Data-driven prediction of cancer cell fates with a nonlinear model of signaling pathways
Fan Zhang, Chee-Keong Kwoh, Min Wu, Jie Zheng · 2014
Signals from the environment of a cell are captured and transmitted by signaling proteins inside the cell. The cell will respond to these signal inputs by leading to one of several possible phenotypic outputs, e.g., cell survival or cell death. However, the underlying mechanisms of processing molecular information are unknown, thus data-driven models are needed to bridge signaling data with phenotypic measurements of cell fates. The traditional linear model has its limitations because it assumes that one cell fate is proportional to the activity of every signaling protein, which is unlikely to be true in the complex biological systems. Therefore, we propose a nonlinear model to predict the probability of cell fates based on activity levels of signaling proteins.