Division of Biostatistics and Bioinformatics, Herbert Wertheim School of Public Health, University of California, San Diego, La Jolla, CA, USA.
Moores Cancer Center, University of California, San Diego, La Jolla, CA, USA.
BMC Bioinformatics. 2023 Feb 20;24(1):57. doi: 10.1186/s12859-023-05171-w.
The growing amount of high dimensional biomolecular data has spawned new statistical and computational models for risk prediction and disease classification. Yet, many of these methods do not yield biologically interpretable models, despite offering high classification accuracy. An exception, the top-scoring pair (TSP) algorithm derives parameter-free, biologically interpretable single pair decision rules that are accurate and robust in disease classification. However, standard TSP methods do not accommodate covariates that could heavily influence feature selection for the top-scoring pair. Herein, we propose a covariate-adjusted TSP method, which uses residuals from a regression of features on the covariates for identifying top scoring pairs. We conduct simulations and a data application to investigate our method, and compare it to existing classifiers, LASSO and random forests.
Our simulations found that features that were highly correlated with clinical variables had high likelihood of being selected as top scoring pairs in the standard TSP setting. However, through residualization, our covariate-adjusted TSP was able to identify new top scoring pairs, that were largely uncorrelated with clinical variables. In the data application, using patients with diabetes (n = 977) selected for metabolomic profiling in the Chronic Renal Insufficiency Cohort (CRIC) study, the standard TSP algorithm identified (valine-betaine, dimethyl-arg) as the top-scoring metabolite pair for classifying diabetic kidney disease (DKD) severity, whereas the covariate-adjusted TSP method identified the pair (pipazethate, octaethylene glycol) as top-scoring. Valine-betaine and dimethyl-arg had, respectively, ≥ 0.4 absolute correlation with urine albumin and serum creatinine, known prognosticators of DKD. Thus without covariate-adjustment the top-scoring pair largely reflected known markers of disease severity, whereas covariate-adjusted TSP uncovered features liberated from confounding, and identified independent prognostic markers of DKD severity. Furthermore, TSP-based methods achieved competitive classification accuracy in DKD to LASSO and random forests, while providing more parsimonious models.
We extended TSP-based methods to account for covariates, via a simple, easy to implement residualizing process. Our covariate-adjusted TSP method identified metabolite features, uncorrelated from clinical covariates, that discriminate DKD severity stage based on the relative ordering between two features, and thus provide insights into future studies on the order reversals in early vs advanced disease states.
随着高维生物分子数据的不断增加，为风险预测和疾病分类已经开发了新的统计和计算模型。然而，尽管这些方法的分类精度很高，但它们并没有产生可生物解释的模型。一个例外是，最高分对（TSP）算法衍生出参数免费、可生物解释的单一配对决策规则，在疾病分类中既准确又稳健。然而，标准的 TSP 方法不适应可能严重影响最优配对特征选择的协变量。在这里，我们提出了一种协变量调整的 TSP 方法，该方法使用特征对协变量进行回归的残差来识别最优配对。我们进行了模拟和数据应用研究，将其与现有的分类器 LASSO 和随机森林进行了比较。
我们的模拟发现，与临床变量高度相关的特征在标准 TSP 环境中很有可能被选为最优配对。然而，通过残差化，我们的协变量调整的 TSP 能够识别出与临床变量基本无关的新的最优配对。在数据应用中，使用慢性肾功能不全队列（CRIC）研究中选择进行代谢组学分析的糖尿病患者（n=977），标准 TSP 算法确定（缬氨酸-甜菜碱、二甲基精氨酸）是用于分类糖尿病肾病（DKD）严重程度的最佳配对代谢物，而协变量调整的 TSP 方法则确定了（哌嗪噻嗪、辛基二醇）是最佳配对。缬氨酸-甜菜碱和二甲基精氨酸与尿白蛋白和血清肌酐分别具有≥0.4的绝对相关性，这是 DKD 的已知预后标志物。因此，如果不进行协变量调整，最优配对主要反映了疾病严重程度的已知标志物，而协变量调整的 TSP 则揭示了不受混杂因素影响的特征，并确定了 DKD 严重程度的独立预后标志物。此外，基于 TSP 的方法在 DKD 中实现了与 LASSO 和随机森林相当的分类准确性，同时提供了更简洁的模型。
我们通过一个简单、易于实现的残差化过程，将基于 TSP 的方法扩展到可以考虑协变量。我们的协变量调整 TSP 方法确定了与临床协变量无关的代谢物特征，根据两个特征之间的相对顺序来区分 DKD 严重程度阶段，从而为研究早期与晚期疾病状态之间的顺序逆转提供了思路。
