Machine learning uncovers a data-driven transcriptional regulatory network for the Crenarchaeal thermoacidophile Sulfolobus acidocaldarius

Abstract

Dynamic cellular responses to environmental constraints are coordinated by the transcriptional regulatory network (TRN), which modulates gene expression. This network controls most fundamental cellular responses, including metabolism, motility, and stress responses. Here, we apply independent component analysis, an unsupervised machine learning approach, to 95 high-quality Sulfolobus acidocaldarius RNA-seq datasets and extract 45 independently modulated gene sets, or iModulons. Together, these iModulons contain 755 genes (32% of the genes identified on the genome) and explain over 70% of the variance in the expression compendium. We show that 5 modules represent the effects of known transcriptional regulators, and hypothesize that most of the remaining modules represent the effects of uncharacterized regulators. Further analysis of these gene sets results in: (1) the prediction of a DNA export system composed of 5 uncharacterized genes, (2) expansion of the LysM regulon, and (3) evidence for an as-yet-undiscovered global regulon. Our approach allows for a mechanistic, systems-level elucidation of an extremophile's responses to biological perturbations, which could inform research on gene-regulator interactions and facilitate regulator discovery in S. acidocaldarius. We also provide the first global TRN for S. acidocaldarius. Collectively, these results provide a roadmap towards regulatory network discovery in archaea.

Advanced transcriptomic analysis reveals the role of efflux pumps and media composition in antibiotic responses ofPseudomonas aeruginosa

“…Regulons are sets of co-regulated genes defined based on bottom-up approaches using a variety of biomolecular methods, whereas iModulons are defined in a top-down manner using machine learning of entire transcriptomic profiles. Previously, we used ICA to annotate the TRNs of Escherichia coli 9 , Staphylococcus aureus 10 , Bacillus subtilis 11 , and Sulfolobus acidocaldarius 12 , which generated valuable hypotheses including putative regulatory interactions, novel associations between regulators and the conditions which may activate them, and specific insights into transcriptomic reallocation during key physiological processes. ICA has also been used to study the effect of adaptive laboratory evolution on the TRN 13,14 .…”