Optimization of Drug Candidates That Inhibit the D-Loop Activity of RAD51

RAD51 is the central protein in homologous recombination (HR) repair, where it first binds ssDNA and then catalyzes strand invasion via a D-loop intermediate. Additionally, RAD51 plays a role in faithful DNA replication by protecting stalled replication forks; this requires RAD51 to bind DNA but may not require the strand invasion activity of RAD51. We previously described a small-molecule inhibitor of RAD51 named RI(dl)-2 (RAD51 inhibitor of D-loop formation #2, hereafter called 2 h), which inhibits D-loop activity while sparing ssDNA binding. However, 2 h is limited in its ability to inhibit HR in vivo, preventing only about 50 % of total HR events in cells. We sought to improve upon this by performing a structure-activity relationship (SAR) campaign for more potent analogues of 2 h. Most compounds were prepared from 1-(2-aminophenyl)pyrroles by forming the quinoxaline moiety either by condensation with aldehydes, then dehydrogenation of the resulting 4,5-dihydro intermediates, or by condensation with N,N '-carbonyldiimidazole, chlorination, and installation of the 4-substituent through Suzuki-Miyaura coupling. Many analogues exhibited enhanced activity against human RAD51, but in several of these compounds the increased inhibition was due to the introduction of dsDNA intercalation activity. We developed a sensitive assay to measure dsDNA intercalation, and identified two analogues of 2 h that promote complete HR inhibition in cells while exerting minimal intercalation activity.