mHolmes improves cross anatomical cadaveric microbiome forecasting for postmortem interval estimation
- 1Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Center of AI Biology, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
Abstract
Forensic microbiology leverages postmortem microbiome succession as a promising biomarker for estimating the postmortem interval (PMI). However, current methods are constrained by sparse sampling (typically 3–5 time points) and limited cross-anatomical generalizability, leading to imprecise PMI estimates with errors often exceeding ±3 days, particularly in cases of dismembered remains. To address these limitations, we developed mHolmes, a Transformer-based transfer learning framework for forecasting cadaveric microbiome dynamics. Trained on daily longitudinal data from 34 cadavers over 21 days, mHolmes achieves daily predictions of microbial dynamics, with reduced error (MAE < 2 days) in cross-anatomical forecasting tasks (e.g., hip to face). Shapley Additive exPlanations (SHAP) analysis supports interpretability by identifying seven bacterial classes as candidate PMI-associated features. This study supports mHolmes as a robust forecasting framework that addresses key limitations in sparse and cross anatomical microbiome data, improves PMI estimation from incomplete observations, and has potential forensic applications in body part matching and higher resolution timeline reconstruction.
Related
- Postmortem Gene Expression and the Thanatotranscriptome: Postmortem Interval Estimation, Forensic Applications, and Future Perspectives
- Development of Synthesiomyia nudiseta (Diptera: Muscidae) Under Constant and Fluctuating Temperatures: Implications for Minimum Postmortem Interval Estimation.
- Current Practices in Postmortem Investigation of Sudden Unexpected Death in Infancy
- Down syndrome postmortem brains exhibit reduction in nifene binding to α4β2* nicotinic acetylcholinergic receptors
- Postmortem Alterations of Metabotropic Glutamate Receptors across Neuropsychiatric Disorders: A Systematic Review
BibTeX
@article{han2026mholmes,
title = {{mHolmes improves cross anatomical cadaveric microbiome forecasting for postmortem interval estimation}},
author = {Jin Han and Yuli Zhang and Haohong Zhang and Kouyi Zhou and Xiaoke Chen and Kang Ning},
journal = {Nature Communications},
year = {2026},
month = sep,
doi = {10.1038/s41467-026-77510-3},
url = {https://doi.org/10.1038/s41467-026-77510-3},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - mHolmes improves cross anatomical cadaveric microbiome forecasting for postmortem interval estimation
AU - Jin Han
AU - Yuli Zhang
AU - Haohong Zhang
AU - Kouyi Zhou
AU - Xiaoke Chen
AU - Kang Ning
PY - 2026
DA - 2026/09/28
JO - Nature Communications
DO - 10.1038/s41467-026-77510-3
UR - https://doi.org/10.1038/s41467-026-77510-3
AB - Forensic microbiology leverages postmortem microbiome succession as a promising biomarker for estimating the postmortem interval (PMI). However, current methods are constrained by sparse sampling (typically 3–5 time points) and limited cross-anatomical generalizability, leading to imprecise PMI estimates with errors often exceeding ±3 days, particularly in cases of dismembered remains. To address these limitations, we developed mHolmes, a Transformer-based transfer learning framework for forecasting cadaveric microbiome dynamics. Trained on daily longitudinal data from 34 cadavers over 21 days, mHolmes achieves daily predictions of microbial dynamics, with reduced error (MAE < 2 days) in cross-anatomical forecasting tasks (e.g., hip to face). Shapley Additive exPlanations (SHAP) analysis supports interpretability by identifying seven bacterial classes as candidate PMI-associated features. This study supports mHolmes as a robust forecasting framework that addresses key limitations in sparse and cross anatomical microbiome data, improves PMI estimation from incomplete observations, and has potential forensic applications in body part matching and higher resolution timeline reconstruction.
SN - 2041-1723
ER -