our two simulation studies, DeepIMB outperformed existing imputation methods in terms of mean squared error, Pearson correlation coefficient, and Wasserstein distance. CONCLUSION: DeepIMB effectively addresses the challenges posed by non-biological zeros in microbiome data. By improving the quality of the data and the reliability of downstream analyses, DeepIMB represents a significant advancement in microbiome research methodologies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, 08826, Republic of Korea.
- Department of Statistics, Seoul National University, Seoul, 08826, Republic of Korea.
- Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, 08826, Republic of Korea. tspark@stats.snu.ac.kr.
- Department of Statistics, Seoul National University, Seoul, 08826, Republic of Korea. tspark@stats.snu.ac.kr.
ORCID-Profile: Taesung Park
Förderung
- National Research Foundation of Korea
Zitieren
APA
Song, H., Hosain, M. M., & Park, T. (2026). DeepIMB: Imputation of non-biological zero counts in microbiome data. Genes & Genomics. https://doi.org/10.1007/s13258-025-01693-0
Vancouver
Song H, Hosain MM, Park T. DeepIMB: Imputation of non-biological zero counts in microbiome data. Genes & Genomics. 2026. doi:10.1007/s13258-025-01693-0
BibTeX
@article{Song2026,
author = {Song, Hanbyul and Hosain, Md Mozaffar and Park, Taesung},
title = {DeepIMB: Imputation of non-biological zero counts in microbiome data},
journal = {Genes & Genomics},
year = {2026},
doi = {10.1007/s13258-025-01693-0}
}
EUVIMED