A Goldilocks Principle for the Gut Microbiome: Taxonomic Resolution Matters for Microbiome-Based Classification of Colorectal Cancer.
A Goldilocks Principle for the Gut Microbiome: Taxonomic Resolution Matters for Microbiome-Based Classification of Colorectal Cancer.
复制标题
DOI：
10.1128/mbio.03161-21
复制
发表时间：
2022-02-22
期刊：
影响因子：
6.4
通讯作者：
Schloss PD
中科院分区：
文献类型：
--
作者：
Armour CR;Topçuoğlu BD;Garretto A;Schloss PD
结直肠癌在美国是一种常见且致命的疾病，2020年有超过50，000人死亡。这种进行性疾病通过早期发现和治疗是高度可预防的，但许多人不遵守推荐的筛查指南。肠道微生物组已成为非侵入性检测结直肠癌的一个有前途的目标。大多数基于微生物组的分类工作利用来自操作分类单位（OTU）或扩增子序列变体（ASV）的分类丰度数据，目的是提高分类分辨率。然而，目前尚不清楚哪种分类分辨率对于基于微生物组的结直肠癌分类是最佳的。为了解决这个问题，我们使用了一个可重复的机器学习框架来量化模型的分类性能，这些模型基于注释到门、纲、目、科、属、OTU和ASV水平的数据。我们发现，模型的性能随着分类分辨率的增加而增加，直到性能相等的家族水平家系间差异无统计学意义（P> 0.05）（平均受试者工作特征曲线下面积[AUROC]，0.689），属在ASV水平降低之前，AUROC（平均AUROC，0.690）和OTU（平均AUROC，0.693）水平（P <0.05;平均AUROC，0.676）。这些结果证明了分类分辨率和预测性能之间的权衡，其中粗分类分辨率（例如，门）不够清晰，但分辨率很高（例如，ASV）过于个性化，无法对样本进行准确分类。类似于金发姑娘和三只熊的故事（L。B。Cauley，Goldilocks and the Three Bears，1981），中等分辨率（即，科、属和OTU）对于从微生物组数据中最佳预测结直肠癌"刚刚好"。
Colorectal cancer is a common and deadly disease in the United States accounting for over 50,000 deaths in 2020. This progressive disease is highly preventable with early detection and treatment, but many people do not comply with the recommended screening guidelines. The gut microbiome has emerged as a promising target for noninvasive detection of colorectal cancer. Most microbiome-based classification efforts utilize taxonomic abundance data from operational taxonomic units (OTUs) or amplicon sequence variants (ASVs) with the goal of increasing taxonomic resolution. However, it is unknown which taxonomic resolution is optimal for microbiome-based classification of colorectal cancer. To address this question, we used a reproducible machine learning framework to quantify classification performance of models based on data annotated to phylum, class, order, family, genus, OTU, and ASV levels. We found that model performance increased with increasing taxonomic resolution, up to the family level where performance was equal (P > 0.05) among family (mean area under the receiver operating characteristic curve [AUROC], 0.689), genus (mean AUROC, 0.690), and OTU (mean AUROC, 0.693) levels before decreasing at the ASV level (P < 0.05; mean AUROC, 0.676). These results demonstrate a trade-off between taxonomic resolution and prediction performance, where coarse taxonomic resolution (e.g., phylum) is not distinct enough, but fine resolution (e.g., ASV) is too individualized to accurately classify samples. Similar to the story of Goldilocks and the three bears (L. B. Cauley, Goldilocks and the Three Bears, 1981), mid-range resolution (i.e., family, genus, and OTU) is “just right” for optimal prediction of colorectal cancer from microbiome data.
登录
查看更多内容
影响因子：
--
作者：
Topcuoglu, Begum D;Lapp, Zena;Schloss, Patrick D
通讯作者：
Schloss, Patrick D
影响因子：
48
作者：
Callahan BJ;McMurdie PJ;Rosen MJ;Han AW;Johnson AJ;Holmes SP
通讯作者：
Holmes SP
影响因子：
6.4
作者：
Lobo, Jorge M.;Jimenez-Valverde, Alberto;Real, Raimundo
通讯作者：
Real, Raimundo
影响因子：
4.4
作者：
Schloss, Patrick D.;Westcott, Sarah L.;Weber, Carolyn F.
通讯作者：
Weber, Carolyn F.
影响因子：
4.8
作者：
Schloss PD
通讯作者：
Schloss PD