MIIDL: a Python package for microbial biomarkers identification powered by interpretable deep learning

TL;DR

MIIDL is a Python package that uses interpretable deep learning techniques, including convolutional neural networks and interpretability algorithms, to identify microbial biomarkers from complex biological data for disease prediction.

Contribution

The paper introduces MIIDL, a novel Python toolkit that combines deep learning and interpretability methods for robust microbial biomarker discovery.

Findings

Provides a comprehensive pipeline for biomarker identification.

Integrates multiple interpretability algorithms for transparency.

Handles high-dimensional, sparse microbiome data effectively.

Abstract

Detecting microbial biomarkers used to predict disease phenotypes and clinical outcomes is crucial for disease early-stage screening and diagnosis. Most methods for biomarker identification are linear-based, which is very limited as biological processes are rarely fully linear. The introduction of machine learning to this field tends to bring a promising solution. However, identifying microbial biomarkers in an interpretable, data-driven and robust manner remains challenging. We present MIIDL, a Python package for the identification of microbial biomarkers based on interpretable deep learning. MIIDL innovatively applies convolutional neural networks, a variety of interpretability algorithms and plenty of pre-processing methods to provide a one-stop and robust pipeline for microbial biomarkers identification from high-dimensional and sparse data sets.