| The
study of how drugs bind to proteins is crucial
in drug discovery. When a drug binds to
proteins in plasma, it can limit the effectiveness
of the drug. Plasma protein binding values
(% fraction bound) are expressed as the
percentage of the total plasma concentration
of a drug that is bound to all plasma proteins.
In the Strand PPB
model, developed by Strand Genomics, several
machine-learning methods including neural
networks, decision trees and support vector
machines were employed to identify a small
set from 1054 molecular descriptors that
correlated with this pharmacokinetic parameter.
The input to the
predictors is the 2-D structure of a molecule,
which is used to compute the descriptors
that are utilized by the models. Structures
may be imported as either SMILES, MOL, SYBYL MOL2, or SD
files.
|
