Abstract
A tantalizing question in cellular physiology is whether the cellular state and environmental conditions can be inferred by the expression signature of an organism. To investigate this relationship, we created an extensive normalized gene expression compendium for the bacterium Escherichia coli that was further enriched with meta-information through an iterative learning procedure. We then constructed an ensemble method to predict environmental and cellular state, including strain, growth phase, medium, oxygen level, antibiotic and carbon source presence. Results show that gene expression is an excellent predictor of environmental structure, with multi-class ensemble models achieving balanced accuracy between 70.0% (±3.5%) to 98.3% (±2.3%) for the various characteristics. Interestingly, this performance can be significantly boosted when environmental and strain characteristics are simultaneously considered, as a composite classifier that captures the inter-dependencies of three characteristics (medium, phase and strain) achieved 10.6% (±1.0%) higher performance than any individual models. Contrary to expectations, only 59% of the top informative genes were also identified as differentially expressed under the respective conditions. Functional analysis of the respective genetic signatures implicates a wide spectrum of Gene Ontology terms and KEGG pathways with condition-specific information content, including iron transport, transferases, and enterobactin synthesis. Further experimental phenotypic-to-genotypic mapping that we conducted for knock-out mutants argues for the information content of top-ranked genes. This work demonstrates the degree at which genome-scale transcriptional information can be predictive of latent, heterogeneous and seemingly disparate phenotypic and environmental characteristics, with far-reaching applications.
Highlights
Genome-scale transcriptional profiling has become a standard and relatively inexpensive way to identify the overall cellular state and condition-specific cellular responses to external stimuli
We have constructed an extensive transcriptome compendium of Escherichia coli that we have further enriched via an iterative learning approach
Our work argues that genome-scale gene expression can be a multi-purpose marker for identifying latent, heterogeneous cellular and environmental states and that optimal classification can be achieved with a feature set of a couple hundred genes that might not necessarily have the most pronounced differential expression in the respective conditions
Summary
Genome-scale transcriptional profiling has become a standard and relatively inexpensive way to identify the overall cellular state and condition-specific cellular responses to external stimuli. After aggregating all high-throughput transcriptional data that is currently available for E. coli, the most well-studied model microbe, we are still limited to a few thousands microarray or RNA-Seq experiments that cover more than 30 strains, a dozen different media and a multitude of other genetic (knock-out, over-expressions, re-wirings), or environmental (carbon limitation, chemicals, abiotic factors) perturbations. This collection has already increased by an order of magnitude from the roughly two hundred genome-wide transcriptional profiles that we had eight years ago, it is still an inadequate sampling of the relevant experimental space. Efficient training of machine learning methods is hindered due to data complexity, compatibility and the curse of dimensionality that plagues datasets with thousands of features (genes) but only a few samples (conditions)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
