Integrating sampling techniques and inverse virtual screening: toward the discovery of artificial peptide-based receptors for ligands

Virtual Screening of Peptide Libraries: The Search for Peptide-Based Therapeutics Using Computational Tools

Over the last few decades, we have witnessed growing interest from both academic and industrial laboratories in peptides as possible therapeutics. Bioactive peptides have a high potential to treat various diseases with specificity and biological safety. Compared to small molecules, peptides represent better candidates as inhibitors (or general modulators) of key protein-protein interactions. In fact, undruggable proteins containing large and smooth surfaces can be more easily targeted with the conformational plasticity of peptides. The discovery of bioactive peptides, working against disease-relevant protein targets, generally requires the high-throughput screening of large libraries, and in silico approaches are highly exploited for their low-cost incidence and efficiency. The present review reports on the potential challenges linked to the employment of peptides as therapeutics and describes computational approaches, mainly structure-based virtual screening (SBVS), to support the identification of novel peptides for therapeutic implementations. Cutting-edge SBVS strategies are reviewed along with examples of applications focused on diverse classes of bioactive peptides (i.e., anticancer, antimicrobial/antiviral peptides, peptides blocking amyloid fiber formation).

Identification of a Selective PDE4B Inhibitor From Bryophyllum pinnatum by Target Fishing Study and In Vitro Evaluation of Quercetin 3-O-α-L-Arabinopyranosyl-(1→2)-O-α-L-Rhamnopyranoside

Natural products are considered an important source of bioactive compounds especially in biodiversity-rich countries like Brazil. The identification of potential targets is crucial to the development of drugs from natural sources. In this context, in silico methodologies, such as inverse virtual screening (target fishing), are interesting tools as they are a rational and direct method that reduces costs and experimental time. Among the species of Brazilian biomes, Bryophyllum pinnatum (Lam.) Oken, native to Madagascar, is widely used by the population to treat inflammation conditions. It has a remarkable presence of flavonoids, including quercetin 3-O-α-L-arabinopyranosyl-(1→2)-O-α-L-rhamnopyranoside (1), considered one of its major compounds. However, until now there were no studies addressing its putative mechanism of action and explaining its pharmacological action. The enzyme PDE4B, known as an antiinflammatory protein, was indicated as a promising target by target fishing methods. This activity was confirmed by in vitro enzymatic inhibition, and an expressive selectivity of PDE4B over PDE4A was demonstrated. The interactions were investigated through molecular dynamics simulations. The results were pioneering, representing an advance in the investigation of the antiinflammatory action of B. pinnatum and confirm the potential of the flavonoid as a chemical extract marker. Also, the flavonoid was shown to be a promising lead for the design of other selective PDE4B blockers to treat inflammatory diseases.

iVS analysis to evaluate the impact of scaffold diversity in the binding to cellular targets relevant in cancer

This study reports the application of inverse virtual screening (iVS) methodologies to identify cellular proteins as suitable targets for a library of heterocyclic small-molecules, with potential pharmacological implications. Standard synthetic procedures allow facile generation of these ligands showing a high degree of core scaffold diversity. Specifically, we have computationally investigated the binding efficacy of the new series for target proteins which are involved in cancer pathogenesis. As a result, nine macromolecules demonstrated efficient binding interactions for the molecular dataset, in comparison to the co-crystallised ligand for each target. Moreover, the iVS analysis led us to confirm that 27 analogues have high affinity for one or more examined cellular proteins. The additional evaluation of ADME and drug score for selected hits also highlights their capability as drug candidates, demonstrating valuable leads for further structure optimisation and biological studies.

Prediction Is a Balancing Act: Importance of Sampling Methods to Balance Sensitivity and Specificity of Predictive Models Based on Imbalanced Chemical Data Sets

Increase in the number of new chemicals synthesized in past decades has resulted in constant growth in the development and application of computational models for prediction of activity as well as safety profiles of the chemicals. Most of the time, such computational models and its application must deal with imbalanced chemical data. It is indeed a challenge to construct a classifier using imbalanced data set. In this study, we analyzed and validated the importance of different sampling methods over non-sampling method, to achieve a well-balanced sensitivity and specificity of a machine learning model trained on imbalanced chemical data. Additionally, this study has achieved an accuracy of 93.00%, an AUC of 0.94, F1 measure of 0.90, sensitivity of 96.00% and specificity of 91.00% using SMOTE sampling and Random Forest classifier for the prediction of Drug Induced Liver Injury (DILI). Our results suggest that, irrespective of data set used, sampling methods can have major influence on reducing the gap between sensitivity and specificity of a model. This study demonstrates the efficacy of different sampling methods for class imbalanced problem using binary chemical data sets.