MetaResNet: Enhancing Microbiome-Based Disease Classification through Colormap Optimization and Imbalance Handling

Abstract

Image-based representations of metagenomic data enable convolutional neural network (CNN) applications for microbiome disease classification. However, the impact of colormap selection on model performance remains unexplored. Current approaches arbitrarily select visualization parameters despite evidence that colormap choices can suppress minority-class features in imbalanced microbiome datasets. This study systematically evaluates colormap effects on metagenomic disease classification to establish evidence-based visualization guidelines. We developed MetaResNet, a custom CNN architecture incorporating residual blocks and attention mechanisms, to assess five colormap schemes (Jet, YlGnBu, Reds, Paired and nipy spectral) across four benchmark datasets: inflammatory bowel disease (n=110), colon cancer (n=121), women type 2 diabetes (n=96), and obesity (n=253). Class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE) versus class weighting strategies. Custom data augmentation preserved taxonomic abundance relationships while enhancing generalization. Performance evaluation employed F1-score, Receiver Operating Characteristic and Area Under the Curve (AUC-ROC), Matthews correlation coefficient (MCC), precision, and recall to address accuracy limitations in imbalanced scenarios. Results identified the Jet colormap coupled with SMOTE as the optimal global configuration, maximizing signal retention and achieving peak performance (AUC 1.00 in Colon). SMOTE significantly improved minority-class recall over class weighting (0.81 {+/-} 0.09 vs. 0.69 {+/-} 0.11, p = 0.003). MetaResNet achieved performance comparable to current state-of-the-art frameworks, while statistically outperforming established deep learning baselines (e.g., DeepMicro, PopPhy-CNN; p = 0.025) in discriminatory power (AUC), with peak values exceeding 0.96. These findings demonstrate that visualization efficacy is strategy-dependent, establishing MetaResNet as a robust framework for microbiome-based diagnostics that supports evidence-based visualization strategies for precision medicine.