Machine learning-based QSAR models to predict sodium ion channel (Na 1.5) blockers.

Journal: Future medicinal chemistry
PMID:

Abstract

Conventional experimental approaches used for the evaluation of the proarrhythmic potential of compounds in the drug discovery process are expensive and time consuming but an integral element in the safety profile required for a new drug to be approved. The voltage-gated sodium ion channel 1.5 (Na 1.5), a target known for arrhythmic drugs, causes adverse cardiac complications when the channel is blocked. Machine learning classification and regression models were built to predict the possibility of blocking these channels by small molecules. The finalized models tested with balanced accuracies of 0.88, 0.93 and 0.94 at three thresholds (1, 10 and 30 µmol, respectively). The regression model built to predict the pIC of compounds had q of 0.84 (root-mean-square error = 0.46). The machine learning models that have been built can act as effective filters to screen out the potentially toxic compounds in the early stages of drug discovery.

Authors

  • Noorain Khalifa
    Jubilant Biosys Limited, 96 Industrial Suburb, 2nd Stage, Yeshwanthpur, Bangalore, 560022, India.
  • Leela Sarath Kumar Konda
    Jubilant Biosys Limited, 96 Industrial Suburb, 2nd Stage, Yeshwanthpur, Bangalore, 560022, India.
  • Rajendra Kristam
    Jubilant Biosys Limited, 96 Industrial Suburb, 2nd Stage, Yeshwanthpur, Bangalore, 560022, India.