We investigate the learning of quantitative structure activity relationships (QSARs) as a case-study of meta-learning. This application area is of the highest societal importance, as it is a key step in the development of new medicines. The standard QSAR learning problem is: given a target (usually a protein) and a set of chemical compounds (small molecules) with associated bioactivities (e.g. inhibition of the target), learn a predictive mapping from molecular representation to activity. Although almost every type of machine learning method has been applied to QSAR learning there is no agreed single best way of learning QSARs, and therefore the problem area is well-suited to meta-learning. We first carried out the most comprehensive ever comparison of machine learning methods for QSAR learning: 18 regression methods, 3 molecular representations, applied to more than 2700 QSAR problems. (These results have been made publicly available on OpenML and represent a valuable resource for testing novel meta-learning methods.) We then investigated the utility of algorithm selection for QSAR problems. We found that this meta-learning approach outperformed the best individual QSAR learning method (random forests using a molecular fingerprint representation) by up to 13%, on average. We conclude that meta-learning outperforms base-learning methods for QSAR learning, and as this investigation is one of the most extensive ever comparisons of base and meta-learning methods ever made, it provides evidence for the general effectiveness of meta-learning over base-learning.

In this article, we present a dataset that comprises different physical rehabilitation movements. The dataset was captured as part of a research project intended to provide automatic feedback on the execution of rehabilitation exercises, even in the absence of a physiotherapist. A Kinect motion sensor camera was used to record gestures. The dataset contains repetitions of nine gestures performed by 29 subjects, out of which 15 were patients and 14 were healthy controls. The data are presented in an easily accessible format, provided as 3D coordinates of 25 body joints along with the corresponding depth map for each frame. Each movement was annotated with the gesture type, the position of the person performing the gesture (sitting or standing) as well as a correctness label. The data are publicly available and were released with to provide a comprehensive dataset that can be used for assessing the performance of different patients while performing simple movements in a rehabilitation setting and for comparing these movements with a control group of healthy individuals.

The goal of quantitative structure activity relationship (QSAR) learning is to learn a function that, given the structure of a small molecule (a potential drug), outputs the predicted activity of the compound. We employed multi-task learning (MTL) to exploit commonalities in drug targets and assays. We used datasets containing curated records about the activity of specific compounds on drug targets provided by ChEMBL. Totally, 1091 assays have been analysed. As a baseline, a single task learning approach that trains random forest to predict drug activity for each drug target individually was considered. We then carried out feature-based and instance-based MTL to predict drug activities. We introduced a natural metric of evolutionary distance between drug targets as a measure of tasks relatedness. Instance-based MTL significantly outperformed both, feature-based MTL and the base learner, on 741 drug targets out of 1091. Feature-based MTL won on 179 occasions and the base learner performed best on 171 drug targets. We conclude that MTL QSAR is improved by incorporating the evolutionary distance between targets. These results indicate that QSAR learning can be performed effectively, even if little data is available for specific drug targets, by leveraging what is known about similar drug targets.

In this study, we propose a new genetic algorithm that uses a statistical-based chromosome replacement strategy determined by the empirical distribution of the objective function values. The proposed genetic algorithm is further used in the training process of a multiplicative neuron model artificial neural network. The objective function value for the genetic algorithm is the root mean square error of the multiplicative neuron model artificial neural network prediction. This combination of methods is proposed for a particular type of problems, that is, time-series prediction. We use different subsets of three stock exchange time series to test the performance of the proposed method and compare it against similar approaches, and the results prove that the proposed genetic algorithm for the multiplicative neuron model of the artificial neural network works better than many other artificial intelligence optimization methods. The ranks of the proposed method are 1.78 for the Nikkei data sets, 1.55 for the S&P500 data sets and 1.22 for the DOW JONES data sets for data corresponding to different years, according to the root mean square error, respectively. Moreover, the overall mean rank is 1.50 for the proposed method. Also, the proposed method obtains the best performance overall as well as the best performance for all the individual tests. The results certify that our method is robust and efficient for the task investigated.