Comprehensive characterization of cytochrome P450 isozyme selectivity across chemical libraries

Development and validation of CYP26A1 inhibition assay for high-throughput screening

All-trans retinoic acid (atRA) is an endogenous ligand of the retinoic acid receptors, which heterodimerize with retinoid X receptors. AtRA is generated in tissues from vitamin A (retinol) metabolism to form a paracrine signal and is locally degraded by cytochrome P450 family 26 (CYP26) enzymes. The CYP26 family consists of three subtypes: A1, B1, and C1, which are differentially expressed during development. This study aims to develop and validate a high throughput screening assay to identify CYP26A1 inhibitors in a cell-free system using a luminescent P450-Glo assay technology. The assay performed well with a signal to background ratio of 25.7, a coefficient of variation of 8.9%, and a Z-factor of 0.7. To validate the assay, we tested a subset of 39 compounds that included known CYP26 inhibitors and retinoids, as well as positive and negative control compounds selected from the literature and/or the ToxCast/Tox21 portfolio. Known CYP26A1 inhibitors were confirmed, and predicted CYP26A1 inhibitors, such as chlorothalonil, prochloraz, and SSR126768, were identified, demonstrating the reliability and robustness of the assay. Given the general importance of atRA as a morphogenetic signal and the localized expression of Cyp26a1 in embryonic tissues, a validated CYP26A1 assay has important implications for evaluating the potential developmental toxicity of chemicals.

Development of scoring-assisted generative exploration (SAGE) and its application to dual inhibitor design for acetylcholinesterase and monoamine oxidase B

De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. SCIENTIFIC CONTRIBUTION: The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria-including target specificity, synthetic accessibility, solubility, and metabolic stability-within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.

Unveiling the Potential of Ent-Kaurane Diterpenoids: Multifaceted Natural Products for Drug Discovery

Natural products hold immense potential for drug discovery, yet many remain unexplored in vast libraries and databases. In an attempt to fill this gap and meet the growing demand for effective drugs, this study delves into the promising world of ent-kaurane diterpenoids, a class of natural products with huge therapeutic potential. With a dataset of 570 ent-kaurane diterpenoids obtained from the literature, we conducted an in silico analysis, evaluating their physicochemical, pharmacokinetic, and toxicological properties with a focus on their therapeutic implications. Notably, these natural compounds exhibit drug-like properties, aligning closely with those of FDA-approved drugs, indicating a high potential for drug development. The ranges of the physicochemical parameters were as follows: molecular weights-288.47 to 626.82 g/mol; number of heavy atoms-21 to 44; the number of hydrogen bond donors and acceptors-0 to 8 and 1 to 11, respectively; the number of rotatable bonds-0 to 11; fraction Csp3-0.65 to 1; and TPSA-20.23 to 189.53 Ų. Additionally, the majority of these molecules display favorable safety profiles, with only 0.70%, 1.40%, 0.70%, and 46.49% exhibiting mutagenic, tumorigenic, reproduction-enhancing, and irritant properties, respectively. Importantly, ent-kaurane diterpenoids exhibit promising biopharmaceutical properties. Their average lipophilicity is optimal for drug absorption, while over 99% are water-soluble, facilitating delivery. Further, 96.5% and 28.20% of these molecules exhibited intestinal and brain bioavailability, expanding their therapeutic reach. The predicted pharmacological activities of these compounds encompass a diverse range, including anticancer, immunosuppressant, chemoprotective, anti-hepatic, hepatoprotectant, anti-inflammation, antihyperthyroidism, and anti-hepatitis activities. This multi-targeted profile highlights ent-kaurane diterpenoids as highly promising candidates for further drug discovery endeavors.

Uncertainty Quantification and Interpretability for Clinical Trial Approval Prediction

Background: Clinical trial is a crucial step in the development of a new therapy (e.g., medication) and is remarkably expensive and time-consuming. Forecasting the approval of clinical trials accurately would enable us to circumvent trials destined to fail, thereby allowing us to allocate more resources to therapies with better chances. However, existing approval prediction algorithms did not quantify the uncertainty and provide interpretability, limiting their usage in real-world clinical trial management. Methods: This paper quantifies uncertainty and improves interpretability in clinical trial approval predictions. We devised a selective classification approach and integrated it with the Hierarchical Interaction Network, the state-of-the-art clinical trial prediction model. Selective classification, encompassing a spectrum of methods for uncertainty quantification, empowers the model to withhold decision-making in the face of samples marked by ambiguity or low confidence. This approach not only amplifies the accuracy of predictions for the instances it chooses to classify but also notably enhances the model's interpretability. Results: Comprehensive experiments demonstrate that incorporating uncertainty markedly enhances the model's performance. Specifically, the proposed method achieved 32.37%, 21.43%, and 13.27% relative improvement on area under the precision-recall curve over the base model (Hierarchical Interaction Network) in phase I, II, and III trial approval predictions, respectively. For phase III trials, our method reaches 0.9022 area under the precision-recall curve scores. In addition, we show a case study of interpretability that helps domain experts to understand model's outcome. The code is publicly available at https://github.com/Vincent-1125/Uncertainty-Quantification-on-Clinical-Trial-Outcome-Prediction. Conclusion: Our approach not only measures model uncertainty but also greatly improves interpretability and performance for clinical trial approval prediction.

Prediction of Cytochrome P450 Inhibition Using a Deep Learning Approach and Substructure Pattern Recognition

Cytochrome P450 (CYP) is a family of enzymes that are responsible for about 75% of all metabolic reactions. Among them, CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4 participate in the metabolism of most drugs and mediate many adverse drug reactions. Therefore, it is necessary to estimate the chemical inhibition of Cytochrome P450 enzymes in drug discovery and the food industry. In the past few decades, many computational models have been reported, and some provided good performance. However, there are still several issues that should be resolved for these models, such as single isoform, models with unbalanced performance, lack of structural characteristics analysis, and poor availability. In the present study, the deep learning models based on python using the Keras framework and TensorFlow were developed for the chemical inhibition of each CYP isoform. These models were established based on a large data set containing 85715 compounds extracted from the PubChem bioassay database. On external validation, the models provided good AUC values with 0.97, 0.94, 0.94, 0.96, and 0.94 for CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4, respectively. The models can be freely accessed on the Web server named CYPi-DNNpredictor (cypi.sapredictor.cn), and the codes for the model were made open source in the Supporting Information. In addition, we also analyzed the structural characteristics of chemicals with CYP450 inhibition and detected the structural alerts (SAs), which should be responsible for the inhibition. The SAs were also made available online, named CYPi-SAdetector (cypisa.sapredictor.cn). The models can be used as a powerful tool for the prediction of CYP450 inhibitors, and the SAs should provide useful information for the mechanisms of Cytochrome P450 inhibition.

Real-World Molecular Out-Of-Distribution: Specification and Investigation

This study presents a rigorous framework for investigating molecular out-of-distribution (MOOD) generalization in drug discovery. The concept of MOOD is first clarified through a problem specification that demonstrates how the covariate shifts encountered during real-world deployment can be characterized by the distribution of sample distances to the training set. We find that these shifts can cause performance to drop by up to 60% and uncertainty calibration by up to 40%. This leads us to propose a splitting protocol that aims to close the gap between the deployment and testing. Then, using this protocol, a thorough investigation is conducted to assess the impact of model design, model selection, and data set characteristics on MOOD performance and uncertainty calibration. We find that appropriate representations and algorithms with built-in uncertainty estimation are crucial to improving performance and uncertainty calibration. This study sets itself apart by its exhaustiveness and opens an exciting avenue to benchmark meaningful algorithmic progress in molecular scoring.

In silico study of antibacterial tyrosyl-tRNA synthetase and toxicity of main phytoconstituents from three active essential oils

The misuse and overuse of antibiotics have resulted in antibiotic resistance. However, there are alternative approaches that could either substitute antibiotics or enhance their effectiveness without harmful side effects. One such approach is the use of terpene-rich essential oils. In this study, we aimed to demonstrate the antibacterial activity of the main components of three plant essential oils, namely Anthemis punctata, Anthemis pedunculata and Daucus crinitus. Specifically, we targeted bacterial tyrosyl-tRNA synthetase, an enzyme that plays a critical role in bacterial protein synthesis. To investigate how the phytocompounds interact with the enzyme's active sites, we employed a molecular docking study using Autodock Software Tools 1.5.7. Our findings revealed that all 28 phytocompounds bound to the enzyme's active sites with binding energies ranging from -6.96 to -4.03 kcal/mol. These results suggest that terpene-rich essential oils could be a potential source of novel antimicrobial agents.Communicated by Ramaswamy H. Sarma.

An Uncertainty-Guided Deep Learning Method Facilitates Rapid Screening of CYP3A4 Inhibitors

Cytochrome P450 3A4 (CYP3A4), a prominent member of the P450 enzyme superfamily, plays a crucial role in metabolizing various xenobiotics, including over 50% of clinically significant drugs. Evaluating CYP3A4 inhibition before drug approval is essential to avoiding potentially harmful pharmacokinetic drug-drug interactions (DDIs) and adverse drug reactions (ADRs). Despite the development of several CYP inhibitor prediction models, the primary approach for screening CYP inhibitors still relies on experimental methods. This might stem from the limitations of existing models, which only provide deterministic classification outcomes instead of precise inhibition intensity (e.g., IC50) and often suffer from inadequate prediction reliability. To address this challenge, we propose an uncertainty-guided regression model to accurately predict the IC50 values of anti-CYP3A4 activities. First, a comprehensive data set of CYP3A4 inhibitors was compiled, consisting of 27,045 compounds with classification labels, including 4395 compounds with explicit IC50 values. Second, by integrating the predictions of the classification model trained on a larger data set and introducing an evidential uncertainty method to rank prediction confidence, we obtained a high-precision and reliable regression model. Finally, we use the evidential uncertainty values as a trustworthy indicator to perform a virtual screening of an in-house compound set. The in vitro experiment results revealed that this new indicator significantly improved the hit ratio and reduced false positives among the top-ranked compounds. Specifically, among the top 20 compounds ranked with uncertainty, 15 compounds were identified as novel CYP3A4 inhibitors, and three of them exhibited activities less than 1 μM. In summary, our findings highlight the effectiveness of incorporating uncertainty in compound screening, providing a promising strategy for drug discovery and development.

A knowledge-guided pre-training framework for improving molecular representation learning

Learning effective molecular feature representation to facilitate molecular property prediction is of great significance for drug discovery. Recently, there has been a surge of interest in pre-training graph neural networks (GNNs) via self-supervised learning techniques to overcome the challenge of data scarcity in molecular property prediction. However, current self-supervised learning-based methods suffer from two main obstacles: the lack of a well-defined self-supervised learning strategy and the limited capacity of GNNs. Here, we propose Knowledge-guided Pre-training of Graph Transformer (KPGT), a self-supervised learning framework to alleviate the aforementioned issues and provide generalizable and robust molecular representations. The KPGT framework integrates a graph transformer specifically designed for molecular graphs and a knowledge-guided pre-training strategy, to fully capture both structural and semantic knowledge of molecules. Through extensive computational tests on 63 datasets, KPGT exhibits superior performance in predicting molecular properties across various domains. Moreover, the practical applicability of KPGT in drug discovery has been validated by identifying potential inhibitors of two antitumor targets: hematopoietic progenitor kinase 1 (HPK1) and fibroblast growth factor receptor 1 (FGFR1). Overall, KPGT can provide a powerful and useful tool for advancing the artificial intelligence (AI)-aided drug discovery process.

Design of a multi-target focused library for antidiabetic targets using a comprehensive set of chemical transformation rules

Virtual small molecule libraries are valuable resources for identifying bioactive compounds in virtual screening campaigns and improving the quality of libraries in terms of physicochemical properties, complexity, and structural diversity. In this context, the computational-aided design of libraries focused against antidiabetic targets can provide novel alternatives for treating type II diabetes mellitus (T2DM). In this work, we integrated the information generated to date on compounds with antidiabetic activity, advances in computational methods, and knowledge of chemical transformations available in the literature to design multi-target compound libraries focused on T2DM. We evaluated the novelty and diversity of the newly generated library by comparing it with antidiabetic compounds approved for clinical use, natural products, and multi-target compounds tested in vivo in experimental antidiabetic models. The designed libraries are freely available and are a valuable starting point for drug design, chemical synthesis, and biological evaluation or further computational filtering. Also, the compendium of 280 transformation rules identified in a medicinal chemistry context is made available in the linear notation SMIRKS for use in other chemical library enumeration or hit optimization approaches.

Computer-aided analysis for identification of novel analogues of ketoprofen based on molecular docking, ADMET, drug-likeness and DFT studies for the treatment of inflammation

Computer-based drug design is increasingly used in strategies for discovering new molecules for therapeutic purposes. The targeted drug is ketoprofen (KTP), which belongs to the family of non-steroidal anti-inflammatory drugs, which are widely used for the treatment of pain, fever, inflammation and certain types of cancers. In an attempt to rationalize the search for 72 new potential anti-inflammatory compounds on the COX-2 enzyme, we carried out an in silico protocol that successfully combines molecular docking towards COX-2 receptor (5F1A), ADMET pharmacokinetic parameters, drug-likeness rules and molecular electrostatic potential (MEP). It was found that six of the compounds analyzed satisfy with the associated values to physico-chemical properties as key evaluation parameters for the drug-likeness and demonstrate a hydrophobic character which makes their solubility in aqueous media difficult and easy in lipids. All the compounds presented good ADMET profile and they showed an interaction with the amino acids responsible for anti-inflammatory activity of the COX-2 isoenzyme. The calculation of the MEP of the six analogues reveals new preferential sites involving the formation of new bonds. Consequently, this result allowed us to understand the origin of the potential increase in the anti-inflammatory activity of the candidates. Finally, it was obtained that six compounds have a binding mode, binding energy, and stability in the active site of COX-2 like the reference drug ketoprofen, suggesting that these compounds could become a powerful candidate in the inhibition of the COX-2 enzyme.Communicated by Ramaswamy H. Sarma.

Fluorescence-Based High-Throughput Assays for Investigating Cytochrome P450 Enzyme-Mediated Drug-Drug Interactions

The cytochrome P450 enzymes (CYPs), a group of heme-containing enzymes, catalyze oxidative metabolism of a wide range of drugs and xenobiotics, as well as different endogenous molecules. Strong inhibition of human CYPs is the most common cause of clinically associated pharmacokinetic drug-drug/herb-drug interactions (DDIs/HDIs), which may result in serious adverse drug reactions, even toxicity. Accurate and rapid assessing of the inhibition potentials on CYP activities for therapeutic agents is crucial for the prediction of clinically relevant DDIs/HDIs. Over the past few decades, significant efforts have been invested into developing optical substrates for the human CYPs, generating a variety of powerful tools for high-throughput assays to detect CYP activities in biologic specimens and for screening of CYP inhibitors. This minireview focuses on recent advances in optical substrates developments for human CYPs, as well as their applications in screening CYP inhibitors and DDIs/HDIs studies. The examples for rational design and optimization of highly specific optical substrates for the target CYP enzyme, as well as applications in investigating CYP-mediated DDIs, are illustrated. Finally, the challenges and future perspectives in this field are proposed. Collectively, this review summarizes the reported optical-based biochemical assays for highly efficient CYP activities detection, which strongly facilitated the discovery of CYP inhibitors and the investigations on CYP-mediated DDIs. SIGNIFICANCE STATEMENT: Optical substrates for cytochrome P450 enzymes (CYPs) have emerged as powerful tools for the construction of high-throughput assays for screening of CYP inhibitors. This mini-review covers the advances and challenges in the development of highly specific optical substrates for sensing human CYP isoenzymes, as well as their applications in constructing fluorescence-based high-throughput assays for investigating CYP-mediated drug-drug interactions.

A quest for the stereo-electronic requirements for selective agonism for the neurotrophin receptors TrkA and TrkB in 17-spirocyclic-dehydroepiandrosterone derivatives

Introduction

The neurotrophin system plays a pivotal role in the development, morphology, and survival of the nervous system, and its dysregulation has been manifested in numerous neurodegenerative and neuroinflammatory diseases. Neurotrophins NGF and BDNF are major growth factors that prevent neuronal death and synaptic loss through binding with high affinity to their specific tropomyosin-related kinase receptors namely, TrkA and TrkB, respectively. The poor pharmacokinetic properties prohibit the use of neurotrophins as therapeutic agents. Our group has previously synthesized BNN27, a prototype small molecule based on dehydroepiandrosterone, mimicking NGF through the activation of the TrkA receptor.

Methods

To obtain a better understanding of the stereo-electronic requirements for selective activation of TrkA and TrkB receptors, 27 new dehydroepiandrosterone derivatives bearing a C17-spiro-dihydropyran or cyclobutyl moiety were synthesized. The new compounds were evaluated for their ability (a) to selectively activate the TrkA receptor and its downstream signaling kinases Akt and Erk1/2 in PC12 cells, protecting these cells from serum deprivation-induced cell death, and (b) to induce phosphorylation of TrkB and to promote cell survival under serum deprivation conditions in NIH3T3 cells stable transfected with the TrkB receptor and primary cortical astrocytes. In addition the metabolic stability and CYP-mediated reaction was assessed.

Results

Among the novel derivatives, six were able to selectively protect PC12 cells through interaction with the TrkA receptor and five more to selectively protect TrkB-expressing cells via interaction with the TrkB receptor. In particular, compound ENT-A025 strongly induces TrkA and Erk1/2 phosphorylation, comparable to NGF, and can protect PC12 cells against serum deprivation-induced cell death. Furthermore, ENT-A065, ENT-A066, ENT-A068, ENT-A069, and ENT-A070 showed promising pro-survival effects in the PC12 cell line. Concerning TrkB agonists, ENT-A009 and ENT-A055 were able to induce phosphorylation of TrkB and reduce cell death levels in NIH3T3-TrkB cells. In addition, ENT-A076, ENT-A087, and ENT-A088 possessed antiapoptotic activity in NIH-3T3-TrkB cells exclusively mediated through the TrkB receptor. The metabolic stability and CYP-mediated reaction phenotyping of the potent analogs did not reveal any major liabilities.

Discussion

We have identified small molecule selective agonists of TrkA and TrkB receptors as promising lead neurotrophin mimetics for the development of potential therapeutics against neurodegenerative conditions.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

A molecular analysis of substituted phenylethylamines as potential microtubule targeting agents through in silico methods and in vitro microtubule-polymerization activity

Natural phenethylamines are trace amine neurotransmitters associated with dopamine transmission and related illnesses such Parkinson's disease, and addiction. Synthetic phenethylamines can have psychoactive and hallucinogenic effects due to their high affinity with the 5-HT2A receptor. Evidence indicates phenethylamines can directly alter the microtubule cytoskeleton being structurally similar to the microtubule destabilizing agent colchicine, however little work has been done on this interaction. As microtubules provide neuron structure, intracellular transport, and influence synaptic plasticity the interaction of phenethylamines with microtubules is important for understanding the potential harms, or potential pharmaceutical use of phenethylamines. We investigated 110 phenethylamines and their interaction with microtubules. Here we performed molecular docking of these compounds at the colchicine binding site and ranked them via binding energy. The top 10% of phenethylamines were further screened based on pharmacokinetic and physicochemical properties derived from SwissADME and LightBBB. Based on these properties 25B-NBF, 25C-NBF, and DMBMPP were tested in in vitro microtubule polymerization assays showing that they alter microtubule polymerization dynamics in a dose dependent manner. As these compounds can rapidly cross the blood brain barrier and directly affect cytoskeletal dynamics, they have the potential to modulate cytoskeletal based neural plasticity. Further investigations into these mechanisms are warranted.

Machine Learning Models to Predict Cytochrome P450 2B6 Inhibitors and Substrates

Cytochrome P450 2B6 (CYP2B6) is responsible for the metabolism of ∼7% of marketed drugs. The in vitro drug interaction studies guidance for industry issued by the FDA stipulates that drug sponsors need to evaluate whether the investigated drugs interact with the major drug-metabolizing P450s including CYP2B6. Therefore, there has been greater attention to the development of predictive models for CYP2B6 inhibitors and substrates. In this study, conventional machine learning and deep learning models were developed to predict CYP2B6 inhibitors and substrates. Our results showed that the best CYP2B6 inhibitor model yielded the AUC values of 0.95 and 0.75 with the 10-fold cross-validation and the test set, respectively, and the best CYP2B6 substrate model produced the AUC values of 0.93 and 0.90 with the 10-fold cross-validation and the test set, respectively. The generalization ability of the CYP2B6 inhibitor and substrate models was assessed by using the external validation sets. Several significant substructural fragments relevant to CYP2B6 inhibitors and substrates were detected via frequency substructure analysis and information gain. In addition, the applicability domain of the models was defined by employing a nonparametric method based on the probability density distribution. We anticipate that our results would be useful for the prediction of potential CYP2B6 inhibitors and substrates in the early stage of drug discovery.

In vitro and in silico studies of antibacterial activities of secofriedelane derivatives from Senna alata (L) Roxb

In this study, six compounds were obtained from a methanolic extract of air-dried leaves of Senna alata and one of them, a triterpenoid (secofriedelane) named as 7-(2-carboxyethyl)-3, 4b, 6a, 8, 10a, 12a-hexamethyl-8-vinyloctadecahydrochrysene-3-carboxylic acid (5) was isolated for the first time from this plant. Then, its chemical structure was detailed and characterised by FT-IR, 1H and 13C- NMR and ESI-MS. Besides, two chemical-modified derivatives of secofriedelane (5a, 5b) were synthesised by methylation and allylation reactions, respectively, and their in vitro antibacterial activities were also evaluated. The results revealed that all the triterpenes showed, against gram-positive and -negative bacterial strains, good and moderate antibacterial activities with bactericidal effects that were enhanced by the methyl groups and altered with the allyl ones. Moreover, the molecular docking results of 5, 5a and 5b in the DNA gyrase (2XCT) active site showed that triterpene 5 has a good score very close to reference (ciprofloxacin).

In-vitro antiviral activity and in-silico targeted study of quinoline-3-carboxylate derivatives against SARS-Cov-2 isolate

In recent years, the viral outbreak named COVID-19 showed that infectious diseases have a huge impact on both global health and the financial and economic sectors. The lack of efficacious antiviral drugs worsened the health problem. Based on our previous experience, we investigated in vitro and in silico a series of quinoline-3-carboxylate derivatives against a SARS-CoV-2 isolate. In the present study, the in-vitro antiviral activity of a series of quinoline-3-carboxylate compounds and the in silico target-based molecular dynamics (MD) and metabolic studies are reported. The compounds' activity against SARS-CoV-2 was evaluated using plaque assay and RT-qPCR. Moreover, from the docking scores, it appears that the most active compounds (1j and 1o) exhibit stronger binding affinity to the primary viral protease (NSP5) and the exoribonuclease domain of non structural protein 14 (NSP14). Additionally, the in-silico metabolic analysis of 1j and 1o defines CYP2C9 and CYP3A4 as the major P450 enzymes involved in their metabolism.

MCFF-MTDDI: multi-channel feature fusion for multi-typed drug-drug interaction prediction

Adverse drug-drug interactions (DDIs) have become an increasingly serious problem in the medical and health system. Recently, the effective application of deep learning and biomedical knowledge graphs (KGs) have improved the DDI prediction performance of computational models. However, the problems of feature redundancy and KG noise also arise, bringing new challenges for researchers. To overcome these challenges, we proposed a Multi-Channel Feature Fusion model for multi-typed DDI prediction (MCFF-MTDDI). Specifically, we first extracted drug chemical structure features, drug pairs' extra label features, and KG features of drugs. Then, these different features were effectively fused by a multi-channel feature fusion module. Finally, multi-typed DDIs were predicted through the fully connected neural network. To our knowledge, we are the first to integrate the extra label information into KG-based multi-typed DDI prediction; besides, we innovatively proposed a novel KG feature learning method and a State Encoder to obtain target drug pairs' KG-based features which contained more abundant and more key drug-related KG information with less noise; furthermore, a Gated Recurrent Unit-based multi-channel feature fusion module was proposed in an innovative way to yield more comprehensive feature information about drug pairs, effectively alleviating the problem of feature redundancy. We experimented with four datasets in the multi-class and the multi-label prediction tasks to comprehensively evaluate the performance of MCFF-MTDDI for predicting interactions of known-known drugs, known-new drugs and new-new drugs. In addition, we further conducted ablation studies and case studies. All the results fully demonstrated the effectiveness of MCFF-MTDDI.

A Robust Machine Learning Framework Built Upon Molecular Representations Predicts CYP450 Inhibition: Toward Precision in Drug Repurposing

Human cytochrome P450 (CYP450) enzymes play a crucial role in drug metabolism and pharmacokinetics. CYP450 inhibition can lead to toxicity, in particular when drugs are co-administered with other drugs and xenobiotics or in the case of polypharmacy. Predicting CYP450 inhibition is also important for rational drug discovery and development, and precision in drug repurposing. In this overarching context, digital transformation of drug discovery and development, for example, using machine and deep learning approaches, offers prospects for prediction of CYP450 inhibition through computational models. We report here the development of a majority-voting machine learning framework to classify inhibitors and noninhibitors for seven major human liver CYP450 isoforms (CYP1A2, CYP2A6, CYP2B6, CYP2C9, CYP2C19, CYP2D6, and CYP3A4). For the machine learning models reported herein, we employed interaction fingerprints that were derived from molecular docking simulations, thus adding an additional layer of information for protein-ligand interactions. The proposed machine learning framework is based on the structure of the binding site of isoforms to produce predictions beyond previously reported approaches. Also, we carried out a comparative analysis so as to identify which representation of test compounds (molecular descriptors, molecular fingerprints, or protein-ligand interaction fingerprints) affects the predictive performance of the models. This work underlines the ways in which the structure of the enzyme catalytic site influences machine learning predictions and the need for robust frameworks toward better-informed predictions.

Identification of Some Glutamic Acid Derivatives with Biological Potential by Computational Methods

Glutamic acid is a non-essential amino acid involved in multiple metabolic pathways. Of high importance is its relationship with glutamine, an essential fuel for cancer cell development. Compounds that can modify glutamine or glutamic acid behaviour in cancer cells have resulted in attractive anticancer therapeutic alternatives. Based on this idea, we theoretically formulated 123 glutamic acid derivatives using Biovia Draw. Suitable candidates for our research were selected among them. For this, online platforms and programs were used to describe specific properties and their behaviour in the human organism. Nine compounds proved to have suitable or easy to optimise properties. The selected compounds showed cytotoxicity against breast adenocarcinoma, lung cancer cell lines, colon carcinoma, and T cells from acute leukaemia. Compound 2Ba5 exhibited the lowest toxicity, and derivative 4Db6 exhibited the most intense bioactivity. Molecular docking studies were also performed. The binding site of the 4Db6 compound in the glutamine synthetase structure was determined, with the D subunit and cluster 1 being the most promising. In conclusion, glutamic acid is an amino acid that can be manipulated very easily. Therefore, molecules derived from its structure have great potential to become innovative drugs, and further research on these will be conducted.

Quantitative Bioactivity Signatures of Dietary Supplements and Natural Products

Dietary supplements and natural products are often marketed as safe and effective alternatives to conventional drugs, but their safety and efficacy are not well regulated. To address the lack of scientific data in these areas, we assembled a collection of Dietary Supplements and Natural Products (DSNP), as well as Traditional Chinese Medicinal (TCM) plant extracts. These collections were then profiled in a series of in vitro high-throughput screening assays, including a liver cytochrome p450 enzyme panel, CAR/PXR signaling pathways, and P-glycoprotein (P-gp) transporter assay activities. This pipeline facilitated the interrogation of natural product-drug interaction (NaPDI) through prominent metabolizing pathways. In addition, we compared the activity profiles of the DSNP/TCM substances with those of an approved drug collection (the NCATS Pharmaceutical Collection or NPC). Many of the approved drugs have well-annotated mechanisms of action (MOAs), while the MOAs for most of the DSNP and TCM samples remain unknown. Based on the premise that compounds with similar activity profiles tend to share similar targets or MOA, we clustered the library activity profiles to identify overlap with the NPC to predict the MOAs of the DSNP/TCM substances. Our results suggest that many of these substances may have significant bioactivity and potential toxicity, and they provide a starting point for further research on their clinical relevance.

Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

Drug metabolism and excretion play crucial roles in determining the efficacy and safety of drug candidates, and predicting these processes is an essential part of drug discovery and development. In recent years, artificial intelligence (AI) has emerged as a powerful tool for predicting drug metabolism and excretion, offering the potential to speed up drug development and improve clinical success rates. This review highlights recent advances in AI-based drug metabolism and excretion prediction, including deep learning and machine learning algorithms. We provide a list of public data sources and free prediction tools for the research community. We also discuss the challenges associated with the development of AI models for drug metabolism and excretion prediction and explore future perspectives in the field. We hope this will be a helpful resource for anyone who is researching in silico drug metabolism, excretion, and pharmacokinetic properties.

Combined and independent effects of OCT1 and CYP2D6 on the cellular disposition of drugs

The organic cation transporter 1 (OCT1) mediates the cell uptake and cytochrome P450 2D6 (CYP2D6) the metabolism of many cationic substrates. Activities of OCT1 and CYP2D6 are affected by enormous genetic variation and frequent drug-drug interactions. Single or combined deficiency of OCT1 and CYP2D6 might result in dramatic differences in systemic exposure, adverse drug reactions, and efficacy. Thus, one should know what drugs are affected to what extent by OCT1, CYP2D6 or both. Here, we compiled all data on CYP2D6 and OCT1 drug substrates. Among 246 CYP2D6 substrates and 132 OCT1 substrates, we identified 31 shared substrates. In OCT1 and CYP2D6 single and double-transfected cells, we studied which, OCT1 or CYP2D6, is more critical for a given drug and whether there are additive, antagonistic or synergistic effects. In general, OCT1 substrates were more hydrophilic than CYP2D6 substrates and smaller in size. Inhibition studies showed unexpectedly pronounced inhibition of substrate depletion by shared OCT1/CYP2D6 inhibitors. In conclusion, there is a distinct overlap in the OCT1/CYP2D6 substrate and inhibitor spectra, so in vivo pharmacokinetics and -dynamics of shared substrates may be significantly affected by frequent OCT1- and CYP2D6-polymorphisms and by comedication with shared inhibitors.

In Vitro Antibacterial Efficacy of Cymbopogon flexuosus Essential Oil against Aeromonas hydrophila of Fish Origin and in Silico Molecular Docking of the Essential Oil Components against DNA Gyrase-B and Their Drug-Likeness

In aquaculture, diseases caused by the Aeromonads with high antibiotic resistance are among the most common and troublesome diseases. Application of herbs is emerging as a tool in controlling these diseases. Plant extracts besides disease control, favor various physiological activities in fish. In this study, essential oil of Cymbopogon flexuosus (Poaceae family) was studied in vitro for its antibacterial efficacy against two oxytetracycline (OTC) resistant and one sensitive strains of Aeromonas hydrophila. The oil was found rich (86.93 %) in oxygenated terpenoids containing 74.15 % of citral. The oil exhibited dose dependent growth inhibition of the bacteria. Mean MIC value of the oil against the sensitive strain was recorded as 2.0 mg mL^-1 whereas MBC value was recorded as 4.0 mg mL^-1 . The oil was found effective against the OTC resistant isolates with the MIC and MBC values ranging from 2.67-3.33 and 4.0-6.67 mg mL^-1 , respectively. In silico molecular docking of the essential oil components against DNA gyrase-B, a vital macromolecule in bacterial cell, was carried out to computationally asses the efficacy of the oil against the bacteria. Some of the components of the essential oil strongly bonded with the enzyme to inhibit its efficacy. Binding energy of some components of the oil was comparable to that of the conventional antibiotic, OTC. The identified phytochemicals exhibited favorable physicochemical and pharmacokinetic properties and satisfied the rule of five (Ro5).

Predictive Models for Human Cytochrome P450 3A7 Selective Inhibitors and Substrates

Inappropriate use of prescription drugs is potentially more harmful in fetuses/neonates than in adults. Cytochrome P450 (CYP) 3A subfamily undergoes developmental changes in expression, such as a transition from CYP3A7 to CYP3A4 shortly after birth, which provides a potential way to distinguish medication effects on fetuses/neonates and adults. The purpose of this study was to build first-in-class predictive models for both inhibitors and substrates of CYP3A7/CYP3A4 using chemical structure analysis. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The performance varied for each CYP3A7/CYP3A4 inhibitor/substrate model depending on the data set type, model type, rebalancing method, and specific feature set. For the active inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.77 ± 0.01 to 0.84 ± 0.01. For the selective inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.72 ± 0.02 to 0.79 ± 0.04. The predictive power of the optimal models was validated by compounds with known potencies as CYP3A7/CYP3A4 inhibitors or substrates. In addition, we identified structural features significant for CYP3A7/CYP3A4 selective or common inhibitors and substrates. In summary, the top performing models can be further applied as a tool to rapidly evaluate the safety and efficacy of new drugs separately for fetuses/neonates and adults. The significant structural features could guide the design of new therapeutic drugs as well as aid in the optimization of existing medicine for fetuses/neonates.

In silico ADMET analysis of the A-, B- and D-modified androstane derivatives with potential anticancer effects

The major challenge in the fight against cancer is to design new drugs that will be more selective for cancer cells, with fewer side effects. Synthetic steroids such as cyproterone, fulvestrant, exemestane and abiraterone are approved powerful drugs for the treatment of hormone-dependent diseases such as breast and prostate cancers. Therefore, androstane derivatives in 17-substituted, 17a-homo lactone and 16,17-seco series, with potent anticancer activity, were selected for pharmacokinetic and druglike predictions from the absorption, distribution, metabolism and excretion (ADME) models. In silico determination of physico-chemical and ADMET properties was performed using SwissADME and ProTox-II web tools. The possibility of gastrointestinal absorption and brain penetration was analyzed using the BOILED-Egg model, while the in silico evaluation of the similarities between selected steroid derivatives and FDA-approved drugs was carried out using the SwissSimilarity tool. Of all tested, two compounds that showed good in silico ADMET results, in addition to promising cytotoxicity and molecular docking results, could potentially be evaluated in in vivo tests.

Diterpene Sonderianin isolated from Croton blanchetianus exhibits acetylcholinesterase inhibitory action and anxiolytic effect in adult zebrafish (Danio rerio) by 5-HT system

Croton blanchetianus is known as 'marmeleiro preto', a very widespread shrub in Northeast Brazil. Terpenoids, steroids and phenolic compounds are among the reported secondary metabolites of the Croton genus that are a potential source of bioactive compounds. This study evaluated the anxiolytic potential of clerodine-type diterpene, sonderianin (CBWS) isolated from the stem bark of C. blanchetianus and its mechanism of action in adult zebrafish (Danio rerio) (ZFa). The anticonvulsant and anti-acetylcholinesterase effects have also been explored. ZFa (n = 6/group) were treated intraperitoneally (ip; 20 µL) with CBWS (4, 12 and 40 mg/kg) and vehicle (3% DMSO; 20 µL) and subjected to locomotor activity tests, as well as toxicity acute 96 h. CBWS was also administered for analysis in the light/dark test. The involvement of the serotonergic system (5-HT) was investigated using 5-HTR₁, 5-HTR_2A/2C and 5-HTR_3A/3B receptor antagonists. Anxiolytic doses were tested for pentylenetetrazol-induced seizure in ZFa. The inhibitory activity of the enzyme acetylcholinesterase (AChE) was measured. CBWS was not considered toxic and reduced locomotor activity. The results of the present study identified for the first time the interaction of the diterpene sonderianina in the CNS. This study provides evidence that CBWS has an anxiolytic effect mediated by serotonergic (5-HT) involvement and anti-acetylcholinesterase action. The 5-HTR₁ and 5-HTR_2A/2C receptors may be implicated in the low anticonvulsant effect in CBWS.Communicated by Ramaswamy H. Sarma.

Quantitative evaluation of explainable graph neural networks for molecular property prediction

Graph neural networks (GNNs) have received increasing attention because of their expressive power on topological data, but they are still criticized for their lack of interpretability. To interpret GNN models, explainable artificial intelligence (XAI) methods have been developed. However, these methods are limited to qualitative analyses without quantitative assessments from the real-world datasets due to a lack of ground truths. In this study, we have established five XAI-specific molecular property benchmarks, including two synthetic and three experimental datasets. Through the datasets, we quantitatively assessed six XAI methods on four GNN models and made comparisons with seven medicinal chemists of different experience levels. The results demonstrated that XAI methods could deliver reliable and informative answers for medicinal chemists in identifying the key substructures. Moreover, the identified substructures were shown to complement existing classical fingerprints to improve molecular property predictions, and the improvements increased with the growth of training data.

Metabolic clearance of select opioids and opioid antagonists using hepatic spheroids and recombinant cytochrome P450 enzymes

The opioid crisis is a pressing public health issue, exacerbated by the emergence of more potent synthetic opioids, particularly fentanyl and its analogs. While competitive antagonists exist, their efficacy against synthetic opioids is largely unknown. Furthermore, due to the short durations of action of current antagonists, renarcotization remains a concern. In this study, metabolic activity was characterized for fentanyl‐class opioids and common opioid antagonists using multiple in vitro systems, namely, cytochrome P450 (CYP) enzymes and hepatic spheroids, after which an in vitro‐in vivo correlation was applied to convert in vitro metabolic activity to predictive in vivo intrinsic clearance. For all substrates, intrinsic hepatic metabolism was higher than the composite of CYP activities, due to fundamental differences between whole cells and single enzymatic reactions. Of the CYP isozymes investigated, 3A4 yielded the highest absolute and relative metabolism across all substrates, with largely negligible contributions from 2D6 and 2C19. Comparative analysis highlighted elevated lipophilicity and diminished CYP3A4 activity as potential considerations for the development of more efficacious opioid antagonists. Finally, antagonists with a high degree of molecular similarity exhibited comparable clearance, providing a basis for structure‐metabolism relationships. Together, these results provide multiple screening criteria for early stage drug discovery involving opioid countermeasures.

Seasonal variation of the composition of essential oils from Piper cernuum Vell and Piper rivinoides Kunth, ADMET study, DFT calculations, molecular docking and dynamics studies of major components as potent inhibitors of the heterodimer methyltransferase complex NSP16-NSP10 SARS COV-2 protein

Coronavirus disease (COVID-19) has the virus that causes the SARS-CoV-2 severe acute respiratory syndrome, which has reached a pandemic proportion, with thousands of deaths worldwide already registered. It has no standardized effective clinical treatment, arousing the urgent need for the discovery of bioactive compounds for the treatment of symptoms of COVID-19. In this context, the present study aimed to evaluate the influence of seasonality on the yield and chemical composition of the essential oils of Piper cernuum and Piper rivinoides as well as to evaluate the anti-SARS-CoV-2 potential of the major components of each oil by molecular docking and quantum chemical calculation (Density Functional Theory method), being possible indicate that the winter and autumn periods, the seasons of the year where it is possible to obtain the highest percentage of Piper cernuum and Piper rivinoides oils, respectively. Regarding the anti-SARS-Cov-2 potential, the present work showed that the dihydroagarofuran present in Piper cernuum, presented a strong interaction with amino acid residues from Mpro, presenting a potential similar to Remdesivir, a drug for clinical use. Regarding methyltransferase, dihydroagarofuran (Piper cernuum) and myristicin (Piper rivinoids) showed better affinity, with important interactions at the active site of the inhibitor Sinefugin, suggesting a potential inhibitory effect of the heterodimer methyltransferase complex NSP16-NSP10 SARS Cov-2. Molecular docking and molecular dynamics studies represent an initial step, being indicative for future in vitro studies of dihydroagarofuran and myristicin, as possible pharmacological tools for COVID-19.

On modeling and utilizing chemical compound information with deep learning technologies: A task-oriented approach

A large number of chemical compounds are available in databases such as PubChem and ZINC. However, currently known compounds, though large, represent only a fraction of possible compounds, which is known as chemical space. Many of these compounds in the databases are annotated with properties and assay data that can be used for drug discovery efforts. For this goal, a number of machine learning algorithms have been developed and recent deep learning technologies can be effectively used to navigate chemical space, especially for unknown chemical compounds, in terms of drug-related tasks. In this article, we survey how deep learning technologies can model and utilize chemical compound information in a task-oriented way by exploiting annotated properties and assay data in the chemical compounds databases. We first compile what kind of tasks are trying to be accomplished by machine learning methods. Then, we survey deep learning technologies to show their modeling power and current applications for accomplishing drug related tasks. Next, we survey deep learning techniques to address the insufficiency issue of annotated data for more effective navigation of chemical space. Chemical compound information alone may not be powerful enough for drug related tasks, thus we survey what kind of information, such as assay and gene expression data, can be used to improve the prediction power of deep learning models. Finally, we conclude this survey with four important newly developed technologies that are yet to be fully incorporated into computational analysis of chemical information.

Identification of Selective CYP3A7 and CYP3A4 Substrates and Inhibitors Using a High-Throughput Screening Platform

Cytochrome P450 (CYP) 3A7 is one of the major xenobiotic metabolizing enzymes in human embryonic, fetal, and newborn liver. CYP3A7 expression has also been observed in a subset of the adult population, including pregnant women, as well as in various cancer patients. The characterization of CYP3A7 is not as extensive as other CYPs, and health authorities have yet to provide guidance towards DDI assessment. To identify potential CYP3A7-specific molecules, we used a P450-Glo CYP3A7 enzyme assay to screen a library of ∼5,000 compounds, including FDA-approved drugs and drug-like molecules, and compared these screening data with that from a P450-Glo CYP3A4 assay. Additionally, a subset of 1,000 randomly selected compounds were tested in a metabolic stability assay. By combining the data from the qHTS P450-Glo and metabolic stability assays, we identified several chemical features important for CYP3A7 selectivity. Halometasone was chosen for further evaluation as a potential CYP3A7-selective inhibitor using molecular docking. From the metabolic stability assay, we identified twenty-two CYP3A7-selective substrates over CYP3A4 in supersome setting. Our data shows that CYP3A7 has ligand promiscuity, much like CYP3A4. Furthermore, we have established a large, high-quality dataset that can be used in predictive modeling for future drug metabolism and interaction studies.

Anticholinesterase Inhibition, Drug-Likeness Assessment, and Molecular Docking Evaluation of Milk Protein-Derived Opioid Peptides for the Control of Alzheimer’s Disease

The drug-likeness and pharmacokinetic properties of 23 dairy-protein-derived opioid peptides were studied using SwissADME and ADMETlab in silico tools. All the opioid peptides had poor drug-like properties based on violations of Lipinski’s rule-of-five. Moreover, prediction of their pharmacokinetic properties showed that the peptides had poor intestinal absorption and bioavailability. Following this, two well-known opioid peptides (βb-casomorphin-5, βb-casomorphin-7) from A1 bovine milk and caffeine (positive control) were selected for in silico molecular docking and in vitro inhibition study with two cholinesterase enzyme receptors important for the pathogenesis of Alzheimer’s disease. Both peptides showed higher binding free energies and inhibitory activities to butyrylcholinesterase (BChE) than caffeine, but in vitro binding energy values were lower than those from the docking model. Moreover, the two casomorphins had lower inhibitory properties against acetylcholinesterase (AChE) than caffeine, although the docking model predicted the opposite. At 1 mg/mL concentrations, βb-casomorphin-5 and βb-casomorphin-7 showed promising results in inhibiting both cholinesterases (i.e., respectively 34% and 43% inhibition of AChE, and 67% and 81% inhibition of BChE). These dairy-derived opioid peptides have the potential to treat Alzheimer’s disease via cholinesterase inhibition. However, appropriate derivatization may be required to improve their poor predicted intestinal absorption and bioavailability.

HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer

MOTIVATION

Accurate ADMET (an abbreviation for "absorption, distribution, metabolism, excretion, and toxicity") predictions can efficiently screen out undesirable drug candidates in the early stage of drug discovery. In recent years, multiple comprehensive ADMET systems that adopt advanced machine learning models have been developed, providing services to estimate multiple endpoints. However, those ADMET systems usually suffer from weak extrapolation ability. First, due to the lack of labelled data for each endpoint, typical machine learning models perform frail for the molecules with unobserved scaffolds. Second, most systems only provide fixed built-in endpoints and cannot be customised to satisfy various research requirements. To this end, we develop a robust and endpoint extensible ADMET system, HelixADMET (H-ADMET). H-ADMET incorporates the concept of self-supervised learning to produce a robust pre-trained model. The model is then fine-tuned with a multi-task and multi-stage framework to transfer knowledge between ADMET endpoints, auxiliary tasks, and self-supervised tasks.

RESULTS

Our results demonstrate that H-ADMET achieves an overall improvement of 4%, compared with existing ADMET systems on comparable endpoints. Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.

AVAILABILITY

H-ADMET is freely accessible at https://paddlehelix.baidu.com/app/drug/admet/train.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

BioChemDDI: Predicting Drug-Drug Interactions by Fusing Biochemical and Structural Information through a Self-Attention Mechanism

Simple Summary

Throughout history, combining drugs has been a common method in the fight against complex diseases. However, potential drug–drug interactions could give rise to unknown toxicity issues, which requires the urgent proposal of efficient methods to identify potential interactions.We use computer technology and machine learning techniques to propose a novel computational framework to calculate scores of drug–drug interaction probability for simplifying the screening process. Additionally, we built an online prescreening tool for biological researchers to further verify possible interactions in the fields of biomedicine and pharmacology. Overall, our study can provide new insights and approaches for rapidly identifying potential drug–drug interactions.

Abstract

During the development of drug and clinical applications, due to the co-administration of different drugs that have a high risk of interfering with each other’s mechanisms of action, correctly identifying potential drug–drug interactions (DDIs) is important to avoid a reduction in drug therapeutic activities and serious injuries to the organism. Therefore, to explore potential DDIs, we develop a computational method of integrating multi-level information. Firstly, the information of chemical sequence is fully captured by the Natural Language Processing (NLP) algorithm, and multiple biological function similarity information is fused by Similarity Network Fusion (SNF). Secondly, we extract deep network structure information through Hierarchical Representation Learning for Networks (HARP). Then, a highly representative comprehensive feature descriptor is constructed through the self-attention module that efficiently integrates biochemical and network features. Finally, a deep neural network (DNN) is employed to generate the prediction results. Contrasted with the previous supervision model, BioChemDDI innovatively introduced graph collapse for extracting a network structure and utilized the biochemical information during the pre-training process. The prediction results of the benchmark dataset indicate that BioChemDDI outperforms other existing models. Moreover, the case studies related to three cancer diseases, including breast cancer, hepatocellular carcinoma and malignancies, were analyzed using BioChemDDI. As a result, 24, 18 and 20 out of the top 30 predicted cancer-related drugs were confirmed by the databases. These experimental results demonstrate that BioChemDDI is a useful model to predict DDIs and can provide reliable candidates for biological experiments. The web server of BioChemDDI predictor is freely available to conduct further studies.

Exploration of chemical space with partial labeled noisy student self-training and self-supervised graph embedding

BACKGROUND

Drug discovery is time-consuming and costly. Machine learning, especially deep learning, shows great potential in quantitative structure-activity relationship (QSAR) modeling to accelerate drug discovery process and reduce its cost. A big challenge in developing robust and generalizable deep learning models for QSAR is the lack of a large amount of data with high-quality and balanced labels. To address this challenge, we developed a self-training method, Partially LAbeled Noisy Student (PLANS), and a novel self-supervised graph embedding, Graph-Isomorphism-Network Fingerprint (GINFP), for chemical compounds representations with substructure information using unlabeled data. The representations can be used for predicting chemical properties such as binding affinity, toxicity, and others. PLANS-GINFP allows us to exploit millions of unlabeled chemical compounds as well as labeled and partially labeled pharmacological data to improve the generalizability of neural network models.

RESULTS

We evaluated the performance of PLANS-GINFP for predicting Cytochrome P450 (CYP450) binding activity in a CYP450 dataset and chemical toxicity in the Tox21 dataset. The extensive benchmark studies demonstrated that PLANS-GINFP could significantly improve the performance in both cases by a large margin. Both PLANS-based self-training and GINFP-based self-supervised learning contribute to the performance improvement.

CONCLUSION

To better exploit chemical structures as an input for machine learning algorithms, we proposed a self-supervised graph neural network-based embedding method that can encode substructure information. Furthermore, we developed a model agnostic self-training method, PLANS, that can be applied to any deep learning architectures to improve prediction accuracies. PLANS provided a way to better utilize partially labeled and unlabeled data. Comprehensive benchmark studies demonstrated their potentials in predicting drug metabolism and toxicity profiles using sparse, noisy, and imbalanced data. PLANS-GINFP could serve as a general solution to improve the predictive modeling for QSAR modeling.

Predicting combinations of drugs by exploiting graph embedding of heterogeneous networks

Background

Drug combination, offering an insight into the increased therapeutic efficacy and reduced toxicity, plays an essential role in the therapy of many complex diseases. Although significant efforts have been devoted to the identification of drugs, the identification of drug combination is still a challenge. The current algorithms assume that the independence of feature selection and drug prediction procedures, which may result in an undesirable performance.

Results

To address this issue, we develop a novel Semi-supervised Heterogeneous Network Embedding algorithm (called SeHNE) to predict the combination patterns of drugs by exploiting the graph embedding. Specifically, the ATC similarity of drugs, drug–target, and protein–protein interaction networks are integrated to construct the heterogeneous networks. Then, SeHNE jointly learns drug features by exploiting the topological structure of heterogeneous networks and predicting drug combination. One distinct advantage of SeHNE is that features of drugs are extracted under the guidance of classification, which improves the quality of features, thereby enhancing the performance of prediction of drugs. Experimental results demonstrate that the proposed algorithm is more accurate than state-of-the-art methods on various data, implying that the joint learning is promising for the identification of drug combination.

Conclusions

The proposed model and algorithm provide an effective strategy for the prediction of combinatorial patterns of drugs, implying that the graph-based drug prediction is promising for the discovery of drugs.

Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9

Cytochrome P450 2C9 (CYP2C9) is a major drug-metabolizing enzyme that represents 20% of the hepatic CYPs and is responsible for the metabolism of 15% of drugs. A general concern in drug discovery is to avoid the inhibition of CYP leading to toxic drug accumulation and adverse drug-drug interactions. However, the prediction of CYP inhibition remains challenging due to its complexity. We developed an original machine learning approach for the prediction of drug-like molecules inhibiting CYP2C9. We created new predictive models by integrating CYP2C9 protein structure and dynamics knowledge, an original selection of physicochemical properties of CYP2C9 inhibitors, and machine learning modeling. We tested the machine learning models on publicly available data and demonstrated that our models successfully predicted CYP2C9 inhibitors with an accuracy, sensitivity and specificity of approximately 80%. We experimentally validated the developed approach and provided the first identification of the drugs vatalanib, piriqualone, ticagrelor and cloperidone as strong inhibitors of CYP2C9 with IC values <18 μM and sertindole, asapiprant, duvelisib and dasatinib as moderate inhibitors with IC50 values between 40 and 85 μM. Vatalanib was identified as the strongest inhibitor with an IC50 value of 0.067 μM. Metabolism assays allowed the characterization of specific metabolites of abemaciclib, cloperidone, vatalanib and tarafenacin produced by CYP2C9. The obtained results demonstrate that such a strategy could improve the prediction of drug-drug interactions in clinical practice and could be utilized to prioritize drug candidates in drug discovery pipelines.

Dietary stigmastane-type saponins as promising dual-target directed inhibitors of SARS-CoV-2 proteases: a structure-based screening

Despite the development of COVID-19 vaccines, at present, there is still no approved antiviral drug against the pandemic. The SARS-CoV-2 3-chymotrypsin-like proteases (S-3CLpro) and papain-like protease (S-PLpro) are essential for the viral proliferation cycle, hence attractive drug targets. Plant-based dietary components that have been extensively reported for antiviral activities may serve as cheap sources of preventive nutraceuticals and/or antiviral drugs. A custom-made library of 176 phytochemicals from five West African antiviral culinary herbs was screened for potential dual-target-directed inhibitors of S-3CLpro and S-PLpro in silico. The docking analysis revealed fifteen steroidal saponins (FSS) from Vernonia amygdalina with the highest binding tendency for the active sites of S-3CLpro and S-PLpro. In an optimized docking analysis, the FSS were further docked against four equilibrated conformers of the S-3CLpro and S-PLpro. Three stigmastane-type steroidal saponins (vernonioside A2, vernonioside A4 and vernonioside D2) were revealed as the lead compounds. These compounds interacted with the catalytic residues of both S-3CLpro and S-PLpro, thereby exhibiting dual inhibitory potential against these SARS-CoV-2 cysteine proteases. The binding free energy calculations further corroborated the static and optimized docking analysis. The complexed proteases with these promising phytochemicals were stable during a full atomistic MD simulation while the phytochemicals exhibited favourable physicochemical and ADMET properties, hence, recommended as promising inhibitors of SARS-CoV-2 cysteine proteases.

FP-ADMET: a compendium of fingerprint-based ADMET prediction models

MOTIVATION

The absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs plays a key role in determining which among the potential candidates are to be prioritized. In silico approaches based on machine learning methods are becoming increasing popular, but are nonetheless limited by the availability of data. With a view to making both data and models available to the scientific community, we have developed FPADMET which is a repository of molecular fingerprint-based predictive models for ADMET properties. In this article, we have examined the efficacy of fingerprint-based machine learning models for a large number of ADMET-related properties. The predictive ability of a set of 20 different binary fingerprints (based on substructure keys, atom pairs, local path environments, as well as custom fingerprints such as all-shortest paths) for over 50 ADMET and ADMET-related endpoints have been evaluated as part of the study. We find that for a majority of the properties, fingerprint-based random forest models yield comparable or better performance compared with traditional 2D/3D molecular descriptors.

AVAILABILITY

The models are made available as part of open access software that can be downloaded from https://gitlab.com/vishsoft/fpadmet .

CYPlebrity: Machine learning models for the prediction of inhibitors of cytochrome P450 enzymes

The vast majority of approved drugs are metabolized by the five major cytochrome P450 (CYP) isozymes, 1A2, 2C9, 2C19, 2D6 and 3A4. Inhibition of CYP isozymes can cause drug-drug interactions with severe pharmacological and toxicological consequences. Computational methods for the fast and reliable prediction of the inhibition of CYP isozymes by small molecules are therefore of high interest and relevance to pharmaceutical companies and a host of other industries, including the cosmetics and agrochemical industries. Today, a large number of machine learning models for predicting the inhibition of the major CYP isozymes by small molecules are available. With this work we aim to go beyond the coverage of existing models, by combining data from several major public and proprietary sources. More specifically, we used up to 18815 compounds with measured bioactivities to train random forest classification models for the individual CYP isozymes. A major advantage of the new data collection over existing ones is the better representation of the minority class, the CYP inhibitors. With the new data collection we achieved inhibitor-to-non-inhibitor ratios in the order of 1:1 (CYP1A2) to 1:3 (CYP2D6). We show that our models reach competitive performance on external data, with Matthews correlation coefficients (MCCs) ranging from 0.62 (CYP2C19) to 0.70 (CYP2D6), and areas under the receiver operating characteristic curve (AUCs) between 0.89 (CYP2C19) and 0.92 (CYPs 2D6 and 3A4). Importantly, the models show a high level of robustness, reflected in a good predictivity also for compounds that are structurally dissimilar to the compounds represented in the training data. The best models presented in this work are freely accessible for academic research via a web service.

Novel A-Ring Chalcone Derivatives of Oleanolic and Ursolic Amides with Anti-Proliferative Effect Mediated through ROS-Triggered Apoptosis

A series of A-ring modified oleanolic and ursolic acid derivatives including C28 amides (3-oxo-C2-nicotinoylidene/furfurylidene, 3β-hydroxy-C2-nicotinoylidene, 3β-nicotinoyloxy-, 2-cyano-3,4-seco-4(23)-ene, indolo-, lactame and azepane) were synthesized and screened for their cytotoxic activity against the NCI-60 cancer cell line panel. The results of the first assay of thirty-two tested compounds showed that eleven derivatives exhibited cytotoxicity against cancer cells, and six of them were selected for complete dose-response studies. A systematic study of local SARs has been carried out by comparative analysis of potency distributions and similarity relationships among the synthesized compounds using network-like similarity graphs. Among the oleanane type triterpenoids, C2-[4-pyridinylidene]-oleanonic C28-morpholinyl amide exhibited sub-micromolar potencies against 15 different tumor cell lines and revealed particular selectivity for non-small cell lung cancer (HOP-92) with a GI50 value of 0.0347 μM. On the other hand, superior results were observed for C2-[3-pyridinylidene]-ursonic N-methyl-piperazinyl amide 29, which exhibited a broad-spectrum inhibition activity with GI50 < 1 μM against 33 tumor cell lines and <2 μM against all 60 cell lines. This compound has been further evaluated for cell cycle analysis to decipher the mechanism of action. The data indicate that compound 29 could exhibit both cytostatic and cytotoxic activity, depending on the cell line evaluated. The cytostatic activity appears to be determined by induction of the cell cycle arrest at the S (MCF-7, SH-SY5Y cells) or G0/G1 phases (A549 cells), whereas cytotoxicity of the compound against normal cells is nonspecific and arises from apoptosis without significant alterations in cell cycle distribution (HEK293 cells). Our results suggest that the antiproliferative effect of compound 29 is mediated through ROS-triggered apoptosis that involves mitochondrial membrane potential depolarization and caspase activation.

Development of Robust Quantitative Structure-Activity Relationship Models for CYP2C9, CYP2D6, and CYP3A4 Catalysis and Inhibition

Cytochrome P450 enzymes are responsible for the metabolism of >75% of marketed drugs, making it essential to identify the contributions of individual cytochromes P450 to the total clearance of a new candidate drug. Overreliance on one cytochrome P450 for clearance levies a high risk of drug-drug interactions; and considering that several human cytochrome P450 enzymes are polymorphic, it can also lead to highly variable pharmacokinetics in the clinic. Thus, it would be advantageous to understand the likelihood of new chemical entities to interact with the major cytochrome P450 enzymes at an early stage in the drug discovery process. Typical screening assays using human liver microsomes do not provide sufficient information to distinguish the specific cytochromes P450 responsible for clearance. In this regard, we experimentally assessed the metabolic stability of ∼5000 compounds for the three most prominent xenobiotic metabolizing human cytochromes P450, i.e., CYP2C9, CYP2D6, and CYP3A4, and used the data sets to develop quantitative structure-activity relationship models for the prediction of high-clearance substrates for these enzymes. Screening library included the NCATS Pharmaceutical Collection, comprising clinically approved low-molecular-weight compounds, and an annotated library consisting of drug-like compounds. To identify inhibitors, the library was screened against a luminescence-based cytochrome P450 inhibition assay; and through crossreferencing hits from the two assays, we were able to distinguish substrates and inhibitors of these enzymes. The best substrate and inhibitor models (balanced accuracies ∼0.7), as well as the data used to develop these models, have been made publicly available (https://opendata.ncats.nih.gov/adme) to advance drug discovery across all research groups. SIGNIFICANCE STATEMENT: In drug discovery and development, drug candidates with indiscriminate cytochrome P450 metabolic profiles are considered advantageous, since they provide less risk of potential issues with cytochrome P450 polymorphisms and drug-drug interactions. This study developed robust substrate and inhibitor quantitative structure-activity relationship models for the three major xenobiotic metabolizing cytochromes P450, i.e., CYP2C9, CYP2D6, and CYP3A4. The use of these models early in drug discovery will enable project teams to strategize or pivot when necessary, thereby accelerating drug discovery research.

Flavonoid content of the Libyan Onosma Cyrenaicum: isolation, identification, electronic chemical reactivity, drug likeness, docking, and MD study

In this work, an attempt to identify the flavonoid content of the Libyan Onosma Cyrenaicum led to the isolation of three flavonoids 7,8-dihydroxy-2-(4-hydroxyphenyl)-4H-chromen-4-one(GE-001), 5,7-dihydroxy-2-(3-hydroxy-4-methoxy phenyl)-4H-chromen-4-one (GE-002) and 5,7-dihydroxy-3-(4-hydroxyphenyl)-4H-chromen-4-one (GE-003), the isolated compounds were characterized using ¹H and ¹³C-NMR techniques. A further DFT study at ωB97-XD with 6-311++G** basis set in water was conducted to calculate the isolated compounds' global and local reactivity descriptors and Fukui indices along with their antioxidant activity. The drug-likeness and bioactivity properties of the isolated compounds were estimated and discussed. Finally, GE-001, GE-002, and GE-003 were docked into HCV NS5B polymerase active siteand this was followed by molecular dynamic simulation to certify the obtained docking result and to obtain the MM-GBSA free binding energyy of the isolated compounds. Communicated by Ramaswamy H. Sarma.