Image and graph convolution networks improve microbiome-based machine learning accuracy

2022-05-13 · Shtossel Oshrit, Isakov Haim, Turjeman Sondra, Koren Omry, Louzoun Yoram

The human gut microbiome is associated with a large number of disease etiologies. As such, it is a natural candidate for machine learning based biomarker development for multiple diseases and conditions. The microbiome is often analyzed using 16S rRNA gene sequencing. However, several properties of microbial 16S rRNA gene sequencing hinder machine learning, including non-uniform representation, a small number of samples compared with the dimension of each sample, and sparsity of the data, with the majority of bacteria present in a small subset of samples. We suggest two novel methods to combine information from different bacteria and improve data representation for machine learning using bacterial taxonomy. iMic and gMic translate the microbiome to images and graphs respectively, and convolutional neural networks are then applied to the graph or image. We show that both algorithms improve performance of static 16S rRNA gene sequence-based machine learning compared to the best state-of-the-art methods. Furthermore, these methods ease the interpretation of the classifiers. iMic is then extended to dynamic microbiome samples, and an iMic explainable AI algorithm is proposed to detect bacteria relevant to each condition.

📄 PDF Abstract BibTeX arXiv:2205.06525

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Multimodal Fusion of Glucose Monitoring and Food Imagery for Caloric Content Prediction

2025-05-13 · Adarsh Kumar

Effective dietary monitoring is critical for managing Type 2 diabetes, yet accurately estimating caloric intake remains a major challenge. While continuous glucose monitors (CGMs) offer valuable physiological data, they …

Multimodal Deep Learning

DCMD: Distance-based Classification Using Mixture Distributions on Microbiome Data

2020-03-29 · Konstantin Shestopaloff, Mei Dong, Fan Gao, Wei Xu

Current advances in next generation sequencing techniques have allowed researchers to conduct comprehensive research on microbiome and human diseases, with recent studies identifying associations between human microbiome…

BIG-bench Machine Learning Classification General Classification

Human Limits in Machine Learning: Prediction of Plant Phenotypes Using Soil Microbiome Data

2023-06-19 · Rosa Aghdam, Xudong Tang, Shan Shan, Richard Lankau 외

The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide the first deep investigation of the predictive potentia…

Data Augmentation Model Selection

iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis

2026-05-28 · Yang Song, Yixuan Zhang, Lingfa Meng, Tongyuan Hu 외 arxiv

Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not expose the latent interactions that often drive scientific labels. We …

Understanding microbiome dynamics via interpretable graph representation learning

2022-03-02 · Kateryna Melnyk, Kuba Weimann, Tim O. F. Conrad

Large-scale perturbations in the microbiome constitution are strongly correlated, whether as a driver or a consequence, with the health and functioning of human physiology. However, understanding the difference in the mi…

Graph Representation Learning Representation Learning