Multitask knowledge-primed neural network for predicting missing metadata and host phenotype based on human microbiome.

ABSTRACT:

Motivation

Microbial signatures in the human microbiome are closely associated with various human diseases, driving the development of machine learning models for microbiome-based disease prediction. Despite progress, challenges remain in enhancing prediction accuracy, generalizability, and interpretability. Confounding factors, such as host's gender, age, and body mass index, significantly influence the human microbiome, complicating microbiome-based predictions.

Results

To address these challenges, we developed MicroKPNN-MT, a unified model for predicting human phenotype based on microbiome data, as well as additional metadata like age and gender. This model builds on our earlier MicroKPNN framework, which incorporates prior knowledge of microbial species into neural netwo

SUBMITTER: Monshizadeh M 

PROVIDER: S-EPMC11676323 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature