Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction

Noel M O'Boyle,David S Palmer,John Bo Mitchell,Florian Nigsch

doi:10.1186/1752-153x-2-21

Abstract

BackgroundWe present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The WAAC algorithm is an extension of the modified ant colony algorithm of Shen et al. (J Chem Inf Model 2005, 45: 1024–1029). We test the ability of the algorithm to develop a predictive partial least squares model for the Karthikeyan dataset (J Chem Inf Model 2005, 45: 581–590) of melting point values. We also test its ability to perform feature selection on a support vector machine model for the same dataset.ResultsStarting from an initial set of 203 descriptors, the WAAC algorithm selected a PLS model with 68 descriptors which has an RMSE on an external test set of 46.6°C and R2 of 0.51. The number of components chosen for the model was 49, which was close to optimal for this feature selection. The selected SVM model has 28 descriptors (cost of 5, ε of 0.21) and an RMSE of 45.1°C and R2 of 0.54. This model outperforms a kNN model (RMSE of 48.3°C, R2 of 0.47) for the same data and has similar performance to a Random Forest model (RMSE of 44.5°C, R2 of 0.55). However it is much less prone to bias at the extremes of the range of melting points as shown by the slope of the line through the residuals: -0.43 for WAAC/SVM, -0.53 for Random Forest.ConclusionWith a careful choice of objective function, the WAAC algorithm can be used to optimise machine learning and regression models that suffer from overfitting. Where model parameters also need to be tuned, as is the case with support vector machine and partial least squares models, it can optimise these simultaneously. The moving probabilities used by the algorithm are easily interpreted in terms of the best and current models of the ants, and the winnowing procedure promotes the removal of irrelevant descriptors.

Highlights

We present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models
Quantitative Structure-Activity and Structure-Property Relationship (QSAR and QSPR) models are based upon the idea, first proposed by Hansch [1], that a molecular property can be related to physicochemical descriptors of the molecule
Feature selection refers to the problem of selecting a subset of the descriptors which can be used to build a model with optimal predictive ability [3]

Summary

Introduction

We present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The filter approach does not take into account the particular model being used for prediction, but rather attempts to determine a priori which descriptors are likely to contain useful information. Examples of this approach include ranking descriptors by their correlation with the target value or by estimates of the mutual information (based on information theory) between each descriptor and the response. Another commonly used filter in QSAR is the removal of highly correlated (or anti-correlated) descriptors [9]. Guyon and Elisseeff show that very high correlation (or anti-correlation) does not necessarily imply an absence of feature complementarity, and that two variables that are useless by themselves can be useful together [3]

Methods

Results

Discussion

Conclusion