Aim and Objective: Plasma protein binding (PPB) has vital importance in the
characterization of drug distribution in the systemic circulation. Unfavorable PPB can pose a
negative effect on clinical development of promising drug candidates. The drug distribution
properties should be considered at the initial phases of the drug design and development. Therefore,
PPB prediction models are receiving an increased attention.
Materials and Methods: In the current study, we present a systematic approach using Support vector
machine, Artificial neural network, k- nearest neighbor, Probabilistic neural network, Partial least
square and Linear discriminant analysis to relate various in vitro and in silico molecular descriptors to a
diverse dataset of 736 drugs/drug-like compounds.
Results: The overall accuracy of Support vector machine with Radial basis function kernel came out to
be comparatively better than the rest of the applied algorithms. The training set accuracy, validation set
accuracy, precision, sensitivity, specificity and F1 score for the Suprort vector machine was found to be
89.73%, 89.97%, 92.56%, 87.26%, 91.97% and 0.898, respectively.
Conclusion: This model can potentially be useful in screening of relevant drug candidates at the
preliminary stages of drug design and development.