Premium
A QSAR Model of hERG Binding Using a Large, Diverse, and Internally Consistent Training Set
Author(s) -
Seierstad Mark,
Agrafiotis Dimitris K.
Publication year - 2006
Publication title -
chemical biology and drug design
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.59
H-Index - 77
eISSN - 1747-0285
pISSN - 1747-0277
DOI - 10.1111/j.1747-0285.2006.00379.x
Subject(s) - herg , quantitative structure–activity relationship , set (abstract data type) , training set , training (meteorology) , computer science , artificial intelligence , chemistry , computational biology , machine learning , biology , potassium channel , biophysics , geography , programming language , meteorology
Over the past decade, the pharmaceutical industry has begun to address an addition to ADME/Tox profiling – the ability of a compound to bind to and inhibit the human ether‐a‐go‐go‐related gene (hERG)‐encoded cardiac potassium channel. With the compilation of a large and diverse set of compounds measured in a single, consistent hERG channel inhibition assay, we recognized a unique opportunity to attempt to construct predictive QSAR models. Early efforts with classification models built from this training set were very encouraging. Here, we report a systematic evaluation of regression models based on neural network ensembles in conjunction with a variety of structure representations and feature selection algorithms. The combination of these modeling techniques (neural networks to capture non‐linear relationships in the data, feature selection to prevent over‐fitting, and aggregation to minimize model instability) was found to produce models with very good internal cross‐validation statistics and good predictivity on external data.