DepMicroDiff: Diffusion-Based Dependency-Aware Multimodal Imputation for Microbiome Data
This work addresses imputation challenges in microbiome data analysis for applications like biomarker discovery, representing an incremental advance by combining existing techniques with novel adaptations.
The paper tackled the problem of imputing sparse and noisy microbiome data by introducing DepMicroDiff, a diffusion-based framework that incorporates dependency-aware modeling and metadata conditioning, resulting in improved performance with Pearson correlation up to 0.712 and cosine similarity up to 0.812 on TCGA datasets.
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 VAE-based pretraining across diverse cancer datasets and conditioning on patient metadata encoded via a large language model (LLM). Experiments on TCGA microbiome datasets show that DepMicroDiff substantially outperforms state-of-the-art baselines, achieving higher Pearson correlation (up to 0.712), cosine similarity (up to 0.812), and lower RMSE and MAE across multiple cancer types, demonstrating its robustness and generalizability for microbiome imputation.