Search

In silico toxicity prediction plays an important role in the regulatory decision making and selection of leads in drug design as in vitro/vivo methods are often limited by ethics, time, budget, and other resources. Many computational methods have been employed in predicting the toxicity profile of chemicals. This review provides a detailed end-to-end overview of the application of machine learning algorithms to Structure-Activity Relationship (SAR)-based predictive toxicology. From raw data to model validation, the importance of data quality is stressed as it greatly affects the predictive power of derived models. Commonly overlooked challenges such as data imbalance, activity cliff, model evaluation, and definition of applicability domain are highlighted, and plausible solutions for alleviating these challenges are discussed.

The challenge of developing facial recognition systems has been the focus of many research efforts in recent years and has numerous applications in areas such as security, entertainment, and biometrics. Recently, most progress in this field has come from training very deep neural networks on massive datasets which is computationally intensive and time consuming. Here, we propose a deep transfer learning (DTL) approach that integrates transfer learning techniques and convolutional neural networks and apply it to the problem of facial recognition to fine-tune facial recognition models. Transfer learning can allow for the training of robust, high-performance machine learning models that require much less time and resources to produce than similarly performing models that have been trained from scratch. Using a pre-trained face recognition model, we were able to perform transfer learning to produce a network that is capable of making accurate predictions on much smaller datasets. We also compare our results with results produced by a selection of classical algorithms on the same datasets to demonstrate the effectiveness of the proposed DTL approach.

Background Multi-label classification of data remains to be a challenging problem. Because of the complexity of the data, it is sometimes difficult to infer information about classes that are not mutually exclusive. For medical data, patients could have symptoms of multiple different diseases at the same time and it is important to develop tools that help to identify problems early. Intelligent health risk prediction models built with deep learning architectures offer a powerful tool for physicians to identify patterns in patient data that indicate risks associated with certain types of chronic diseases. Results Physical examination records of 110,300 anonymous patients were used to predict diabetes, hypertension, fatty liver, a combination of these three chronic diseases, and the absence of disease (8 classes in total). The dataset was split into training (90%) and testing (10%) sub-datasets. Ten-fold cross validation was used to evaluate prediction accuracy with metrics such as precision, recall, and F-score. Deep Learning (DL) architectures were compared with standard and state-of-the-art multi-label classification methods. Preliminary results suggest that Deep Neural Networks (DNN), a DL architecture, when applied to multi-label classification of chronic diseases, produced accuracy that was comparable to that of common methods such as Support Vector Machines. We have implemented DNNs to handle both problem transformation and algorithm adaption type multi-label methods and compare both to see which is preferable. Conclusions Deep Learning architectures have the potential of inferring more information about the patterns of physical examination data than common classification methods. The advanced techniques of Deep Learning can be used to identify the significance of different features from physical examination data as well as to learn the contributions of each feature that impact a patient’s risk for chronic diseases. However, accurate prediction of chronic disease risks remains a challenging problem that warrants further studies.

The challenge of developing facial recognition systems has been the focus of many research efforts in recent years and has numerous applications in areas such as security, entertainment, and biometrics. Recently, most progress in this field has come from training very deep neural networks on massive datasets. Here, we use a pre-trained face recognition model and perform transfer learning to produce a network that is capable of making accurate predictions on a much smaller dataset. We also compare our results with results produced by a selection of classical algorithms on the same dataset.

In this paper, we introduce an experiment evaluating performance of football players in countermovement jumps (CMJs). Three methods including time domain, frequency domain, and machine learning algorithms are proposed for performance evaluation. Correlation coefficients and p-values are given for time domain and frequency domain methods, and prediction errors are given for different machine learning algorithms.