Quantitative prediction of selectivity between the A1 and A2A adenosine receptors

Chemical library design, QSAR modeling and molecular dynamics simulations of naturally occurring coumarins as dual inhibitors of MAO-B and AChE

Coumarins are a highly privileged scaffold in medicinal chemistry. It is present in many natural products and is reported to display various pharmacological properties. A large plethora of compounds based on the coumarin ring system have been synthesized and were found to possess biological activities such as anticonvulsant, antiviral, anti-inflammatory, antibacterial, antioxidant as well as neuroprotective properties. Despite the wide activity spectrum of coumarins, its naturally occurring derivatives are yet to be investigated in detail. In the current study, a chemical library was created to assemble all chemical information related to naturally occurring coumarins from the literature. Additionally, a multi-stage virtual screening combining QSAR modeling, molecular docking, and ADMET prediction was conducted against monoamine oxidase B and acetylcholinesterase, two relevant targets known for their neuroprotective properties and 'disease-modifying' potential in Parkinson's and Alzheimer's disease. Our findings revealed ten coumarin derivatives that may act as dual-target drugs against MAO-B and AChE. Two coumarin candidates were selected from the molecular docking study: CDB0738 and CDB0046 displayed favorable interactions for both proteins as well as suitable ADMET profiles. The stability of the selected coumarins was assessed through 100 ns molecular dynamics simulations which revealed promising stability through key molecular interactions for CDB0738 to act as dual inhibitor of MAO-B and AChE. However, experimental studies are necessary to evaluate the bioactivity of the proposed candidate. The current results may generate an increasing interest in bioprospecting naturally occurring coumarins as potential candidates against relevant macromolecular targets by encouraging virtual screening studies against our chemical library.Communicated by Ramaswamy H. Sarma.

AI & experimental-based discovery and preclinical IND-enabling studies of selective BMX inhibitors for development of cancer therapeutics

The current work aims to design and provide a preliminary IND-enabling study of selective BMX inhibitors for cancer therapeutics development. BMX is an emerging target, more notably in oncological and immunological diseases. In this work, we have employed a predictive AI-based platform to design the selective inhibitors considering the novelty, IP prior protection, and drug-likeness properties. Furthermore, selected top candidates from the initial iteration of the design were synthesized and chemically characterized utilizing 1H NMR and LC-MS. Employing a panel of biochemical (enzymatic) and cancer cell lines, the selected molecules were tested against these assays. In addition, we used artificial intelligence to predict and evaluate several critical IND-focused physicochemical and pharmacokinetics values of the selected molecules. A secondary objective of the current work was also to validate the sole role of BMX in animal models known to be mediated by BMX. More than 50 molecules were designed in the present study employing five novel discovered scaffolds. Two molecules were nominated for further IND-focused studies. Compound II showed promising in-vitro activity against BMX in both enzymatic assays compared to other kinases and in cancer cell lines with known BMX overexpression. Interestingly, compound II showed very favorable physicochemical and pharmacokinetics properties as predicted by the used platforms. The animal study further confirmed the sole role of BMX in the disease model. The current work provides promising data on a selective BMX inhibitor as a potential lead for therapeutics development, and the asset is currently in the optimization stage. Notably, the current study shows a framework for a combined approach employing both AI and experimentation that can be used by academic labs in their research programs to more streamline programs into IND-focused to be bridged easily for further clinical development with industrial partners.

Pmf-cpi: assessing drug selectivity with a pretrained multi-functional model for compound-protein interactions

Compound-protein interactions (CPI) play significant roles in drug development. To avoid side effects, it is also crucial to evaluate drug selectivity when binding to different targets. However, most selectivity prediction models are constructed for specific targets with limited data. In this study, we present a pretrained multi-functional model for compound-protein interaction prediction (PMF-CPI) and fine-tune it to assess drug selectivity. This model uses recurrent neural networks to process the protein embedding based on the pretrained language model TAPE, extracts molecular information from a graph encoder, and produces the output from dense layers. PMF-CPI obtained the best performance compared to outstanding approaches on both the binding affinity regression and CPI classification tasks. Meanwhile, we apply the model to analyzing drug selectivity after fine-tuning it on three datasets related to specific targets, including human cytochrome P450s. The study shows that PMF-CPI can accurately predict different drug affinities or opposite interactions toward similar targets, recognizing selective drugs for precise therapeutics.Kindly confirm if corresponding authors affiliations are identified correctly and amend if any.Yes, it is correct.

AI-based identification of therapeutic agents targeting GPCRs: introducing ligand type classifiers and systems biology

Identifying ligands targeting G protein coupled receptors (GPCRs) with novel chemotypes other than the physiological ligands is a challenge for in silico screening campaigns. Here we present an approach that identifies novel chemotype ligands by combining structural data with a random forest agonist/antagonist classifier and a signal-transduction kinetic model. As a test case, we apply this approach to identify novel antagonists of the human adenosine transmembrane receptor type 2A, an attractive target against Parkinson's disease and cancer. The identified antagonists were tested here in a radio ligand binding assay. Among those, we found a promising ligand whose chemotype differs significantly from all so-far reported antagonists, with a binding affinity of 310 ± 23.4 nM. Thus, our protocol emerges as a powerful approach to identify promising ligand candidates with novel chemotypes while preserving antagonistic potential and affinity in the nanomolar range.

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.

pdCSM-GPCR: predicting potent GPCR ligands with graph-based signatures

MOTIVATION

G protein-coupled receptors (GPCRs) can selectively bind to many types of ligands, ranging from light-sensitive compounds, ions, hormones, pheromones and neurotransmitters, modulating cell physiology. Considering their role in many essential cellular processes, they are one of the most targeted protein families, with over a third of all approved drugs modulating GPCR signalling. Despite this, the large diversity of receptors and their multipass transmembrane architectures make the identification and development of novel specific, and safe GPCR ligands a challenge. While computational approaches have the potential to assist GPCR drug development, they have presented limited performance and generalization capabilities. Here, we explored the use of graph-based signatures to develop pdCSM-GPCR, a method capable of rapidly and accurately screening potential GPCR ligands.

RESULTS

Bioactivity data (IC50, EC50, Ki and Kd) for individual GPCRs were curated. After curation, we used the data for developing predictive models for 36 major GPCR targets, across 4 classes (A, B, C and F). Our models compose the most comprehensive computational resource for GPCR bioactivity prediction to date. Across stratified 10-fold cross-validation and blind tests, our approach achieved Pearson's correlations of up to 0.89, significantly outperforming previous methods. Interpreting our results, we identified common important features of potent GPCRs ligands, which tend to have bicyclic rings, leading to higher levels of aromaticity. We believe pdCSM-GPCR will be an invaluable tool to assist screening efforts, enriching compound libraries and ranking candidates for further experimental validation.

AVAILABILITY AND IMPLEMENTATION

pdCSM-GPCR predictive models and datasets used have been made available via a freely accessible and easy-to-use web server at http://biosig.unimelb.edu.au/pdcsm_gpcr/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics Advances online.