Resistor: an algorithm for predicting resistance mutations using Pareto optimization over multistate protein design and mutational signatures
Guerin, N.; Kaserer, T.; Donald, B. R.
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.
Similar papers in this journal
- Novel, provable algorithms for efficient ensemble-based computational protein design and their application to the redesign of the c-Raf-RBD:KRas protein-protein interface 98%
- Predicting Affinity Through Homology (PATH): Interpretable Binding Affinity Prediction with Persistent Homology 95%
- Computational design of novel Cas9 PAM-interacting domains using evolution-based modelling and structural quality assessment 94%
Similar papers in this journal
- nanoBERT: A deep learning model for gene agnostic navigation of the nanobody mutational space 94%
- NRGSuite-Qt: A PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions and the detection of binding-site similarities 93%
- Estimating Protein Complex Model Accuracy Using Graph Transformers and Pairwise Similarity Graphs 93%
Similar papers in this journal
Similar papers in this journal
- Protein-protein interaction prediction for targeted protein degradation 95%
- vScreenML v2.0: Improved Machine Learning Classification for Reducing False Positives in Structure-Based Virtual Screening 94%
- AMaLa: analysis of Directed Evolution experiments via Annealed Mutational approximated Landscape 94%
"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.