A k-nearest neighbor classification of hERG K+ channel blockers

被引:27
作者
Chavan, Swapnil [1 ]
Abdelaziz, Ahmed [2 ]
Wiklander, Jesper G. [1 ]
Nicholls, Ian A. [1 ,3 ]
机构
[1] Linnaeus Univ, Linnaeus Univ Ctr Biomat Chem, Dept Chem & Biomed Sci, Bioorgan & Biophys Chem Lab, S-39182 Kalmar, Sweden
[2] eADMET GmbH, Lichtenbergstr 8, D-85748 Munich, Germany
[3] Uppsala Univ, Dept Chem BMC, Box 576, S-75123 Uppsala, Sweden
关键词
Classification model; hERG blockers; Ikr; KCNH2; k-nearest neighbor (k-NN); Toxicity; QT-INTERVAL PROLONGATION; TORSADE-DE-POINTES; STRUCTURAL BASIS; ION CHANNELS; PREDICTION; DRUGS; MODELS; DESCRIPTORS; TOXICITY; BLOCKAGE;
D O I
10.1007/s10822-016-9898-z
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
A series of 172 molecular structures that block the hERG K+ channel were used to develop a classification model where, initially, eight types of PaDEL fingerprints were used for k-nearest neighbor model development. A consensus model constructed using Extended-CDK, PubChem and Substructure count fingerprint-based models was found to be a robust predictor of hERG activity. This consensus model demonstrated sensitivity and specificity values of 0.78 and 0.61 for the internal dataset compounds and 0.63 and 0.54 for the external (PubChem) dataset compounds, respectively. This model has identified the highest number of true positives (i.e. 140) from the PubChem dataset so far, as compared to other published models, and can potentially serve as a basis for the prediction of hERG active compounds. Validating this model against FDA-withdrawn substances indicated that it may even be useful for differentiating between mechanisms underlying QT prolongation.
引用
收藏
页码:229 / 236
页数:8
相关论文
共 45 条
[1]   A COMMON STRUCTURAL BASIS FOR CNS DRUG-ACTION [J].
ANDREWS, PR ;
LLOYD, EJ .
JOURNAL OF PHARMACY AND PHARMACOLOGY, 1983, 35 (08) :516-518
[2]   Predictive in silico modeling for hERG channelblockers [J].
Aronov, MM .
DRUG DISCOVERY TODAY, 2005, 10 (02) :149-155
[3]   Classification tools in chemistry. Part 1: linear models. PLS-DA [J].
Ballabio, Davide ;
Consonni, Viviana .
ANALYTICAL METHODS, 2013, 5 (16) :3790-3798
[4]  
Ballabio D, 2009, INFRARED SPECTROSCOPY FOR FOOD QUALITY ANALYSIS AND CONTROL, P83, DOI 10.1016/B978-0-12-374136-3.00004-3
[5]  
Bolton EE, 2010, ANN REP COMP CHEM, V4, P217, DOI 10.1016/S1574-1400(08)00012-1
[6]   Toward a pharmacophore for drugs inducing the long QT syndrome:: Insights from a CoMFA study of HERG K+ channel blockers [J].
Cavalli, A ;
Poluzzi, E ;
De Ponti, F ;
Recanatini, M .
JOURNAL OF MEDICINAL CHEMISTRY, 2002, 45 (18) :3844-3853
[7]   Acute Toxicity-Supported Chronic Toxicity Prediction: A k-Nearest Neighbor Coupled Read-Across Strategy [J].
Chavan, Swapnil ;
Friedman, Ran ;
Nicholls, Ian A. .
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2015, 16 (05) :11659-11677
[8]   Towards Global QSAR Model Building for Acute Toxicity: Munro Database Case Study [J].
Chavan, Swapnil ;
Nicholls, Ian A. ;
Karlsson, Bjorn C. G. ;
Rosengren, Annika M. ;
Ballabio, Davide ;
Consonni, Viviana ;
Todeschini, Roberto .
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2014, 15 (10) :18162-18174
[9]   A novel hypothesis for the binding mode of HERG channel blockers [J].
Choe, H ;
Nah, KH ;
Lee, SN ;
Lee, HS ;
Lee, HS ;
Jo, SH ;
Leem, CH ;
Jang, YJ .
BIOCHEMICAL AND BIOPHYSICAL RESEARCH COMMUNICATIONS, 2006, 344 (01) :72-78
[10]   Clinical evaluation of QT/QTc prolongation and proarrhythmic potential for nonantiarrhythmic drugs: The International Conference on Harmonization of Technical Requirements for Registration of Pharmaceuticals for Human use E14 Guideline [J].
Darpo, B ;
Nebout, T ;
T Sager, P .
JOURNAL OF CLINICAL PHARMACOLOGY, 2006, 46 (05) :498-507