Our “New Medicines Innovation” strategy utilizes deep learning algorithms that can analyze large datasets of protein structures to identify patterns and relationships that can be used to predict the structure of new proteins with high accuracy. This can significantly reduce the time and resources required for experimental protein structure determination, which is often a time-consuming and expensive process.
In drug design, our deep learning is used to predict the binding affinity of small molecules to specific proteins, allowing for the identification of potential drug candidates with high potency and specificity. Deep learning algorithms is also being used to predict the effect of mutations or modifications on protein function, providing insights into the potential impact of these changes on drug efficacy or safety.
A hypothesis driven medicinal chemistry approach is utilized which involves the iterative design and optimization of compounds based on a set of hypotheses about the target and the chemical structure-activity relationships (SAR) of the compounds. Our approach is based on the principle that a deep understanding of the biology of the target and the SAR of the compounds can guide the design of effective molecules with improved potency, selectivity, and pharmacokinetic properties.