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

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.

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.