Searching for AChE inhibitors from natural compounds by using machine learning and atomistic simulations

Acetylcholinesterase inhibitory activities of some flavonoids from the root bark of Pinus krempfii Lecomte: in vitro and in silico study

From the root bark of Pinus krempfii Lecomte, four flavonoids were isolated and evaluated for their inhibitory activities against AChE and BChE enzymes in vitro and in silico. Tectochrysin (1) was found to inhibit AChE with an IC50 value of 33.69 ± 2.80 μM. The docking study results also showed agreement with the in vitro test results. All four compounds also showed the best binding affinity for the AChE enzyme, characterised by binding energy (ΔG) values as low as -8.1 to -9.3 kcal/mol, in which, the compound tectochrysin had the best binding affinity for the AChE protein with a ΔG value of -9.329 kcal/mol. Tectochrysin (1) was also bound to the amino acid Phe295 of AChE with a bond length of 2.8 Å, similar to the control dihydrotanshinone-I. Galangin (2) also showed its in vitro inhibitory activity against BChE with an IC50 value of 82.21 ± 2.70 μM. In silico, it also had the best binding energy value of -9.072 kcal/mol with BChE and formed hydrogen bonds with the His438 (2.85 Å) residues of BChE like the positive control (tacrine). The steered molecular dynamics (SMD) simulation results of these two complexes revealed a mechanistic insight that the protein-ligand complexes showed stable trajectories throughout the 20 and 150 ns simulations. Moreover, the drug likeliness suggested that both flavonoids (1 and 2) were expected to be drug-like and have an LD50 toxicity level of 5. This study has contributed new results for drug discovery and the development of substances with neuroprotective effects, especially for the treatment of Alzheimer's disease.Communicated by Ramaswamy H. Sarma.

Machine learning combines atomistic simulations to predict SARS-CoV-2 Mpro inhibitors from natural compounds

To date, the COVID-19 pandemic has still been infectious around the world, continuously causing social and economic damage on a global scale. One of the most important therapeutic targets for the treatment of COVID-19 is the main protease (Mpro) of SARS-CoV-2. In this study, we combined machine-learning (ML) model with atomistic simulations to computationally search for highly promising SARS-CoV-2 Mpro inhibitors from the representative natural compounds of the National Cancer Institute (NCI) Database. First, the trained ML model was used to scan the library quickly and reliably for possible Mpro inhibitors. The ML output was then confirmed using atomistic simulations integrating molecular docking and molecular dynamic simulations with the linear interaction energy scheme. The results turned out to show that there was evidently good agreement between ML and atomistic simulations. Ten substances were proposed to be able to inhibit SARS-CoV-2 Mpro. Seven of them have high-nanomolar affinity and are very potential inhibitors. The strategy has been proven to be reliable and appropriate for fast prediction of SARS-CoV-2 Mpro inhibitors, benefiting for new emerging SARS-CoV-2 variants in the future accordingly.

Natural compounds inhibit Monkeypox virus methyltransferase VP39 in silico studies

VP39, an essential 2'-O-RNA methyltransferase enzyme discovered in Monkeypox virus (MPXV), plays a vital role in viral RNA replication and transcription. Inhibition of the enzyme may prevent viral replication. In this context, using a combination of molecular docking and molecular dynamics (MDs) simulations, the inhibitory ability of NCI Diversity Set VII natural compounds to VP39 protein was investigated. It should be noted that the computed binding free energy of ligand via molecular docking and linear interaction energy (LIE) approaches are in good agreement with the corresponding experiments with coefficients of R = 0.72 and 0.75, respectively. NSC 319990, NSC 196515 and NSC 376254 compounds were demonstrated that can inhibit MPVX methyltransferase VP39 protein with the similar affinity compared to available inhibitor sinefungin. Moreover, nine residues involving Gln39, Gly68, Gly72, Asp95, Arg97, Val116, Asp138, Arg140 and Asn156 may be argued that they play an important role in binding process of inhibitors to VP39.Communicated by Ramaswamy H. Sarma.

Bacopa monnieri: A promising herbal approach for neurodegenerative disease treatment supported by in silico and in vitro research

Neurodegenerative disorders, caused by progressive neuron loss, are a global health issue. Among the various factors implicated in their pathogenesis, dysregulation of acetylcholinesterase activity has been recognized as a key contributor. Acetylcholinesterase breaks down the neurotransmitter acetylcholine, important for neural transmission. Evaluating phyto-compounds from Bacopa monnieri Linn. through in vitro and in silico analysis may expand their role as alternative therapeutic agents by modulating the function of acetylcholinesterase and complementing existing treatments. To accomplish this objective, chemical structures of phyto-compounds were retrieved from PubChem database and subjected to in silico and in vitro approaches. Virtual screening was performed through molecular docking and molecular dynamic simulation resulting in four top hit compounds including quercetin, apigenin, wogonin, and bacopaside X (novel lead compound for acetylcholinesterase inhibitor) with least binding score. Further, dose dependent acetylcholinesterase inhibition biochemical assay depicted that bacopaside X, apigenin, quercetin, and wogonin exhibited strong potential against acetylcholinesterase with IC50 values of 12.78 μM, 13.83 μM, 12.73 μM and 15.48 μM respectively, in comparison with the donepezil (IC50: 0.0204 μM). The in silico and in vitro research suggests that B. monnieri phyto-compounds have the potential to modulate molecular targets associated with neurodegenerative diseases and have a role in neuroprotection.

CADD, AI and ML in drug discovery: A comprehensive review

Computer-aided drug design (CADD) is an emerging field that has drawn a lot of interest because of its potential to expedite and lower the cost of the drug development process. Drug discovery research is expensive and time-consuming, and it frequently took 10-15 years for a drug to be commercially available. CADD has significantly impacted this area of research. Further, the combination of CADD with Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) technologies to handle enormous amounts of biological data has reduced the time and cost associated with the drug development process. This review will discuss how CADD, AI, ML, and DL approaches help identify drug candidates and various other steps of the drug discovery process. It will also provide a detailed overview of the different in silico tools used and how these approaches interact.

Characterizing the ligand-binding affinity toward SARS-CoV-2 Mpro via physics- and knowledge-based approaches

Computational approaches, including physics- and knowledge-based methods, have commonly been used to determine the ligand-binding affinity toward SARS-CoV-2 main protease (Mpro or 3CLpro). Strong binding ligands can thus be suggested as potential inhibitors for blocking the biological activity of the protease. In this context, this paper aims to provide a short review of computational approaches that have recently been applied in the search for inhibitor candidates of Mpro. In particular, molecular docking and molecular dynamics (MD) simulations are usually combined to predict the binding affinity of thousands of compounds. Quantitative structure-activity relationship (QSAR) is the least computationally demanding and therefore can be used for large chemical collections of ligands. However, its accuracy may not be high. Moreover, the quantum mechanics/molecular mechanics (QM/MM) method is most commonly used for covalently binding inhibitors, which also play an important role in inhibiting the activity of SARS-CoV-2. Furthermore, machine learning (ML) models can significantly increase the searching space of ligands with high accuracy for binding affinity prediction. Physical insights into the binding process can then be confirmed via physics-based calculations. Integration of ML models into computational chemistry provides many more benefits and can lead to new therapies sooner.

Identifying Possible AChE Inhibitors from Drug-like Molecules via Machine Learning and Experimental Studies

Acetylcholinesterase (AChE) is one of the most important drug targets for Alzheimer's disease (AD) treatment. In this work, a machine learning model was trained to rapidly and accurately screen large chemical databases for the potential inhibitors of AChE. The obtained results were then validated via in vitro enzyme assay. Moreover, atomistic simulations including molecular docking and molecular dynamics simulations were then used to understand molecular insights into the binding process of ligands to AChE. In particular, two compounds including benzyl trifluoromethyl ketone and trifluoromethylstyryl ketone were indicated as highly potent inhibitors of AChE because they established IC₅₀ values of 0.51 and 0.33 μM, respectively. The obtained IC₅₀ of two compounds is significantly lower than that of galantamine (2.10 μM). The predicted log(BB) suggests that the compounds may be able to traverse the blood-brain barrier. A good agreement between computational and experimental studies was observed, indicating that the hybrid approach can enhance AD therapy.