Search

In light of the growing resistance toward current antiviral drugs, efforts to discover novel and effective antiviral therapeutic agents remain a pressing scientific effort. Antiviral peptides (AVPs) represent promising therapeutic agents due to their extraordinary advantages in terms of potency, efficacy and pharmacokinetic properties. The growing volume of newly discovered peptide sequences in the post-genomic era requires computational approaches for timely and accurate identification of AVPs. Machine learning (ML) methods such as random forest and support vector machine represent robust learning algorithms that are instrumental in successful peptide-based drug discovery. Therefore, this review summarizes the current state-of-the-art application of ML methods for identifying AVPs directly from the sequence information. We compare the efficiency of these methods in terms of the underlying characteristics of the dataset used along with feature encoding methods, ML algorithms, cross-validation methods and prediction performance. Finally, guidelines for the development of robust AVP models are also discussed. It is anticipated that this review will serve as a useful guide for the design and development of robust AVP and related therapeutic peptide predictors in the future.

Sickle cell disease (SCD), an autosomal recessive genetic disorder, has been recognized by the World Health Organization (WHO) as a major public health problem as it affects 300 000 individuals worldwide. Complications arising from SCD include anemia, microvascular occlusion, severe pain, stokes, renal dysfunction and infections. A lucrative therapeutic strategy is to employ anti-sickling agents that can disrupt the formation of the HbS polymer. This study therefore employed cheminformatic approaches, encompassing classification structure–activity relationship (CSAR) modeling, to deduce the privileged substructures giving rise to the anti-sickling activity of an investigated set of 115 compounds, followed by substructure analysis. Briefly, the compiled compounds were described by fingerprint descriptors and used in the construction of CSAR models via several machine learning algorithms. The modelability of the data set, as exemplified by the MODI index, was determined to be in the range of 0.70–0.84. The predictive performance was deduced by the accuracy, sensitivity, specificity and Matthews correlation coefficient, which was found to be statistically robust, whereby the former three parameters afforded values in excess of 0.7 while the latter statistical parameter provided a value greater than 0.5. An analysis of the top 20 important substructure descriptors for anti-sickling activity revealed that 10 important features were significant in the differentiation of actives from inactives, as illustrated by aromaticity/conjugation (e.g. SubFPC287, SubFPC171 and SubFPC5), carbonyl groups (e.g. SubFPC137, SubFPC139, SubFPC49 and SubFPC135) and miscellaneous groups (e.g. SubFPC303, SubFPC302 and SubFPC275). Furthermore, an analysis of the structure–activity relationship revealed that the length of alkyl chains, choice of functional moiety and position of substitution on the benzene ring may affect the anti-sickling activity of these compounds. Thus, this knowledge is anticipated to be useful for guiding the design of robust compounds against the gelling activity of HbS, as preliminarily demonstrated in the data-driven compound design presented herein.

The rising cost of drug development has necessitated the search for efficient approaches for the discovery of novel drugs. Such difficulty arises from the fact that promising lead compounds would need to be further scrutinized via preclinical and clinical studies so as to characterize their absorption, distribution, metabolism, excretion, and toxicity in order to verify their safety for clinical use. In this respect, drug repositioning/repurposing represents an attractive venue for the discovery of novel therapeutic indications for existing food and drug administration-approved drugs, which in a nutshell repurposes old drugs for treating new diseases for which they were not originally developed. Computational approaches have been instrumental in drug repositioning efforts as they make use of existing biological and chemical data to uncover new therapeutic indications by relying on the concept that similar compounds bind to similar targets. Quantitative structure-activity relationship (QSAR) is a powerful ligand-based approach that correlates structural features of compounds with their observed biological activity against a single target protein. Proteochemometric modeling (PCM) extends QSAR to an extra dimension by allowing several target proteins to be considered in a single model. This chapter briefly explores the concepts of polypharmacology and computational drug discovery and finally examines the use of PCM for drug repositioning.

A three series of thioureas, monothiourea type I (4a–g), 1,4-bisthiourea type II (5a–h) and 1,3-bisthiourea type III (6a–h) were synthesized. Their aromatase inhibitory activities have been evaluated. Interestingly, eight thiourea derivatives (4e, 5f–h, 6d, 6f–h) exhibited the aromatase inhibitory activities with IC50 range of 0.6–10.2 μM. The meta-bisthiourea bearing 4-NO2 group (6f) and 3,5-diCF3 groups (6h) were shown to be the most potent compounds with sub-micromolar IC50 values of 0.8 and 0.6 μM, respectively. Molecular docking also revealed that one of the thiourea moieties of these two compounds could mimic steroidal backbone of the natural androstenedione (ASD) via hydrophobic interactions with enzyme residues (Val370, Leu477, Thr310, and Phe221 for 6f, Val370, Leu477, Ser478, and Ile133 for 6h). This is the first time that the bisthioureas have been reported for their potential to be developed as aromatase inhibitors, in which the 4-NO2 and 3,5-diCF3 analogs have been highlighted as promising candidates.

Sickle cell disease (SCD), an autosomal recessive genetic disorder, has been recognized by the World Health Organization (WHO) as a major public health problem as it affects 300 000 individuals worldwide. Complications arising from SCD include anemia, microvascular occlusion, severe pain, stokes, renal dysfunction and infections. A lucrative therapeutic strategy is to employ anti-sickling agents that can disrupt the formation of the HbS polymer. This study therefore employed cheminformatic approaches, encompassing classification structure-activity relationship (CSAR) modeling, to deduce the privileged substructures giving rise to the anti-sickling activity of an investigated set of 115 compounds, followed by substructure analysis. Briefly, the compiled compounds were described by fingerprint descriptors and used in the construction of CSAR models

Quantitative structure-activity relationship (QSAR) has been instrumental in aiding medicinal chemists and physical scientists in understanding how modification of substituents at different positions on a molecular structure exert its influence on the observed biological activity and physicochemical property, respectively. QSAR has received great attention owing to its predictive capability and as such efforts had been directed toward obtaining models with high prediction performance. However, to be useful QSAR models need to be informative and interpretable in which the underlying molecular features that contribute to the increase or decrease of the biological activity are revealed by the model. Thus, the aim of this chapter is to briefly review the general concepts of QSAR modeling, its development and discussions on key issues influencing and contributing to the interpretability of QSAR models.

The fight against the emergence of mutant influenza strains has led to the screening of an increasing number of compounds for inhibitory activity against influenza neuraminidase. This study explores the chemical space of neuraminidase inhibitors (NAIs), which provides an opportunity to obtain further molecular insights regarding the underlying basis of their bioactivity. In particular, a large set of 347 and 175 NAIs against influenza A and B, respectively, was compiled from the literature. Molecular and quantum chemical descriptors were obtained from low-energy conformational structures geometrically optimized at the B3LYP/6-31G(d) level. The bioactivities of NAIs were classified as active or inactive according to their half maximum inhibitory concentration (IC50) value in which IC50 < 1 μM and > 10 μM were defined as active and inactive compounds, respectively. Interpretable decision rules were derived from a quantitative structure-activity relationship (QSAR) model established using a set of 13 descriptors via decision tree analysis. Good predictive performance was achieved as deduced from 10-fold cross-validation, in which an accuracy and MCC of 82.46% and 0.649, respectively, were obtained for influenza A NAIs while values of 80.00% and 0.553 were obtained for influenza B NAIs. Both univariate and multivariate analyses revealed the importance of the lowest unoccupied molecular orbital, number of hydrogen bond donors and number of hydrogen bond acceptors in the predictive model of NAIs against influenza A while the number of hydrogen bond acceptors, molecular energy and the energy gap between the highest occupied and lowest unoccupied molecular orbitals were important in the predictive model for influenza B NAIs. Molecular scaffold analysis was performed on both data sets for discriminating important structural features among active and inactive NAIs. Furthermore, molecular docking was employed to investigate the binding modes and their moiety preferences of active NAIs against both influenza A and B neuraminidase. Moreover, novel NAIs with robust binding fitness towards influenza A and B neuraminidase were generated via combinatorial library enumeration and their binding fitness was on par or better than FDA-approved drugs. The results from this study are anticipated to be beneficial for guiding the rational drug design of novel NAIs for treating influenza infections.

Considerable attention has been given on the search for novel anticancer drugs with respect to the disease sequelae on human health and well-being. Triazole is considered to be an attractive scaffold possessing diverse biological activities. Structural modification on the privileged structures is noted as an effective strategy towards successful design and development of novel drugs. The quantitative structure–activity relationships (QSAR) is well-known as a powerful computational tool to facilitate the discovery of potential compounds. In this study, a series of thirty-two 1,2,3-triazole derivatives (1–32) together with their experimentally measured cytotoxic activities against four cancer cell lines i.e., HuCCA-1, HepG2, A549 and MOLT-3 were used for QSAR analysis. Four QSAR models were successfully constructed with acceptable predictive performance affording RCV ranging from 0.5958 to 0.8957 and RMSECV ranging from 0.2070 to 0.4526. An additional set of 64 structurally modified triazole compounds (1A–1R, 2A–2R, 7A–7R and 8A–8R) were constructed in silico and their predicted cytotoxic activities were obtained using the constructed QSAR models. The study suggested crucial moieties and certain properties essential for potent anticancer activity and highlighted a series of promising compounds (21, 28, 32, 1P, 8G, 8N and 8Q) for further development as novel triazole-based anticancer agents. Electronic supplementary material The online version of this article (doi:10.1186/s40064-015-1352-5) contains supplementary material, which is available to authorized users.

Correction for ‘Privileged substructures for anti-sickling activity via cheminformatic analysis’ by Chuleeporn Phanus-umporn et al., RSC Adv., 2018, 8, 5920–5935.

Watshara Shoombuatong,1 Veda Prachayasittikul,1,2 Nuttapat Anuwongcharoen,1 Napat Songtawee,1 Teerawat Monnor,1 Supaluk Prachayasittikul,1 Virapong Prachayasittikul,2 Chanin Nantasenamat1,2 1Center of Data Mining and Biomedical Informatics, 2Department of Clinical Microbiology and Applied Technology, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand Abstract: This study represents the first large-scale study on the chemical space of inhibitors of dipeptidyl peptidase-4 (DPP4), which is a potential therapeutic protein target for the treatment of diabetes mellitus. Herein, a large set of 2,937 compounds evaluated for their ability to inhibit DPP4 was compiled from the literature. Molecular descriptors were generated from the geometrically optimized low-energy conformers of these compounds at the semiempirical AM1 level. The origins of DPP4 inhibitory activity were elucidated from computed molecular descriptors that accounted for the unique physicochemical properties inherently present in the active and inactive sets of compounds as defined by their respective half maximal inhibitory concentration values of less than 1 µM and greater than 10 µM, respectively. Decision tree analysis revealed the importance of molecular weight, total energy of a molecule, topological polar surface area, lowest unoccupied molecular orbital, and number of hydrogen-bond donors, which correspond to molecular size, energy, surface polarity, electron acceptors, and hydrogen bond donors, respectively. The prediction model was subjected to rigorous independent testing via three external sets. Scaffold and chemical fragment analysis was also performed on these active and inactive sets of compounds to shed light on the distinguishing features of the functional moieties. Docking of representative active DPP4 inhibitors was also performed to unravel key interacting residues. The results of this study are anticipated to be useful in guiding the rational design of novel and robust DPP4 inhibitors for the treatment of diabetes. Keywords: QSAR, decision tree, scaffold analysis, fragment analysis, antidiabetic, molecular docking, rational drug design

Inhibition of non-structural protein 5B (NS5B) represents an attractive strategy for the therapeutic treatment of hepatitis C virus (HCV). In this study, machine learning classifiers such as artificial neural network (ANN), support vector machine (SVM), random forest (RF) and decision tree (DT) analyses were used to classify 970 compounds based on their physicochemical properties, including quantum chemical descriptors, constitutional descriptors, functional groups and molecular properties. Good predictive performance was obtained from all classifiers, providing accuracies ranging from 82.47–89.61% for external validation set. SVM was noted as the best classifier, indicated by its highest accuracy of 89.61%. The analyses were performed on data sets stratified by structural scaffolds (nucleoside and non-nucleoside) and bioactivities (active and inactive properties). In addition, a molecular fragment analysis was performed to investigate molecular substructures corresponding to biological activities. Furthermore, common substructures and potential functional groups governing the activities of active and inactive inhibitors were noted for the benefit of rational design and high-throughput screening towards potential HCV NS5B inhibitors.

Currently, monomeric fluorescent proteins (FP) are ideal markers for protein tagging. The prediction of oligomeric states is helpful for enhancing live biomedical imaging. Computational prediction of FP oligomeric states can accelerate the effort of protein engineering efforts of creating monomeric FPs. To the best of our knowledge, this study represents the first computational model for predicting and analyzing FP oligomerization directly from the amino acid sequence. After data curation, an exhaustive data set consisting of 397 non-redundant FP oligomeric states was compiled from the literature. Results from benchmarking of the protein descriptors revealed that the model built with amino acid composition descriptors was the top performing model with accuracy, sensitivity and specificity in excess of 80% and MCC greater than 0.6 for all three data subsets (e.g. training, tenfold cross-validation and external sets). The model provided insights on the important residues governing the oligomerization of FP. To maximize the benefit of the generated predictive model, it was implemented as a web server under the R programming environment. osFP affords a user-friendly interface that can be used to predict the oligomeric state of FP using the protein sequence. The advantage of osFP is that it is platform-independent meaning that it can be accessed via a web browser on any operating system and device. osFP is freely accessible at http://codes.bio/osfp/ while the source code and data set is provided on GitHub at https://github.com/chaninn/osFP/ .