Back

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

Guerin, N.; Kaserer, T.; Donald, B. R.

2022-01-20 bioinformatics
10.1101/2022.01.18.476733 bioRxiv
Show abstract

Resistance to pharmacological treatments is a major public health challenge. Here we report RO_SCPLOWESISTORC_SCPLOW--a novel structure- and sequence-based algorithm for drug design providing prospective prediction of resistance mutations. RO_SCPLOWESISTORC_SCPLOW computes the Pareto frontier of four resistance-causing criteria: the change in binding affinity ({Delta}Ka) of the (1) drug and (2) endogenous ligand upon a proteins mutation; (3) the probability a mutation will occur based on empirically derived mutational signatures; and (4) the cardinality of mutations comprising a hotspot. To validate RO_SCPLOWESISTORC_SCPLOW, we applied it to kinase inhibitors targeting EGFR and BRAF in lung adenocarcinoma and melanoma. RO_SCPLOWESISTORC_SCPLOW correctly identified eight clinically significant EGFR resistance mutations, including the "gatekeeper" T790M mutation to erlotinib and gefitinib and five known resistance mutations to osimertinib. Furthermore, RO_SCPLOWESISTORC_SCPLOW predictions are consistent with sensitivity data on BRAF inhibitors from both retrospective and prospective experiments using the KinCon biosensor technology. RO_SCPLOWESISTORC_SCPLOW is available in the open-source protein design software OSPREY.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.