Antonius Ter Laak

Benchmark data set for in silico prediction of Ames mutagenicity.

Up to now, publicly available data sets to build and evaluate Ames mutagenicity prediction tools have been very limited in terms of size and chemical space covered. In this report we describe a new unique public Ames mutagenicity data set comprising about 6500 nonconfidential compounds (available as SMILES strings and SDF) together with their biological activity. Three commercial tools (DEREK, MultiCASE, and an off-the-shelf Bayesian machine learner in Pipeline Pilot) are compared with four noncommercial machine learning implementations (Support Vector Machines, Random Forests, k-Nearest Neighbors, and Gaussian Processes) on the new benchmark data set.

Chemogenomic Analysis of G-Protein Coupled Receptors and Their Ligands Deciphers Locks and Keys Governing Diverse Aspects of Signalling

Understanding the molecular mechanism of signalling in the important super-family of G-protein-coupled receptors (GPCRs) is causally related to questions of how and where these receptors can be activated or inhibited. In this context, it is of great interest to unravel the common molecular features of GPCRs as well as those related to an active or inactive state or to subtype specific G-protein coupling. In our underlying chemogenomics study, we analyse for the first time the statistical link between the properties of G-protein-coupled receptors and GPCR ligands. The technique of mutual information (MI) is able to reveal statistical inter-dependence between variations in amino acid residues on the one hand and variations in ligand molecular descriptors on the other. Although this MI analysis uses novel information that differs from the results of known site-directed mutagenesis studies or published GPCR crystal structures, the method is capable of identifying the well-known common ligand binding region of GPCRs between the upper part of the seven transmembrane helices and the second extracellular loop. The analysis shows amino acid positions that are sensitive to either stimulating (agonistic) or inhibitory (antagonistic) ligand effects or both. It appears that amino acid positions for antagonistic and agonistic effects are both concentrated around the extracellular region, but selective agonistic effects are cumulated between transmembrane helices (TMHs) 2, 3, and ECL2, while selective residues for antagonistic effects are located at the top of helices 5 and 6. Above all, the MI analysis provides detailed indications about amino acids located in the transmembrane region of these receptors that determine G-protein signalling pathway preferences.

A maximum common subgraph kernel method for predicting the chromosome aberration test.

The chromosome aberration test is frequently used for the assessment of the potential of chemicals and drugs to elicit genetic damage in mammalian cells in vitro. Due to the limitations of experimental genotoxicity testing in early drug discovery phases, a model to predict the chromosome aberration test yielding high accuracy and providing guidance for structure optimization is urgently needed. In this paper, we describe a machine learning approach for predicting the outcome of this assay based on the structure of the investigated compound. The novelty of the proposed method consists in combining a maximum common subgraph kernel for measuring the similarity of two chemical graphs with the potential support vector machine for classification. In contrast to standard support vector machine classifiers, the proposed approach does not provide a black box model but rather allows to visualize structural elements with high positive or negative contribution to the class decision. In order to compare the performance of different methods for predicting the outcome of the chromosome aberration test, we compiled a large data set exhibiting high quality, reliability, and consistency from public sources and configured a fixed cross-validation protocol, which we make publicly available. In a comparison to standard methods currently used in pharmaceutical industry as well as to other graph kernel approaches, the proposed method achieved significantly better performance.

Predicting Lipophilicity of Drug‐Discovery Molecules using Gaussian Process Models

Many drug failures are due to an unfavorable ADMET profile (Absorption, Distribution, Metabolism, Excretion & Toxicity). Lipophilicity is intimately connected with ADMET and in today’s drug discovery process, the octanol water partition coefficient log P and it’s pH dependant counterpart log D have to be taken into account early on in lead discovery. Commercial tools available for ’in silico’ prediction of ADMET or lipophilicity parameters usually have been trained on relatively small and mostly neutral molecules, therefore their accuracy on industrial in-house data leaves room for considerable improvement (see Bruneau et al. and references therein). Using modern kernel-based machine learning algorithms – so called Gaussian Processes (GP)– this study constructs different log P and log D7 models that exhibit excellent predictions which compare favorably to state-of-the-art tools on both benchmark and in-house data sets.

Efficiency of different measures for defining the applicability domain of classification models

The goal of defining an applicability domain for a predictive classification model is to identify the region in chemical space where the model’s predictions are reliable. The boundary of the applicability domain is defined with the help of a measure that shall reflect the reliability of an individual prediction. Here, the available measures are differentiated into those that flag unusual objects and which are independent of the original classifier and those that use information of the trained classifier. The former set of techniques is referred to as novelty detection while the latter is designated as confidence estimation. A review of the available confidence estimators shows that most of these measures estimate the probability of class membership of the predicted objects which is inversely related to the error probability. Thus, class probability estimates are natural candidates for defining the applicability domain but were not comprehensively included in previous benchmark studies. The focus of the present study is to find the best measure for defining the applicability domain for a given binary classification technique and to determine the performance of novelty detection versus confidence estimation. Six different binary classification techniques in combination with ten data sets were studied to benchmark the various measures. The area under the receiver operating characteristic curve (AUC ROC) was employed as main benchmark criterion. It is shown that class probability estimates constantly perform best to differentiate between reliable and unreliable predictions. Previously proposed alternatives to class probability estimates do not perform better than the latter and are inferior in most cases. Interestingly, the impact of defining an applicability domain depends on the observed area under the receiver operator characteristic curve. That means that it depends on the level of difficulty of the classification problem (expressed as AUC ROC) and will be largest for intermediately difficult problems (range AUC ROC 0.7–0.9). In the ranking of classifiers, classification random forests performed best on average. Hence, classification random forests in combination with the respective class probability estimate are a good starting point for predictive binary chemoinformatic classifiers with applicability domain.Graphical abstract.

Predicting Error Bars for QSAR Models

Unfavorable physicochemical properties often cause drug failures. It is therefore important to take lipophilicity and water solubility into account early on in lead discovery. This study presents log D7 models built using Gaussian Process regression, Support Vector Machines, decision trees and ridge regression algorithms based on 14556 drug discovery compounds of Bayer Schering Pharma. A blind test was conducted using 7013 new measurements from the last months. We also present independent evaluations using public data. Apart from accuracy, we discuss the quality of error bars that can be computed by Gaussian Process models, and ensemble and distance based techniques for the other modelling approaches.