Search

After the initial wave of antibiotic discovery, few novel classes of antibiotics have emerged, with the latest dating back to the 1980's. Furthermore, the pace of antibiotic drug discovery is unable to keep up with the increasing prevalence of antibiotic drug resistance. However, the increasing amount of available data promotes the use of machine learning techniques (MLT) in drug discovery projects (In this review, the authors cover some of the applications of MLT in medicinal chemistry, focusing on the development of new antibiotics, the prediction of resistance and its mechanisms. The aim of this review is to illustrate the main advantages and disadvantages and the major trends from studies over the past 5 years.The application of MLT to antibacterial drug discovery can aid the selection of new and potent lead compounds, with desirable pharmacokinetic and toxic profiles for further optimization. The increasing volume of available data along with the constant improvement in computational power and algorithms has meant that we are experiencing a transition in the way we face modern issues such as drug resistance, where our decisions are data-driven and experiments can be focused by data-suggested hypotheses.

Since the emergence of the new severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2) at the end of December 2019 in China, and with the urge of the coronavirus disease 2019 (COVID-19) pandemic, there have been huge efforts of many research teams and governmental institutions worldwide to mitigate the current scenario. Reaching more than 1,377,000 deaths in the world and still with a growing number of infections, SARS-CoV-2 remains a critical issue for global health and economic systems, with an urgency for available therapeutic options. In this scenario, as drug repurposing and discovery remains a challenge, computer-aided drug design (CADD) approaches, including machine learning (ML) techniques, can be useful tools to the design and discovery of novel potential antiviral inhibitors against SARS-CoV-2. In this work, we describe and review the current knowledge on this virus and the pandemic, the latest strategies and computational approaches applied to search for treatment options, as well as the challenges to overcome COVID-19.

Computational methods have been widely used in drug design. The recent developments in machine learning techniques and the ever-growing chemical and biological databases are fertile ground for discoveries in this area. In this study, we evaluated the performance of Deep Learning models in comparison to Random Forest, and Support Vector Regression for predicting the biological activity (pIC50) of ALK-5 inhibitors as candidates to treat cancer. The generalization power of the models was assessed by internal and external validation procedures. A deep neural network model obtained the best performance in this comparative study, achieving a coefficient of determination of 0.658 on the external validation set with mean square error and mean absolute error of 0.373 and 0.450, respectively. Additionally, the relevance of the chemical descriptors for the prediction of biological activity was estimated using Permutation Importance. We can conclude that the forecast model obtained by the deep neural network is suitable for the problem and can be employed to predict the biological activity of new ALK-5 inhibitors.

Recent developments in the fields of medicinal chemistry and computer science have made possible to perform rational drug design, helping reduce the cost and time required to discover new therapeutic agents. Particularly, quantitative structure-activity relationship (QSAR) studies have been widely employed to correlate molecular structure to biological activity. Such analyses take into account a set of chemical compounds encoded by numerical descriptors and biological data for generating mathematical models capable to predict biological activity values for structurally similar unknown compounds. Although a huge amount of chemical and biological data has become publicly available, there is an increasing need for integrating and sharing the data from various repositories in order to derive a reusable domain knowledge base. Attempting to overcome such limitation, this article proposes an ontology for QSAR studies, named OntoQSAR, which describes the major concepts in these analyses, like methods used to obtain chemical descriptors and biological properties of chemical compounds. Since the compounds of interest in these studies must be subjected to the same methods for obtaining the necessary numerical descriptors, the developed ontology will allow that information to be reused in other related researches.

Discovering (or planning) a new drug candidate involves many parameters, which makes this process slow, costly, and leading to failures at the end in some cases. In the last decades, we have witnessed a revolution in the computational area (hardware, software, large-scale computing, etc.), as well as an explosion in data generation (big data), which raises the need for more sophisticated algorithms to analyze this myriad of data. In this scenario, we can highlight the potentialities of artificial intelligence (AI) or computational intelligence (CI) as a powerful tool to analyze medicinal chemistry data. According to IEEE, computational intelligence involves the theory, the design, the application, and the development of biologically and linguistically motivated computational paradigms. In addition, CI encompasses three main methodologies: neural networks (NN), fuzzy systems, and evolutionary computation. In particular, artificial neural networks have been successfully applied in medicinal chemistry studies. A branch of the NN area that has attracted a lot of attention refers to deep learning (DL) due to its generalization power and ability to extract features from data. Therefore, in this mini-review we will briefly outline the present scope, advances, and challenges related to the use of DL in drug design and discovery, describing successful studies involving quantitative structure-activity relationships (QSAR) and virtual screening (VS) of databases containing thousands of compounds.

Vehicular ad hoc networks (VANETs) have unique features and rely on vehicle-to-vehicle (V2V) communication to mitigate adversities in traffic dynamics management and to support drivers providing safety alerts. Congestions, originating from an incident, frequently endanger traffic and, consequently, cause all kinds of losses. In this scenario, the paper herein proposes eFIRST, a robust solution to autonomous detection of the current congestion condition in order to disseminate safety alerts and to reduce problems with the interruption of traffic in a section of the highway. The approach is supported only by V2V communication and the local neighborhood identification records, which are brought together in a fuzzy strategy and in the adaptive adjustment of the transmission signal power. The estimate of local traffic conditions establishes the dynamic reach of transmission for the vehicle, supporting the connective maintenance. In these circumstances, the drivers receive an alert emitted soon enough for the proper response action. The results during simulations show how the elaborated solution leads to minimized delays, with low communication overload, besides relevantly mapping the congest levels and efficiently providing the event coverage to satisfactory propagation distances inside the area of interest for the dissemination. Promptly, the alert finds vehicles far from the traffic accident located at nearly 1/6 from the evaluated extension. In accordance with the intelligent protocols, this evaluation contributes providing grants for the ratification of fuzzy approximation as an adaptive strategy to fluctuations in vehicular density in different traffic basis.

INTRODUCTION Novel drug discovery remains an enormous challenge, with various computer-aided drug design (CADD) approaches having been widely employed for this purpose. CADD, specifically the commonly used support vector machines (SVMs), can employ machine learning techniques. SVMs and their variations offer numerous drug discovery applications, which range from the classification of substances (as active or inactive) to the construction of regression models and the ranking/virtual screening of databased compounds. Areas covered: Herein, the authors consider some of the applications of SVMs in medicinal chemistry, illustrating their main advantages and disadvantages, as well as trends in their utilization, via the available published literature. The aim of this review is to provide an up-to-date review of the recent applications of SVMs in drug discovery as described by the literature, thereby highlighting their strengths, weaknesses, and future challenges. Expert opinion: Techniques based on SVMs are considered as powerful approaches in early drug discovery. The ability of SVMs to classify active or inactive compounds has enabled the prioritization of substances for virtual screening. Indeed, one of the main advantages of SVMs is related to their potential in the analysis of nonlinear problems. However, despite successes in employing SVMs, the challenges of improving accuracy remain.

Métodos para extração de características têm como objetivo selecionar, a partir de um conjunto de dados, características que representem informações relevantes ou que sejam básicas para diferenciar uma classe de objetos de outras. Neste trabalho, são apresentadas duas metodologias que podem ser usadas para extração de características. A primeira utiliza métodos estatísticos clássicos como Análise de Componentes Principais (PCA), Análise Discriminante Linear (LDA) e Análise de Cluster. A segunda consiste na utilização de arquiteturas de Redes Neurais Artificiais (RNA) que implementam os mesmos métodos estatísticos. O desempenho dos modelos de RNA apresentados são avaliados, considerando-se a utilização destes na extração de características de um pequeno conjunto de dados e, para investigar a aplicabilidade desses modelos na área de processamento de imagens, uma das redes que implementa PCA é utilizada na tarefa de compressão de algumas imagens médicas. Os resultados obtidos pela rede PCA são comparados com outros provenientes da aplicação da análise PCA clássica e do padrão JPEG (Joint Photographic Experts Group) para o mesmo conjunto de imagens. Methods for feature extraction are used to select from an initial data set, some features that represent the most important information of this set or that are essential to differentiate one class of objects from other. In this work, two methodologies that can be used for feature extraction are presented. The first uses classical statistical methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Cluster Analysis. The other approach is based on Artificial Neural Networks architectures that implement the same statistical methods. The performance of the presented neural network models is appraised considering the use of these in the feature extraction of a small data set. Also, to investigate the usability of these models in applications of image processing, one of the neural networks that implements PCA is used for compressing some medical images. The results obtained by the PCA network are compared with others obtained by applying classical PCA and JPEG compression standard to the same group of images.

Combretastatin-like chalcones are promising anticancer compounds that inhibit the mitotic process through interactions with β-tubulin. A detailed study of these compounds can contribute for the rational drug design of new structures aiming at compounds with high biological activity. For this purpose, we have studied 87 combretastatin-like chalcones and proposed multivariate models based on partial least squares (PLS), artificial neural network consensus model (ANN-CM), and general consensus model (GCM). The proposed models have showed good predictive ability with r2test = 0.812 and MSE (test set) = 0.327 for the PLS model, r2test = 0.829 and MSE (test set) = 0.286 for the ANN-CM, and r2test = 0.822 and and MSE (test set) = 0.302 for the GCM. The selected molecular and electronic descriptors (RDF045e, RTv, RDF155u, RDF035m, SP02, PI, UNIP and EHOMO-3) represent molecular features of the compounds that can be associated to the biological activity and can be employed to help the design of new bioactive ligands with improved biological activity.

Medicinal chemistry projects involve some steps aiming to develop a new drug, such as the analysis of biological targets related to a given disease, the discovery and the development of drug candidates for these targets, performing parallel biological tests to validate the drug effectiveness and side effects. Approaches as quantitative study of activity-structure relationships (QSAR) involve the construction of predictive models that relate a set of descriptors of a chemical compound series and its biological activities with respect to one or more targets in the human body. Datasets used to perform QSAR analyses are generally characterized by a small number of samples and this makes them more complex to build accurate predictive models. In this context, transfer and multi-task learning techniques are very suitable since they take information from other QSAR models to the same biological target, reducing efforts and costs for generating new chemical compounds. Therefore, this review will present the main features of transfer and multi-task learning studies, as well as some applications and its potentiality in drug design projects.

Aiming at avoiding high costs in the production and analysis of new drug candidates, databases containing molecular information have been generated, and thus, computational models can be constructed from these data. The quantitative study of structure-activity relationships (QSAR) involves building predictive models that relate chemical descriptors for a compound set and biological activity with respect to one or more targets in the human body. Datasets manipulated by researchers in QSAR analyses are generally characterized by a small number of instances, which can affect the accuracy of the resulting models. In this context, transfer learning techniques that take information from other QSAR models to the same biological target would be desirable, reducing efforts and costs for evaluating new chemical compounds. This article presents a novel transfer learning method that can be applied to build QSAR regression models by Support Vectors Regression (SVR). The SVR-Adapted method for Transfer Learning (ATL) was compared with standard SVR method regarding values of mean squared error. From experimental studies, the performance of both methods was evaluated for different proportions of the original training set. The obtained results show that transfer learning is capable to exploit knowledge from models built from other datasets, which is effective primarily for small target training datasets.

The treatment of neuropathic pain is very complex and there are few drugs approved for this purpose. Among the studied compounds in the literature, sigma-1 receptor antagonists have shown to be promising. In order to develop QSAR studies applied to the compounds of 1-arylpyrazole derivatives, multivariate analyses have been performed in this work using partial least square (PLS) and artificial neural network (ANN) methods. A PLS model has been obtained and validated with 45 compounds in the training set and 13 compounds in the test set (r2 training = 0.761, q2 = 0.656, r2 test = 0.746, MSEtest = 0.132 and MAEtest = 0.258). Additionally, multi-layer perceptron ANNs (MLP-ANNs) were employed in order to propose non-linear models trained by gradient descent with momentum backpropagation function. Based on MSEtest values, the best MLP-ANN models were combined in a MLP-ANN consensus model (MLP-ANN-CM; r2 test = 0.824, MSEtest = 0.088 and MAEtest = 0.197). In the end, a general consensus model (GCM) has been obtained using PLS and MLP-ANN-CM models (r2 test = 0.811, MSEtest = 0.100 and MAEtest = 0.218). Besides, the selected descriptors (GGI6, Mor23m, SRW06, H7m, MLOGP, and μ) revealed important features that should be considered when one is planning new compounds of the 1-arylpyrazole class. The multivariate models proposed in this work are definitely a powerful tool for the rational drug design of new compounds for neuropathic pain treatment.

Image segmentation is considered, among all the stages of image processing, the most critical stage of data processing, because a good classification is dependent on the features extracted from the segmented images. In this work, we are proposing to use the technique called Enhanced ICA Mixture Model (EICAMM) for automatic segmentation of breast masses, aiming to comparing it to other segmentation methods known for segmentation of medical images such as Watershed, Self-Organizing Map (SOM), K-means and Fuzzy C-means techniques. For the analysis of the results, it was used Jaccard similarity measure for comparing the result obtained by the segmentation techniques with that one obtained by an expert opinion. All images considered in this work were segmented and then analyzed by us to improve the segmentation performed by an expert and to detect lesion shape for further classification. These models have been applied for the segmentation of suspicious masses in digital mammographic images, including images of dense breasts. The obtained results show a good performance of EICAMM that was the unique technique able to detect masses in dense breast interest region in preprocessed images and in original images. In this way, EICAMM could be considered as a good alternative approach to be applied for breast masses classification.

The discovery of new drugs is a very important area of study in medicinal chemistry. Developing a drug is not an easy task, as much time and money are needed to undertake all steps required for the development and test of new drugs. Amid this context, chemoinformatics is the area that has the role of interfacing between chemistry and computing, assisting in the process of identifying potential new drugs, through machine learning techniques for classification. This article will present the difficulties of classification found in chemoinformatics and approach machine learning techniques that, applied in the context of chemoinformatics, assist in treating issues related to uncertainty in data labeling and unbalanced classes, as they are common problems when using data sets of a chemical nature.

Principal Component Analysis (PCA) is a well known statistical method that has successfully been applied for reducing data dimensionality. Focusing on a neural network which approximates the results obtained by classical PCA, the main contribution of this work consists in introducing a paralle l modeling for such network. A comparative study shows that the proposal presents promising results when a multi-core computer is available.

The assembling process of an academic timetable structure is one of hardest scholar planning tasks. A well done schedule requires considerable time, because of many factors involved (e.g. professor availability, courses and their workload, students and classrooms). Based on related researches, it is possible to claim that in the most of the institutions, the solution is done by manual work, which requires more time and effort. Although the search for the best solution is infeasible, it is possible to find near optimal solutions using heuristics. Most current solutions provide answers optimizing administrative factors, i.e. considering mainly the factors related to the disciplines, classrooms and professors, not considering students needs, e.g. reducing time gaps between non-consecutive classes. In this work, we focus on the timetable improvement for the students and assess our results using real data from a Brazilian university.

Background: Sympathetic activation and arterial baroreflex (ABR) dysfunction typify chronic heart failure (CHF). In addition, decreased oscillatory pattern of muscle sympathetic nerve activity (MSNA, LF MSNA /HF MSNA ) seems to contribute to sympathetic exacerbation in patients with CHF. Unknown is whether the LF MSNA /HF MSNA is associated with ABR dysfunction in CHF patients. To answer this question, we investigated the association between gain, latency and coupling of ABR function and LF MSNA /HF MSNA in CHF patients. Methods and Results: Forty-three CHF patients, Functional Class II to III, NYHA, ejection fraction ≤40% were allocated into two groups according to the level of LF MSNA /HF MSNA index: 1) Higher LF MSNA /HF MSNA (n=21, 52±2 years) and 2) Lower LF MSNA /HF MSNA (n=22, 54±1 years). Blood pressure (BP, oscillometric beat-to-beat basis) and MSNA (microneurography technique) were recorded during 10 min at rest. Spectral and cross-spectral analyses of BP and MSNA variabilities were conducted to assess the LF MSNA /HF MSNA and the gain, latency and coupling between BP and MSNA of ABR function. Etiology, ejection fraction, gain and latency of ABR function were similar between groups. However, the patients with lower LF MSNA /HF MSNA had increased MSNA bursts frequency (53±2vs. 39±3 bursts/min, PMSNA /HF MSNA . In contrast, the patients with lower LF MSNA /HF MSNA had reduced coupling of ABR function (69±3 vs. 80±2 %, PMSNA /HF MSNA (R=0.36, P=0.02). Conclusions: There is an inverse association between the LF MSNA /HF MSNA index and sympathetic nerve activity. In addition, there is a direct association between the LF MSNA /HF MSNA index and the coupling of ABR, which suggests that the ABR dysfunction explains, at least in part, the augmented sympathetic nerve activity in CHF patients.

Today several different unsupervised classification algorithms are commonly used to cluster similar patterns in a data set based only on its statistical properties. Specially in image data applications, self-organizing methods for unsupervised classification have been successfully applied for clustering pixels or group of pixels in order to perform segmentation tasks. The first important contribution of this paper refers to the development of a self-organizing method for data classification, named Enhanced Independent Component Analysis Mixture Model (EICAMM), which was built by proposing some modifications in the Independent Component Analysis Mixture Model (ICAMM). Such improvements were proposed by considering some of the model limitations as well as by analyzing how it should be improved in order to become more efficient. Moreover, a pre-processing methodology was also proposed, which is based on combining the Sparse Code Shrinkage (SCS) for image denoising and the Sobel edge detector. In the experiments of this work, the EICAMM and other self-organizing models were applied for segmenting images in their original and pre-processed versions. A comparative analysis showed satisfactory and competitive image segmentation results obtained by the proposals presented herein.

Database management systems are very sophisticated, efficient, and fast in information retrieval tasks involving traditional data sets such as numbers, strings, and so on, but many limitations become evident when the data are more complex, that is, high or nondimensional data. Considering some existing problems in information retrieval processes, this work proposes a hybrid system that combines a model of the ART family neural network, ART2-A, with the Slim-Tree data structure, which is a metric access method. This approach is an alternative to perform clustering on data in an intelligent way so that the data can be recovered from the corresponding Slim-Tree. The proposed hybrid system is able to perform range and k-nearest neighbor queries, which is not an inherent characteristic in implementations involving artificial neural networks. Furthermore, experimental results showed that the performance of the hybrid system was better than the performance of Slim-Tree. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 319–336, 2007.

Pharmacokinetics involves the study of absorption, distribution, metabolism, excretion and toxicity of xenobiotics (ADME-Tox). In this sense, the ADME-Tox profile of a bioactive compound can impact its efficacy and safety. Moreover, efficacy and safety were considered some of the major causes of clinical failures in the development of new chemical entities. In this context, machine learning (ML) techniques have been often used in ADME-Tox studies due to the existence of compounds with known pharmacokinetic properties available for generating predictive models.This review examines the growth in the use of some ML techniques in ADME-Tox studies, in particular supervised and unsupervised techniques. Also, some critical points (e.g., size of the data set and type of output variable) must be considered during the generation of models that relate ADME-Tox properties and biological activity.ML techniques have been successfully employed in pharmacokinetic studies, helping the complex process of designing new drug candidates from the use of reliable ML models. An application of this procedure would be the prediction of ADME-Tox properties from studies of quantitative structure-activity relationships or the discovery of new compounds from a virtual screening using filters based on results obtained from ML techniques.

Previous studies have demonstrated that muscle mechanoreflex and metaboreflex controls are altered in heart failure (HF), which seems to be due to changes in cyclooxygenase (COX) pathway and changes in receptors on afferent neurons, including transient receptor potential vanilloid type-1 (TRPV1) and cannabinoid receptor type-1 (CB1). The purpose of the present study was to test the hypotheses: 1) exercise training (ET) alters the muscle metaboreflex and mechanoreflex control of muscle sympathetic nerve activity (MSNA) in HF patients. 2) The alteration in metaboreflex control is accompanied by increased expression of TRPV1 and CB1 receptors in skeletal muscle. 3) The alteration in mechanoreflex control is accompanied by COX-2 pathway in skeletal muscle. Thirty-four consecutive HF patients with ejection fractions 2receptor-4, and thromboxane-A2receptor and by decreased in muscle inflammation, as indicated by increased miRNA-146 levels and the stable NF-κB/IκB-α ratio. In conclusion, ET alters muscle metaboreflex and mechanoreflex control of MSNA in HF patients. This alteration with ET is accompanied by alteration in TRPV1 and CB1 expression and COX-2 pathway and inflammation in skeletal muscle.

The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

In order to obtain a good image compression result, it would be appropriate to previously estimate the error between a distorted image and its reference in such a process. Traditionally, the Mean-Squared Error (MSE) has been used as a standard measure for evaluate the effect of dimensionality reduction methods. More recently, other measures for assessing perceptual image quality has been proposed in the literature. In this paper, the main interest relies on a comparative study between the MSE and the Structural Similarity Index (SSIM), which uses structural similarity as a principle for measuring image quality. The basic aiming for such study is the proposal of an ordering and selecting procedure of the transformation basis found by Independent Component Analysis (ICA), which can take one of these measures into account. The principal motivation for this idea is that, in contrast to Principal Component Analysis (PCA), ICA does not have a property that allows a natural ordering for its components (called ICs). For evaluating the efficiency of such approach, a comparative study between PCA and the ICA-based proposal is also carried out for an image dimensionality reduction application. It can been noted that the ICA method, when using hyperbolic tangent function, could provide an efficient method to select the best ICs.

Despite being one of the most widely-spoken languages in the world, Portuguese remains a relatively resource-poor language, for which only in recently years NLP tools such as parsers, taggers and (fairly) large corpora have become available. In this work we describe the task of pronominal co-reference annotation and resolution in Portuguese texts, in which we take advantage of information provided by a tagged corpus and a simple annotation tool that has been developed for this purpose. Besides developing some of these basic resources from scratch, our ultimate goal is to investigate the multilingual resolution of Portuguese personal pronouns to improve the accuracy of their translations to both Spanish and English in an underlying MT project.

The ICA mixture model was originally proposed to perform unsupervised classification of data modelled as a mixture of classes described by linear combinations of independent, non-Gaussian densities. Since the original learning algorithm is based on a gradient optimization technique, it was noted that its performance is affected by some known limitations associated with this kind of approach. In this paper, improvements based on implementation and modelling aspects are incorporated to ICA mixture model aiming to achieve better classification results. Comparative experimental results obtained by the enhanced method and the original one are presented to show that the proposed modifications can significantly improve the classification performance considering random generated data and the well-known iris flower data set.

Principal component analysis (PCA), also called Karhunen-Loeve transform, is a statistical method for multivariate data analysis that can be used in particular to reduce the data set being considered. There are two approaches for performing PCA. The first utilizes the classical statistical method and the other, artificial neural networks. In this paper, neural networks that performing PCA are presented and used to realize tomographic image compression. The results obtained are compared to that obtained by using JPEG compression standard technique and show the usefulness of neural networks for performing image compression.

Some techniques for image compression are investigated in this article. The first one is the well known JPEG that is the most widely used technique for image compression. The second is principal component analysis (PCA), also called Karhunen-Loeve transform, that is a statistical method applied for multivariate data analysis and feature extraction. In the latter, two approaches are being considered. The first approach uses the classical statistical method and the other one is based on artificial neural networks. In a comparative study, the results obtained by PCA neural network for compressing medical images are analyzed together with those obtained by using the classical statistical method and JPEG compression standard technique.

An autonomous segmentation process is one of the most difficult tasks of a visual system. Among the main aspects that can affect the results of this process is the presence of noise. In this paper, it is showed how a technique for denoising images can be combined with the Fuzzy ART clustering for improving the image segmentation results. A mobile robot application is used for testing the efficiency of the proposed combination.