Development of quantitative structure-activity relationship models to predict potential nephrotoxic ingredients in traditional Chinese medicines

In silico prediction of drug-induced nephrotoxicity: current progress and pitfalls

INTRODUCTION

Due to its role in absorption and metabolism, the kidney is an important target for drug toxicity. Drug-induced nephrotoxicity (DIN) presents a significant challenge in clinical practice and drug development. Conventional methods for assessing nephrotoxicity have limitations, highlighting the need for innovative approaches. In recent years, in silico methods have emerged as promising tools for predicting DIN.

AREAS COVERED

A literature search was performed using PubMed and Web of Science, from 2013 to February 2023 for this review. This review provides an overview of the current progress and pitfalls in the in silico prediction of DIN, which discusses the principles and methodologies of computational models.

EXPERT OPINION

Despite significant advancements, this review identified issues accentuates the pivotal imperatives of data fidelity, model optimization, interdisciplinary collaboration, and mechanistic comprehension in sculpting the vista of DIN prediction. Integration of multiple data sources and collaboration between disciplines are essential for improving predictive models. Ultimately, a holistic approach combining computational, experimental, and clinical methods will enhance our understanding and management of DIN.

Data-driven toxicity prediction in drug discovery: Current status and future directions

Early toxicity assessment plays a vital role in the drug discovery process on account of its significant influence on the attrition rate of candidates. Recently, constant upgrading of information technology has greatly promoted the continuous development of toxicity prediction. To give an overview of the current state of data-driven toxicity prediction, we reviewed relevant studies and summarized them in three main respects: the features and difficulties of toxicity prediction, the evolution of modeling approaches, and the available tools for toxicity prediction. For each part, we expound the research status, existing challenges, and feasible solutions. Finally, several new directions and suggestions for toxicity prediction are also put forward.

In silico toxicity studies of traditional Chinese herbal medicine: A mini review

With the availability of public databases that store compound-target/compound-toxicity information, and Traditional Chinese medicine (TCM) databases, in silico approaches are used in toxicity studies of TCM herbal medicine. Here, three in silico approaches for toxicity studies were reviewed, which include machine learning, network toxicology and molecular docking. For each method, its application and implementation e.g., single classifier vs. multiple classifier, single compound vs. multiple compounds, validation vs. screening, were explored. While these methods provide data-driven toxicity prediction that is validated in vitro and/or in vivo, it is still limited to single compound analysis. In addition, these methods are limited to several types of toxicity, with hepatotoxicity being the most dominant. Future studies involving the testing of combination of compounds on the front end i.e., to generate data for in silico modeling, and back end i.e., validate findings from prediction models will advance the in silico toxicity modeling of TCM compounds.

CORAL Models for Drug-Induced Nephrotoxicity

Drug-induced nephrotoxicity is a major cause of kidney dysfunction with potentially fatal consequences. The poor prediction of clinical responses based on preclinical research hampers the development of new pharmaceuticals. This emphasises the need for new methods for earlier and more accurate diagnosis to avoid drug-induced kidney injuries. Computational predictions of drug-induced nephrotoxicity are an attractive approach to facilitate such an assessment and such models could serve as robust and reliable replacements for animal testing. To provide the chemical information for computational prediction, we used the convenient and common SMILES format. We examined several versions of so-called optimal SMILES-based descriptors. We obtained the highest statistical values, considering the specificity, sensitivity and accuracy of the prediction, by applying recently suggested atoms pairs proportions vectors and the index of ideality of correlation, which is a special statistical measure of the predictive potential. Implementation of this tool in the drug development process might lead to safer drugs in the future.

Machine Learning Approaches in Traditional Chinese Medicine: A Systematic Review

Machine learning (ML), as a branch of artificial intelligence, acquires the potential and meaningful rules from the mass of data via diverse algorithms. Owing to all research of traditional Chinese medicine (TCM) belonging to the digitalization of clinical records or experimental works, a massive and complex amount of data has become an inextricable part of the related studies. It is thus not surprising that ML approaches, as novel and efficient tools to mine the useful knowledge from data, have created inroads in a diversity of scopes of TCM over the past decade of years. However, by browsing lots of literature, we find that not all of the ML approaches perform well in the same field. Upon further consideration, we infer that the specificity may inhere between the ML approaches and their applied fields. This systematic review focuses its attention on the four categories of ML approaches and their eight application scopes in TCM. According to the function, ML approaches are classified into four categories, including classification, regression, clustering, and dimensionality reduction, and into 14 models as follows in more detail: support vector machine, least square-support vector machine, logistic regression, partial least squares regression, k-means clustering, hierarchical cluster analysis, artificial neural network, back propagation neural network, convolutional neural network, decision tree, random forest, principal component analysis, partial least squares-discriminant analysis, and orthogonal partial least squares-discriminant analysis. The eight common applied fields are divided into two parts: one for TCM, such as the diagnosis of diseases, the determination of syndromes, and the analysis of prescription, and the other for the related researches of Chinese herbal medicine, such as the quality control, the identification of geographic origins, the pharmacodynamic material basis, the medicinal properties, and the pharmacokinetics and pharmacodynamics. Additionally, this paper discusses the function and feature difference among ML approaches when they are applied to the corresponding fields via comparing their principles. The specificity of each approach to its applied fields has also been affirmed, whereby laying a foundation for subsequent studies applying ML approaches to TCM.

In Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity

Drug induced nephrotoxicity is a major clinical challenge, and it is always associated with higher costs for the pharmaceutical industry and due to detection during the late stages of drug development. It is desirable for improving the health outcomes for patients to distinguish nephrotoxic structures at an early stage of drug development. In this study, we focused on in silico prediction and insights into the structural basis of drug induced nephrotoxicity, based on reliable data on human nephrotoxicity. We collected 565 diverse chemical structures, including 287 nephrotoxic drugs on humans in the real world, and 278 non-nephrotoxic approved drugs. Several different machine learning and deep learning algorithms were employed for in silico model building. Then, a consensus model was developed based on three best individual models (RFR_QNPR, XGBOOST_QNPR, and CNF). The consensus model performed much better than individual models on internal validation and it achieved prediction accuracy of 86.24% external validation. The results of analysis of molecular properties differences between nephrotoxic and non-nephrotoxic structures indicated that several key molecular properties differ significantly, including molecular weight (MW), molecular polar surface area (MPSA), AlogP, number of hydrogen bond acceptors (nHBA), molecular solubility (LogS), the number of rotatable bonds (nRotB), and the number of aromatic rings (nAR). These molecular properties may be able to play an important part in the identification of nephrotoxic chemicals. Finally, 87 structural alerts for chemical nephrotoxicity were mined with f-score and positive rate analysis of substructures from Klekota-Roth fingerprint (KRFP). These structural alerts can well identify nephrotoxic drug structures in the data set. The in silico models and the structural alerts could be freely accessed via https://ochem.eu/article/140251 and http://www.sapredictor.cn, respectively. We hope the results should provide useful tools for early nephrotoxicity estimation in drug development.

Phytochemical content and potential health applications of pecan [Carya illinoinensis (Wangenh) K. Koch] nutshell

BACKGROUND

The pecan nutshell contains phytochemicals with various biological activities that are potentially useful in the prevention or treatment of diseases such as cancer, diabetes, and metabolic imbalances associated with heart diseases.

OBJECTIVE

To update this topic by means of a literature review and include those that contribute to the knowledge of the chemical composition and biological activities of pecan nutshell, particularly of those related to the therapeutic potential against some chronic degenerative diseases associated with oxidative stress.

METHOD

Exhaustive and detailed review of the existing literature using electronic databases.

CONCLUSION

The pecan nutshell is a promising natural product with pharmaceutical uses in various diseases. However, additional research related to the assessment of efficient extraction methods and characterization, particularly the evaluation of the mechanisms of action in new in vivo models, is necessary to confirm these findings and development of new drugs with therapeutic use.

Preliminary screening of the potential active ingredients in traditional Chinese medicines using the Ussing chamber model combined with HPLC-PDA-MS

An in vitro intestinal absorption model combined with high-performance liquid chromatography-photo diode array-tandem mass spectrometry (HPLC-PDA-MS) was used for preliminary screening of potential active ingredients from complex multi-component traditional Chinese medicine (TCM) system. Oral administration is one of the main administration methods for TCMs. Only the ingredients that could be absorbed have the opportunity to play a role. Thus, these were defined as potential active ingredients. Studying of intestinal absorption can provide a theoretical basis for the mechanism of TCMs. The Caco-2 cell model, the everted rat gut sac model, and the Ussing chamber model were established for TCMs. The degree of anastomosis between the in vitro intestinal model and the actual intestinal absorption of TCMs were evaluated by the gavage method in rats. The Ussing chamber model was best fit for oral experiments in rats and was selected as the research means to preliminarily screen potential active ingredients from eight TCMs, including Salvia miltiorrhiza Bunge, Astragalus propinquus Schischkin, Plantago asiatica L, Fallopia multiflora (Thunb.) Harald, Epimedium brevicornu Maxim, Moutan Cortex, Citrus reticulata Blanco, and Panax notoginseng (Burkill) F. H. Chen ex C. H. Chow. A total of 44 components were absorbed and screened as the potential active ingredients from the 80 components identified in eight TCMs by HPLC-PDA-MS.

Thermodynamics-Based Model Construction for the Accurate Prediction of Molecular Properties From Partition Coefficients

Developing models for predicting molecular properties of organic compounds is imperative for drug development and environmental safety; however, development of such models that have high predictive power and are independent of the compounds used is challenging. To overcome the challenges, we used a thermodynamics-based theoretical derivation to construct models for accurately predicting molecular properties. The free energy change that determines a property equals the sum of the free energy changes (ΔG_Fs) caused by the factors affecting the property. By developing or selecting molecular descriptors that are directly proportional to ΔG_Fs, we built a general linear free energy relationship (LFER) for predicting the property with the molecular descriptors as predictive variables. The LFER can be used to construct models for predicting various specific properties from partition coefficients. Validations show that the models constructed according to the LFER have high predictive power and their performance is independent of the compounds used, including the models for the properties having little correlation with partition coefficients. The findings in this study are highly useful for applications in drug development and environmental safety.

Predicting the potential toxicity of 26 components in Cassiae semen using in silico and in vitro approaches

•

A combination of in silico and in vitro methods was applied.

•

The potential toxicity of 26 components isolated from Cassiae semen is predicted.

•

Six compounds were predicted toxic to liver & ten compounds toxic to kidney.

•

Special anthraquinones and anthraquinone-glucosides are potential toxicants.

•

Specific group of anthraquinones influences hepatic or renal cytotoxicity.

Cassiae semen are dried and ripe seeds of Cassia obtusifolia L. or Cassia tora L. (Fabaceae) and have been made into roasted tea or used as a traditional medicine in Asian countries. However, it was reported to result in liver and renal toxicity. The components of Cassiae semen that induce hepatotoxicity or nephrotoxicity remain unknown. In the present study, we evaluate the potential toxicity of 26 newly isolated compounds from Cassiae semen using quantitative structure–activity relationship (QSAR) methods and co-culture of hepatic and renal cell approaches, and we aim to illustrate the relationship between the structural characteristics and cytotoxicity by general linear models (GLMs). Both the QSAR models and co-culture of hepatic and renal cell systems predicted that 6 compounds were potentially hepatotoxic, 10 compounds were potentially nephrotoxic, and specific anthraquinones and anthraquinone-glucosides were potential toxicants in Cassiae semen. Specific groups such as –OH and –OCH₃ at the R1, R2, R3, and R7 positions influenced the cytotoxicity.

Fast Identification of Adverse Drug Reactions (ADRs) of Digestive and Nervous Systems of Organic Drugs by In Silico Models

This study aimed to discover concurrences of adverse drug reactions (ADRs) and derive models of the most frequent items of ADRs based on the SIDER database, which included 1430 marketed drugs and 5868 ADRs. First, common ADRs of organic drugs were manually reclassified according to side effects in the human system and followed by an association rule analysis, which found ADRs of digestive and nervous systems often occurred at the same time with a good association rule. Then, three algorithms, linear discriminant analysis (LDA), support vector machine (SVM) and deep learning, were used to derive models of ADRs of digestive and nervous systems based on 497 organic monomer drugs and to identify key structural features in defining these ADRs. The statistical results indicated that these kinds of QSAR models were good tools for screening ADRs of digestive and nervous systems, which gave the ROC AUC values of 81.5%, 98.9%, 91.5%, 69.5%, 78.4% and 78.8%, respectively. Then, these models were applied to investigate ADRs of 1536 organic compounds with four phase and zero rule-of-five (RO5) violations from the ChEMBL database. Based on the consensus ADRs’ predictions of models, 58.1% and 42.6% of compounds were predicted to cause these two ADRs, respectively, indicating the significance of initial assessment of ADRs in early drug discovery.

Potential of Raman spectroscopy in facilitating pharmaceutical formulations development - An AI perspective

Drug development is time-consuming and inherently possesses a high failure rate. Pharmaceutical formulation development is the bridge that links a new chemical entity (NCE) to pre-clinical and clinical trials, and has a high impact on the efficacy and safety of the final drug product. Further, the time required for this process is escalating as formulation techniques are becoming more complicated due to the rising demands for drug products with better efficacy and patient compliance, as well as the inherent difficulties of addressing the unfavorable properties of NCEs such as low water solubility. The advent of artificial intelligence (AI) provides possibilities to accelerate the drug development process. In this review, we first examine applications of AI methods in different types of pharmaceutical formulations and formulation techniques. Moreover, as availability of data is the engine for the advancement of AI, we then suggest a potential way (i.e. applying Raman spectroscopy) for faster high-quality data gathering from formulations. Raman techniques have the capability of analyzing the composition and distribution of components and the physicochemical properties thereof within formulations, which are prominent factors governing drug dissolution profiles and subsequently bioavailability. Thus, useful information can be obtained bridging formulation development to the final product quality.

Web-based online resources about adverse interactions or side effects associated with complementary and alternative medicine: a systematic review, summarization and quality assessment

BACKGROUND

Given an increased global prevalence of complementary and alternative medicine (CAM) use, healthcare providers commonly seek CAM-related health information online. Numerous online resources containing CAM-specific information exist, many of which are readily available/accessible, containing information shareable with their patients. To the authors' knowledge, no study has summarized nor assessed the quality of content contained within these online resources for at least a decade, specifically pertaining to information about adverse effects or interactions.

METHODS

This study provides summaries of web-based online resources that provide safety information on potential interactions or adverse effects of CAM. Specifically, clinicians are the intended users of these online resources containing patient information which they can then disseminate to their patients. All online resources were assessed for content quality using the validated rating tool, DISCERN.

RESULTS

Of 21 articles identified in our previously published scoping review, 23 online resources were eligible. DISCERN assessments suggests that online resources containing CAM-specific information vary in quality. Summed DISCERN scores had a mean of 56.13 (SD = 10.25) out of 75. Online resources with the highest total DISCERN scores across all questions included Micromedex (68.50), Merck Manual (67.50) and Drugs.com (66.50). Online resources with the lowest total scores included Drug Information (33.00), Caremark Drug Interactions (42.50) and HIV Drug Interactions (43.00). The DISCERN questions that received the highest mean score across all online resources referred to whether the risks were described for each treatment (4.66), whether the aims were clear (4.58), whether the source achieved those aims (4.58), and whether the website referred to areas of uncertainty (4.58). The DISCERN questions that received the lowest mean score across all online resources assessed whether there was discussion about no treatment being used (1.29) and how treatment choices would affect quality of life (2.00).

CONCLUSION

This study provides a comprehensive list of online resources containing CAM-specific information. Informed by the appraisal of these resources, this study provides a summarized list of high quality, evidence-based, online resources about CAM and CAM-related adverse effects. This list of recommended resources can thereby serve as a useful reference for clinicians, researchers, and patients.

eHealth technologies assisting in identifying potential adverse interactions with complementary and alternative medicine (CAM) or standalone CAM adverse events or side effects: a scoping review

BACKGROUND

While there are several existing eHealth technologies for drug-drug interactions and stand-alone drug adverse effects, it appears that considerably less attention is focussed on that of complementary and alternative medicine (CAM). Despite poor knowledge of their potential interactions and side effects, many patients use CAM. This justifies the need to identify what eHealth technologies are assisting in identifying potential 1) adverse drug interactions with CAM, 2) adverse CAM-CAM interactions or 3) standalone CAM adverse events or side effects.

METHODS

A scoping review was conducted to identify eHealth technologies assisting in identifying potential adverse interactions with CAM or standalone CAM adverse events or side effects, following Arksey and O'Malley's five-stage scoping review framework. MEDLINE, EMBASE, and AMED databases and the Canadian Agency for Drugs and Technologies in Health website were systematically searched. Eligible articles had to have assessed or referenced an eHealth technology assisting in identifying potential one or more of the three aforementioned items. We placed no eligibility restrictions on type of eHealth technology.

RESULTS

Searches identified 3467 items, of which 2763 were unique, and 2674 titles and abstracts were eliminated, leaving 89 full-text articles to be considered. Of those, 48 were not eligible, leaving a total of 41 articles eligible for review. From these 41 articles, 69 unique eHealth technologies meeting our eligibility criteria were identified. Themes which emerged from our analysis included the following: the lack of recent reviews of CAM-related healthcare information; a large number of databases; and the presence of government adverse drug/event surveillance.

CONCLUSIONS

The present scoping review is the first, to our knowledge, to provide a descriptive map of the literature and eHealth technologies relating to our research question. We highlight that while an ample number of resources are available to healthcare providers, researchers, and patients, we caution that the quality and update frequency for many of these resources vary widely, and until formally assessed, remain unknown. We identify that a need exists to conduct an updated and systematically-searched review of CAM-related healthcare or research resources, as well as develop guidance documents associated with the development and evaluation of CAM-related eHealth technologies.

Digital Pharmaceutical Sciences

Artificial intelligence (AI) and machine learning, in particular, have gained significant interest in many fields, including pharmaceutical sciences. The enormous growth of data from several sources, the recent advances in various analytical tools, and the continuous developments in machine learning algorithms have resulted in a rapid increase in new machine learning applications in different areas of pharmaceutical sciences. This review summarizes the past, present, and potential future impacts of machine learning technologies on different areas of pharmaceutical sciences, including drug design and discovery, preformulation, and formulation. The machine learning methods commonly used in pharmaceutical sciences are discussed, with a specific emphasis on artificial neural networks due to their capability to model the nonlinear relationships that are commonly encountered in pharmaceutical research. AI and machine learning technologies in common day-to-day pharma needs as well as industrial and regulatory insights are reviewed. Beyond traditional potentials of implementing digital technologies using machine learning in the development of more efficient, fast, and economical solutions in pharmaceutical sciences are also discussed.

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

Drug-induced liver injury (DILI) remains one of the challenges in the safety profile of both authorized and candidate drugs, and predicting hepatotoxicity from the chemical structure of a substance remains a task worth pursuing. Such an approach is coherent with the current tendency for replacing non-clinical tests with in vitro or in silico alternatives. In 2016, a group of researchers from the FDA published an improved annotated list of drugs with respect to their DILI risk, constituting “the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans” (DILIrank). This paper is one of the few attempting to predict liver toxicity using the DILIrank dataset. Molecular descriptors were computed with the Dragon 7.0 software, and a variety of feature selection and machine learning algorithms were implemented in the R computing environment. Nested (double) cross-validation was used to externally validate the models selected. A total of 78 models with reasonable performance were selected and stacked through several approaches, including the building of multiple meta-models. The performance of the stacked models was slightly superior to other models published. The models were applied in a virtual screening exercise on over 100,000 compounds from the ZINC database and about 20% of them were predicted to be non-hepatotoxic.

Online coupling of the Ussing chamber, solid-phase extraction and high-performance liquid chromatography for screening and analysis of active constituents of traditional Chinese medicines

A semi-automated online platform was established successfully for preliminary screening of potential active flavonoids of traditional Chinese medicines (TCMs) in multicomponent system. Online coupling of the in vitro intestinal absorption model, solid phase extraction (SPE) and high-performance liquid chromatography (HPLC) was actualized at the first time. The Ussing chamber model was selected to absorb the constituents of TCMs. A mini chromatographic column filled with C18 was used as a SPE column for online enrichment of flavonoids. HPLC was applied to analyze the constituents screened by platform. With the use of rutin as a model flavonoid, the specifications of SPE column, eluting solvent, elution time and flow rate of eluent were systematically investigated to optimize online system. Under the optimal conditions, the linear range of rutin was 0.125-368 µg/mL with the correlation coefficient (R²) greater than 0.9947. The limit of detection (LOD) was as low as 0.0500 µg/mL and the limit of quantification (LOQ) was 0.125 µg/mL. The intra-day relative standard deviation (RSD) and inter-day RSD was 2.5% and 3.8%, respectively. The recoveries of rutin in the intestinal absorption samples ranged from 93.2% to 94.0%. Finally, the online system was applied to screen the potential active flavonoids of Scutellaria baicalensis Georgi (Huangqin, HQ) and Polygoni Cuspidati Rhizoma et Radix (Huzhang, HZ). A total of 14 flavonoids of these two TCMs were identified by ultra-performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS), and 12 flavonoids of them were screened as the potential active components by online Ussing chamber-SPE-HPLC. In comparison with offline method and gavage in rats, the online system can screen the active constituents from TCMs more accurately and completely. The results demonstrated that the online system was reliable and sufficiently accurate for screening and determination of the potential active flavonoids of TCMs in multicomponent system.

Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-src Tyrosine Kinase

A prototype of a family of at least nine members, cellular Src tyrosine kinase is a therapeutically interesting target because its inhibition might be of interest not only in a number of malignancies, but also in a diverse array of conditions, from neurodegenerative pathologies to certain viral infections. Computational methods in drug discovery are considerably cheaper than conventional methods and offer opportunities of screening very large numbers of compounds in conditions that would be simply impossible within the wet lab experimental settings. We explored the use of global quantitative structure-activity relationship (QSAR) models and molecular ligand docking in the discovery of new c-src tyrosine kinase inhibitors. Using a dataset of 1038 compounds from ChEMBL database, we developed over 350 QSAR classification models. A total of 49 models with reasonably good performance were selected and the models were assembled by stacking with a simple majority vote and used for the virtual screening of over 100,000 compounds. A total of 744 compounds were predicted by at least 50% of the QSAR models as active, 147 compounds were within the applicability domain and predicted by at least 75% of the models to be active. The latter 147 compounds were submitted to molecular ligand docking using AutoDock Vina and LeDock, and 89 were predicted to be active based on the energy of binding.