NADPHnet: a novel strategy to predict compounds for regulation of NADPH metabolism via network-based methods.

Identification of compounds to modulate NADPH metabolism is crucial for understanding complex diseases and developing effective therapies. However, the complex nature of NADPH metabolism poses challenges in achieving this goal. In this study, we proposed a novel strategy named NADPHnet to predict key proteins and drug-target interactions related to NADPH metabolism via network-based methods. Different from traditional approaches only focusing on one single protein, NADPHnet could screen compounds to modulate NADPH metabolism from a comprehensive view. Specifically, NADPHnet identified key proteins involved in regulation of NADPH metabolism using network-based methods, and characterized the impact of natural products on NADPH metabolism using a combined score, NADPH-Score. NADPHnet demonstrated a broader applicability domain and improved accuracy in the external validation set. This approach was further employed along with molecular docking to identify 27 compounds from a natural product library, 6 of which exhibited concentration-dependent changes of cellular NADPH level within 100 µM, with Oxyberberine showing promising effects even at 10 µM. Mechanistic and pathological analyses of Oxyberberine suggest potential novel mechanisms to affect diabetes and cancer. Overall, NADPHnet offers a promising method for prediction of NADPH metabolism modulation and advances drug discovery for complex diseases.

AptaDB: a comprehensive database integrating aptamer-target interactions.

Aptamers have emerged as research hotspots of the next generation due to excellent performance benefits and application potentials in pharmacology, medicine, and analytical chemistry. Despite the numerous aptamer investigations, the lack of comprehensive data integration has hindered the development of computational methods for aptamers and the reuse of aptamers. A public access database named AptaDB, derived from experimentally validated data manually collected from the literature, was hence developed, integrating comprehensive aptamer-related data, which include six key components: (i) experimentally validated aptamer-target interaction information, (ii) aptamer property information, (iii) structure information of aptamer, (iv) target information, (v) experimental activity information, and (vi) algorithmically calculated similar aptamers. AptaDB currently contains 1350 experimentally validated aptamer-target interactions, 1230 binding affinity constants, 1293 aptamer sequences, and more. Compared to other aptamer databases, it contains twice the number of entries found in available databases. The collection and integration of the above information categories is unique among available aptamer databases and provides a user-friendly interface. AptaDB will also be continuously updated as aptamer research evolves. We expect that AptaDB will become a powerful source for aptamer rational design and a valuable tool for aptamer screening in the future. For access to AptaDB, please visit http://lmmd.ecust.edu.cn/aptadb/.

mtADENet: A novel interpretable method integrating multiple types of network-based inference approaches for prediction of adverse drug events.

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and accelerate drug safety assessment. ADEs are mainly caused by unintended interactions with primary or additional targets (off-targets). In this study, we proposed a novel interpretable method named mtADENet, which integrates multiple types of network-based inference approaches for ADE prediction. Different from phenotype-based methods, mtADENet introduced computational target profiles predicted by network-based methods to bridge the gap between chemical structures and ADEs, and hence can not only predict ADEs for drugs and novel compounds within or outside the drug-ADE association network, but also provide insights for the elucidation of molecular mechanisms of the ADEs caused by drugs. We constructed a series of network-based prediction models for 23 ADE categories. These models achieved high AUC values ranging from 0.865 to 0.942 in 10-fold cross validation. The best model further showed high performance on four external validation sets, which outperformed two previous network-based methods. To show the practical value of mtADENet, we performed case studies on developmental neurotoxicity and cardio-oncology, and over 50 % of predicted ADEs and targets for drugs and novel compounds were validated by literature. Moreover, mtADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer/). In summary, mtADENet would be a powerful tool for ADE prediction and drug safety assessment in drug discovery and development.

Network-Based Methods and Their Applications in Drug Discovery.

Drug discovery is time-consuming, expensive, and predominantly follows the "one drug → one target → one disease" paradigm. With the rapid development of systems biology and network pharmacology, a novel drug discovery paradigm, "multidrug → multitarget → multidisease", has emerged. This new holistic paradigm of drug discovery aligns well with the essence of networks, leading to the emergence of network-based methods in the field of drug discovery. In this Perspective, we initially introduce the concept and data sources of networks and highlight classical methodologies employed in network-based methods. Subsequently, we focus on the practical applications of network-based methods across various areas of drug discovery, such as target prediction, virtual screening, prediction of drug therapeutic effects or adverse drug events, and elucidation of molecular mechanisms. In addition, we provide representative web servers for researchers to use network-based methods in specific applications. Finally, we discuss several challenges of network-based methods and the directions for future development. In a word, network-based methods could serve as powerful tools to accelerate drug discovery.

Pharmaceutical Cocrystal Discovery via 3D-SMINBR: A New Network Recommendation Tool Augmented by 3D Molecular Conformations.

Cocrystals have significant potential in various fields such as chemistry, material, and medicine. For instance, pharmaceutical cocrystals have the ability to address issues associated with physicochemical and biopharmaceutical properties. However, it can be challenging to find proper coformers to form cocrystals with drugs of interest. Herein, a new in silico tool called 3D substructure-molecular-interaction network-based recommendation (3D-SMINBR) has been developed to address this problem. This tool first integrated 3D molecular conformations with a weighted network-based recommendation model to prioritize potential coformers for target drugs. In cross-validation, the performance of 3D-SMINBR surpassed the 2D substructure-based predictive model SMINBR in our previous study. Additionally, the generalization capability of 3D-SMINBR was confirmed by testing on unseen cocrystal data. The practicality of this tool was further demonstrated by case studies on cocrystal screening of armillarisin A (Arm) and isoimperatorin (iIM). The obtained Arm-piperazine and iIM-salicylamide cocrystals present improved solubility and dissolution rate compared to their parent drugs. Overall, 3D-SMINBR augmented by 3D molecular conformations would be a useful network-based tool for cocrystal discovery. A free web server for 3D-SMINBR can be freely accessed at http://lmmd.ecust.edu.cn/netcorecsys/.

In silico prediction of drug-induced liver injury with a complementary integration strategy based on hybrid representation.

Drug-induced liver injury (DILI) is one of the major causes of drug withdrawals, acute liver injury and blackbox warnings. Clinical diagnosis of DILI is a huge challenge due to the complex pathogenesis and lack of specific biomarkers. In recent years, machine learning methods have been used for DILI risk assessment, but the model generalization does not perform satisfactorily. In this study, we constructed a large DILI data set and proposed an integration strategy based on hybrid representations for DILI prediction (HR-DILI). Benefited from feature integration, the hybrid graph neural network models outperformed single representation-based models, among which hybrid-GraphSAGE showed balanced performance in cross-validation with AUC (area under the curve) as 0.804±0.019. In the external validation set, HR-DILI improved the AUC by 6.4 %-35.9 % compared to the base model with a single representation. Compared with published DILI prediction models, HR-DILI had better and balanced performance. The performance of local models for natural products and synthetic compounds were also explored. Furthermore, eight key descriptors and six structural alerts associated with DILI were analyzed to increase the interpretability of the models. The improved performance of HR-DILI indicated that it would provide reliable guidance for DILI risk assessment.

Investigation of Anti-Alzheimer's Mechanisms of Sarsasapogenin Derivatives by Network-Based Combining Structure-Based Methods.

Alzheimer's disease (AD), a neurodegenerative disease with no cure, affects millions of people worldwide and has become one of the biggest healthcare challenges. Some investigated compounds play anti-AD roles at the cellular or the animal level, but their molecular mechanisms remain unclear. In this study, we designed a strategy combining network-based and structure-based methods together to identify targets for anti-AD sarsasapogenin derivatives (AAs). First, we collected drug-target interactions (DTIs) data from public databases, constructed a global DTI network, and generated drug-substructure associations. After network construction, network-based models were built for DTI prediction. The best bSDTNBI-FCFP_4 model was further used to predict DTIs for AAs. Second, a structure-based molecular docking method was employed for rescreening the prediction results to obtain more credible target proteins. Finally, in vitro experiments were conducted for validation of the predicted targets, and Nrf2 showed significant evidence as the target of anti-AD compound AA13. Moreover, we analyzed the potential mechanisms of AA13 for the treatment of AD. Generally, our combined strategy could be applied to other novel drugs or compounds and become a useful tool in identification of new targets and elucidation of disease mechanisms. Our model was deployed on our NetInfer web server (http://lmmd.ecust.edu.cn/netinfer/).

EDC-Predictor: A Novel Strategy for Prediction of Endocrine-Disrupting Chemicals by Integrating Pharmacological and Toxicological Profiles.

Identification of endocrine-disrupting chemicals (EDCs) is crucial in the reduction of human health risks. However, it is hard to do so because of the complex mechanisms of the EDCs. In this study, we propose a novel strategy named EDC-Predictor to integrate pharmacological and toxicological profiles for the prediction of EDCs. Different from conventional methods that only focus on a few nuclear receptors (NRs), EDC-Predictor considers more targets. It uses computational target profiles from network-based and machine learning-based methods to characterize compounds, including both EDCs and non-EDCs. The best model constructed by these target profiles outperformed those models by molecular fingerprints. In a case study to predict NR-related EDCs, EDC-Predictor showed a wider applicability domain and higher accuracy than four previous tools. Another case study further demonstrated that EDC-Predictor could predict EDCs targeting other proteins rather than NRs. Finally, a free web server was developed to make EDC prediction easier (http://lmmd.ecust.edu.cn/edcpred/). In summary, EDC-Predictor would be a powerful tool in EDC prediction and drug safety assessment.

Uncovering the Oxidative Stress Mechanisms and Targets in Alzheimer's Disease by Integrating Phenotypic Screening Data and Polypharmacology Networks.

BACKGROUND: The oxidative stress hypothesis is challenging the dominant position of amyloid-ß (Aß) in the field of understanding the mechanisms of Alzheimer's disease (AD), a complicated and untreatable neurodegenerative disease. OBJECTIVE: The goal of the present study was to uncover the oxidative stress mechanisms causing AD, as well as the potential therapeutic targets and neuroprotective drugs against oxidative stress mechanisms. METHODS: In this study, a systematic workflow combining pharmacological experiments and computational prediction were proposed. 222 drugs and natural products were collected first and then tested on SH-SY5Y cells to obtain phenotypic screening data on neuroprotection. The preliminary screening data were integrated with drug-target interactions (DTIs) and multi-scale biomedical data, which were analyzed with statistical tests and gene set enrichment analysis. A polypharmacology network was further constructed for investigation. RESULTS: 340 DTIs were matched in multiple databases, and 222 cell viability ratios were calculated for experimental compounds. We identified significant potential therapeutic targets based on oxidative stress mechanisms for AD, including NR3C1, SHBG, ESR1, PGR, and AVPR1A, which might be closely related to neuroprotective effects and pathogenesis. 50% of the top 14 enriched pathways were found to correlate with AD, such as arachidonic acid metabolism and neuroactive ligand-receptor interaction. Several approved drugs in this research were also found to exert neuroprotective effects against oxidative stress mechanisms, including beclometasone, methylprednisolone, and conivaptan. CONCLUSION: Our results indicated that NR3C1, SHBG, ESR1, PGR, and AVPR1A were promising therapeutic targets and several drugs may be repurposed from the perspective of oxidative stress and AD.

In Silico discovery of aptamers with an enhanced library design strategy.

With advances in force fields and algorithms, robust tools have been developed for molecular simulation of three-dimensional structures of nucleic acids and investigation of aptamer-target interactions. The traditional aptamer discovery technique, Systematic Evolution of Ligands by EXponential enrichment (SELEX), continues to suffer from high investment and low return, while in vitro screening by simulated SELEX remains a challenging task, where more accurate structural modeling and enhanced sampling limit the large-scale application of the method. Here, we proposed a modified aptamer enhanced library design strategy to facilitate the screening of target-binding aptamers. In this strategy, a comprehensive analysis of the original complexes and the target secondary structure were used to construct an enhanced initial library for screening. Our enhanced sequence library design strategy based on the target secondary structure explored a certain sequence space while ensuring the accuracy of the structural conformation and the calculation method. In an enhanced library of only a few dozen sequences, four sequences showed a similar or better binding free energy than the original aptamer, with consistently high binding stability over three rounds of multi-timescale simulations, ranging from - 30.27 to - 32.25 kcal/mol. Consequently, the enhanced library strategy based on the target secondary structure is shown to have very significant potential as a new aptamer design and optimization strategy.

Identification of vital chemical information via visualization of graph neural networks.

Qualitative or quantitative prediction models of structure-activity relationships based on graph neural networks (GNNs) are prevalent in drug discovery applications and commonly have excellently predictive power. However, the network information flows of GNNs are highly complex and accompanied by poor interpretability. Unfortunately, there are relatively less studies on GNN attributions, and their developments in drug research are still at the early stages. In this work, we adopted several advanced attribution techniques for different GNN frameworks and applied them to explain multiple drug molecule property prediction tasks, enabling the identification and visualization of vital chemical information in the networks. Additionally, we evaluated them quantitatively with attribution metrics such as accuracy, sparsity, fidelity and infidelity, stability and sensitivity; discussed their applicability and limitations; and provided an open-source benchmark platform for researchers. The results showed that all attribution techniques were effective, while those directly related to the predicted labels, such as integrated gradient, preferred to have better attribution performance. These attribution techniques we have implemented could be directly used for the vast majority of chemical GNN interpretation tasks.

Development of In Silico Models for Predicting Potential Time-Dependent Inhibitors of Cytochrome P450 3A4.

Cytochrome P450 3A4 (CYP3A4) is one of the major drug metabolizing enzymes in the human body and metabolizes ∼30-50% of clinically used drugs. Inhibition of CYP3A4 must always be considered in the development of new drugs. Time-dependent inhibition (TDI) is an important P450 inhibition type that could cause undesired drug-drug interactions. Therefore, identification of CYP3A4 TDI by a rapid convenient way is of great importance to any new drug discovery effort. Here, we report the development of in silico classification models for prediction of potential CYP3A4 time-dependent inhibitors. On the basis of the CYP3A4 TDI data set that we manually collected from literature and databases, both conventional machine learning and deep learning models were constructed. The comparisons of different sampling strategies, molecular representations, and machine-learning algorithms showed the benefits of a balanced data set and the deep-learning model featured by GraphConv. The generalization ability of the best model was tested by screening an external data set, and the prediction results were validated by biological experiments. In addition, several structural alerts that are relevant to CYP3A4 time-dependent inhibitors were identified via information gain and frequency analysis. We anticipate that our effort would be useful for identification of potential CYP3A4 time-dependent inhibitors in drug discovery and design.

Prediction of anti-inflammatory peptides by a sequence-based stacking ensemble model named AIPStack.

Accurate and efficient identification of anti-inflammatory peptides (AIPs) is crucial for the treatment of inflammation. Here, we proposed a two-layer stacking ensemble model, AIPStack, to effectively predict AIPs. At first, we constructed a new dataset for model building and validation. Then, peptide sequences were represented by hybrid features, which were fused by two amino acid composition descriptors. Next, the stacking ensemble model was constructed by random forest and extremely randomized tree as the base-classifiers and logistic regression as the meta-classifier to receive the outputs from the base-classifiers. AIPStack achieved an AUC of 0.819, accuracy of 0.755, and MCC of 0.510 on the independent set 3, which were higher than other AIP predictors. Furthermore, the essential sequence features were highlighted by the Shapley Additive exPlanation (SHAP) method. It is anticipated that AIPStack could be used for AIP prediction in a high-throughput manner and facilitate the hypothesis-driven experimental design.

Profiling prediction of nuclear receptor modulators with multi-task deep learning methods: toward the virtual screening.

Nuclear receptors (NRs) are ligand-activated transcription factors, which constitute one of the most important targets for drug discovery. Current computational strategies mainly focus on a single target, and the transfer of learned knowledge among NRs was not considered yet. Herein we proposed a novel computational framework named NR-Profiler for prediction of potential NR modulators with high affinity and specificity. First, we built a comprehensive NR data set including 42 684 interactions to connect 42 NRs and 31 033 compounds. Then, we used multi-task deep neural network and multi-task graph convolutional neural network architectures to construct multi-task multi-classification models. To improve the predictive capability and robustness, we built a consensus model with an area under the receiver operating characteristic curve (AUC) = 0.883. Compared with conventional machine learning and structure-based approaches, the consensus model showed better performance in external validation. Using this consensus model, we demonstrated the practical value of NR-Profiler in virtual screening for NRs. In addition, we designed a selectivity score to quantitatively measure the specificity of NR modulators. Finally, we developed a freely available standalone software for users to make profiling predictions for their compounds of interest. In summary, our NR-Profiler provides a useful tool for NR-profiling prediction and is expected to facilitate NR-based drug discovery.

In silico prediction of UGT-mediated metabolism in drug-like molecules via graph neural network.

UDP-glucuronosyltransferases (UGTs) have gained increasing attention as they play important roles in the phase II metabolism of drugs. Due to the time-consuming process and high cost of experimental approaches to identify the metabolic fate of UGT enzymes, in silico methods have been developed to predict the UGT-mediated metabolism of drug-like molecules. We developed consensus models with the combination of machine learning (ML) and graph neural network (GNN) methods to predict if a drug-like molecule is a potential UGT substrate, and then we applied the Weisfeiler-Lehman Network (WLN) model to identify the sites of metabolism (SOMs) of UGT-catalyzed substrates. For the substrate model, the accuracy of the single substrate prediction model on the test set could reach to 0.835. Compared with the single estimators, the consensus models are more stable and have better generalization ability, and the accuracy on the test set reached to 0.851. For the SOM model, the top-1 accuracy of the SOM model on the test set reached to 0.898, outperforming existing works. Thus, in this study, we proposed a computational framework, named Meta-UGT, which would provide a useful tool for the prediction and optimization of metabolic profiles and drug design.

Investigation of the mechanism of Shen Qi Wan prescription in the treatment of T2DM via network pharmacology and molecular docking.

Shen Qi Wan (SQW) prescription has been used to treat type 2 diabetes mellitus (T2DM) for thousands of years, but its pharmacological mechanism is still unclear. The network pharmacology method was used to reveal the potential pharmacological mechanism of SQW in the treatment of T2DM in this study. Nine core targets were identified through protein-protein interaction (PPI) network analysis and KEGG pathway enrichment analysis, which were AKT1, INSR, SLC2A1, EGFR, PPARG, PPARA, GCK, NOS3, and PTPN1. Besides, this study found that SQW treated the T2DM through insulin resistance (has04931), insulin signaling pathway (has04910), adipocytokine signaling pathway (has04920), AMPK signaling pathway (has04152) and FoxO signaling pathway (has04068) via ingredient-hub target-pathway network analysis. Finally, molecular docking was used to verify the drug-target interaction network in this research. This study provides a certain explanation for treating T2DM by SQW prescription, and provides a certain angle and method for researchers to study the mechanism of TCM in the treatment of complex diseases. Supplementary information: The online version contains supplementary material available at 10.1007/s40203-022-00124-2.

In silico prediction of potential drug-induced nephrotoxicity with machine learning methods.

In recent years, drug-induced nephrotoxicity has been one of the main reasons for the failure of drug development. Early prediction of the nephrotoxicity for drug candidates is critical to the success of clinical trials. Therefore, it is very important to construct an effective model that can predict the potential nephrotoxicity of compounds. Machine learning methods have been widely used to predict the physicochemical properties, biological activities, and safety assessment of compounds. In this study, we manually collected 777 valid drug data and constructed a total of 72 classification models using nine types of molecular fingerprints combined with different machine learning algorithms. From experimental literature and the US FDA Drugs Database, some marketed drugs were screened for external validation of the models. Finally, three models exhibited good performance in the prediction of nephrotoxicity of both chemical drugs and Chinese herbal medicines. The best model was the support vector machine algorithm combined with CDK graph only fingerprint. Furthermore, the applicability domain of the models was analyzed according to the OECD principles, and we also used the SARpy and information gain methods to find eight substructures that might cause nephrotoxicity, so as to attract attention in the future drug discovery.

Drug Repurposing for Newly Emerged Diseases via Network-based Inference on a Gene-disease-drug Network.

Identification of disease-drug associations is an effective strategy for drug repurposing, especially in searching old drugs for newly emerged diseases like COVID-19. In this study, we put forward a network-based method named NEDNBI to predict disease-drug associations based on a gene-disease-drug tripartite network, which could be applied in drug repurposing. The novelty of our method lies in the fact that no negative data are required, and new disease could be added into the disease-drug network with gene as the bridge. The comprehensive evaluation results showed that the proposed method had good performance, with AUC value 0.948±0.009 for 10-fold cross validation. In a case study, 8 of the 20 predicted old drugs have been tested clinically for the treatment of COVID-19, which illustrated the usefulness of our method in drug repurposing. The source code and data of the method are available at https://github.com/Qli97/NEDNBI.

A multitask GNN-based interpretable model for discovery of selective JAK inhibitors.

The Janus kinase (JAK) family plays a pivotal role in most cytokine-mediated inflammatory and autoimmune responses via JAK/STAT signaling, and administration of JAK inhibitors is a promising therapeutic strategy for several diseases including COVID-19. However, to screen and design selective JAK inhibitors is a daunting task due to the extremely high homology among four JAK isoforms. In this study, we aimed to simultaneously predict pIC50 values of compounds for all JAK subtypes by constructing an interpretable GNN multitask regression model. The final model performance was positive, with R2 values of 0.96, 0.79 and 0.78 on the training, validation and test sets, respectively. Meanwhile, we calculated and visualized atom weights, followed by the rank sum tests and local mean comparisons to obtain key atoms and substructures that could be fine-tuned to design selective JAK inhibitors. Several successful case studies have demonstrated that our approach is feasible and our model could learn the interactions between proteins and small molecules well, which could provide practitioners with a novel way to discover and design JAK inhibitors with selectivity.

wSDTNBI: a novel network-based inference method for virtual screening.

In recent years, the rapid development of network-based methods for the prediction of drug-target interactions (DTIs) provides an opportunity for the emergence of a new type of virtual screening (VS), namely, network-based VS. Herein, we reported a novel network-based inference method named wSDTNBI. Compared with previous network-based methods that use unweighted DTI networks, wSDTNBI uses weighted DTI networks whose edge weights are correlated with binding affinities. A two-pronged approach based on weighted DTI and drug-substructure association networks was employed to calculate prediction scores. To show the practical value of wSDTNBI, we performed network-based VS on retinoid-related orphan receptor γt (RORγt), and purchased 72 compounds for experimental validation. Seven of the purchased compounds were confirmed to be novel RORγt inverse agonists by in vitro experiments, including ursonic acid and oleanonic acid with IC50 values of 10 nM and 0.28 µM, respectively. Moreover, the direct contact between ursonic acid and RORγt was confirmed using the X-ray crystal structure, and in vivo experiments demonstrated that ursonic acid and oleanonic acid have therapeutic effects on multiple sclerosis. These results indicate that wSDTNBI might be a powerful tool for network-based VS in drug discovery.