Data Mining and Machine Learning Techniques for the Identification of Mutagenicity Inducing Substructures and Structure—Activity Relationships of Noncongeneric Compounds.

Abstract

This paper explores the utility of data mining and machine learning algorithms for the induction of mutagenicity structure-activity relationships (SARs) from noncongeneric data sets. We compare (i) a newly developed algorithm (MOLFEA) for the generation of descriptors (molecular fragments) for noncongeneric compounds with traditional SAR approaches (molecular properties) and (ii) different machine learning algorithms for the induction of SARs from these descriptors. In addition we investigate the optimal parameter settings for these programs and give an exemplary interpretation of the derived models. The predictive accuracies of models using MOLFEA derived descriptors is ∼10-15%age points higher than those using molecular properties alone. Using both types of descriptors together does not improve the derived models. From the applied machine learning techniques the rule learner PART and support vector machines gave the best results, although the differences between the learning algorithms are only marginal. We were able to achieve predictive accuracies up to 78% for 10-fold cross-validation. The resulting models are relatively easy to interpret and usable for predictive as well as for explanatory purposes.

The Challenges Involved in Modeling Toxicity Data In Silico: A Review

“…A recent comprehensive review [232] of different in silico models and approaches for predictions of genotoxic outcome, shows that most of the earlier approaches described for the prediction of Ames mutagenicity produced good specificity and sensitivity values (prediction accuracy of up to 85%). Depending on the descriptors and the statistical methods used, some of the models offer simple SAR information [82,244], whilst others are harder to interpret due to the choice of chemical descriptors derived from structural information [245,246].…”

“…Different QSAR and machine learning methods have been used to derive in silico predictions about the Ames outcome of the chemicals. These include Ames test QSAR models using PLS, NN, RF, and SVM [46,[244][245][246][247][248][249][250].…”

On extending extreme learning machine to non-redundant synergy pattern based graph classification

“…In these scientific applications, graph patterns can help build classification model for better predicting unknown graphs between different classes and understanding these complex structures. For example, in chemical compounds data analysis, graph patterns can reveal that which substructures are the characteristics of chemical toxicity [6].…”

Partial least squares regression for graph mining

“…Specifically, each graph is represented as a binary vector of pattern indicators (Figure 1). Graph mining is especially popular in chemoinformatics, where the task is to classify chemical compounds [11,7]. When all possible subgraphs are used, the dimensionality of the feature space is too large for usual statistical methods.…”

“…A naive approach is to use a frequent substructure mining algorithm such as AGM [9], gSpan [36] or Gaston [20] to collect frequently appearing patterns. This approach was employed by [7] and [11], where a linear support vector machine is used for classification. A more advanced approach is to mine informative patterns with high correlation to the output variable [19,1].…”