AI and Computational Methods for Multitarget Design in Anticancer Drug Discovery

Drug discovery is a long, costly, and high-risk process. This talk will show how artificial intelligence and computer-aided drug design can substantially accelerate the discovery pipeline, starting from diagnosis to regulatory approvals. One tool that will be highlighted in the lead optimization phase is the Average Electron Density tool, a quantum-based method developed in our laboratory to evaluate bioisosteric replacements and guide rational molecular design.

The talk will also present examples in which we combined AI, computational methods, and experimental validation to support the targeting of multiple receptors in anticancer drug discovery. One example is about identifying inhibitors of chromatin remodelers, ATP-dependent protein complexes that regulate access to DNA. Their inhibition would lead to cell death. A second example is related to evaluating the binding affinity of DNA intercalators. Because intercalators have planar parts that insert between DNA base pairs, they can distort the DNA structure, which disrupts essential cellular processes, and ultimately induces cancer-cell death.