Optimal selection of molecular descriptors for antimicrobial peptides classification: an evolutionary feature weighting approach

Abstract

BackgroundAntimicrobial peptides are a promising alternative for combating pathogens resistant to conventional antibiotics. Computer-assisted peptide discovery strategies are necessary to automatically assess a significant amount of data by generating models that efficiently classify what an antimicrobial peptide is, before its evaluation in the wet lab. Model’s performance depends on the selection of molecular descriptors for which an efficient and effective approach has recently been proposed. Unfortunately, how to adapt this method to the selection of molecular descriptors for the classification of antimicrobial peptides and the performance it can achieve, have only preliminary been explored.ResultsWe propose an adaptation of this successful feature selection approach for the weighting of molecular descriptors and assess its performance. The evaluation is conducted on six high-quality benchmark datasets that have previously been used for the empirical evaluation of state-of-art antimicrobial prediction tools in an unbiased manner. The results indicate that our approach substantially reduces the number of required molecular descriptors, improving, at the same time, the performance of classification with respect to using all molecular descriptors. Our models also outperform state-of-art prediction tools for the classification of antimicrobial and antibacterial peptides.ConclusionsThe proposed methodology is an efficient approach for the development of models to classify antimicrobial peptides. Particularly in the generation of models for discrimination against a specific antimicrobial activity, such as antibacterial. One of our future directions is aimed at using the obtained classifier to search for antimicrobial peptides in various transcriptomes.Electronic supplementary materialThe online version of this article (10.1186/s12864-018-5030-1) contains supplementary material, which is available to authorized users.

Diagnostic approaches of pneumonia for commercial-scale biomedical applications: an overview

“…It is imperative to explore other methods for the discovery of AMPs and optimization of the aptamer sequences obtained from SELEX because they might not give the required length during their in vitro generation, thus straining their specificity and sensitivity towards the receptors or manipulation during molecular conjugation on the matrix surfaces. Many computational methods have been introduced to predict AMPs and aptamers based on the different features such as the binary pattern method using AntiBP server, for prediction of antibacterial peptides (Veltri et al 2018), the CAMP methods (Tucker et al 2018), the combination of sequence alignment and the feature selection method (Beltran et al 2018), and the pseudo amino acid composition method (Bhadra et al 2018). Other methods for predicting peptides include Support Vector Machine (SVM), quantitative matrices (QM), and artificial neural network (ANN).…”

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

“…Among in silico approaches, both qualitative classification and quantitative prediction models by quantitative structureactivity relationship (QSAR) methods were reported using a large collection of environmental chemicals (Zang et al, 2013;Niu et al, 2016;Norinder and Boyer, 2016;Cotterill et al, 2019;Dreier et al, 2019;Heo et al, 2019). However, building highperformance prediction model requires specialized techniques, such as selecting appropriate features and algorithms (Beltran et al, 2018;Khan and Roy, 2018). In addition, the prediction results of the current model are often difficult to develop the drug discovery for clinical trials (Gayvert et al, 2016;Neves et al, 2018;Vamathevan et al, 2019).…”

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap–Deep Learning

“…Recently, QSAR analysis using the deep neural network (DNN) has shown superior prediction performance compared with other conventional machine learning (ML) methods [38][39][40][41][42]. Such high-performance prediction methods may rely on the clear definition of feature representation or selection as it depends on the chemical space [43,44]. For appropriate feature selection or representation, some exclusive procedures based on chemical intuition and observed properties or filtering methods that evaluate features according to a given criterion have been employed [43,45].…”

“…Such high-performance prediction methods may rely on the clear definition of feature representation or selection as it depends on the chemical space [43,44]. For appropriate feature selection or representation, some exclusive procedures based on chemical intuition and observed properties or filtering methods that evaluate features according to a given criterion have been employed [43,45]. However, these approaches do not completely apply to the construction of all prediction models because of the complicated interactions of multiple molecular descriptors.…”