美国斯坦福大学Brice Gaudillière研究团队利用Stabl发现稀疏、可靠的组学生物标记物。2024年1月2日，国际知名学术期刊《自然—生物技术》在线发表了这一成果。

研究人员表示，在临床研究中采用高内涵组学技术并结合计算方法，产生了大量候选生物标志物。然而，将这些研究结果转化为真正的临床生物标志物仍具有挑战性。

为了推动这一进程，研究人员引入了Stabl，这是一种通用的机器学习方法，通过将噪声注入和数据驱动的信噪比阈值整合到多变量预测建模中，来识别一组稀疏、可靠的生物标记物。在合成数据集和五项独立临床研究中对Stabl的评估表明，与常用的稀疏性促进正则化方法相比，该方法提高了生物标记物的稀疏性和可靠性，同时保持了预测性能；它将包含1400-35000个特征的数据集精简为4-34个候选生物标记物。

Stabl还可扩展到多组学整合任务，对复杂的预测模型进行生物学解释，因为它能筛选出预测分娩开始的蛋白质组、代谢组和细胞计量学事件、早产的微生物生物标志物以及手术后感染的术前免疫特征。Stabl可在https://github.com/gregbellan/Stabl获取。

附：英文原文

Title: Discovery of sparse, reliable omic biomarkers with Stabl

Author: Hdou, Julien, Mari, Ivana, Bellan, Grgoire, Einhaus, Jakob, Gaudillire, Dyani K., Ladant, Francois-Xavier, Verdonk, Franck, Stelzer, Ina A., Feyaerts, Dorien, Tsai, Amy S., Ganio, Edward A., Sabayev, Maximilian, Gillard, Joshua, Amar, Jonas, Cambriel, Amelie, Oskotsky, Tomiko T., Roldan, Alennie, Golob, Jonathan L., Sirota, Marina, Bonham, Thomas A., Sato, Masaki, Diop, Magane, Durand, Xavier, Angst, Martin S., Stevenson, David K., Aghaeepour, Nima, Montanari, Andrea, Gaudillire, Brice

Issue&Volume: 2024-01-02

Abstract: Adoption of high-content omic technologies in clinical studies, coupled with computational methods, has yielded an abundance of candidate biomarkers. However, translating such findings into bona fide clinical biomarkers remains challenging. To facilitate this process, we introduce Stabl, a general machine learning method that identifies a sparse, reliable set of biomarkers by integrating noise injection and a data-driven signal-to-noise threshold into multivariable predictive modeling. Evaluation of Stabl on synthetic datasets and five independent clinical studies demonstrates improved biomarker sparsity and reliability compared to commonly used sparsity-promoting regularization methods while maintaining predictive performance; it distills datasets containing 1,400–35,000 features down to 4–34 candidate biomarkers. Stabl extends to multi-omic integration tasks, enabling biological interpretation of complex predictive models, as it hones in on a shortlist of proteomic, metabolomic and cytometric events predicting labor onset, microbial biomarkers of pre-term birth and a pre-operative immune signature of post-surgical infections. Stabl is available at https://github.com/gregbellan/Stabl.

DOI: 10.1038/s41587-023-02033-x

Source: https://www.nature.com/articles/s41587-023-02033-x