Drug Discovery Process Research Articles

The System of Self-Consistent Models: QSAR Analysis of Drug-Induced Liver Toxicity.

Removing a drug-like substance that can cause drug-induced liver injury from the drug discovery process is a significant task for medicinal chemistry. In silico models can facilitate this process. Semi-correlation is an approach to building in silico models representing the prediction in the active (1)-inactive (0) format. The so-called system of self-consistent models has been suggested as an approach for two tasks: (i) building up a model and (ii) estimating its predictive potential. However, this approach has been tested so far for regression models. Here, the approach is applied to building up and estimating a categorical hepatotoxicity model using the CORAL software. This new process yields good results: sensitivity = 0.77, specificity = 0.75, accuracy = 0.76, and Matthew correlation coefficient = 0.51 (all compounds) and sensitivity = 0.83, specificity = 0.81, accuracy = 0.83 and Matthew correlation coefficient = 0.63 (validation set).

A Quantitative Structure-Activity Relationship for Human Plasma Protein Binding: Prediction, Validation and Applicability Domain.

The purpose of this study was to develop a robust and externally predictive in silico QSAR-neural network model for predicting plasma protein binding of drugs. This model aims to enhance drug discovery processes by reducing the need for chemical synthesis and extensive laboratory testing. A dataset of 277 drugs was used to develop the QSAR-neural network model. The model was constructed using a Filter method to select 55 molecular descriptors. The validation set's external accuracy was assessed through the predictive squared correlation coefficient Q2 and the root mean squared error (RMSE). The developed QSAR-neural network model demonstrated robustness and good applicability domain. The external accuracy of the validation set was high, with a predictive squared correlation coefficient Q2 of 0.966 and a root mean squared error (RMSE) of 0.063. Comparatively, this model outperformed previously published models in the literature. The study successfully developed an advanced QSAR-neural network model capable of predicting plasma protein binding in human plasma for a diverse set of 277 drugs. This model's accuracy and robustness make it a valuable tool in drug discovery, potentially reducing the need for resource-intensive chemical synthesis and laboratory testing.

Explainability and white box in drug discovery.

Recently, artificial intelligence (AI) techniques have been increasingly used to overcome the challenges in drug discovery. Although traditional AI techniques generally have high accuracy rates, there may be difficulties in explaining the decision process and patterns. This can create difficulties in understanding and making sense of the outputs of algorithms used in drug discovery. Therefore, using explainable AI (XAI) techniques, the causes and consequences of the decision process are better understood. This can help further improve the drug discovery process and make the right decisions. To address this issue, Explainable Artificial Intelligence (XAI) emerged as a process and method that securely captures the results and outputs of machine learning (ML) and deep learning (DL) algorithms. Using techniques such as SHAP (SHApley Additive ExPlanations) and LIME (Locally Interpretable Model-Independent Explanations) has made the drug targeting phase clearer and more understandable. XAI methods are expected to reduce time and cost in future computational drug discovery studies. This review provides a comprehensive overview of XAI-based drug discovery and development prediction. XAI mechanisms to increase confidence in AI and modeling methods. The limitations and future directions of XAI in drug discovery are also discussed.

Computational approaches streamlining drug discovery.

Computer-aided drug discovery has been around for decades, although the past few years have seen a tectonic shift towards embracing computational technologies in both academia and pharma. This shift is largely defined by the flood of data on ligand properties and binding to therapeutic targets and their 3D structures, abundant computing capacities and the advent of on-demand virtual libraries of drug-like small molecules in their billions. Taking full advantage of these resources requires fast computational methods for effective ligand screening. This includes structure-based virtual screening of gigascale chemical spaces, further facilitated by fast iterative screening approaches. Highly synergistic are developments in deep learning predictions of ligand properties and target activities in lieu of receptor structure. Here we review recent advances in ligand discovery technologies, their potential for reshaping the whole process of drug discovery and development, as well as the challenges they encounter. We also discuss how the rapid identification of highly diverse, potent, target-selective and drug-like ligands to protein targets can democratize the drug discovery process, presenting new opportunities for the cost-effective development of safer and more effective small-molecule treatments.

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives.

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Phytochemical Screening, Antioxidant, Antibacterial, and α-Amylase Inhibitory Activity of Moringa oleifera Lam. Leaves

Moringa oleifera is a perennial deciduous plant abundant in tropical countries that contains many important bioactive compounds. This study aimed to evaluate phytochemical analysis, antioxidant, antibacterial, and α-amylase inhibitory activities of the methanol and hexane leaf extracts of the plant collected from Nepal. Phytochemical screening of the extracts revealed the presence of a wide spectrum of secondary metabolites such as alkaloids, flavonoids, phenolics, saponins, tannins, terpenoids, etc. Methanol and hexane extracts showed the presence of significant quantities of total phenolics (207.75± 2.75 mg GAE/g, and 137.09 ± 1.1 mg GAE/g) and total flavonoids (94.56 ± 1.88 mg QE/g, and 82.71 ± 1.47 mg QE/g) respectively. The methanol extract exhibited higher 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity. The half-maximal concentration causing 50% inhibition of the radical (IC50) of methanol and hexane extracts was 39.19 ± 0.33 and 61.07 ± 1.46 μg/mL respectively which are comparable to that of standard ascorbic acid (28.90 ± 0.24 μg/mL. Methanol extract of M. oleifera leaves showed moderate antibacterial activity against Staphylococcus aureus (ATCC25923), Bacillus cereus, and Klebsiella pneumonia (ATCC700603). In-vitro antidiabetic activity was performed by a starch-iodine method using α-amylase enzyme and methanol extract showed significant antidiabetic activity (IC50 value 31.78 ± 0.52 μg/mL). The results of this study corroborate the potential application of the plant in traditional medicine and the drug discovery process.

Improving drug-target affinity prediction via feature fusion and knowledge distillation.

Rapid and accurate prediction of drug-target affinity can accelerate and improve the drug discovery process. Recent studies show that deep learning models may have the potential to provide fast and accurate drug-target affinity prediction. However, the existing deep learning models still have their own disadvantages that make it difficult to complete the task satisfactorily. Complex-based models rely heavily on the time-consuming docking process, and complex-free models lacks interpretability. In this study, we introduced a novel knowledge-distillation insights drug-target affinity prediction model with feature fusion inputs to make fast, accurate and explainable predictions. We benchmarked the model on public affinity prediction and virtual screening dataset. The results show that it outperformed previous state-of-the-art models and achieved comparable performance to previous complex-based models. Finally, we study the interpretability of this model through visualization and find it can provide meaningful explanations for pairwise interaction. We believe this model can further improve the drug-target affinity prediction for its higher accuracy and reliable interpretability.

Determination of Total Phenolic and Flavonoid Content, Antidiabetic, and Antioxidant Activities of Leaves and Seeds Extracts of Eucalyptus robusta Sm. and Ageratina adenophora Spreng

The present study aimed at the determination of total phenolic and flavonoid content and biological activities of Eucalyptus robusta (Sm.) and Ageratina adenophora (Spreng.) growing in Kathmandu Nepal. People have been using these medicinal plants for many years against infectious diseases and to control diabetes. The extraction of plant secondary metabolites was done by the cold percolation method. The total phenolic (TPC) and flavonoid content (TFC) were quantified by the Folin-Ciocalteu phenol reagent and aluminium chloride colorimetric method. The α-amylase enzyme inhibition activity was performed to evaluate the antidiabetic property of plant extracts. The antioxidant potential of plant extracts was evaluated by DPPH (2,2-diphenyl- 1-picrylhydrazyl) radical scavenging assay. The methanol extract of Ageratina adenophora Spreng leaves is found rich in plant secondary metabolites of a yield percentage 36.83% whereas Eucalyptus robusta Sm. leaves and seeds have a yield percentage of 30.75% and 27.12% respectively. The extract of E. robusta leaves showed the highest phenolic content (200.89±6.67 mg gallic acid equivalent/g of dry extract) and A. adenophora Spreng. leaves extract showed the flavonoid content (0.49±0.02 mg quercetin equivalent/g of dry extract) among the three samples studied, respectively. The extract of E. robusta Sm. seeds showed the strongest DPPH radical scavenging activity with a half-maximal inhibitory concentration IC50 of 110.8±1.73 μg/mL. The extract of A. adenophora Spreng. was found potent towards α-amylase enzyme inhibition activity of IC50 16.05±0.24 μg/mL whereas E. robusta Sm. leaves and seeds extracts showed IC50 21.93±1.24 mg/mL and 21.82±0.09 mg/mL respectively. This study showed the leaves and seeds extracts of these two medicinal plants are found rich in phenolic and flavonoid compounds. These medicinal plants could be used to isolate the natural antioxidant and antidiabetic compounds that may be potential drug candidates in the future drug discovery process. This study supports providing scientific validation for using these medicinal plants against diabetes.

Machine learning and drug discovery for neglected tropical diseases

Neglected tropical diseases affect millions of individuals and cause loss of productivity worldwide. They are common in developing countries without the financial resources for research and drug development. With increased availability of data from high throughput screening, machine learning has been introduced into the drug discovery process. Models can be trained to predict biological activities of compounds before working in the lab. In this study, we use three publicly available, high-throughput screening datasets to train machine learning models to predict biological activities related to inhibition of species that cause leishmaniasis, American trypanosomiasis (Chagas disease), and African trypanosomiasis (sleeping sickness). We compare machine learning models (tree based models, naive Bayes classifiers, and neural networks), featurizing methods (circular fingerprints, MACCS fingerprints, and RDKit descriptors), and techniques to deal with the imbalanced data (oversampling, undersampling, class weight/sample weight).

SophosQM: Accurate Binding Affinity Prediction in Compound Optimization.

The optimization of compounds' binding affinity for a biological target is a crucial aspect of the drug development process. Being able to accurately predict binding energies in advance of synthesizing compounds would have a massive impact on the speed of the drug discovery process. The ideal binding affinity prediction method should combine accuracy, reliability, and speed. In this paper, we present SophosQM, a quantum mechanics (QM)-based approach, which can accurately predict the binding affinities of compounds to proteins. The binding affinity predictive models generated by SophosQM are based on the fragment molecular orbital (FMO) method to estimate the enthalpic component of the binding free energy, and a macroscopic descriptor, clog P, is used as an approximation of the entropic component. The affinity prediction is performed using multilinear regression, fitting the experimental values against the FMO-computed enthalpic term and clog P. The quality of the prediction can be assessed in terms of the correlation coefficient between experimental and predicted values. In this work, the method's reliability and accuracy are exemplified by applying SophosQM to 70 compounds binding to six different targets of pharmaceutical relevance. Overall, the results show a very satisfactory performance with a global correlation coefficient in the order of 0.9. Our predictions also show a satisfactory performance compared to data based on free energy perturbation. Finally, SophosQM can also be applied in high-throughput mode by using semiempirical QM methods to evaluate large portions of chemical space, while retaining a good level of accuracy, but decreasing the computing time to just a few seconds per compound.

The Application of New Approach Methodologies in Respiratory Disease Research: Their Role in Improving Translational Medicine from Bench to Bedside.

The SARS-CoV-2 outbreak focused global attention on the shortcomings of the drug discovery process. It led to its acceleration in several areas, particularly in the processes associated with the development and approval of COVID-19 vaccines. This situation contrasts with the low approval rates of new drugs for respiratory system diseases (e.g. asthma, chronic obstructive pulmonary disease, cancer, tuberculosis), which are leading causes of morbidity and mortality worldwide. In this context, innovation in respiratory system drug discovery is surely needed, and it is most likely to succeed through the use of preclinical models that are cost-effective, high-throughput and generate predictive human-relevant outcomes. Here, we highlight several non-animal new approach methodologies (NAMs) and their applications in respiratory research. We describe their potential uses for efficacy and toxicity assessments, to optimise the drug development process and reduce the high failure rates in clinical trials.

Retrospective Analysis of Chemical Structure-Based in silico Prediction of Primary Drug Target and Off-Targets

In early phases of the drug discovery process, evaluating the off-target pharmacology of a candidate drug is important when considering potential safety risks. Such off-target liabilities are most commonly evaluated using panels of in vitro pharmacology assays with strong association to well-defined toxicological events. In addition to in vitro panels, preliminary in silico evaluation is emerging as a valuable approach to support identification of potential off-target hits, even prior to synthesis of chemical material. To ascertain the utility of in silico target profiling, the predictive performance of a proprietary in silico predictive tool was evaluated against an in-house data set of 94 compounds with associated in vitro panel data, including binding inhibition and functional agonism/antagonism. Of the compounds tested, the primary target was predicted with 35% sensitivity. However, the sensitivity to predict the primary target decreased to 16% for a subset of compounds not reported within the Chemical Abstracts Service registry. For the known off-target hits for all tested compounds, the value of sensitivity was 16% for binding assays and 23% for functional assays. To better understand the applicability of the in silico off-target prediction, we performed in vitro binding assays, to evaluate five additional off-targets that were predicted by in silico but not covered by our standard off-target binding or functional panels. Although no new off-target hit was identified through this campaign, as technologies evolve, the in silico predictions could provide valuable insights to identify potential off-targets and mechanistic insights on target organ toxicities caused by compounds in in vivo studies.

Exploring the Patent Landscape and Regulatory Prospective on Pharmaceutical Cocrystals

Background: Cocrystals are not new, they have sparked considerable interest among scientists and the pharmaceutical business in the last decade. Cocrystals are multiphase formations composed of at least two particles that are held together by noncovalent bonds. Cocrystal offers unmatched physio-engineered attributes (like stability, melting point, taste concealment, dissolvability, purity, bioavailability, etc.) without changing the pharmacological capabilities of the drug. Recently, as pharmaceutical cocrystal development has increased, we have given more attention to the absurd state of cocrystals. Purpose: The purpose of the current review is to explore the patent perspective on pharmaceutical cocrystals. And to discuss the new regulations that came up from the U.S. Food and Drug Administration (USFDA) and European Medicines Agency (EMA). Methods: In order to accomplish the said objectives, literature was surveyed from GOOGLE PATENTS, GOOGLE SCHOLAR, PUBMED, EBSCO, etc. type for search engines for a detailed overview of the patentability and regulatory status of pharmaceutical cocrystals. Conclusions: The journey of pharmaceutical cocrystals is bit challenging and still going on. In addition, if attention is drawn on some challenging aspects such as scalability, reproducibility, herbal bioactives cocrystals and 3D printed cocrystals related preparation and stability challenges, it can prove to be a paradigm shift in drug discovery processes.

Predicting activatory and inhibitory drug-target interactions based on structural compound representations and genetically perturbed transcriptomes.

A computational approach to identifying drug-target interactions (DTIs) is a credible strategy for accelerating drug development and understanding the mechanisms of action of small molecules. However, current methods to predict DTIs have mainly focused on identifying simple interactions, requiring further experiments to understand mechanism of drug. Here, we propose AI-DTI, a novel method that predicts activatory and inhibitory DTIs by combining the mol2vec and genetically perturbed transcriptomes. We trained the model on large-scale DTIs with MoA and found that our model outperformed a previous model that predicted activatory and inhibitory DTIs. Data augmentation of target feature vectors enabled the model to predict DTIs for a wide druggable targets. Our method achieved substantial performance in an independent dataset where the target was unseen in the training set and a high-throughput screening dataset where positive and negative samples were explicitly defined. Also, our method successfully rediscovered approximately half of the DTIs for drugs used in the treatment of COVID-19. These results indicate that AI-DTI is a practically useful tool for guiding drug discovery processes and generating plausible hypotheses that can reveal unknown mechanisms of drug action.

ADME, Pharmacokinetic Scaling, Pharmacodynamic and Prediction of Human Dose and Regimen of Novel Antiviral Drugs.

The search for new drugs is an extremely time-consuming and expensive endeavour. Much of that time and money go into generating predictive human pharmacokinetic profiles from preclinical efficacy and safety animal data. These pharmacokinetic profiles are used to prioritize or minimize the attrition at later stages of the drug discovery process. In the area of antiviral drug research, these pharmacokinetic profiles are equally important for the optimization, estimation of half-life, determination of effective dose, and dosing regimen, in humans. In this article we have highlighted three important aspects of these profiles. First, the impact of plasma protein binding on two primary pharmacokinetic parameters-volume of distribution and clearance. Second, interdependence of primary parameters on unbound fraction of the drug. Third, the ability to extrapolate human pharmacokinetic parameters and concentration time profiles from animal profiles.

Artificial Intelligence in Drugs Discovery and Development

Artificial intelligence (AI) has the potential to transform drug discovery and development by accelerating the identification of new drug targets, improving the efficiency of drug discovery processes, and enabling personalized medicine. AI can help by analyzing large amounts of data, such as genetic data, protein structures, and disease pathways, to identify new drug targets. This can significantly speed up the drug discovery process and increase the success rate of drug development.

Aminoacyl tRNA Synthetases: Implications of Structural Biology in Drug Development against Trypanosomatid Parasites.

The ensemble of aminoacyl tRNA synthetases is regarded as a key component of the protein translation machinery. With the progressive increase in structure-based studies on tRNA synthetase-ligand complexes, the detailed picture of these enzymes is becoming clear. Having known their critical role in deciphering the genetic code in a living system, they have always been chosen as one of the important targets for development of antimicrobial drugs. Later on, the role of aminoacyl tRNA synthetases (aaRSs) on the survivability of trypanosomatids has also been validated. It became evident through several gene knockout studies that targeting even one of these enzymes affected parasitic growth drastically. Such successful studies have inspired researchers to search for inhibitors that could specifically target trypanosomal aaRSs, and their never-ending efforts have provided fruitful results. Taking all such studies into consideration, these macromolecules of prime importance deserve further investigation for the development of drugs that cure spectrum of infections caused by trypanosomatids. In this review, we have compiled advancements of over a decade that have taken place in the pursuit of devising drugs by using trypanosomatid aaRSs as a major target of interest. Several of these inhibitors work on an exemplary low concentration range without posing any threat to the mammalian cells which is a very critical aspect of the drug discovery process. Advancements have been made in terms of using structural biology as an important tool to analyze the architecture of the trypanosomatids aaRSs and concoction of inhibitors with augmented specificities toward their targets. Some of the inhibitors that have been tested on other parasites successfully but their efficacy has so far not been validated against these trypanosomatids have also been appended.

Carnosine Counteracts the Molecular Alterations Aβ Oligomers-Induced in Human Retinal Pigment Epithelial Cells.

Age-related macular degeneration (AMD) has been described as a progressive eye disease characterized by irreversible impairment of central vision, and unfortunately, an effective treatment is still not available. It is well-known that amyloid-beta (Aβ) peptide is one of the major culprits in causing neurodegeneration in Alzheimer's disease (AD). The extracellular accumulation of this peptide has also been found in drusen which lies under the retinal pigment epithelium (RPE) and represents one of the early signs of AMD pathology. Aβ aggregates, especially in the form of oligomers, are able to induce pro-oxidant (oxidative stress) and pro-inflammatory phenomena in RPE cells. ARPE-19 is a spontaneously arising human RPE cell line validated for drug discovery processes in AMD. In the present study, we employed ARPE-19 treated with Aβ oligomers, representing an in vitro model of AMD. We used a combination of methods, including ATPlite, quantitative real-time PCR, immunocytochemistry, as well as a fluorescent probe for reactive oxygen species to investigate the molecular alterations induced by Aβ oligomers. In particular, we found that Aβ exposure decreased the cell viability of ARPE-19 cells which was paralleled by increased inflammation (increased expression of pro-inflammatory mediators) and oxidative stress (increased expression of NADPH oxidase and ROS production) along with the destruction of ZO-1 tight junction protein. Once the damage was clarified, we investigated the therapeutic potential of carnosine, an endogenous dipeptide that is known to be reduced in AMD patients. Our findings demonstrate that carnosine was able to counteract most of the molecular alterations induced by the challenge of ARPE-19 with Aβ oligomers. These new findings obtained with ARPE-19 cells challenged with Aβ1-42 oligomers, along with the well-demonstrated multimodal mechanism of action of carnosine both in vitro and in vivo, able to prevent and/or counteract the dysfunctions elicited by Aβ oligomers, substantiate the neuroprotective potential of this dipeptide in the context of AMD pathology.

Predicting compound activity from phenotypic profiles and chemical structures

Predicting assay results for compounds virtually using chemical structures and phenotypic profiles has the potential to reduce the time and resources of screens for drug discovery. Here, we evaluate the relative strength of three high-throughput data sources—chemical structures, imaging (Cell Painting), and gene-expression profiles (L1000)—to predict compound bioactivity using a historical collection of 16,170 compounds tested in 270 assays for a total of 585,439 readouts. All three data modalities can predict compound activity for 6–10% of assays, and in combination they predict 21% of assays with high accuracy, which is a 2 to 3 times higher success rate than using a single modality alone. In practice, the accuracy of predictors could be lower and still be useful, increasing the assays that can be predicted from 37% with chemical structures alone up to 64% when combined with phenotypic data. Our study shows that unbiased phenotypic profiling can be leveraged to enhance compound bioactivity prediction to accelerate the early stages of the drug-discovery process.

Personal Care Products as a Contributing Factor to Antimicrobial Resistance: Current State and Novel Approach to Investigation.

Antimicrobial resistance (AMR) is one of the world's industrialized nations' biggest issues. It has a significant influence on the ecosystem and negatively affects human health. The overuse of antibiotics in the healthcare and agri-food industries has historically been defined as a leading factor, although the use of antimicrobial-containing personal care products plays a significant role in the spread of AMR. Lotions, creams, shampoos, soaps, shower gels, toothpaste, fragrances, and other items are used for everyday grooming and hygiene. However, in addition to the primary ingredients, additives are included to help preserve the product by lowering its microbial load and provide disinfection properties. These same substances are released into the environment, escaping traditional wastewater treatment methods and remaining in ecosystems where they contact microbial communities and promote the spread of resistance. The study of antimicrobial compounds, which are often solely researched from a toxicological point of view, must be resumed considering the recent discoveries, to highlight their contribution to AMR. Parabens, triclocarban, and triclosan are among the most worrying chemicals. To investigate this issue, more effective models must be chosen. Among them, zebrafish is a crucial study system because it allows for the assessment of both the risks associated with exposure to these substances as well as environmental monitoring. Furthermore, artificial intelligence-based computer systems are useful in simplifying the handling of antibiotic resistance data and speeding up drug discovery processes.