Background: Trypanosomiasis is a widespread zoonotic disease and the existing drugs are
not enough to prevent and treat it.
Objective: This study aimed to build a quantitative structure-activity relationship model by the chemical
structures of a class of thiazolidone/thiazolidamide based hybrids. The model was used to screen new
antitrypanosomal agents and predict the properties of composite molecules.
Methods: All compounds were randomly divided into a training set and a test set. A large number of
descriptors were calculated by the software, then some of the best descriptors were selected to build the
models. The linear model was built by the heuristic method and the nonlinear model was built by gene
expression programming method.
Results: In the heuristic method, the correlation coefficients ,R2
were 0.581, 0.457,
14.053 and 15.311, respectively. In gene expression programming, the R2
were 0.715, 10.997
in the training set and 0.617, 22.778 in the test set. The results showed that the relative number of S atoms
and the minimum bond order of an H atom had a significant positive contribution to IC50. Meanwhile,
the relative number of double bonds and the count of hydrogen-bonding acceptor sites had a great
negative impact on IC50.
Conclusion: Both the heuristic method and gene expression programming had a good predictive performance.
By contrast, the gene expression programming method fitted well with the experimental values
and it was expected to be beneficial in the synthesis of new antitrypanosomal drugs.