DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues

PMODiff: Physics-Informed Multi-Objective Optimization Diffusion Model for Protein-Specific 3D Molecule Generation

3D generative models have shown great potential in structure-based drug design for generating ligands tailored to specific protein binding pockets. However, existing methods primarily emphasize ligand-target geometric interactions and binding affinity prediction, often overlooking intrinsic physicochemical principles driving protein-ligand interactions as well as critical pharmaceutical properties, such as drug-likeness and synthetic accessibility. To address these limitations, PMODiff (Physics-Informed Multi-Objective Optimization Diffusion Model) integrates a physics-informed component into the denoising phase, minimizing protein-ligand interaction energy modeled by a simplified Lennard-Jones potential, thus generating conformations aligned with essential physicochemical constraints. In addition, pretrained networks guide the sampling process toward ligands exhibiting high affinity, favorable drug-likeness, and synthetic accessibility, thus addressing multiobjective optimization challenges in practical drug development. Experimental results on the CrossDocked2020 data set indicate that PMODiff generates more realistic 3D structures with higher binding affinity, achieving an average Vina Score of -7.44. This performance represents a 13% improvement over existing methods, highlighting the potential of PMODiff for more comprehensive drug design.

Identification and characterization of binding thermodynamics and kinetics of inhibitors targeting FGFR1 via molecular modelling and ligand Gaussian accelerated molecular dynamics simulations

Fibroblast growth factor receptor1 (FGFR1) kinase has a crucial role in cell proliferation, migration, and differentiation. Any imbalance in its level can cause cancer and many other illnesses. Despite the availability of numerous treatments, cytotoxicity, selectivity, and drug resistance issues demand the development of new FGFR1 inhibitors. Herein, we performed a high-throughput virtual screening of 54 624 compounds from NPASS and HMDB databases using the Schrodinger software suite. Compounds with a docking score cutoff of -11.0 kcal mol-1 were further screened for ADMET properties. Following the all-atom molecular dynamics simulation of selected molecules in replica, the binding free energy was calculated using the molecular mechanics Poisson Boltzmann surface area (MM-PBSA) scheme. We obtained two compounds, namely, bevantolol and 3-hydroxy glabrol, which exhibited higher binding affinities than the control drug ponatinib. Bevantolol was further optimized via virtual screening and simulation studies of its 100 structural analogues to obtain the best analogue. Subsequently, we investigated the binding thermodynamics and kinetics of the best analogue molecule via ligand Gaussian accelerated molecular dynamics (LiGaMD) simulation, performing independent replica runs of 4 μs each. The 1D and 2D potential of mean force and Kramer's rate theory determined the kinetic rate constants (kon/koff) associated with the FGFR1 complex. The binding constant was estimated to be 7.4 ± 0.27 nM, which was similar to the type II tyrosine kinase inhibitor ponatinib. Overall, this study highlights the dynamics of FGFR1-ligand interaction while proposing bevantolol and its analogue molecule ANLG-2 as promising drug candidates for FGFR1 therapeutic intervention.

SIGMAP: an explainable artificial intelligence tool for SIGMA-1 receptor affinity prediction

Developing sigma-1 receptor (S1R) modulators is considered a valuable therapeutic strategy to counteract neurodegeneration, cancer progression, and viral infections, including COVID-19. In this context, in silico tools capable of accurately predicting S1R affinity are highly desirable. Herein, we present a panel of 25 classifiers trained on a curated dataset of high-quality bioactivity data of small molecules, experimentally tested as potential S1R modulators. All data were extracted from ChEMBL v33, and the models were built using five different fingerprints and machine-learning algorithms. Remarkably, most of the developed classifiers demonstrated good predictive performance. The best-performing model, which achieved an AUC of 0.90, was developed using the support vector machine algorithm with Morgan fingerprints. To provide additional, user-friendly information for medicinal chemists in the rational design of S1R modulators, two independent explainable artificial intelligence (XAI) approaches were employed, namely Shapley Additive exPlanations (SHAP) and Contrastive Explanation. The top-performing model is accessible through a user-friendly web platform, SIGMAP (https://www.ba.ic.cnr.it/softwareic/sigmap/), specifically developed for this purpose. With its intuitive interface, robust predictive power, and implemented XAI approaches, SIGMAP serves as a valuable tool for the rational design of new and more effective S1R modulators.

Transformer Decoder Learns from a Pretrained Protein Language Model to Generate Ligands with High Affinity

The drug discovery process can be significantly accelerated by using deep learning methods to suggest molecules with druglike features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging (i) the information carried by a pretrained protein language model and (ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for designing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favorable physicochemical properties and high affinity toward specific targets. Moreover, Prot2Drug reproduced numerous known interactions between compounds and proteins used for generating them and suggested novel protein targets for known compounds, indicating potential drug repurposing strategies. Remarkably, Prot2Drug facilitates the design of promising ligands even for protein targets with limited or no information about their ligands or 3D structure.

Progress in the application of artificial intelligence in molecular generation models based on protein structure

The molecular generation models based on protein structures represent a cutting-edge research direction in artificial intelligence-assisted drug discovery. This article aims to comprehensively summarize the research methods and developments by analyzing a series of novel molecular generation models predicated on protein structures. Initially, we categorize the molecular generation models based on protein structures and highlight the architectural frameworks utilized in these models. Subsequently, we detail the design and implementation of protein structure-based molecular generation models by introducing different specific examples. Lastly, we outline the current opportunities and challenges encountered in this field, intending to offer guidance and a referential framework for developing and studying new models in related fields in the future.

DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search

A growing number of deep learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these neural network approaches design molecules to specifically bind a target based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthesis using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski's "rule of 5″, show a high proportion of highly water-soluble nontoxic predicted-to-be synthesizable compounds, and efficiently expand the chemical space within the libraries, without reliance on training data sets, synthesizability metrics, or enforcing during SMILES generation. Our approach can function with or without an underlying neural network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job-oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://github.com/RoucairolMilo/DrugSynthMC.

Unraveling effective extracellular signal-regulated kinase 2 inhibitors: a de novo drug design strategy enhanced by in-depth in silico analyses

Extracellular signal-regulated kinase 2 (ERK-2) is a serine/threonine protein kinase in eukaryotic cells and belongs to the mitogen-activated protein kinase (MAPK) family. An activated form of ERK-2 phosphorylates substrates in the nucleus or cytoplasm and causes specific proteins to be expressed or activated, regulating cell proliferation, differentiation and other functions. Caffeic acid (3,4 - dihydroxy cinnamic acid), as previously reported, directly interacts with ERK-2 and reduces its effects in vitro. It is also reported to have a variety of pharmacological effects, including anti-inflammatory, immunomodulatory, antioxidant and anticancer activities. In the current study, a deep-learning protocol was employed to develop effective 100 compounds by modifying the chemical structure of DHC to improve its inhibitory performance against ERK-2. Calculations of physicochemical properties for those compounds revealed that 20 compounds had drug scores better than DHC (≥ 80%). Following that, molecular docking calculations were performed on the selected compounds and DHC. The obtained data revealed that five compounds had docking scores better than DHC (≥ -5.9 kcal/mol). Moreover, data from molecular mechanics and the Poisson - Boltzmann surface area (MM/PBSA) binding energy over 200 ns MD simulation confirmed that Cmd-1 and Cmd-4 exhibited higher stability with ΔGbinding of -40.8 and -49.1 kcal/mol, respectively, which is better than DHC (-35.1 kcal/mol). Finally, various energetic and structural studies showed the high stability of the two generated compounds within the active site of ERK-2. This study highlights the potential use of Cmd-1 and Cmd-4 as promising anti-ERK-2 drug candidates.Communicated by Ramaswamy H. Sarma.

Identification of potential modulators for human GPD1 by docking-based virtual screening, molecular dynamics simulations, binding free energy calculations, and DeLA-drug analysis

Cytosolic Glycerol-3-phosphate dehydrogenase 1 (GPD1, EC 1.1.1.8) plays a pivotal role in regulating the Embden-Meyerhof glucose glycolysis pathway (E-M pathway), as well as in conditions such as Huntington's disease, cancer, and its potential role as a specific marker for Dormant Glioma Stem Cells. In this study, we conducted virtual screening using the ZINC database ( http://zinc.docking.org/ ) and the GPD1 structure to identify potential GPD1 modulators. The investigation involved screening active candidate ligands using ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) parameters, combined with molecular docking, pose analysis, and interaction analysis based on Lipinski and Veber criteria. Subsequently, the top 10 ligands were subjected to 200 ns all-atom molecular dynamics (M.D.) simulations, and binding free energies were calculated. The findings revealed that specific residues, namely TRP14, PRO94, LYS120, ASN151, THR264, ASP260, and GLN298, played a crucial role in ensuring system stability. Furthermore, through a comprehensive analysis involving molecular docking, molecular M.D., and DeLA-Drug, we identified 10 promising small molecules. These molecules represent potential lead compounds for developing effective therapeutics targeting GPD1-associated diseases, thereby contributing to a deeper understanding of GPD1-associated mechanisms. This study's significance lies in identifying key residues associated with GPD1 and discovering valuable small molecules, providing a foundation for further research and development.

DeLA-DrugSelf: Empowering multi-objective de novo design through SELFIES molecular representation

In this paper, we introduce DeLA-DrugSelf, an upgraded version of DeLA-Drug [J. Chem. Inf. Model. 62 (2022) 1411-1424], which incorporates essential advancements for automated multi-objective de novo design. Unlike its predecessor, which relies on SMILES notation for molecular representation, DeLA-DrugSelf employs a novel and robust molecular representation string named SELFIES (SELF-referencing Embedded String). The generation process in DeLA-DrugSelf not only involves substitutions to the initial string representing the starting query molecule but also incorporates insertions and deletions. This enhancement makes DeLA-DrugSelf significantly more adept at executing data-driven scaffold decoration and lead optimization strategies. Remarkably, DeLA-DrugSelf explicitly addresses the SELFIES-related collapse issue, considering only collapse-free compounds during generation. These compounds undergo a rigorous quality metrics evaluation, highlighting substantial advancements in terms of drug-likeness, uniqueness, and novelty compared to the molecules generated by the previous version of the algorithm. To evaluate the potential of DeLA-DrugSelf as a mutational operator within a genetic algorithm framework for multi-objective optimization, we employed a fitness function based on Pareto dominance. Our objectives focused on target-oriented properties aimed at optimizing known cannabinoid receptor 2 (CB2R) ligands. The results obtained indicate that DeLA-DrugSelf, available as a user-friendly web platform (https://www.ba.ic.cnr.it/softwareic/delaself/), can effectively contribute to the data-driven optimization of starting bioactive molecules based on user-defined parameters.

Identification of inhibitors for neurodegenerative diseases targeting dual leucine zipper kinase through virtual screening and molecular dynamics simulations

Neurodegenerative diseases lead to a gradual decline in cognitive and motor functions due to the progressive loss of neurons in the central nervous system. The role of dual leucine zipper kinase (DLK) in regulating stress responses and neuronal death pathways highlights its significance as a target against neurodegenerative diseases. The non-availability of FDA-approved drugs emphasizes a need to identify novel DLK-inhibitors. We screened NPAtlas (Natural products) and MedChemExpress (FDA-approved) libraries to identify potent ATP-competitive DLK inhibitors. ADMET analyses identified four compounds (two natural products and two FDA-approved) with favourable features. Subsequently, we performed molecular dynamics simulations to examine the binding-stability and ligand-induced conformational dynamics. Molecular mechanics Poisson Boltzmann surface area (MM-PBSA) calculations demonstrated CID139591660, dithranol, and danthron having greater affinity, while CID156581477 showed lower affinity than control sunitinib. PCA and network analysis results indicated structural and network alteration post-ligand binding. Furthermore, we identified an analogue of CID156581477 using the deep learning-based web server DeLA Drug which demonstrated a higher affinity than its parent compound and the control and identified several crucial interacting residues. Overall, our study provides significant theoretical guidance for designing potent novel DLK inhibitors and compounds that could emerge as promising drug candidates against DLK following laboratory validation.

Structural basis for specific inhibition of salicylate synthase from Mycobacterium abscessus

Blocking iron uptake and metabolism has been emerging as a promising therapeutic strategy for the development of novel antimicrobial compounds. Like all mycobacteria, M. abscessus (Mab) has evolved several countermeasures to scavenge iron from host carrier proteins, including the production of siderophores, which play a crucial role in these processes. In this study, we solved, for the first time, the crystal structure of Mab-SaS, the first enzyme involved in the biosynthesis of siderophores. Moreover, we screened a small, focused library and identified a compound exhibiting a potent inhibitory effect against Mab-SaS (IC50 ≈ 2 μM). Its binding mode was investigated by means of Induced Fit Docking simulations, performed on the crystal structure presented herein. Furthermore, cytotoxicity data and pharmacokinetic predictions revealed the safety and drug-likeness of this class of compounds. Finally, the crystallographic data were used to optimize the model for future virtual screening campaigns. Taken together, the findings of our study pave the way for the identification of potent Mab-SaS inhibitors, based on both established and unexplored chemotypes.

AMALPHI: A Machine Learning Platform for Predicting Drug-Induced PhospholIpidosis

Drug-induced phospholipidosis (PLD) involves the accumulation of phospholipids in cells of multiple tissues, particularly within lysosomes, and it is associated with prolonged exposure to druglike compounds, predominantly cationic amphiphilic drugs (CADs). PLD affects a significant portion of drugs currently in development and has recently been proven to be responsible for confounding antiviral data during drug repurposing for SARS-CoV-2. In these scenarios, it has become crucial to identify potential safe drug candidates in advance and distinguish them from those that may lead to false in vitro antiviral activity. In this work, we developed a series of machine learning classifiers with the aim of predicting the PLD-inducing potential of drug candidates. The models were built on a high-quality chemical collection comprising 545 curated small molecules extracted from ChEMBL v30. The most effective model, obtained using the balanced random forest algorithm, achieved high performance, including an AUC value computed in validation as high as 0.90. The model was made freely available through a user-friendly web platform named AMALPHI (https://www.ba.ic.cnr.it/softwareic/amalphiportal/), which can represent a valuable tool for medicinal chemists interested in conducting an early evaluation of PLD inducer potential.

CONSMI: Contrastive Learning in the Simplified Molecular Input Line Entry System Helps Generate Better Molecules

In recent years, the application of deep learning in molecular de novo design has gained significant attention. One successful approach involves using SMILES representations of molecules and treating the generation task as a text generation problem, yielding promising results. However, the generation of more effective and novel molecules remains a key research area. Due to the fact that a molecule can have multiple SMILES representations, it is not sufficient to consider only one of them for molecular generation. To make up for this deficiency, and also motivated by the advancements in contrastive learning in natural language processing, we propose a contrastive learning framework called CONSMI to learn more comprehensive SMILES representations. This framework leverages different SMILES representations of the same molecule as positive examples and other SMILES representations as negative examples for contrastive learning. The experimental results of generation tasks demonstrate that CONSMI significantly enhances the novelty of generated molecules while maintaining a high validity. Moreover, the generated molecules have similar chemical properties compared to the original dataset. Additionally, we find that CONSMI can achieve favorable results in classifier tasks, such as the compound-protein interaction task.

Exploring molecular interactions of potential inhibitors against the spleen tyrosine kinase implicated in autoimmune disorders via virtual screening and molecular dynamics simulations

The spleen tyrosine kinase (Syk) plays a pivotal role in immune cells' signal transduction mechanism. While fostamatinib, an FDA-approved Syk inhibitor, is currently used to treat immune thrombocytopenia, the search for improved Syk-targeted medications to treat autoimmune diseases is still underway. Herein, we screened 38,493 compounds against Syk and selected eight leads based on the docking score and ADMET properties, and performed 3× 200 ns long molecular dynamics simulations of the apo and Syk-ligand complexes. We considered R406, the active component of fostamatinib, as a control. The molecular mechanics Poisson-Boltzmann surface area (MM-PBSA) calculations demonstrated the lead1 (Δ G b i n d  = -30.35 kcal/mol) exhibited a similar binding free energy as the control (Δ G b i n d = -29.82 kcal/mol). The Syk stabilizing effect of lead1 was also indicated in its network features, sampling space, and residual correlation motion analysis. We further generated 100 structural analogues of lead1 using deep learning, and one of the analogues displayed a better binding free energy (Δ G b i n d = -47.58 kcal/mol) compared to the control or lead1, facilitated by more favourable van der Waals interactions and lesser binding-opposing net polar forces. This analogue may be further exploited to develop effective therapeutics against Syk-associated diseases after validation in vitro and in vivo.

ALPACA: A machine Learning Platform for Affinity and selectivity profiling of CAnnabinoids receptors modulators

The development of small molecules that selectively target the cannabinoid receptor subtype 2 (CB2R) is emerging as an intriguing therapeutic strategy to treat neurodegeneration, as well as to contrast the onset and progression of cancer. In this context, in-silico tools able to predict CB2R affinity and selectivity with respect to the subtype 1 (CB1R), whose modulation is responsible for undesired psychotropic effects, are highly desirable. In this work, we developed a series of machine learning classifiers trained on high-quality bioactivity data of small molecules acting on CB2R and/or CB1R extracted from ChEMBL v30. Our classifiers showed strong predictive power in accurately determining CB2R affinity, CB1R affinity, and CB2R/CB1R selectivity. Among the built models, those obtained using random forest as algorithm proved to be the top-performing ones (AUC in validation ≥0.96) and were made freely accessible through a user-friendly web platform developed ad hoc and called ALPACA (https://www.ba.ic.cnr.it/softwareic/alpaca/). Due to its user-friendly interface and robust predictive power, ALPACA can be a valuable tool in saving both time and resources involved in the design of selective CB2R modulators.

GENERA: A Combined Genetic/Deep-Learning Algorithm for Multiobjective Target-Oriented De Novo Design

This study introduces a new de novo design algorithm called GENERA that combines the capabilities of a deep-learning algorithm for automated drug-like analogue design, called DeLA-Drug, with a genetic algorithm for generating molecules with desired target-oriented properties. Specifically, GENERA was applied to the angiotensin-converting enzyme 2 (ACE2) target, which is implicated in many pathological conditions, including COVID-19. The ability of GENERA to de novo design promising candidates for a specific target was assessed using two docking programs, PLANTS and GLIDE. A fitness function based on the Pareto dominance resulting from computed PLANTS and GLIDE scores was applied to demonstrate the algorithm's ability to perform multiobjective optimizations effectively. GENERA can quickly generate focused libraries that produce better scores compared to a starting set of known ACE-2 binders. This study is the first to utilize a DL-based algorithm designed for analogue generation as a mutational operator within a GA framework, representing an innovative approach to target-oriented de novo design.

N-adamantyl-anthranil amide derivatives: New selective ligands for the cannabinoid receptor subtype 2 (CB2R)

Cannabinoid type 2 receptor (CB2R) is a G-protein-coupled receptor that, together with Cannabinoid type 1 receptor (CB1R), endogenous cannabinoids and enzymes responsible for their synthesis and degradation, forms the EndoCannabinoid System (ECS). In the last decade, several studies have shown that CB2R is overexpressed in activated central nervous system (CNS) microglia cells, in disorders based on an inflammatory state, such as neurodegenerative diseases, neuropathic pain, and cancer. For this reason, the anti-inflammatory and immune-modulatory potentials of CB2R ligands are emerging as a novel therapeutic approach. The design of selective ligands is however hampered by the high sequence homology of transmembrane domains of CB1R and CB2R. Based on a recent three-arm pharmacophore hypothesis and latest CB2R crystal structures, we designed, synthesized, and evaluated a series of new N-adamantyl-anthranil amide derivatives as CB2R selective ligands. Interestingly, this new class of compounds displayed a high affinity for human CB2R along with an excellent selectivity respect to CB1R. In this respect, compounds exhibiting the best pharmacodynamic profile in terms of CB2R affinity were also evaluated for the functional behavior and molecular docking simulations provided a sound rationale by highlighting the relevance of the arm 1 substitution to prompt CB2R action. Moreover, the modulation of the pro- and anti-inflammatory cytokines production was also investigated to exert the ability of the best compounds to modulate the inflammatory cascade.

UnCorrupt SMILES: a novel approach to de novo design

Generative deep learning models have emerged as a powerful approach for de novo drug design as they aid researchers in finding new molecules with desired properties. Despite continuous improvements in the field, a subset of the outputs that sequence-based de novo generators produce cannot be progressed due to errors. Here, we propose to fix these invalid outputs post hoc. In similar tasks, transformer models from the field of natural language processing have been shown to be very effective. Therefore, here this type of model was trained to translate invalid Simplified Molecular-Input Line-Entry System (SMILES) into valid representations. The performance of this SMILES corrector was evaluated on four representative methods of de novo generation: a recurrent neural network (RNN), a target-directed RNN, a generative adversarial network (GAN), and a variational autoencoder (VAE). This study has found that the percentage of invalid outputs from these specific generative models ranges between 4 and 89%, with different models having different error-type distributions. Post hoc correction of SMILES was shown to increase model validity. The SMILES corrector trained with one error per input alters 60-90% of invalid generator outputs and fixes 35-80% of them. However, a higher error detection and performance was obtained for transformer models trained with multiple errors per input. In this case, the best model was able to correct 60-95% of invalid generator outputs. Further analysis showed that these fixed molecules are comparable to the correct molecules from the de novo generators based on novelty and similarity. Additionally, the SMILES corrector can be used to expand the amount of interesting new molecules within the targeted chemical space. Introducing different errors into existing molecules yields novel analogs with a uniqueness of 39% and a novelty of approximately 20%. The results of this research demonstrate that SMILES correction is a viable post hoc extension and can enhance the search for better drug candidates.

Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening

Many bioactive peptides demonstrated therapeutic effects over complicated diseases, such as antiviral, antibacterial, anticancer, etc. It is possible to generate a large number of potentially bioactive peptides using deep learning in a manner analogous to the generation of de novo chemical compounds using the acquired bioactive peptides as a training set. Such generative techniques would be significant for drug development since peptides are much easier and cheaper to synthesize than compounds. Despite the limited availability of deep learning-based peptide-generating models, we have built an LSTM model (called LSTM_Pep) to generate de novo peptides and fine-tuned the model to generate de novo peptides with specific prospective therapeutic benefits. Remarkably, the Antimicrobial Peptide Database has been effectively utilized to generate various kinds of potential active de novo peptides. We proposed a pipeline for screening those generated peptides for a given target and used the main protease of SARS-COV-2 as a proof-of-concept. Moreover, we have developed a deep learning-based protein-peptide prediction model (DeepPep) for rapid screening of the generated peptides for the given targets. Together with the generating model, we have demonstrated that iteratively fine-tuning training, generating, and screening peptides for higher-predicted binding affinity peptides can be achieved. Our work sheds light on developing deep learning-based methods and pipelines to effectively generate and obtain bioactive peptides with a specific therapeutic effect and showcases how artificial intelligence can help discover de novo bioactive peptides that can bind to a particular target.

Endocannabinoid Degradation Enzyme Inhibitors as Potential Antipsychotics: A Medicinal Chemistry Perspective

The endocannabinoid system (ECS) plays a very important role in numerous physiological and pharmacological processes, such as those related to the central nervous system (CNS), including learning, memory, emotional processing, as well pain control, inflammatory and immune response, and as a biomarker in certain psychiatric disorders. Unfortunately, the half-life of the natural ligands responsible for these effects is very short. This perspective describes the potential role of the inhibitors of the enzymes fatty acid amide hydrolase (FAAH) and monoacylglycerol lipase (MGL), which are mainly responsible for the degradation of endogenous ligands in psychic disorders and related pathologies. The examination was carried out considering both the impact that the classical exogenous ligands such as Δ⁹-tetrahydrocannabinol (THC) and (-)-trans-cannabidiol (CBD) have on the ECS and through an analysis focused on the possibility of predicting the potential toxicity of the inhibitors before they are subjected to clinical studies. In particular, cardiotoxicity (hERG liability), probably the worst early adverse reaction studied during clinical studies focused on acute toxicity, was predicted, and some of the most used and robust metrics available were considered to select which of the analyzed compounds could be repositioned as possible oral antipsychotics.

Development of N-(1-Adamantyl)benzamides as Novel Anti-Inflammatory Multitarget Agents Acting as Dual Modulators of the Cannabinoid CB2 Receptor and Fatty Acid Amide Hydrolase

Cannabinoid type 2 receptor (CB2R), belonging to the endocannabinoid system, is overexpressed in pathologies characterized by inflammation, and its activation counteracts inflammatory states. Fatty acid amide hydrolase (FAAH) is an enzyme responsible for the degradation of the main endocannabinoid anandamide; thus, the simultaneous CB2R activation and FAAH inhibition may be a synergistic anti-inflammatory strategy. Encouraged by principal component analysis (PCA) data identifying a wide chemical space shared by CB2R and FAAH ligands, we designed a small library of adamantyl-benzamides, as potential dual agents, CB2R agonists, and FAAH inhibitors. The new compounds were tested for their CB2R affinity/selectivity and CB2R and FAAH activity. Derivatives 13, 26, and 27, displaying the best pharmacodynamic profile as CB2R full agonists and FAAH inhibitors, decreased pro-inflammatory and increased anti-inflammatory cytokines production. Molecular docking simulations complemented the experimental findings by providing a molecular rationale behind the observed activities. These multitarget ligands constitute promising anti-inflammatory agents.

An Efficient Modern Strategy to Screen Drug Candidates Targeting RdRp of SARS-CoV-2 With Potentially High Selectivity and Specificity

Desired drug candidates should have both a high potential binding chance and high specificity. Recently, many drug screening strategies have been developed to screen compounds with high possible binding chances or high binding affinity. However, there is still no good solution to detect whether those selected compounds possess high specificity. Here, we developed a reverse DFCNN (Dense Fully Connected Neural Network) and a reverse docking protocol to check a given compound’s ability to bind diversified targets and estimate its specificity with homemade formulas. We used the RNA-dependent RNA polymerase (RdRp) target as a proof-of-concept example to identify drug candidates with high selectivity and high specificity. We first used a previously developed hybrid screening method to find drug candidates from an 8888-size compound database. The hybrid screening method takes advantage of the deep learning-based method, traditional molecular docking, molecular dynamics simulation, and binding free energy calculated by metadynamics, which should be powerful in selecting high binding affinity candidates. Also, we integrated the reverse DFCNN and reversed docking against a diversified 102 proteins to the pipeline for assessing the specificity of those selected candidates, and finally got compounds that have both predicted selectivity and specificity. Among the eight selected candidates, Platycodin D and Tubeimoside III were confirmed to effectively inhibit SARS-CoV-2 replication in vitro with EC₅₀ values of 619.5 and 265.5 nM, respectively. Our study discovered that Tubeimoside III could inhibit SARS-CoV-2 replication potently for the first time. Furthermore, the underlying mechanisms of Platycodin D and Tubeimoside III inhibiting SARS-CoV-2 are highly possible by blocking the RdRp cavity according to our screening procedure. In addition, the careful analysis predicted common critical residues involved in the binding with active inhibitors Platycodin D and Tubeimoside III, Azithromycin, and Pralatrexate, which hopefully promote the development of non-covalent binding inhibitors against RdRp.