Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins

Omics technologies have led to the discovery of a vast number of proteins that are expressed but have no functional annotation - so called hypothetical proteins (HPs). Even in the best-studied model organism <i>Escherichia coli</i> K-12, over 2 % of the proteome remains uncharacterized. This knowledge gap becomes even worse when looking at microbial dark matter. However, knowing the functions of proteins is crucial for elucidating cellular and metabolic processes and harnessing biotechnological potentials. Here, we employed machine learning to decipher the transcriptional regulatory network of <i>E. coli</i> K-12, as well as other <i>in silico</i> tools to assign functions to uncharacterized HPs. We further provide experimental validation of <i>in silico</i> predicted functions for three HP-encoding genes (<i>yhdN</i>, <i>yeaC</i> and <i>ydgH</i>) as proof of concept, by analyzing growth patterns of deletion mutants compared to the wild type, as well as their transcriptional responses to specific conditions. This study demonstrates that the use of Big Omics Data in combination with Artificial Intelligence and experimental controls is a powerful approach to illuminate functional dark matter.