The therapeutic approach to Chronic Myeloid Leukemia (CML) has changed since the advent of the tyrosine kinase inhibitor (TKI) imatinib, which was then followed by the second generation TKIs dasatinib, nilotinib, and, finally, by ponatinib, a third-generation drug. At present, these therapeutic options represent the first-line treatment for adults. Based on clinical experience, imatinb, dasatinib, and nilotinib have been approved for children even though the studies that were concerned with efficacy and safety toward pediatric patients are still awaiting more specific and high-quality data. In this scenario, it is of utmost importance to prospectively validate data extrapolated from adult studies to set a standard therapeutic management for pediatric CML by employing appropriate formulations on the basis of pediatric clinical trials, which allow a careful monitoring of TKI-induced adverse effects especially in growing children exposed to long-term therapy.

The fusion oncoprotein Bcr-Abl is an aberrant tyrosine kinase responsible for chronic myeloid leukemia and acute lymphoblastic leukemia. The auto-inhibition regulatory module observed in the progenitor kinase c-Abl is lost in the aberrant Bcr-Abl, because of the lack of the N-myristoylated cap able to bind the myristoyl binding pocket also conserved in the Bcr-Abl kinase domain. A way to overcome the occurrence of resistance phenomena frequently observed for Bcr-Abl orthosteric drugs is the rational design of allosteric ligands approaching the so-called myristoyl binding pocket. The discovery of these allosteric inhibitors although very difficult and extremely challenging, represents a valuable option to minimize drug resistance, mostly due to the occurrence of mutations more frequently affecting orthosteric pockets, and to enhance target selectivity with lower off-target effects. In this perspective, we will elucidate at a molecular level the structural bases behind the Bcr-Abl allosteric control and will show how artificial intelligence can be effective to drive the automated de novo design towards off-patent regions of the chemical space.