Purpose: To identify sensitive genes for space radiation, we integrated the transcriptomic samples of spaceflight mice from GeneLab and predicted the radiation doses absorbed by individuals in space.
Methods and materials: A single-sample network (SSN) for each individual sample was constructed. Then, using machine learning and genetic algorithms, we built the regression models to predict the absorbed dose equivalent based on the topological structure of SSNs. Moreover, we analyzed the SSNs from each tissue and compared the similarities and differences among them.
Results: Our model exhibited excellent performance with the following metrics: , , and the Pearson correlation coefficient of 0.990 (p value <.0001) between predicted and actual values. We identified 20 key genes, the majority of which had been proven to be associated with radiation. However, we uniquely established them as space radiation sensitive genes for the first time. Through further analysis of the SSNs, we discovered that the different tissues exhibited distinct mechanisms in response to space stressors.
Conclusions: The topology structures of SSNs effectively predicted radiation doses under spaceflight conditions, and the SSNs revealed the gene regulatory patterns within the organisms under space stressors.
Keywords: GeneLab; Space stressors; genetic algorithm; radiation dose prediction; radiation sensitive genes; single-sample network.