deactivatedARFFPublicly available Visibility: public Uploaded 15-07-2016 by Noureddin Sadawi 0 likes
downloaded by 0 people , 0 total downloads0 issues0 downvotes
This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1741221 (TID: 104017), and it has 330 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.