【工具】adverSCarial评估单细胞 RNA 测序分类器抵御对抗性攻击的脆弱性

介绍

针对单细胞 RNA 测序（scRNA-seq）数据中健康细胞类型与病变细胞类型的检测，已有多项机器学习（ML）算法被提出用于医学研究目的。这引发了人们对于这些算法易受对抗性攻击的担忧，即存在利用缺陷输入和精心设计的输入来恶意篡改分类器输出的威胁。
借助 adverSCarial，单细胞转录组数据的对抗性攻击（adversarial attacks）能够以多种方式轻松模拟出来，从扩大的但不可察觉的修改到激进且有针对性的修改，从而能够评估 scRNA-seq 分类器对基因表达变化（无论是技术性的、生物性的还是有意为之的）的脆弱性。我们通过评估 adverSCarial 中提出的攻击模式面板中的五种 scRNA-seq 分类器（每种分类器都属于不同的机器学习算法类别）的鲁棒性，展示了其有用性和性能，并在四个不同的数据集上探索了暴露其内部运作和敏感性所解锁的潜力。这些分析可以指导开发更可靠、更具可解释性的模型，这些模型可用于生物医学研究和未来的临床应用，并具有更好的可使用性。

Several machine learning (ML) algorithms dedicated to the detection of healthy and diseased cell types from single-cell RNA sequencing (scRNA-seq) data have been proposed for biomedical purposes. This raises concerns about their vulnerability to adversarial attacks, exploiting threats causing malicious alterations of the classifiers’ output with defective and well-crafted input.

With adverSCarial, adversarial attacks of single-cell transcriptomic data can easily be simulated in a range of ways, from expanded but undetectable modifications to aggressive and targeted ones, enabling vulnerability assessment of scRNA-seq classifiers to variations of gene expression, whether technical, biological, or intentional. We exemplify the usefulness and performance with a panel of attack modes proposed in adverSCarial by assessing the robustness of five scRNA-seq classifiers, each belonging to a distinct class of ML algorithm, and explore the potential unlocked by exposing their inner workings and sensitivities on four different datasets. These analyses can guide the development of more reliable models, with improved interpretability, usable in biomedical research and future clinical applications.

代码

https://github.com/GhislainFievet/adverSCarial

参考

• adverSCarial: assessing the vulnerability of single-cell RNA-sequencing classifiers to adversarial attacks
• https://bioconductor.org/packages/release/bioc/html/adverSCarial.html