Search

Hepatitis B and C viruses (HBV and HCV) are significant causes of chronic liver diseases, with approximately 350 million infections globally. To accelerate the finding of effective treatment options, we introduce HBCVTr, a novel ligand-based drug design (LBDD) method for predicting the inhibitory activity of small molecules against HBV and HCV. HBCVTr employs a hybrid model consisting of double encoders of transformers and a deep neural network to learn the relationship between small molecules’ simplified molecular-input line-entry system (SMILES) and their antiviral activity against HBV or HCV. The prediction accuracy of HBCVTr has surpassed baseline machine learning models and existing methods, with R-squared values of 0.641 and 0.721 for the HBV and HCV test sets, respectively. The trained models were successfully applied to virtual screening against 10 million compounds within 240 h, leading to the discovery of the top novel inhibitor candidates, including IJN04 for HBV and IJN12 and IJN19 for HCV. Molecular docking and dynamics simulations identified IJN04, IJN12, and IJN19 target proteins as the HBV core antigen, HCV NS5B RNA-dependent RNA polymerase, and HCV NS3/4A serine protease, respectively. Overall, HBCVTr offers a new and rapid drug discovery and development screening method targeting HBV and HCV. [ABSTRACT FROM AUTHOR]

A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 105 molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale. [ABSTRACT FROM AUTHOR]

Background: In 2003, the first case of severe acute respiratory syndrome coronavirus (SARS-CoV) was recorded. Coronaviruses (CoVs) have caused a major outbreak of human fatal pneumonia. Currently, there is no specific drug or treatment for diseases caused by SARS CoV 2. Computational approach that adopts dynamic models is widely accepted as indispensable tool in drug design but yet to be exploited in covid-19 in Zaria, Nigeria. In this study, steps were taken to advance on the successful achievements in the field of covid-19 drug, with the aid of in silico drug design technique, to create novel inhibitor drug candidates with better activity. In this study, one thousand human immunodeficiency virus (HIV1) antiviral chemical compounds from www.bindingBD.org were docked on the SARS CoV 2 main protease protein data bank identification number 6XBH (PDB ID: 6XBH) and the molecular docking score were ranked in order to identify the compounds with the highest inhibitory effects, and easy selection for future studies. Results: The docking studies showed some interesting results. Inhibitors with Index numbers 331, 741, and 819 had the highest binding affinity. Similarly, inhibitors with Index number 441, 847, and 46 had the lowest hydrogen bond energy. Inhibitor with index number 331 was reported with the lowest value (− 48.38kCal/mol). Five new compounds were designed from the selected six (6) compounds with the best binding score giving a total of thirty (30) novel compounds. The low binding energy of inhibitor with index no. 847b is unique, as most of the interaction energies are of H-bond type with amino acids (Thr26, Gly143, Ser144, Cys145, Glu166, Gln189, Hie164, Met49, Thr26, Thr25, Thr190, Asn142, Met165) resulting in an overall negative value (−16.31 kCal/mol) making it the best of all the newly designed inhibitors. Conclusions: The novel inhibitor is 2-(2-(5-amino-2-((((3-aminobenzyl)oxy)carbonyl)amino)-5-oxopentanamido)-4-(2-(tert-butyl)-4-oxo-4-(pentan-3-ylamino) butanamido)-3-hydroxybutyl) benzoic acid. The improvement it has over the parent inhibitor is from the primary amine group attached to meta position of first benzene ring and the carboxyl group attached to the ortho position of the second benzene ring. The molecular dynamics studies also show that the novel inhibitor remains stable after the study. This result makes it a better drug candidate against SARS CoV 2 main protease when compared with the co-crystallized inhibitor or any of the 1000 docked inhibitors. [ABSTRACT FROM AUTHOR]

Abelson kinase (c-Abl) is a non-receptor tyrosine kinase involved in several biological processes essential for cell differentiation, migration, proliferation, and survival. This enzyme's activation might be an alternative strategy for treating diseases such as neutropenia induced by chemotherapy, prostate, and breast cancer. Recently, a series of compounds that promote the activation of c-Abl has been identified, opening a promising ground for c-Abl drug development. Structure-based drug design (SBDD) and ligand-based drug design (LBDD) methodologies have significantly impacted recent drug development initiatives. Here, we combined SBDD and LBDD approaches to characterize critical chemical properties and interactions of identified c-Abl's activators. We used molecular docking simulations combined with tree-based machine learning models—decision tree, AdaBoost, and random forest to understand the c-Abl activators' structural features required for binding to myristoyl pocket, and consequently, to promote enzyme and cellular activation. We obtained predictive and robust models with Matthews correlation coefficient values higher than 0.4 for all endpoints and identified characteristics that led to constructing a structure–activity relationship model (SAR). [ABSTRACT FROM AUTHOR]

Deep generative models have shown the ability to devise both valid and novel chemistry, which could significantly accelerate the identification of bioactive compounds. Many current models, however, use molecular descriptors or ligand-based predictive methods to guide molecule generation towards a desirable property space. This restricts their application to relatively data-rich targets, neglecting those where little data is available to sufficiently train a predictor. Moreover, ligand-based approaches often bias molecule generation towards previously established chemical space, thereby limiting their ability to identify truly novel chemotypes. In this work, we assess the ability of using molecular docking via Glide—a structure-based approach—as a scoring function to guide the deep generative model REINVENT and compare model performance and behaviour to a ligand-based scoring function. Additionally, we modify the previously published MOSES benchmarking dataset to remove any induced bias towards non-protonatable groups. We also propose a new metric to measure dataset diversity, which is less confounded by the distribution of heavy atom count than the commonly used internal diversity metric. With respect to the main findings, we found that when optimizing the docking score against DRD2, the model improves predicted ligand affinity beyond that of known DRD2 active molecules. In addition, generated molecules occupy complementary chemical and physicochemical space compared to the ligand-based approach, and novel physicochemical space compared to known DRD2 active molecules. Furthermore, the structure-based approach learns to generate molecules that satisfy crucial residue interactions, which is information only available when taking protein structure into account. Overall, this work demonstrates the advantage of using molecular docking to guide de novo molecule generation over ligand-based predictors with respect to predicted affinity, novelty, and the ability to identify key interactions between ligand and protein target. Practically, this approach has applications in early hit generation campaigns to enrich a virtual library towards a particular target, and also in novelty-focused projects, where de novo molecule generation either has no prior ligand knowledge available or should not be biased by it. [ABSTRACT FROM AUTHOR]

Background: A series of known Food and Drug Administration (FDA) approved anticancer drugs were collected from the literature and docked against mTOR receptor which has been identified in present time as a target for therapeutic anticancer agents. The compounds binding affinity were calculated after minimising the interaction within the binding pockets' of the mTOR (4JT6) receptor. Results: The result shows that PF-04691502 ligand best inhibited mTOR while occupying the Adenosine triphosphate (ATP)-binding site on the receptor. PF-04691502 had the best binding affinity with a reported value of − 39.261 kcal/mol, and a hydrogen bond energy contribution of − 8.326 kcal/mol. Polamid529 is also found to have a good binding affinity of − 36.75 kcal/mol with the receptor, but was less significant than that calculated for the reference or standard inhibitor (X6K) used (− 37.862 kcal/mol). Further analysis revealed that Palomid529 formed a more stable complex with the receptor than torin2 and X6K due to the significant hydrogen bond contributions it adds to its overall binding score. Conclusion: PF-04691502 ligand was identified as the best inhibitor due to its high binding affinity for mTOR and should be considered as the best alternative to the reference inhibitor X6K. [ABSTRACT FROM AUTHOR]

Recently, there has been increasing interest in new modalities such as therapeutic antibodies and gene therapy at a number of pharmaceutical companies. Moreover, in small-molecule drug discovery at such companies, efforts have focused on hard-to-drug targets such as inhibiting protein–protein interactions. Biomolecular NMR spectroscopy has been used in drug discovery in a variety of ways, such as for the reliable detection of binding and providing three-dimensional structural information for structure-based drug design. The advantages of using NMR spectroscopy have been known for decades (Jahnke in J Biomol NMR 39:87–90, (2007); Gossert and Jahnke in Prog Nucl Magn Reson Spectrosc 97:82–125, (2016)). For tackling hard-to-drug targets and increasing the success in discovering drug molecules, in-depth analysis of drug–target protein interactions performed by biophysical methods will be more and more essential. Here, we review the advantages of NMR spectroscopy as a key technology of biophysical methods and also discuss issues such as using cutting-edge NMR spectrometers and increasing the demand of utilizing conformational dynamics information for promoting small-molecule drug discovery. [ABSTRACT FROM AUTHOR]