Garbage in, garbage out: how reliable training data improved a virtual screening approach against SARS-CoV-2 MPro

Introduction: The identification of chemical compounds that interfere with SARS-CoV-2 replication continues to be a priority in several academic and pharmaceutical laboratories. Computational tools and approaches have the power to integrate, process and analyze multiple data in a short time. However, these initiatives may yield unrealistic results if the applied models are not inferred from reliable data and the resulting predictions are not confirmed by experimental evidence. Methods: We undertook a drug discovery campaign against the essential major protease (MPro) from SARS-CoV-2, which relied on an in silico search strategy -performed in a large and diverse chemolibrary- complemented by experimental validation. The computational method comprises a recently reported ligand-based approach developed upon refinement/learning cycles, and structure-based approximations. Search models were applied to both retrospective (in silico) and prospective (experimentally confirmed) screening. Results: The first generation of ligand-based models were fed by data, which to a great extent, had not been published in peer-reviewed articles. The first screening campaign performed with 188 compounds (46 in silico hits and 100 analogues, and 40 unrelated compounds: flavonols and pyrazoles) yielded three hits against MPro (IC₅₀ ≤ 25 μM): two analogues of in silico hits (one glycoside and one benzo-thiazol) and one flavonol. A second generation of ligand-based models was developed based on this negative information and newly published peer-reviewed data for MPro inhibitors. This led to 43 new hit candidates belonging to different chemical families. From 45 compounds (28 in silico hits and 17 related analogues) tested in the second screening campaign, eight inhibited MPro with IC₅₀ = 0.12-20 μM and five of them also impaired the proliferation of SARS-CoV-2 in Vero cells (EC₅₀ 7-45 μM). Discussion: Our study provides an example of a virtuous loop between computational and experimental approaches applied to target-focused drug discovery against a major and global pathogen, reaffirming the well-known "garbage in, garbage out" machine learning principle.

iRaPCA and SOMoC: Development and Validation of Web Applications for New Approaches for the Clustering of Small Molecules

The clustering of small molecules implies the organization of a group of chemical structures into smaller subgroups with similar features. Clustering has important applications to sample chemical datasets or libraries in a representative manner (e.g., to choose, from a virtual screening hit list, a chemically diverse subset of compounds to be submitted to experimental confirmation, or to split datasets into representative training and validation sets when implementing machine learning models). Most strategies for clustering molecules are based on molecular fingerprints and hierarchical clustering algorithms. Here, two open-source in-house methodologies for clustering of small molecules are presented: iterative Random subspace Principal Component Analysis clustering (iRaPCA), an iterative approach based on feature bagging, dimensionality reduction, and K-means optimization; and Silhouette Optimized Molecular Clustering (SOMoC), which combines molecular fingerprints with the Uniform Manifold Approximation and Projection (UMAP) and Gaussian Mixture Model algorithm (GMM). In a benchmarking exercise, the performance of both clustering methods has been examined across 29 datasets containing between 100 and 5000 small molecules, comparing these results with those given by two other well-known clustering methods, Ward and Butina. iRaPCA and SOMoC consistently showed the best performance across these 29 datasets, both in terms of within-cluster and between-cluster distances. Both iRaPCA and SOMoC have been implemented as free Web Apps and standalone applications, to allow their use to a wide audience within the scientific community.

Homology Modeling and Molecular Dynamics Simulations of Trypanosoma cruzi Phosphodiesterase b1

Cyclic nucleotide phosphodiesterases have been implicated in the proliferation, differentiation and osmotic regulation of trypanosomatids; in some trypanosomatid species, they have been validated as molecular targets for the development of new therapeutic agents. Because the experimental structure of Trypanosoma cruzi PDEb1 (TcrPDEb1) has not been solved so far, an homology model of the target was created using the structure of Trypanosoma brucei PDEb1 (TbrPDEb1) as a template. The model was refined by extensive enhanced sampling molecular dynamics simulations, and representative snapshots were extracted from the trajectory by combined clustering analysis. This structural ensemble was used to develop a structure-based docking model of the target. The docking accuracy of the model was validated by redocking and cross-docking experiments using all available crystal structures of TbrPDEb1, whereas the scoring accuracy was validated through a retrospective screen, using a carefully curated dataset of compounds assayed against TbrPDEb1 and/or TcrPDEb1. Considering the results from in silico validations, the model may be applied in prospective virtual screening campaigns to identify novel hits, as well as to guide the rational design of potent and selective inhibitors targeting this enzyme.

Strengths and Weaknesses of Docking Simulations in the SARS-CoV-2 Era: the Main Protease (Mpro) Case Study

The scientific community is working against the clock to arrive at therapeutic interventions to treat patients with COVID-19. Among the strategies for drug discovery, virtual screening approaches have the capacity to search potential hits within millions of chemical structures in days, with the appropriate computing infrastructure. In this article, we first analyzed the published research targeting the inhibition of the main protease (Mpro), one of the most studied targets of SARS-CoV-2, by docking-based methods. An alarming finding was the lack of an adequate validation of the docking protocols (i.e., pose prediction and virtual screening accuracy) before applying them in virtual screening campaigns. The performance of the docking protocols was tested at some level in 57.7% of the 168 investigations analyzed. However, we found only three examples of a complete retrospective analysis of the scoring functions to quantify the virtual screening accuracy of the methods. Moreover, only two publications reported some experimental evaluation of the proposed hits until preparing this manuscript. All of these findings led us to carry out a retrospective performance validation of three different docking protocols, through the analysis of their pose prediction and screening accuracy. Surprisingly, we found that even though all tested docking protocols have a good pose prediction, their screening accuracy is quite limited as they fail to correctly rank a test set of compounds. These results highlight the importance of conducting an adequate validation of the docking protocols before carrying out virtual screening campaigns, and to experimentally confirm the predictions made by the models before drawing bold conclusions. Finally, successful structure-based drug discovery investigations published during the redaction of this manuscript allow us to propose the inclusion of target flexibility and consensus scoring as alternatives to improve the accuracy of the methods.

Ensemble learning application to discover new trypanothione synthetase inhibitors

Trypanosomatid-caused diseases are among the neglected infectious diseases with the highest disease burden, affecting about 27 million people worldwide and, in particular, socio-economically vulnerable populations. Trypanothione synthetase (TryS) is considered one of the most attractive drug targets within the thiol-polyamine metabolism of typanosomatids, being unique, essential and druggable. Here, we have compiled a dataset of 401 T. brucei TryS inhibitors that includes compounds with inhibitory data reported in the literature, but also in-house acquired data. QSAR classifiers were derived and validated from such dataset, using publicly available and open-source software, thus assuring the portability of the obtained models. The performance and robustness of the resulting models were substantially improved through ensemble learning. The performance of the individual models and the model ensembles was further assessed through retrospective virtual screening campaigns. At last, as an application example, the chosen model-ensemble has been applied in a prospective virtual screening campaign on DrugBank 5.1.6 compound library. All the in-house scripts used in this study are available on request, whereas the dataset has been included as supplementary material.

Positive Predictive Value Surfaces as a Complementary Tool to Assess the Performance of Virtual Screening Methods

BACKGROUND

Since their introduction in the virtual screening field, Receiver Operating Characteristic (ROC) curve-derived metrics have been widely used for benchmarking of computational methods and algorithms intended for virtual screening applications. Whereas in classification problems, the ratio between sensitivity and specificity for a given score value is very informative, a practical concern in virtual screening campaigns is to predict the actual probability that a predicted hit will prove truly active when submitted to experimental testing (in other words, the Positive Predictive Value - PPV). Estimation of such probability is however, obstructed due to its dependency on the yield of actives of the screened library, which cannot be known a priori.

OBJECTIVE

To explore the use of PPV surfaces derived from simulated ranking experiments (retrospective virtual screening) as a complementary tool to ROC curves, for both benchmarking and optimization of score cutoff values.

METHODS

The utility of the proposed approach is assessed in retrospective virtual screening experiments with four datasets used to infer QSAR classifiers: inhibitors of Trypanosoma cruzi trypanothione synthetase; inhibitors of Trypanosoma brucei N-myristoyltransferase; inhibitors of GABA transaminase and anticonvulsant activity in the 6 Hz seizure model.

RESULTS

Besides illustrating the utility of PPV surfaces to compare the performance of machine learning models for virtual screening applications and to select an adequate score threshold, our results also suggest that ensemble learning provides models with better predictivity and more robust behavior.

CONCLUSION

PPV surfaces are valuable tools to assess virtual screening tools and choose score thresholds to be applied in prospective in silico screens. Ensemble learning approaches seem to consistently lead to improved predictivity and robustness.

Can drug repurposing strategies be the solution to the COVID-19 crisis?

Introduction: The COVID-19 pandemic resulted in disastrous human and economic costs, mainly due to the initial lack of specific treatments. Complementary to immunotherapies, drug repurposing is possibly the best option to arrive at COVID-19 treatments in the short term.Areas covered: Repurposing prospects undergoing clinical trials or with some level of evidence emerging from clinical studies are overviewed. The authors discuss some possible intellectual property and commercial barriers to drug repurposing, and strategies to facilitate equitable access to incoming therapeutic solutions, highlighting the importance of collaborative drug discovery models. Based on a critical analysis of the available literature about in silico screens against SARS-CoV-2 main protease, the authors illustrate how frequently overconfident conclusions are being drawn in COVID-19-related literature.Expert opinion: Most of the current clinical trials on potential COVID-19 treatments are, in fact, drug repurposing examples. In October 2020, the FDA approved a repurposed antiviral, remdesivir, as the first treatment for COVID-19. Considering the high expectations invested in approaching therapeutic solutions, the scientific community must be careful not to raise unrealistic expectations. Today more than ever, the conclusions drawn in scientific reports have to be fully supported by the level of evidence, avoiding any sort of unfounded speculation.

In Silico Drug Repositioning for Chagas Disease

Chagas disease is an infectious tropical disease included within the group of neglected tropical diseases. Though historically endemic to Latin America, it has lately spread to high-income countries due to human migration. At present, there are only two available drugs, nifurtimox and benznidazole, approved for this treatment, both with considerable side-effects (which often result in treatment interruption) and limited efficacy in the chronic stage of the disease in adults. Drug repositioning involves finding novel therapeutic indications for known drugs, including approved, withdrawn, abandoned and investigational drugs. It is today a broadly applied approach to develop innovative medications, since indication shifts are built on existing safety, ADME and manufacturing information, thus greatly shortening development timeframes. Drug repositioning has been signaled as a particularly interesting strategy to search for new therapeutic solutions for neglected and rare conditions, which traditionally present limited commercial interest and are mostly covered by the public sector and not-for-profit initiatives and organizations. Here, we review the applications of computer-aided technologies as systematic approaches to drug repositioning in the field of Chagas disease. In silico screening represents the most explored approach, whereas other rational methods such as network-based and signature-based approximations have still not been applied.

Quantitative structure-activity relationship models for compounds with anticonvulsant activity

Introduction: Third-generation antiepileptic drugs have seemingly failed to improve the global figures of seizure control and can still be regarded as symptomatic treatments. Quantitative structure-activity relationships (QSAR) can be used to guide hit-to-lead and lead optimization projects and applied to the large-scale virtual screening of chemical libraries. Areas covered: In this review, the authors cover reports on QSAR models related to antiepileptic drugs and drug targets in epilepsy, analyzing whether they refer to classic or non-classic QSAR and if they apply QSAR as a descriptive or predictive approach, among other considerations. The article finally focuses on a more detailed discussion of those predictive studies which include some sort of experimental validation, i.e. papers in which the reported models have been used to identify novel active compounds which have been tested in vitro and/or in vivo. Expert opinion: There are significant opportunities to apply the QSAR methodology to assist the discovery of more efficacious antiepileptic drugs. Considering the intrinsic complexity of the disorder, such applications should focus on state-of-the-art approximations (e.g. systemic, multi-target and multi-scale QSAR as well as ensemble and deep learning) and modeling the effects on novel drug targets and modern screening tools.

Modern Approaches for the Discovery of Anti-Infectious Drugs for the Treatment of Neglected Diseases

Neglected diseases comprise a number of infectious diseases historically endemic to low- and middle-income countries, though recently they have spread to high-income countries due to human migrations. In the past, pharmaceutical companies have shown hesitant to invest in these health conditions, due to the limited return on investment. As a result, the role of the academic sector and not-for-profit organizations in the discovery of new drugs for neglected diseases has been particularly relevant. Here, we review recent applications of modern drug discovery technologies in the field of neglected diseases, including high-throughput screening, in silico screening and computer-aided drug design. The suitability and perspectives of each approach are discussed depending on the context, along with the technology and translational gaps influencing them.

The application of molecular topology for ulcerative colitis drug discovery

INTRODUCTION

Although the therapeutic arsenal against ulcerative colitis has greatly expanded (including the revolutionary advent of biologics), there remain patients who are refractory to current medications while the safety of the available therapeutics could also be improved. Molecular topology provides a theoretic framework for the discovery of new therapeutic agents in a very efficient manner, and its applications in the field of ulcerative colitis have slowly begun to flourish. Areas covered: After discussing the basics of molecular topology, the authors review QSAR models focusing on validated targets for the treatment of ulcerative colitis, entirely or partially based on topological descriptors. Expert opinion: The application of molecular topology to ulcerative colitis drug discovery is still very limited, and many of the existing reports seem to be strictly theoretic, with no experimental validation or practical applications. Interestingly, mechanism-independent models based on phenotypic responses have recently been reported. Such models are in agreement with the recent interest raised by network pharmacology as a potential solution for complex disorders. These and other similar studies applying molecular topology suggest that some therapeutic categories may present a 'topological pattern' that goes beyond a specific mechanism of action.

High-throughput drug repositioning for the discovery of new treatments for Chagas disease

Despite affecting around 8 million people worldwide and representing an economic burden above $7 billion/ year, currently approved medications to treat Chagas disease are still limited to two drugs, nifurtimox and benznidazole, which were developed more than 40 years ago and present important efficacy and safety limitations. Drug repositioning (i.e. finding second or further therapeutic indications for known drugs) has raised considerable interest within the international drug development community. There are many explanations to the current interest on drug repositioning including the possibility to partially circumvent clinical trials and the consequent saving in time and resources. It has been suggested as a particular attractive approach for the development of novel therapeutics for neglected diseases, which are usually driven by public or non-profit organizations. Here we review current computer-guided approaches to drug repositioning and reports on drug repositioning stories oriented to Chagas disease, with a focus on computer-guided drug repositioning campaigns.

Identification of levothyroxine antichagasic activity through computer-aided drug repurposing

Cruzipain (Cz) is the major cysteine protease of the protozoan Trypanosoma cruzi, etiological agent of Chagas disease. A conformation-independent classifier capable of identifying Cz inhibitors was derived from a 163-compound dataset and later applied in a virtual screening campaign on the DrugBank database, which compiles FDA-approved and investigational drugs. 54 approved drugs were selected as candidates, 3 of which were acquired and tested on Cz and T. cruzi epimastigotes proliferation. Among them, levothyroxine, traditionally used in hormone replacement therapy in patients with hypothyroidism, showed dose-dependent inhibition of Cz and antiproliferative activity on the parasite.

Application of computer-aided drug repurposing in the search of new cruzipain inhibitors: discovery of amiodarone and bromocriptine inhibitory effects

Cruzipain (Cz) is the major cystein protease of the protozoan Trypanosoma cruzi , etiological agent of Chagas disease. From a 163 compound data set, a 2D-classifier capable of identifying Cz inhibitors was obtained and applied in a virtual screening campaign on the DrugBank database, which compiles FDA-approved and investigational drugs. Fifty-four approved drugs were selected as candidates, four of which were acquired and tested on Cz and T. cruzi epimastigotes. Among them, the antiparkinsonian and antidiabetic drug bromocriptine and the antiarrhythmic amiodarone showed dose-dependent inhibition of Cz and antiproliferative activity on the parasite.

CNS drug development - lost in translation?

CNS drug development is characterized by an especially high attrition rate, despite clear unmet medical needs in the field of neuro-pharmacology and significant investment in R of novel CNS drug treatments. Here, we overview the issues underlying the intrinsic difficulty of CNS drugs development, including obstacles of pharmacokinetic nature and lack of predictivity of preclinical tests. We highlight current efforts to overcome these limitations, with an emphasis on modeling opportunities towards early recognition of CNS candidates (stressing the possibilities of multi-target directed ligands or "magic shotguns") and different approaches to improve CNS bioavailability.