Page 131 out of 225 pages in this book.
Tripos Bookshelf  >  QSAR  >  QSAR Theory  >  QSAR Techniques

4.5.4 Partial Least Squares (PLS)

Partial Least Squares is one of several techniques producing an equation, or QSAR to describe or predict differences in the values in one or more table columns (the dependent variables, or target properties) from differences in the values in other table columns (the explanatory properties, or descriptors).When multiple dependent variables are involved, a separate QSAR equation is made for each target property but the coefficients are interrelated and generally differ from those which would be obtained analyzing the target properties one by one. PLS is an extension of the more familiar technique known as multiple regression (MR).

• Terminology of Multiple Regression and PLS
• Labeled Output From SYBYL/QSAR PLS
• PLS Text Output
• Examples of PLS ANALYSIS LIST Output
• Comparison Between PLS and Multiple Regression
• Algorithmic Description of Partial Least Squares