Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA.
Bioinformatics. 2019 Apr 1;35(7):1197-1203. doi: 10.1093/bioinformatics/bty768.
Flow cytometry and mass cytometry are widely used to diagnose diseases and to predict clinical outcomes. When associating clinical features with cytometry data, traditional analysis methods require cell gating as an intermediate step, leading to information loss and susceptibility to batch effects. Here, we wish to explore an alternative approach that predicts clinical features from cytometry data without the cell-gating step. We also wish to test if such a gating-free approach increases the accuracy and robustness of the prediction.
We propose a novel strategy (CytoDx) to predict clinical outcomes using cytometry data without cell gating. Applying CytoDx on real-world datasets allow us to predict multiple types of clinical features. In particular, CytoDx is able to predict the response to influenza vaccine using highly heterogeneous datasets, demonstrating that it is not only accurate but also robust to batch effects and cytometry platforms.
CytoDx is available as an R package on Bioconductor (bioconductor.org/packages/CytoDx). Data and scripts for reproducing the results are available on bitbucket.org/zichenghu_ucsf/cytodx_study_code/downloads.
Supplementary data are available at Bioinformatics online.
流式细胞术和液滴式数字细胞术被广泛用于疾病诊断和临床结果预测。在将临床特征与细胞术数据关联时，传统分析方法需要细胞门控作为中间步骤，这会导致信息丢失和批次效应的易感性。在这里，我们希望探索一种替代方法，可以在不进行细胞门控步骤的情况下从细胞术数据中预测临床特征。我们还希望测试这种无门控方法是否可以提高预测的准确性和稳健性。
我们提出了一种新的策略（CytoDx），无需细胞门控即可使用细胞术数据预测临床结局。在真实数据集上应用 CytoDx 允许我们预测多种类型的临床特征。特别是，CytoDx 能够使用高度异质的数据集预测流感疫苗的反应，表明它不仅准确，而且对批次效应和细胞术平台具有稳健性。
CytoDx 可作为 Bioconductor（bioconductor.org/packages/CytoDx）上的 R 包使用。可在 bitbucket.org/zichenghu_ucsf/cytodx_study_code/downloads 上获得用于重现结果的数据集和脚本。
补充数据可在生物信息学在线获得。
