Neural network based prediction of site-specific stable mutants in wild type CFTR protein

Abstract

Cystic fibrosis is a genetic disorder characterized by defective ion transport across cell membranes, primarily affecting the lungs and other vital organs. The cystic fibrosis transmembrane conductance regulator (CFTR) protein plays a pivotal role in cystic fibrosis pathophysiology, and mutations in the CFTR gene lead to dysfunctional protein function. The CFTR modulators, including ivacaftor, lumacaftor, and tezacaftor, represent promising therapeutic options for improving CFTR function and ameliorating cystic fibrosis symptoms the CFTR (PDB ID: 5UAK) structure stability was assessed by replacing the phenylalanine with other amino acid at 508^th position by using the ThermoMPNN tool. The stable mutant structure (F508W) was identified and its structure was generated using the Biopython library. In this study, we employed molecular docking to investigate the interactions between CFTR modulators and CFTR protein structures. For the wild type CFTR and F508W mutant counterpart, docking was performed with ivacaftor, lumacaftor, and tezacaftor using the CB-Dock2 platform. Our results indicate that lumacaftor exhibited the highest predicted binding affinity among the tested CFTR modulators for the F508W mutant CFTR, suggesting its potential as a therapeutic option for individuals with cystic fibrosis carrying this mutation. Additionally, interaction profile analyses revealed stable complexes formed between the CFTR modulators and both wild type and mutant CFTR structures, highlighting their potential effectiveness in targeting CFTR dysfunction. Overall, this study provides valuable insights into the molecular mechanisms underlying the therapeutic efficacy of CFTR modulators in cystic fibrosis. Further experimental validation is warranted to confirm these computational findings and to explore the clinical utility of these drugs in treating cystic fibrosis.