Intrinsic Dimension Estimation-Based Feature Selection and Multinomial Logistic Regression for Classification of Bearing Faults Using Compressively Sampled Vibration Signals

As failures of rolling bearings lead to major failures in rotating machines, recent vibration-based rolling bearing fault diagnosis techniques are focused on obtaining useful fault features from the huge collection of raw data. However, too many features reduce the classification accuracy and increase the computation time. This paper proposes an effective feature selection technique based on intrinsic dimension estimation of compressively sampled vibration signals. First, compressive sampling (CS) is used to get compressed measurements from the collected raw vibration signals. Then, a global dimension estimator, the geodesic minimal spanning tree (GMST), is employed to compute the minimal number of features needed to represent efficiently the compressively sampled signals. Finally, a feature selection process, combining the stochastic proximity embedding (SPE) and the neighbourhood component analysis (NCA), is used to select fewer features for bearing fault diagnosis. With regression analysis-based predictive modelling technique and the multinomial logistic regression (MLR) classifier, the selected features are assessed in two case studies of rolling bearings vibration signals under different working loads. The experimental results demonstrate that the proposed method can successfully select fewer features, with which the MLR-based trained model achieves high classification accuracy and significantly reduced computation times compared to published research.

Performance Improvement of Driving Fatigue Identification Based on Power Spectra and Connectivity Using Feature Level and Decision Level Fusions

Power and connectivity features extracted from EEG signals have been previously utilized to detect mental fatigue during driving. Although each of the feature categories has the discriminative power to differentiate alert and fatigue states, they might represent different aspects of information relevant to fatigue identification. Two fusion methods, feature level and decision level fusions, were proposed in this study to combine individual channel information (i.e., power features) and between-channel information (i.e., connectivity features). According to the results of the study, the average accuracies of the fusion methods were higher than the accuracies of the individual feature categories (feature level fusion: 84.70%, decision level fusion: 87.13%, power features: 80.82%, connectivity features: 79.36%). The statistical analysis demonstrated that the two fusion methods significantly improved the classification performance of driving fatigue. The fusion methods proposed in this study can be embedded into a driving fatigue detection system for a practical use in a vehicle.

Fast, efficient fragment-based coordinate generation for Open Babel

Rapidly predicting an accurate three dimensional geometry of a molecule is a crucial task for cheminformatics and across a wide range of molecular modeling. Consequently, developing a fast, accurate, and open implementation of structure prediction is necessary for reproducible cheminformatics research. We introduce a fragment-based coordinate generation implementation for Open Babel, a widely-used open source toolkit for cheminformatics. The new implementation improves speed and stereochemical accuracy, while retaining or improving accuracy of bond lengths, bond angles, and dihedral torsions. Input molecules are broken into fragments by cutting at rotatable bonds. The coordinates of fragments are set according to a fragment library, prepared from open crystallographic databases. Since the coordinates of multiple atoms are decided at once, coordinate prediction is accelerated over the previous rules-based implementation in Open Babel, as well as the widely-used distance geometry methods in RDKit. This new implementation will be beneficial for a wide range of applications, including computational property prediction in polymers, molecular materials and drug design.

Conformation Generation: The State of the Art

The generation of conformations for small molecules is a problem of continuing interest in cheminformatics and computational drug discovery. This review will present an overview of methods used to sample conformational space, focusing on those methods designed for organic molecules commonly of interest in drug discovery. Different approaches to both the sampling of conformational space and the scoring of conformational stability will be compared and contrasted, with an emphasis on those methods suitable for conformer sampling of large numbers of drug-like molecules. Particular attention will be devoted to the appropriate utilization of information from experimental solid-state structures in validating and evaluating the performance of these tools. The review will conclude with some areas worthy of further investigation.

Nonlinear dimensionality reduction and mapping of compound libraries for drug discovery

Visualization of 'chemical space' and compound distributions has received much attraction by medicinal chemists as it may help to intuitively comprehend pharmaceutically relevant molecular features. It has been realized that for meaningful feature extraction from complex multivariate chemical data, such as compound libraries represented by many molecular descriptors, nonlinear projection techniques are required. Recent advances in machine-learning and artificial intelligence have resulted in a transfer of such methods to chemistry. We provide an overview of prominent visualization methods based on nonlinear dimensionality reduction, and highlight applications in drug discovery. Emphasis is on neural network techniques, kernel methods and stochastic embedding approaches, which have been successfully used for ligand-based virtual screening, SAR landscape analysis, combinatorial library design, and screening compound selection.

Designing antimicrobial peptides: form follows function

Multidrug-resistant bacteria are a severe threat to public health. Conventional antibiotics are becoming increasingly ineffective as a result of resistance, and it is imperative to find new antibacterial strategies. Natural antimicrobials, known as host defence peptides or antimicrobial peptides, defend host organisms against microbes but most have modest direct antibiotic activity. Enhanced variants have been developed using straightforward design and optimization strategies and are being tested clinically. Here, we describe advanced computer-assisted design strategies that address the difficult problem of relating primary sequence to peptide structure, and are delivering more potent, cost-effective, broad-spectrum peptides as potential next-generation antibiotics.

Stochastic proximity embedding on graphics processing units: taking multidimensional scaling to a new scale

Stochastic proximity embedding (SPE) was developed as a method for efficiently calculating lower dimensional embeddings of high-dimensional data sets. Rather than using a global minimization scheme, SPE relies upon updating the distances of randomly selected points in an iterative fashion. This was found to generate embeddings of comparable quality to those obtained using classical multidimensional scaling algorithms. However, SPE is able to obtain these results in O(n) rather than O(n²) time and thus is much better suited to large data sets. In an effort both to speed up SPE and utilize it for even larger problems, we have created a multithreaded implementation which takes advantage of the growing general computing power of graphics processing units (GPUs). The use of GPUs allows the embedding of data sets containing millions of data points in interactive time scales.

Reaction-driven de novo design, synthesis and testing of potential type II kinase inhibitors

BACKGROUND

De novo design of drug-like compounds with a desired pharmacological activity profile has become feasible through innovative computer algorithms. Fragment-based design and simulated chemical reactions allow for the rapid generation of candidate compounds as blueprints for organic synthesis.

METHODS

We used a combination of complementary virtual-screening tools for the analysis of de novo designed compounds that were generated with the aim to inhibit inactive polo-like kinase 1 (Plk1), a target for the development of cancer therapeutics. A homology model of the inactive state of Plk1 was constructed and the nucleotide binding pocket conformations in the DFG-in and DFG-out state were compared. The de novo-designed compounds were analyzed using pharmacophore matching, structure-activity landscape analysis, and automated ligand docking. One compound was synthesized and tested in vitro.

RESULTS

The majority of the designed compounds possess a generic architecture present in known kinase inhibitors. Predictions favor kinases as targets of these compounds but also suggest potential off-target effects. Several bioisosteric replacements were suggested, and de novo designed compounds were assessed by automated docking for potential binding preference toward the inactive (type II inhibitors) over the active conformation (type I inhibitors) of the kinase ATP binding site. One selected compound was successfully synthesized as suggested by the software. The de novo-designed compound exhibited inhibitory activity against inactive Plk1 in vitro, but did not show significant inhibition of active Plk1 and 38 other kinases tested.

CONCLUSIONS

Computer-based de novo design of screening candidates in combination with ligand- and receptor-based virtual screening generates motivated suggestions for focused library design in hit and lead discovery. Attractive, synthetically accessible compounds can be obtained together with predicted on- and off-target profiles and desired activities.