DepMicroDiff: Diffusion-Based Dependency-Aware Multimodal Imputation for Microbiome Data.

Microbiome data analysis is essential for understanding host health and disease, yet its inherent sparsity and noise pose major challenges for accurate imputation, hindering downstream tasks such as biomarker discovery. Existing imputation methods, including recent diffusion-based models, often fail to capture the complex interdependencies between microbial taxa and overlook contextual metadata that can inform imputation. We introduce DepMicroDiff, a novel framework that combines diffusion-based generative modeling with a Dependency-Aware Transformer (DAT) to explicitly capture both mutual pairwise dependencies and autoregressive relationships. DepMicroDiff is further enhanced by variational autoencoder-based pretraining across diverse cancer datasets and conditioning on patient metadata encoded via a pretrained Transformer-based encoder (Bidirectional Encoder Representations from Transformers). Experiments on The Cancer Genome Atlas microbiome datasets show that DepMicroDiff substantially outperforms state-of-the-art baselines, achieving higher Pearson correlation coefficient (up to 0.788), cosine similarity (up to 0.812), and lower root mean square error and mean absolute error across multiple cancer types, demonstrating its robustness and generalizability for microbiome imputation.