Synthetic and Systems Biology Unit, Biological Research Centre (BRC), Szeged, Hungary.
Department of Anatomy and Stem Cells and Metabolism Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland.
Nat Commun. 2021 May 5;12(1):2532. doi: 10.1038/s41467-021-22866-x.
Biological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce the Regression Plane (RP), a user-friendly discovery tool enabling class-free phenotypic supervised machine learning, to describe and explore biological data in a continuous manner. First, we compare traditional classification with regression in a simulated experimental setup. Second, we use our framework to identify genes involved in regulating triglyceride levels in human cells. Subsequently, we analyse a time-lapse dataset on mitosis to demonstrate that the proposed methodology is capable of modelling complex processes at infinite resolution. Finally, we show that hemocyte differentiation in Drosophila melanogaster has continuous characteristics.
生物过程本质上是连续的，而将它们离散化极大地限制了表型发现的机会。我们使用多参数主动回归方法引入了回归平面（Regression Plane，RP），这是一种用户友好的发现工具，可实现无类别表型监督机器学习，从而以连续的方式描述和探索生物数据。首先，我们在模拟实验设置中比较了传统分类和回归。其次，我们使用我们的框架来识别参与调节人类细胞中甘油三酯水平的基因。随后，我们分析有丝分裂的延时数据集，以证明所提出的方法能够以无限分辨率对复杂过程进行建模。最后，我们表明果蝇血细胞分化具有连续特征。
