Resistor: an algorithm for predicting resistance mutations using Pareto optimization over multistate protein design and mutational signatures

Resistance to pharmacological treatments is a major public health challenge. Here we introduce R esistor —a structure- and sequence-based algorithm that prospectively predicts resistance mutations for drug design. R esistor computes the Pareto frontier of four resistance-causing criteria: the change in binding affinity (Δ K a ) of the (1) drug and (2) endogenous ligand upon a protein’s mutation; (3) the probability a mutation will occur based on empirically derived mutational signatures; and (4) the cardinality of mutations comprising a hotspot. For validation, we applied R esistor to EGFR and BRAF kinase inhibitors treating lung adenocarcinoma and melanoma. R esistor correctly identified eight clinically significant EGFR resistance mutations, including the erlotinib and gefitinib “gatekeeper” T790M mutation and five known osimertinib resistance mutations. Furthermore, R esistor predictions are consistent with BRAF inhibitor sensitivity data from both retrospective and prospective experiments using KinCon biosensors. R esistor is available in the open-source protein design software OSPREY.