Sutherland and Weaver (2004) discuss QSAR models for dihydrofolate reductase (DHFR) inhibition. This data set contains values for 325 compounds. For each compound, 228 molecular descriptors have been calculated. Additionally, each samples is designated as "active" or "inactive".
Sutherland, J.J. and Weaver, D.F. (2004). Three-dimensional quantitative structure-activity and structure-selectivity relationships of dihydrofolate reductase inhibitors, Journal of Computer-Aided Molecular Design, Vol. 18, pg. 309-331.
data frame of chemical descriptors and the activity values
The data frame dhfr
contains a column called Y
with the
outcome classification. The remainder of the columns are molecular
descriptor values.