Computational strategies for the identification of a transcriptional biomarker panel to sense cellular growth states in Bacillus subtilis

Our current knowledge of how different environmental treatments modulate gene regulation and bring about physiology adaptations is limited, and hence it is difficult to determine the mechanisms that lead to their effects. Patterns of gene expression, revealed using technologies such as microarrays or RNA-seq, can provide useful biomarkers of different gene regulatory states indicative of a bacterium's physiological status. It is desirable to have only a few key genes as the biomarkers to reduce the costs of determining the transcriptional state by opening the way for methods such as quantitative RT-PCR and amplicon panels.

In this talk, I will describe how we used unsupervised machine learning to construct a transcriptional landscape model from condition-dependent transcriptome data (linked to different cellular growth states), including data processing strategies, and feature elimination. Finally, I will discuss the identified 10 biomarker genes that achieved best cross-validation accuracy.