Multi-Target QSAR Approaches for Modeling Protein Inhibitors. Simultaneous Prediction of Activities Against Biomacromolecules Present in Gram-Negative Bacteria

Machine Learning Study of Metabolic Networks vs ChEMBL Data of Antibacterial Compounds

Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.

Prediction of QcrB Inhibition as a Measure of Antitubercular Activity with Machine Learning Protocols

It has always been a challenge to develop interventional therapies for Mycobacterium tuberculosis. Over the years, several attempts at developing such therapies have hit a dead-end owing to rapid mutation rates of the tubercular bacilli and their ability to lay dormant for years. Recently, cytochrome bcc complex (QcrB) has shown some promise as a novel target against the tubercular bacilli, with Q203 being the first molecule acting on this target. In this paper, we report the deployment of several ML-based approaches to design molecules against QcrB. Machine learning (ML) models were developed based on a data set of 350 molecules using three different sets of molecular features, i.e., MACCS keys, ECFP6 fingerprints, and Mordred descriptors. Each feature set was trained on eight ML classifier algorithms and optimized to classify molecules accurately. The support vector machine-based classifier using the ECFP6 feature set was found to be the best classifier in this study. Further, screening of the known imidazopyridine amide inhibitors demonstrated that the model correctly classified the most potent molecules as actives, hence validating the model for future applications.

Moving Average-Based Multitasking In Silico Classification Modeling: Where Do We Stand and What Is Next?

Conventional in silico modeling is often viewed as 'one-target' or 'single-task' computer-aided modeling since it mainly relies on forecasting an endpoint of interest from similar input data. Multitasking or multitarget in silico modeling, in contrast, embraces a set of computational techniques that efficiently integrate multiple types of input data for setting up unique in silico models able to predict the outcome(s) relating to various experimental and/or theoretical conditions. The latter, specifically, based upon the Box-Jenkins moving average approach, has been applied in the last decade to several research fields including drug and materials design, environmental sciences, and nanotechnology. The present review discusses the current status of multitasking computer-aided modeling efforts, meanwhile describing both the existing challenges and future opportunities of its underlying techniques. Some important applications are also discussed to exemplify the ability of multitasking modeling in deriving holistic and reliable in silico classification-based models as well as in designing new chemical entities, either through fragment-based design or virtual screening. Focus will also be given to some software recently developed to automate and accelerate such types of modeling. Overall, this review may serve as a guideline for researchers to grasp the scope of multitasking computer-aided modeling as a promising in silico tool.

Recent Advances in In Silico Target Fishing

In silico target fishing, whose aim is to identify possible protein targets for a query molecule, is an emerging approach used in drug discovery due its wide variety of applications. This strategy allows the clarification of mechanism of action and biological activities of compounds whose target is still unknown. Moreover, target fishing can be employed for the identification of off targets of drug candidates, thus recognizing and preventing their possible adverse effects. For these reasons, target fishing has increasingly become a key approach for polypharmacology, drug repurposing, and the identification of new drug targets. While experimental target fishing can be lengthy and difficult to implement, due to the plethora of interactions that may occur for a single small-molecule with different protein targets, an in silico approach can be quicker, less expensive, more efficient for specific protein structures, and thus easier to employ. Moreover, the possibility to use it in combination with docking and virtual screening studies, as well as the increasing number of web-based tools that have been recently developed, make target fishing a more appealing method for drug discovery. It is especially worth underlining the increasing implementation of machine learning in this field, both as a main target fishing approach and as a further development of already applied strategies. This review reports on the main in silico target fishing strategies, belonging to both ligand-based and receptor-based approaches, developed and applied in the last years, with a particular attention to the different web tools freely accessible by the scientific community for performing target fishing studies.

The QSAR Paradigm in Fragment-Based Drug Discovery: From the Virtual Generation of Target Inhibitors to Multi-Scale Modeling

Fragment-Based Drug Design (FBDD) has established itself as a promising approach in modern drug discovery, accelerating and improving lead optimization, while playing a crucial role in diminishing the high attrition rates at all stages in the drug development process. On the other hand, FBDD has benefited from the application of computational methodologies, where the models derived from the Quantitative Structure-Activity Relationships (QSAR) have become consolidated tools. This mini-review focuses on the evolution and main applications of the QSAR paradigm in the context of FBDD in the last five years. This report places particular emphasis on the QSAR models derived from fragment-based topological approaches to extract physicochemical and/or structural information, allowing to design potentially novel mono- or multi-target inhibitors from relatively large and heterogeneous databases. Here, we also discuss the need to apply multi-scale modeling, to exemplify how different datasets based on target inhibition can be simultaneously integrated and predicted together with other relevant endpoints such as the biological activity against non-biomolecular targets, as well as in vitro and in vivo toxicity and pharmacokinetic properties. In this context, seminal papers are briefly analyzed. As huge amounts of data continue to accumulate in the domains of the chemical, biological and biomedical sciences, it has become clear that drug discovery must be viewed as a multi-scale optimization process. An ideal multi-scale approach should integrate diverse chemical and biological data and also serve as a knowledge generator, enabling the design of potentially optimal chemicals that may become therapeutic agents.

Pesticides, cosmetics, drugs: identical and opposite influences of various molecular features as measures of endpoints similarity and dissimilarity

The similarity is an important category in natural sciences. A measure of similarity for a group of various biochemical endpoints is suggested. The list of examined endpoints contains (1) toxicity of pesticides towards rainbow trout; (2) human skin sensitization; (3) mutagenicity; (4) toxicity of psychotropic drugs; and (5) anti HIV activity. Further applying and evolution of the suggested approach is discussed. In particular, the conception of the similarity (dissimilarity) of endpoints can play the role of a "useful bridge" between quantitative structure property/activity relationships (QSPRs/QSARs) and read-across technique.

Virtual Screening of Anti-Cancer Compounds: Application of Monte Carlo Technique

Possibility and necessity of standardization of predictive models for anti-cancer activity are discussed. The hypothesis about rationality of common quantitative analysis of anti-cancer activity and carcinogenicity is developed. Potential of optimal descriptors to be used as a tool to build up predictive models for anti-cancer activity is examined from practical point of view. Various perspectives of application of optimal descriptors are reviewed. Stochastic nature of phenomena which are related to carcinogenic potential of various substances can be successfully detected and interpreted by the Monte Carlo technique. Hypothesises related to practical strategy and tactics of the searching for new anticancer agents are suggested.

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Machine learning methods have revolutionized modern science, providing fast and accurate solutions to multiple problems. However, they are commonly treated as "black boxes". Therefore, in important scientific fields such as medicinal chemistry and drug discovery, machine learning methods are restricted almost exclusively to the task of performing predictions of large and heterogeneous data sets of chemicals. The lack of interpretability prevents the full exploitation of the machine learning models as generators of new chemical knowledge. This work focuses on the development of an ensemble learning model for the prediction and design of potent dual heat shock protein 90 (Hsp90) inhibitors. The model displays accuracy higher than 80% in both training and test sets. To use the ensemble model as a generator of new chemical knowledge, three steps were followed. First, a physicochemical and/or structural interpretation was provided for each molecular descriptor present in the ensemble learning model. Second, the term "pseudolinear equation" was introduced within the context of machine learning to calculate the relative quantitative contributions of different molecular fragments to the inhibitory activity against the two Hsp90 isoforms studied here. Finally, by assembling the fragments with positive contributions, new molecules were designed, being predicted as potent Hsp90 inhibitors. According to Lipinski's rule of five, the designed molecules were found to exhibit potentially good oral bioavailability, a primordial property that chemicals must have to pass early stages in drug discovery. The present approach based on the combination of ensemble learning and fragment-based topological design holds great promise in drug discovery, and it can be adapted and applied to many different scientific disciplines.

Theoretical Prediction of the Complex P-Glycoprotein Substrate Efflux Based on the Novel Hierarchical Support Vector Regression Scheme

P-glycoprotein (P-gp), a membrane-bound transporter, can eliminate xenobiotics by transporting them out of the cells or blood⁻brain barrier (BBB) at the expense of ATP hydrolysis. Thus, P-gp mediated efflux plays a pivotal role in altering the absorption and disposition of a wide range of substrates. Nevertheless, the mechanism of P-gp substrate efflux is rather complex since it can take place through active transport and passive permeability in addition to multiple P-gp substrate binding sites. A nonlinear quantitative structure⁻activity relationship (QSAR) model was developed in this study using the novel machine learning-based hierarchical support vector regression (HSVR) scheme to explore the perplexing relationships between descriptors and efflux ratio. The predictions by HSVR were found to be in good agreement with the observed values for the molecules in the training set (n = 50, r² = 0.96, qCV2 = 0.94, RMSE = 0.10, s = 0.10) and test set (n = 13, q² = 0.80⁻0.87, RMSE = 0.21, s = 0.22). When subjected to a variety of statistical validations, the developed HSVR model consistently met the most stringent criteria. A mock test also asserted the predictivity of HSVR. Consequently, this HSVR model can be adopted to facilitate drug discovery and development.

Designing multi-targeted agents: An emerging anticancer drug discovery paradigm

The dominant paradigm in drug discovery is to design ligands with maximum selectivity to act on individual drug targets. With the target-based approach, many new chemical entities have been discovered, developed, and further approved as drugs. However, there are a large number of complex diseases such as cancer that cannot be effectively treated or cured only with one medicine to modulate the biological function of a single target. As simultaneous intervention of two (or multiple) cancer progression relevant targets has shown improved therapeutic efficacy, the innovation of multi-targeted drugs has become a promising and prevailing research topic and numerous multi-targeted anticancer agents are currently at various developmental stages. However, most multi-pharmacophore scaffolds are usually discovered by serendipity or screening, while rational design by combining existing pharmacophore scaffolds remains an enormous challenge. In this review, four types of multi-pharmacophore modes are discussed, and the examples from literature will be used to introduce attractive lead compounds with the capability of simultaneously interfering with different enzyme or signaling pathway of cancer progression, which will reveal the trends and insights to help the design of the next generation multi-targeted anticancer agents.

Fragment-based in silico modeling of multi-target inhibitors against breast cancer-related proteins

Breast cancer is the most frequent cancer reported in women, being responsible for hundreds of thousands of deaths. Chemotherapy has proven to be effective against this malignant neoplasm depending on different biological factors such as the histopathology, grade, and stage, among others. However, breast cancer cells have become resistant to current chemotherapeutic regimens, urging the discovery of new anti-breast cancer drugs. Computational approaches have the potential to offer promising alternatives to accelerate the search for potent and versatile anti-breast cancer agents. In the present work, we introduce the first multitasking (mtk) computational model devoted to the in silico fragment-based design of new molecules with high inhibitory activity against 19 different proteins involved in breast cancer. The mtk-computational model was created from a dataset formed by 24,285 cases, and it exhibited accuracy around 93% in both training and prediction (test) sets. Several molecular fragments were extracted from the molecules present in the dataset, and their quantitative contributions to the inhibitory activities against all the proteins under study were calculated. The combined use of the fragment contributions and the physicochemical interpretations of the different molecular descriptors in the mtk-computational model allowed the design of eight new molecular entities not reported in our dataset. These molecules were predicted as potent multi-target inhibitors against all the proteins, and they exhibited a desirable druglikeness according to the Lipinski's rule of five and its variants.

Enabling the Discovery and Virtual Screening of Potent and Safe Antimicrobial Peptides. Simultaneous Prediction of Antibacterial Activity and Cytotoxicity

Antimicrobial peptides (AMPs) represent promising alternatives to fight against bacterial pathogens. However, cellular toxicity remains one of the main concerns in the early development of peptide-based drugs. This work introduces the first multitasking (mtk) computational model focused on performing simultaneous predictions of antibacterial activities, and cytotoxicities of peptides. The model was created from a data set containing 3592 cases, and it displayed accuracy higher than 96% for classifying/predicting peptides in both training and prediction (test) sets. The technique known as alanine scanning was computationally applied to illustrate the calculation of the quantitative contributions of the amino acids (in their respective positions of the sequence) to the biological effects of a defined peptide. A small library formed by 10 peptides was generated, where peptides were designed by considering the interpretations of the different descriptors in the mtk-computational model. All the peptides were predicted to exhibit high antibacterial activities against multiple bacterial strains, and low cytotoxicity against various cell types. The present mtk-computational model can be considered a very useful tool to support high throughput research for the discovery of potent and safe AMPs.

How Reliable Are Ligand-Centric Methods for Target Fishing?

Computational methods for Target Fishing (TF), also known as Target Prediction or Polypharmacology Prediction, can be used to discover new targets for small-molecule drugs. This may result in repositioning the drug in a new indication or improving our current understanding of its efficacy and side effects. While there is a substantial body of research on TF methods, there is still a need to improve their validation, which is often limited to a small part of the available targets and not easily interpretable by the user. Here we discuss how target-centric TF methods are inherently limited by the number of targets that can possibly predict (this number is by construction much larger in ligand-centric techniques). We also propose a new benchmark to validate TF methods, which is particularly suited to analyse how predictive performance varies with the query molecule. On average over approved drugs, we estimate that only five predicted targets will have to be tested to find two true targets with submicromolar potency (a strong variability in performance is however observed). In addition, we find that an approved drug has currently an average of eight known targets, which reinforces the notion that polypharmacology is a common and strong event. Furthermore, with the assistance of a control group of randomly-selected molecules, we show that the targets of approved drugs are generally harder to predict. The benchmark and a simple target prediction method to use as a performance baseline are available at http://ballester.marseille.inserm.fr/TF-benchmark.tar.gz.