Corpusome, a cross-body-site human microbiome corpus for representation learning
- 1Indiana University
Abstract
Machine-learning models of the human microbiome are trained mostly on stool samples from single cohorts, limiting cross-body-site representation and cross-study generalization. Progress is constrained less by algorithms than by the absence of a harmonized multi-body-site corpus carrying the technical metadata needed to model, rather than ignore, batch structure. Here we release Corpusome, a harmonized two-tier cross-body-site human microbiome corpus for representation learning: a harmonized corpus of 187,546 human microbiome samples integrating standardized profiles from curatedMetagenomicData, the American Gut Project, and the EBI MGnify platform. Corpusome follows a two-tier design preserving both functional depth and cross-body-site breadth: a shotgun tier (22,588 samples, 93 studies) with species- and pathway-level profiles, and a 16S tier (164,958 samples, from a full pull of 708 MGnify studies) with genus-level profiles extending coverage to oral, skin, respiratory, and urogenital sites. It spans six body sites and two modalities, with harmonized metadata for batch-aware modelling. Body-site signal exceeds technical/source variance in the 16S tier by approximately 2.4-fold.
Related
- Simultaneous multi-task assessment of five neurological language disorders via cross-corpus multimodal learning
- Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy
- Concept-aware contrastive representation learning for cross-translation semantic consistency modeling of the Analects
- Whole-Genome Metagenomics Insights Revealed a Uranium Bio-remediating Cross-Domain Microbiome in the Dhala Impact Structure, India
- High-dimensional hippocampus representation facilitates learning of low-dimensional abstract representation and supports generalization
BibTeX
@misc{xuan2026corpusome,
title = {{Corpusome, a cross-body-site human microbiome corpus for representation learning}},
author = {H. Xuan and Y. Huang and J. Bian},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.28.747922},
url = {https://www.biorxiv.org/content/10.64898/2026.08.28.747922v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - Corpusome, a cross-body-site human microbiome corpus for representation learning
AU - H. Xuan
AU - Y. Huang
AU - J. Bian
PY - 2026
DA - 2026/08/28
PB - bioRxiv
DO - 10.64898/2026.08.28.747922
UR - https://www.biorxiv.org/content/10.64898/2026.08.28.747922v2
AB - Machine-learning models of the human microbiome are trained mostly on stool samples from single cohorts, limiting cross-body-site representation and cross-study generalization. Progress is constrained less by algorithms than by the absence of a harmonized multi-body-site corpus carrying the technical metadata needed to model, rather than ignore, batch structure. Here we release Corpusome, a harmonized two-tier cross-body-site human microbiome corpus for representation learning: a harmonized corpus of 187,546 human microbiome samples integrating standardized profiles from curatedMetagenomicData, the American Gut Project, and the EBI MGnify platform. Corpusome follows a two-tier design preserving both functional depth and cross-body-site breadth: a shotgun tier (22,588 samples, 93 studies) with species- and pathway-level profiles, and a 16S tier (164,958 samples, from a full pull of 708 MGnify studies) with genus-level profiles extending coverage to oral, skin, respiratory, and urogenital sites. It spans six body sites and two modalities, with harmonized metadata for batch-aware modelling. Body-site signal exceeds technical/source variance in the 16S tier by approximately 2.4-fold.
ER -