Mechtersheimer Daniel, Ding Wenze, Xu Xiangnan, Kim Sanghyun, Sue Carolyn, Cao Yue, Yang Jean
School of Mathematics and Statistics, The University of Sydney, Sydney, NSW 2006, Australia.
Sydney Precision Data Science Centre, The University of Sydney, Sydney, NSW 2006, Australia.
Bioinformatics. 2024 Dec 26;41(1). doi: 10.1093/bioinformatics/btae702.
The human gut microbiome, consisting of trillions of bacteria, significantly impacts health and disease. High-throughput profiling through the advancement of modern technology provides the potential to enhance our understanding of the link between the microbiome and complex disease outcomes. However, there remains an open challenge where current microbiome models lack interpretability of microbial features, limiting a deeper understanding of the role of the gut microbiome in disease. To address this, we present a framework that combines a feature engineering step to transform tabular abundance data to image format using functional microbial annotation databases, with a residual spatial attention transformer block architecture for phenotype classification.
Our model, IMPACT, delivers improved predictive accuracy performance across multiclass classification compared to similar methods. More importantly, our approach provides interpretable feature importance through image classification saliency methods. This enables the extraction of taxa markers (features) associated with a disease outcome and also their associated functional microbial traits and metabolites.
IMPACT is available at https://github.com/SydneyBioX/IMPACT. We providedirect installation of IMPACT via pip.
由数万亿细菌组成的人类肠道微生物群对健康和疾病有重大影响。现代技术的进步带来的高通量分析为增进我们对微生物群与复杂疾病结果之间联系的理解提供了潜力。然而，目前仍存在一个开放的挑战，即当前的微生物群模型缺乏对微生物特征的可解释性，限制了对肠道微生物群在疾病中作用的更深入理解。为解决这一问题，我们提出了一个框架，该框架结合了一个特征工程步骤，使用功能性微生物注释数据库将表格形式的丰度数据转换为图像格式，并采用残差空间注意力变压器块架构进行表型分类。
与类似方法相比，我们的模型IMPACT在多类分类中提供了更高的预测准确性。更重要的是，我们的方法通过图像分类显著性方法提供了可解释的特征重要性。这使得能够提取与疾病结果相关的分类群标记（特征）及其相关的功能性微生物特征和代谢物。
IMPACT可在https://github.com/SydneyBioX/IMPACT上获取。我们通过pip提供IMPACT的直接安装。
