QSAR-TID-12000
OpenML dataset with id 3212
No author found.
Full work available at URL: https://api.openml.org/data/v1/download/1675010/QSAR-TID-12000.sparse_arff
Upload date: 6 October 2015
Dataset Characteristics
Number of classes: 0
Number of features: 1,026 (numeric: 1,025, symbolic: 1 and in total binary: 0 )
Number of instances: 366
Number of instances with missing values: 0
Number of missing values: 0
Author: Dr Ivan Olier, Dr Jeremy Besnard, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn Source: MetaQSAR project - September 2015 Please cite:
This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target TID: 12000, and it has 366 rows and 1026 features (including IDs and class feature: MOLECULE_CHEMBL_ID and MEDIAN_PXC50). The features represent FCFP 1024bit Molecular Fingerprints which were generated from SMILES strings. They were obtained using the Pipeline Pilot program, Dassault Systèmes BIOVIA. Generating Fingerprints does not usually require missing value imputation as all bits are generated.
