Exploring Activity Cliffs from a Chemoinformatics Perspective

The activity cliff concept experiences considerable interest in medicinal chemistry and chemoinformatics. Activity cliffs are defined as pairs or groups of structurally similar or analogous active compounds having large differences in potency. Depending on the research field, views of activity cliffs partly differ. While interpretability and utility of activity cliff information is considered to be of critical importance in medicinal chemistry, large‐scale exploration and prediction of activity cliffs are of special interest in chemoinformatics. Much emphasis has recently been put on making activity cliff information accessible for medicinal chemistry applications. Herein, different approaches to the analysis and prediction of activity cliffs are discussed that are of particular relevance from a chemoinformatics viewpoint.

[1]  Jürgen Bajorath,et al.  Emerging Chemical Patterns: A New Methodology for Molecular Classification and Compound Selection , 2006, J. Chem. Inf. Model..

[2]  Rajarshi Guha,et al.  Exploring Uncharted Territories: Predicting Activity Clis in Structure-Activity Landscapes , 2012, J. Chem. Inf. Model..

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  Jürgen Bajorath,et al.  Searching for Coordinated Activity Cliffs Using Particle Swarm Optimization , 2012, J. Chem. Inf. Model..

[5]  Kathrin Heikamp,et al.  Prediction of Activity Cliffs Using Support Vector Machines , 2012, J. Chem. Inf. Model..

[6]  Jürgen Bajorath,et al.  Methods for SAR visualization , 2012 .

[7]  J. Bajorath,et al.  Advancing the activity cliff concept , 2013 .

[8]  Pierre Baldi,et al.  Graph kernels for chemical informatics , 2005, Neural Networks.

[9]  Jürgen Bajorath,et al.  MMP-Cliffs: Systematic Identification of Activity Cliffs on the Basis of Matched Molecular Pairs , 2012, J. Chem. Inf. Model..

[10]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[11]  Kotagiri Ramamohanarao,et al.  Making Use of the Most Expressive Jumping Emerging Patterns for Classification , 2001, Knowledge and Information Systems.

[12]  G. Maggiora,et al.  Molecular similarity in medicinal chemistry. , 2014, Journal of medicinal chemistry.

[13]  Jameed Hussain,et al.  Computationally Efficient Algorithm to Identify Matched Molecular Pairs (MMPs) in Large Data Sets , 2010, J. Chem. Inf. Model..

[14]  Kathrin Heikamp,et al.  Compound Pathway Model To Capture SAR Progression: Comparison of Activity Cliff-Dependent and -Independent Pathways , 2013, J. Chem. Inf. Model..

[15]  Jürgen Bajorath,et al.  Prediction of Individual Compounds Forming Activity Cliffs Using Emerging Chemical Patterns , 2013, J. Chem. Inf. Model..

[16]  J. Bajorath,et al.  Activity landscape representations for structure-activity relationship analysis. , 2010, Journal of medicinal chemistry.

[17]  Jürgen Bajorath,et al.  Composition and Topology of Activity Cliff Clusters Formed by Bioactive Compounds , 2014, J. Chem. Inf. Model..

[18]  Jürgen Bajorath,et al.  Recent progress in understanding activity cliffs and their utility in medicinal chemistry. , 2014, Journal of medicinal chemistry.

[19]  Jürgen Bajorath,et al.  Exploring activity cliffs in medicinal chemistry. , 2012, Journal of medicinal chemistry.