Almost all major cellular processes involve at least a single RNA molecule interacting with one or more proteins, collectively called RNA-binding proteins (RBPs). Transcription, translation, RNA processing and editing require coordinated interactions between RNA molecules with their protein partners. Such interactions are diverse in terms of complexity and duration, ranging from transient to long-lasting associations with small deep interaction pockets to large shallow surfaces. Such diversity makes RBPs challenging target for developing drugs despite their significant and diverse roles in biology. A deep understanding of these interactions and identification of patterns associated the RNA-protein interface may open opportunities to target RBPs for a wide array of therapeutic and biotechnological applications.
A few RBPs inhibitors have been reported but only for a limited number of proteins and many of such inhibitors work via the allosteric mechanism rather than by binding to the RNA-binding region. Given the dire need for new antibiotics and the array of RBPs known to be essential for bacterial survival or virulence, targeting these proteins could unlock a largely untapped reservoir of novel antimicrobial agents. In this work, we analyzed the structural and physicochemical properties of the interface regions in experimentally solved bacterial RNA-protein structures deposited in the Protein Data Bank. Using a combination of machine learning and deep learning, we clustered these complexes based on their interaction characteristics into subsets that appear to be consistent with the published literature and our in-house experimental data. As a proof-of-concept, we selected a representative from a druggable subset for downstream identification of potential inhibitors. Deep learning guided virtual screening and molecular dynamics (MD) simulations suggested potential hits. Experimental validation data are currently being collected on compounds from various sources. This hybrid approach provides a framework for identifying and investigating RBP interactions, paving the way for novel therapeutic strategies that can be extended to include RBPs previously considered undruggable.