Abstract

Motivation

The human microbiome, found throughout various body parts, plays a crucial role in health dynamics and disease development. Recent research has highlighted microbiome disparities between patients with different diseases and healthy individuals, suggesting the microbiome's potential in recognizing health states. Traditionally, microbiome-based status classification relies on pre-trained machine learning (ML) models. However, most ML methods overlook microbial relationships, limiting model performance.

Results

To address this gap, we propose PM-CNN (Phylogenetic Multi-path Convolutional Neural Network), a novel phylogeny-based neural network model for multi-status classification and disease detection using microbiome data. PM-CNN organizes microbes based on their phylogenetic relationships and extracts features using a multi-path convolutional neural network. An ensemble learning method then fuses these features to make accurate classification decisions. We applied PM-CNN to human microbiome data for status and disease detection, demonstrating its significant superiority over existing ML models. These results provide a robust foundation for microbiome-based state recognition and disease prediction in future research and applications.

Availability and implementation

PM-CNN software is available at https://github.com/qdu-bioinfo/PM_CNN.

MeSH

Multiple Chronic Conditions, Classification, Phylogeny, Research, Learning

Cited by

• Exploring the frontier of microbiome biomarker discovery with artificial intelligence. Natl Sci Rev, 2024
• Quantifying uncertainty in microbiome-based prediction using Gaussian processes with microbial community dissimilarities. Bioinform Adv, 2025