An interaction-based drug discovery screen explains known SARS-CoV-2 inhibitors and predicts new compound scaffolds.

The recent outbreak of the COVID-19 pandemic caused by severe acute respiratory syndrome-Coronavirus-2 (SARS-CoV-2) has shown the necessity for fast and broad drug discovery methods to enable us to react quickly to novel and highly infectious diseases. A well-known SARS-CoV-2 target is the viral main 3-chymotrypsin-like cysteine protease (Mpro), known to control coronavirus replication, which is essential for the viral life cycle. Here, we applied an interaction-based drug repositioning algorithm on all protein-compound complexes available in the protein database (PDB) to identify Mpro inhibitors and potential novel compound scaffolds against SARS-CoV-2. The screen revealed a heterogeneous set of 692 potential Mpro inhibitors containing known ones such as Dasatinib, Amodiaquine, and Flavin mononucleotide, as well as so far untested chemical scaffolds. In a follow-up evaluation, we used publicly available data published almost two years after the screen to validate our results. In total, we are able to validate 17% of the top 100 predictions with publicly available data and can furthermore show that predicted compounds do cover scaffolds that are yet not associated with Mpro. Finally, we detected a potentially important binding pattern consisting of 3 hydrogen bonds with hydrogen donors of an oxyanion hole within the active side of Mpro. Overall, these results give hope that we will be better prepared for future pandemics and that drug development will become more efficient in the upcoming years.

Past, Present, and Future Perspectives on Computer-Aided Drug Design Methodologies.

The application of computational approaches in drug discovery has been consolidated in the last decades. These families of techniques are usually grouped under the common name of "computer-aided drug design" (CADD), and they now constitute one of the pillars in the pharmaceutical discovery pipelines in many academic and industrial environments. Their implementation has been demonstrated to tremendously improve the speed of the early discovery steps, allowing for the proficient and rational choice of proper compounds for a desired therapeutic need among the extreme vastness of the drug-like chemical space. Moreover, the application of CADD approaches allows the rationalization of biochemical and interactive processes of pharmaceutical interest at the molecular level. Because of this, computational tools are now extensively used also in the field of rational 3D design and optimization of chemical entities starting from the structural information of the targets, which can be experimentally resolved or can also be obtained with other computer-based techniques. In this work, we revised the state-of-the-art computer-aided drug design methods, focusing on their application in different scenarios of pharmaceutical and biological interest, not only highlighting their great potential and their benefits, but also discussing their actual limitations and eventual weaknesses. This work can be considered a brief overview of computational methods for drug discovery.

AI-Driven De Novo Design and Molecular Modeling for Discovery of Small-Molecule Compounds as Potential Drug Candidates Targeting SARS-CoV-2 Main Protease.

Over the past three years, significant progress has been made in the development of novel promising drug candidates against COVID-19. However, SARS-CoV-2 mutations resulting in the emergence of new viral strains that can be resistant to the drugs used currently in the clinic necessitate the development of novel potent and broad therapeutic agents targeting different vulnerable spots of the viral proteins. In this study, two deep learning generative models were developed and used in combination with molecular modeling tools for de novo design of small molecule compounds that can inhibit the catalytic activity of SARS-CoV-2 main protease (Mpro), an enzyme critically important for mediating viral replication and transcription. As a result, the seven best scoring compounds that exhibited low values of binding free energy comparable with those calculated for two potent inhibitors of Mpro, via the same computational protocol, were selected as the most probable inhibitors of the enzyme catalytic site. In light of the data obtained, the identified compounds are assumed to present promising scaffolds for the development of new potent and broad-spectrum drugs inhibiting SARS-CoV-2 Mpro, an attractive therapeutic target for anti-COVID-19 agents.

A Review on Artificial Intelligence Approaches and Rational Approaches in Drug Discovery.

Artificial intelligence (AI) speeds up the drug development process and reduces its time, as well as the cost which is of enormous importance in outbreaks such as COVID-19. It uses a set of machine learning algorithms that collects the available data from resources, categorises, processes and develops novel learning methodologies. Virtual screening is a successful application of AI, which is used in screening huge drug-like databases and filtering to a small number of compounds. The brain's thinking of AI is its neural networking which uses techniques such as Convoluted Neural Network (CNN), Recursive Neural Network (RNN) or Generative Adversial Neural Network (GANN). The application ranges from small molecule drug discovery to the development of vaccines. In the present review article, we discussed various techniques of drug design, structure and ligand-based, pharmacokinetics and toxicity prediction using AI. The rapid phase of discovery is the need of the hour and AI is a targeted approach to achieve this.

Predicting activatory and inhibitory drug-target interactions based on structural compound representations and genetically perturbed transcriptomes.

A computational approach to identifying drug-target interactions (DTIs) is a credible strategy for accelerating drug development and understanding the mechanisms of action of small molecules. However, current methods to predict DTIs have mainly focused on identifying simple interactions, requiring further experiments to understand mechanism of drug. Here, we propose AI-DTI, a novel method that predicts activatory and inhibitory DTIs by combining the mol2vec and genetically perturbed transcriptomes. We trained the model on large-scale DTIs with MoA and found that our model outperformed a previous model that predicted activatory and inhibitory DTIs. Data augmentation of target feature vectors enabled the model to predict DTIs for a wide druggable targets. Our method achieved substantial performance in an independent dataset where the target was unseen in the training set and a high-throughput screening dataset where positive and negative samples were explicitly defined. Also, our method successfully rediscovered approximately half of the DTIs for drugs used in the treatment of COVID-19. These results indicate that AI-DTI is a practically useful tool for guiding drug discovery processes and generating plausible hypotheses that can reveal unknown mechanisms of drug action.

Reverse tracking from drug-induced transcriptomes through multilayer molecular networks reveals hidden drug targets.

Identifying molecular targets of a drug is an essential process for drug discovery and development. The recent in-silico approaches are usually based on the structure information of chemicals and proteins. However, 3D structure information is hard to obtain and machine-learning methods using 2D structure suffer from data imbalance problem. Here, we present a reverse tracking method from genes to target proteins using drug-perturbed gene transcriptional profiles and multilayer molecular networks. We scored how well the protein explains gene expression changes perturbed by a drug. We validated the protein scores of our method in predicting known targets of drugs. Our method performs better than other methods using the gene transcriptional profiles and shows the ability to suggest the molecular mechanism of drugs. Furthermore, our method has the potential to predict targets for objects that do not have rigid structural information, such as coronavirus.

DRaW: prediction of COVID-19 antivirals by deep learning-an objection on using matrix factorization.

BACKGROUND: Due to the high resource consumption of introducing a new drug, drug repurposing plays an essential role in drug discovery. To do this, researchers examine the current drug-target interaction (DTI) to predict new interactions for the approved drugs. Matrix factorization methods have much attention and utilization in DTIs. However, they suffer from some drawbacks. METHODS: We explain why matrix factorization is not the best for DTI prediction. Then, we propose a deep learning model (DRaW) to predict DTIs without having input data leakage. We compare our model with several matrix factorization methods and a deep model on three COVID-19 datasets. In addition, to ensure the validation of DRaW, we evaluate it on benchmark datasets. Furthermore, as an external validation, we conduct a docking study on the COVID-19 recommended drugs. RESULTS: In all cases, the results confirm that DRaW outperforms matrix factorization and deep models. The docking results approve the top-ranked recommended drugs for COVID-19. CONCLUSIONS: In this paper, we show that it may not be the best choice to use matrix factorization in the DTI prediction. Matrix factorization methods suffer from some intrinsic issues, e.g., sparsity in the domain of bioinformatics applications and fixed-unchanged size of the matrix-related paradigm. Therefore, we propose an alternative method (DRaW) that uses feature vectors rather than matrix factorization and demonstrates better performance than other famous methods on three COVID-19 and four benchmark datasets.

[Data-driven drug discovery for drug repurposing].

To improve the decreased efficiency of drug discovery and development, drug repurposing (also called drug repositioning) has been expected, that it is a strategy for identifying new medical indications for approved, investigational or suspended drugs. Particularly, according to the rapid expansion of medical and life science data and the remarkable technological progress of AI technology in recent years, the approach of computational drug repurposing has been attracted as one of the applications in data-driven drug discovery. Computational drug repurposing is a method of systematical and strategical research for identifying novel indication candidates and prioritizing the indication candidates based on the various profiles of drugs, genes, and diseases. In this review article, the typical data science techniques for data-driven drug repurposing, 1. drug-target interaction prediction, 2. transcriptomics-based approach by using differentially gene expression profiles, 3. natural language processing and word embedding, and their current status were summarized. We have also introduced a use case of data-driven drug repurposing for the PPARγ/α agonist Netoglitazone that we actually analyzed. In addition, as an excellent successful case of data-driven drug repurposing in recent years, we have also discussed a repurposing case reported by BenevolentAI in 2020, that Baricitinib has been identified as a potential intervention for COVID-19, based on immunomodulatory treatment by its mechanism of action as a JAK1 and JAK2 inhibition.

DeepMPF: deep learning framework for predicting drug-target interactions based on multi-modal representation with meta-path semantic analysis.

BACKGROUND: Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and drug discovery. However, the traditional biological experiment is time-consuming and expensive, as there are abundant complex interactions present in the large size of genomic and chemical spaces. For alleviating this phenomenon, plenty of computational methods are conducted to effectively complement biological experiments and narrow the search spaces into a preferred candidate domain. Whereas, most of the previous approaches cannot fully consider association behavior semantic information based on several schemas to represent complex the structure of heterogeneous biological networks. Additionally, the prediction of DTI based on single modalities cannot satisfy the demand for prediction accuracy. METHODS: We propose a multi-modal representation framework of 'DeepMPF' based on meta-path semantic analysis, which effectively utilizes heterogeneous information to predict DTI. Specifically, we first construct protein-drug-disease heterogeneous networks composed of three entities. Then the feature information is obtained under three views, containing sequence modality, heterogeneous structure modality and similarity modality. We proposed six representative schemas of meta-path to preserve the high-order nonlinear structure and catch hidden structural information of the heterogeneous network. Finally, DeepMPF generates highly representative comprehensive feature descriptors and calculates the probability of interaction through joint learning. RESULTS: To evaluate the predictive performance of DeepMPF, comparison experiments are conducted on four gold datasets. Our method can obtain competitive performance in all datasets. We also explore the influence of the different feature embedding dimensions, learning strategies and classification methods. Meaningfully, the drug repositioning experiments on COVID-19 and HIV demonstrate DeepMPF can be applied to solve problems in reality and help drug discovery. The further analysis of molecular docking experiments enhances the credibility of the drug candidates predicted by DeepMPF. CONCLUSIONS: All the results demonstrate the effectively predictive capability of DeepMPF for drug-target interactions. It can be utilized as a useful tool to prescreen the most potential drug candidates for the protein. The web server of the DeepMPF predictor is freely available at http://120.77.11.78/DeepMPF/ , which can help relevant researchers to further study.

Advances in the discovery of new chemotypes through ultra-large library docking.

INTRODUCTION: The size and complexity of virtual screening libraries in drug discovery have skyrocketed in recent years, reaching up to multiple billions of accessible compounds. However, virtual screening of such ultra-large libraries poses several challenges associated with preparing the libraries, sampling, and pre-selection of suitable compounds. The utilization of artificial intelligence (AI)-assisted screening approaches, such as deep learning, poses a promising countermeasure to deal with this rapidly expanding chemical space. For example, various AI-driven methods were recently successfully used to identify novel small molecule inhibitors of the SARS-CoV-2 main protease (Mpro). AREAS COVERED: This review focuses on presenting various kinds of virtual screening methods suitable for dealing with ultra-large libraries. Challenges associated with these computational methodologies are discussed, and recent advances are highlighted in the example of the discovery of novel Mpro inhibitors targeting the SARS-CoV-2 virus. EXPERT OPINION: With the rapid expansion of the virtual chemical space, the methodologies for docking and screening such quantities of molecules need to keep pace. Employment of AI-driven screening compounds has already been shown to be effective in a range from a few thousand to multiple billion compounds, furthered by de novo generation of drug-like molecules without human interference.

Reciprocal perspective as a super learner improves drug-target interaction prediction (MUSDTI).

The identification of novel drug-target interactions (DTI) is critical to drug discovery and drug repurposing to address contemporary medical and public health challenges presented by emergent diseases. Historically, computational methods have framed DTI prediction as a binary classification problem (indicating whether or not a drug physically interacts with a given protein target); however, framing the problem instead as a regression-based prediction of the physiochemical binding affinity is more meaningful. With growing databases of experimentally derived drug-target interactions (e.g. Davis, Binding-DB, and Kiba), deep learning-based DTI predictors can be effectively leveraged to achieve state-of-the-art (SOTA) performance. In this work, we formulated a DTI competition as part of the coursework for a senior undergraduate machine learning course and challenged students to generate component DTI models that might surpass SOTA models and effectively combine these component models as part of a meta-model using the Reciprocal Perspective (RP) multi-view learning framework. Following 6 weeks of concerted effort, 28 student-produced component deep-learning DTI models were leveraged in this work to produce a new SOTA RP-DTI model, denoted the Meta Undergraduate Student DTI (MUSDTI) model. Through a series of experiments we demonstrate that (1) RP can considerably improve SOTA DTI prediction, (2) our new double-cold experimental design is more appropriate for emergent DTI challenges, (3) that our novel MUSDTI meta-model outperforms SOTA models, (4) that RP can improve upon individual models as an ensembling method, and finally, (5) RP can be utilized for low computation transfer learning. This work introduces a number of important revelations for the field of DTI prediction and sequence-based, pairwise prediction in general.

Advances in covalent drug discovery.

Covalent drugs have been used to treat diseases for more than a century, but tools that facilitate the rational design of covalent drugs have emerged more recently. The purposeful addition of reactive functional groups to existing ligands can enable potent and selective inhibition of target proteins, as demonstrated by the covalent epidermal growth factor receptor (EGFR) and Bruton's tyrosine kinase (BTK) inhibitors used to treat various cancers. Moreover, the identification of covalent ligands through 'electrophile-first' approaches has also led to the discovery of covalent drugs, such as covalent inhibitors for KRAS(G12C) and SARS-CoV-2 main protease. In particular, the discovery of KRAS(G12C) inhibitors validates the use of covalent screening technologies, which have become more powerful and widespread over the past decade. Chemoproteomics platforms have emerged to complement covalent ligand screening and assist in ligand discovery, selectivity profiling and target identification. This Review showcases covalent drug discovery milestones with emphasis on the lessons learned from these programmes and how an evolving toolbox of covalent drug discovery techniques facilitates success in this field.

Emerging therapeutic opportunities for integrin inhibitors.

Integrins are cell adhesion and signalling proteins crucial to a wide range of biological functions. Effective marketed treatments have successfully targeted integrins αIIbß3, α4ß7/α4ß1 and αLß2 for cardiovascular diseases, inflammatory bowel disease/multiple sclerosis and dry eye disease, respectively. Yet, clinical development of others, notably within the RGD-binding subfamily of αv integrins, including αvß3, have faced significant challenges in the fields of cancer, ophthalmology and osteoporosis. New inhibitors of the related integrins αvß6 and αvß1 have recently come to the fore and are being investigated clinically for the treatment of fibrotic diseases, including idiopathic pulmonary fibrosis and nonalcoholic steatohepatitis. The design of integrin drugs may now be at a turning point, with opportunities to learn from previous clinical trials, to explore new modalities and to incorporate new findings in pharmacological and structural biology. This Review intertwines research from biological, clinical and medicinal chemistry disciplines to discuss historical and current RGD-binding integrin drug discovery, with an emphasis on small-molecule inhibitors of the αv integrins.

A review on computer-aided chemogenomics and drug repositioning for rational COVID-19 drug discovery.

Application of materials capable of energy harvesting to increase the efficiency and environmental adaptability is sometimes reflected in the ability of discovery of some traces in an environment-either experimentally or computationally-to enlarge practical application window. The emergence of computational methods, particularly computer-aided drug discovery (CADD), provides ample opportunities for the rapid discovery and development of unprecedented drugs. The expensive and time-consuming process of traditional drug discovery is no longer feasible, for nowadays the identification of potential drug candidates is much easier for therapeutic targets through elaborate in silico approaches, allowing the prediction of the toxicity of drugs, such as drug repositioning (DR) and chemical genomics (chemogenomics). Coronaviruses (CoVs) are cross-species viruses that are able to spread expeditiously from the into new host species, which in turn cause epidemic diseases. In this sense, this review furnishes an outline of computational strategies and their applications in drug discovery. A special focus is placed on chemogenomics and DR as unique and emerging system-based disciplines on CoV drug and target discovery to model protein networks against a library of compounds. Furthermore, to demonstrate the special advantages of CADD methods in rapidly finding a drug for this deadly virus, numerous examples of the recent achievements grounded on molecular docking, chemogenomics, and DR are reported, analyzed, and interpreted in detail. It is believed that the outcome of this review assists developers of energy harvesting materials and systems for detection of future unexpected kinds of CoVs or other variants.

Discovery of 2-(furan-2-ylmethylene)hydrazine-1-carbothioamide derivatives as novel inhibitors of SARS-CoV-2 main protease.

The COVID-19 posed a serious threat to human life and health, and SARS-CoV-2 Mpro has been considered as an attractive drug target for the treatment of COVID-19. Herein, we report 2-(furan-2-ylmethylene)hydrazine-1-carbothioamide derivatives as novel inhibitors of SARS-CoV-2 Mpro developed by in-house library screening and biological evaluation. Similarity search led to the identification of compound F8-S43 with the enzymatic IC50 value of 10.76 µM. Further structure-based drug design and synthetic optimization uncovered compounds F8-B6 and F8-B22 as novel non-peptidomimetic inhibitors of Mpro with IC50 values of 1.57 µM and 1.55 µM, respectively. Moreover, enzymatic kinetic assay and mass spectrometry demonstrated that F8-B6 was a reversible covalent inhibitor of Mpro. Besides, F8-B6 showed low cytotoxicity with CC50 values of more than 100 µM in Vero and MDCK cells. Overall, these novel SARS-CoV-2 Mpro non-peptidomimetic inhibitors provide a useful starting point for further structural optimization.

Breakthroughs in Medicinal Chemistry: New Targets and Mechanisms, New Drugs, New Hopes-7.

Breakthroughs in Medicinal Chemistry [...].

From Traditional Ethnopharmacology to Modern Natural Drug Discovery: A Methodology Discussion and Specific Examples.

Ethnopharmacology, through the description of the beneficial effects of plants, has provided an early framework for the therapeutic use of natural compounds. Natural products, either in their native form or after crude extraction of their active ingredients, have long been used by different populations and explored as invaluable sources for drug design. The transition from traditional ethnopharmacology to drug discovery has followed a straightforward path, assisted by the evolution of isolation and characterization methods, the increase in computational power, and the development of specific chemoinformatic methods. The deriving extensive exploitation of the natural product chemical space has led to the discovery of novel compounds with pharmaceutical properties, although this was not followed by an analogous increase in novel drugs. In this work, we discuss the evolution of ideas and methods, from traditional ethnopharmacology to in silico drug discovery, applied to natural products. We point out that, in the past, the starting point was the plant itself, identified by sustained ethnopharmacological research, with the active compound deriving after extensive analysis and testing. In contrast, in recent years, the active substance has been pinpointed by computational methods (in silico docking and molecular dynamics, network pharmacology), followed by the identification of the plant(s) containing the active ingredient, identified by existing or putative ethnopharmacological information. We further stress the potential pitfalls of recent in silico methods and discuss the absolute need for in vitro and in vivo validation as an absolute requirement. Finally, we present our contribution to natural products' drug discovery by discussing specific examples, applying the whole continuum of this rapidly evolving field. In detail, we report the isolation of novel antiviral compounds, based on natural products active against influenza and SARS-CoV-2 and novel substances active on a specific GPCR, OXER1.

UnbiasedDTI: Mitigating Real-World Bias of Drug-Target Interaction Prediction by Using Deep Ensemble-Balanced Learning.

Drug-target interaction (DTI) prediction through in vitro methods is expensive and time-consuming. On the other hand, computational methods can save time and money while enhancing drug discovery efficiency. Most of the computational methods frame DTI prediction as a binary classification task. One important challenge is that the number of negative interactions in all DTI-related datasets is far greater than the number of positive interactions, leading to the class imbalance problem. As a result, a classifier is trained biased towards the majority class (negative class), whereas the minority class (interacting pairs) is of interest. This class imbalance problem is not widely taken into account in DTI prediction studies, and the few previous studies considering balancing in DTI do not focus on the imbalance issue itself. Additionally, they do not benefit from deep learning models and experimental validation. In this study, we propose a computational framework along with experimental validations to predict drug-target interaction using an ensemble of deep learning models to address the class imbalance problem in the DTI domain. The objective of this paper is to mitigate the bias in the prediction of DTI by focusing on the impact of balancing and maintaining other involved parameters at a constant value. Our analysis shows that the proposed model outperforms unbalanced models with the same architecture trained on the BindingDB both computationally and experimentally. These findings demonstrate the significance of balancing, which reduces the bias towards the negative class and leads to better performance. It is important to note that leaning on computational results without experimentally validating them and by relying solely on AUROC and AUPRC metrics is not credible, particularly when the testing set remains unbalanced.

Allostery and Missense Mutations as Intermittently Linked Promising Aspects of Modern Computational Drug Discovery.

Drug research and development is a multidisciplinary field with its own successes. Yet, given the complexity of the process, it also faces challenges over the long development stages and even includes those that develop once a drug is marketed, i.e. drug toxicity and drug resistance. Better success can be achieved via well designed criteria in the early drug development stages. Here, we introduce the concepts of allostery and missense mutations, and argue that incorporation of these two intermittently linked biological phenomena into the early computational drug discovery stages would help to reduce the attrition risk in later stages of the process. We discuss the individual or in concert mechanisms of actions of mutations in allostery. Design of allosteric drugs is challenging compared to orthosteric drugs, yet they have been gaining popularity in recent years as alternative systems for the therapeutic regulation of proteins with an action-at-a-distance mode and non-invasive mechanisms. We propose an easy-to-apply computational allosteric drug discovery protocol which considers the mutation effect, and detail it with three case studies focusing on (1) analysis of effect of an allosteric mutation related to isoniazid drug resistance in tuberculosis; (2) identification of a cryptic pocket in the presence of an allosteric mutation of falcipain-2 as a malarial drug target; and (3) deciphering the effects of SARS-CoV-2 evolutionary mutations on a potential allosteric modulator with changes to allosteric communication paths.