The antifungal activities of a series of azole derivatives have been modeled by using MIA (multivariate image analysis) descriptors. Two regression methods were applied to correlate such descriptors with the activities column vector: bilinear (classical) and multilinear (N-way) partial least squares - PLS and N-PLS, respectively. The PLS-based model for this series of compounds demonstrated higher predictive ability than the N-PLS-based model, in opposition to some published results for other series of compounds. The activities block was taken in logarithmic scale (pMIC90(cpd)/pMIC90(bifonazole)) and the statistical performance of both models was found to be significantly better than the CoMFA analysis previously established.
- N-PLS regression
- PLS regression
ASJC Scopus subject areas
- Analytical Chemistry
- Process Chemistry and Technology
- Computer Science Applications