A 3D bio-printed spheroids based perfusion in vitro liver on chip for drug toxicity assays

Liver is the foremost organ of human being for drug metabolism, and it played a significant role in toxicity evaluation of drugs. Establishing a liver model in vitro can accelerate the process of the drug screening and new drug research and development. We provide a 3D printing based hepatic sinusoid-on-a-chip microdevice that reconstitutes organ-level liver functions to create a drug screening model of toxicity evaluation on chip. The microfluidic device, which recapitulates the hepatic sinusoi...     

In silico models for the prediction of dose-dependent human hepatotoxicity

The liver is extremely vulnerable to the effects of xenobiotics due to its critical role in metabolism. Drug-induced hepatotoxicity may involve any number of different liver injuries, some of which lead to organ failure and, ultimately, patient death. Understandably, liver toxicity is one of the most important dose-limiting considerations in the drug development cycle, yet there remains a serious shortage of methods to predict hepatotoxicity from chemical structure. We discuss our latest findings in this area and present a new, fully general in silico model which is able to predict the occurrence of dose-dependent human hepatotoxicity with greater than 80% accuracy. Utilizing an ensemble recursive partitioning approach, the model classifies compounds as toxic or non-toxic and provides a confidence level to indicate which predictions are most likely to be correct. Only 2D structural information is required and predictions can be made quite rapidly, so this approach is entirely appropriate for data mining applications and for profiling large synthetic and/or virtual libraries.     

Virtual screening of dipeptidyl peptidase-4 inhibitors using quantitative structure–activity relationship-based artificial intelligence and molecular docking of hit compounds

Dipeptidyl peptidase-4 (DPP-4) inhibitors are becoming an essential drug in the treatment of type 2 diabetes mellitus; however, some classes of these drugs exert side effects, including joint pain and pancreatitis. Studies suggest that these side effects might be related to secondary inhibition of DPP-8 and DPP-9. In this study, we identified DPP-4-inhibitor hit compounds selective against DPP-8 and DPP-9. We built a virtual screening workflow using a quantitative structure–activity relationship (QSAR) strategy based on artificial intelligence to allow faster screening of millions of molecules for the DPP-4 target relative to other screening methods. Five regression machine learning algorithms and four classification machine learning algorithms were applied to build virtual screening workflows, with the QSAR model applied using support vector regression (R²_pred 0.78) and the classification QSAR model using the random forest algorithm with 92.2% accuracy. Virtual screening results of > 10 million molecules obtained 2 716 hits compounds with a pIC₅₀ value of > 7.5. Additionally, molecular docking results of several potential hit compounds for DPP-4, DPP-8, and DPP-9 identified CH0002 as showing high inhibitory potential against DPP-4 and low inhibitory potential for DPP-8 and DPP-9 enzymes. These results demonstrated the effectiveness of this technique for identifying DPP-4-inhibitor hit compounds selective for DPP-4 and against DPP-8 and DPP-9 and suggest its potential efficacy for applications to discover hit compounds of other targets.     

New combined model for the prediction of regioselectivity in cytochrome P450/3A4 mediated metabolism

Cytochrome P450 3A4 metabolizes nearly 50% of the drugs currently in clinical use with a broad range of substrate specificity. Early prediction of metabolites of xenobiotic compounds is crucial for cost efficient drug discovery and development. We developed a new combined model, MLite, for the prediction of regioselectivity in the cytochrome P450 3A4 mediated metabolism. In the model, the ensemble catalyticphore- based docking method was implemented for the accessibility prediction, and the activation energy estimation method of Korzekwa et al. was used for the reactivity prediction. Four major metabolic reactions, aliphatic hydroxylation, N-dealkylation, O-dealkylation, and aromatic hydroxylation reaction, were included and the reaction data, metabolite information, were collected for 72 well-known substrates. The 47 drug molecules were used as the training set, and the 25 well-known substrates were used as the test set for the ensemble catalyticphore-based docking method. MLite predicted correctly about 76% of the first two sites in the ranking list of the test set. This predictability is comparable with that of another combined model, MetaSite, and the recently published QSAR model proposed by Sheridan et al. MLite also offers information about binding configurations of the substrate-enzyme complex. This may be useful in drug modification by the structure-based drug design.     

Prediction of drug metabolites using neural machine translation

Metabolic processes in the human body can alter the structure of a drug affecting its efficacy and safety. As a result, the investigation of the metabolic fate of a candidate drug is an essential part of drug design studies. Computational approaches have been developed for the prediction of possible drug metabolites in an effort to assist the traditional and resource-demanding experimental route. Current methodologies are based upon metabolic transformation rules, which are tied to specific enzyme families and therefore lack generalization, and additionally may involve manual work from experts limiting scalability. We present a rule-free, end-to-end learning-based method for predicting possible human metabolites of small molecules including drugs. The metabolite prediction task is approached as a sequence translation problem with chemical compounds represented using the SMILES notation. We perform transfer learning on a deep learning transformer model for sequence translation, originally trained on chemical reaction data, to predict the outcome of human metabolic reactions. We further build an ensemble model to account for multiple and diverse metabolites. Extensive evaluation reveals that the proposed method generalizes well to different enzyme families, as it can correctly predict metabolites through phase I and phase II drug metabolism as well as other enzymes. Compared to existing rule-based approaches, our method has equivalent performance on the major enzyme families while it additionally finds metabolites through less common enzymes. Our results indicate that the proposed approach can provide a comprehensive study of drug metabolism that does not restrict to the major enzyme families and does not require the extraction of transformation rules.

The structure of the drug, represented with a SMILES sequence, is being translated into the structures of possible metabolites that can be formed in the human body.     

Efficient machine learning model for predicting drug-target interactions with case study for Covid-19

BackgroundDiscover possible Drug Target Interactions (DTIs) is a decisive step in the detection of the effects of drugs as well as drug repositioning. There is a strong incentive to develop effective computational methods that can effectively predict potential DTIs, as traditional DTI laboratory experiments are expensive, time-consuming, and labor-intensive. Some technologies have been developed for this purpose, however large numbers of interactions have not yet been detected, the accuracy of their prediction still low, and protein sequences and structured data are rarely used together in the prediction process.MethodsThis paper presents DTIs prediction model that takes advantage of the special capacity of the structured form of proteins and drugs. Our model obtains features from protein amino-acid sequences using physical and chemical properties, and from drugs smiles (Simplified Molecular Input Line Entry System) strings using encoding techniques. Comparing the proposed model with different existing methods under K-fold cross validation, empirical results show that our model based on ensemble learning algorithms for DTI prediction provide more accurate results from both structures and features data.ResultsThe proposed model is applied on two datasets:Benchmark (feature only) datasets and DrugBank (Structure data) datasets. Experimental results obtained by Light-Boost and ExtraTree using structures and feature data results in 98 % accuracy and 0.97 f-score comparing to 94 % and 0.92 achieved by the existing methods. Moreover, our model can successfully predict more yet undiscovered interactions, and hence can be used as a practical tool to drug repositioning.A case study of applying our prediction model on the proteins that are known to be affected by Corona viruses in order to predict the possible interactions among these proteins and existing drugs is performed. Also, our model is applied on Covid-19 related drugs announced on DrugBank. The results show that some drugs like DB00691 and DB05203 are predicted with 100 % accuracy to interact with ACE2 protein. This protein is a self-membrane protein that enables Covid-19 infection. Hence, our model can be used as an effective tool in drug reposition to predict possible drug treatments for Covid-19.     

Computational models to predict blood–brain barrier permeation and CNS activity

The blood-brain permeation of a structurally diverse set of 281 compounds was modeled using linear regression and a multivariate genetic partial least squares (G/PLS) approach. Key structural features affecting the logarithm of blood-brain partitioning (logBB) were captured through statistically significant quantitative structure-activity relationship (QSAR) models. These relationships reveal the importance of logP, polar surface area, and a variety of electrotopological indices for accurate predictions of logBB. The best models reveal an excellent correlation (r > 0.9) for a training set of 58 compounds. Likewise, the comparison of the average logBB values obtained from an ensemble of QSAR models with experimental values also verifies the statistical quality of the models (r > 0.9). The models provide good agreement (r approximately 0.7) between the predicted logBB values for 34 molecules in the external validation set and the experimental values. To further validate the models for use during the drug discovery process, a prediction set of 181 drugs with reported CNS penetration data was used. A >70% success rate is obtained by using any of the QSAR models in the qualitative prediction for CNS permeable (active) drugs. A lower success rate (approximately 60%) was obtained for the best model for CNS impermeable (inactive) drugs. Combining the predictions obtained from all the models (consensus) did not significantly improve the discrimination of CNS active and CNS inactive molecules. Finally, using the therapeutic classification as a guiding tool, the CNS penetration capability of over 2000 compounds in the Synthline database was estimated. The results were very similar to the smaller set of 181 compounds.     

Predicting Absorption-Distribution Properties of Neuroprotective Phosphine-Borane Compounds Using In Silico Modeling and Machine Learning

Phosphine-borane complexes are novel chemical entities with preclinical efficacy in neuronal and ophthalmic disease models. In vitro and in vivo studies showed that the metabolites of these compounds are capable of cleaving disulfide bonds implicated in the downstream effects of axonal injury. A difficulty in using standard in silico methods for studying these drugs is that most computational tools are not designed for borane-containing compounds. Using in silico and machine learning methodologies, the absorption-distribution properties of these unique compounds were assessed. Features examined with in silico methods included cellular permeability, octanol-water partition coefficient, blood-brain barrier permeability, oral absorption and serum protein binding. The resultant neural networks demonstrated an appropriate level of accuracy and were comparable to existing in silico methodologies. Specifically, they were able to reliably predict pharmacokinetic features of known boron-containing compounds. These methods predicted that phosphine-borane compounds and their metabolites meet the necessary pharmacokinetic features for orally active drug candidates. This study showed that the combination of standard in silico predictive and machine learning models with neural networks is effective in predicting pharmacokinetic features of novel boron-containing compounds as neuroprotective drugs.     

Use of surface charges from DFT calculations to predict intestinal absorption

A model for prediction of percent intestinal absorption (%Abs) of neutral molecules was developed based upon surface charges of the molecule calculated by density functional theory (DFT). The surface charges are decomposed into sigma moments which are correlated to a partition coefficient representing transfer of the molecule between water and the epithelial membrane. The model was built and tested using a data set of 241 drugs. It achieved an RMS deviation of 13% on a training set of 38 compounds as well as on a test set of 107 drugs for which the experimental data were classified as high quality. Property maps of the molecule, depicting which atoms contribute to or hinder absorption, are produced to aid drug design.     

超高效液相色谱-四极杆-飞行时间质谱法快速筛查和确证渔药中86种非法添加化学品

建立了超高效液相色谱-四极杆-飞行时间质谱法快速筛查与确证渔药中86种非法添加禁限用药物的方法。渔药以80%(v/v)乙腈水溶液进行提取,通过稀释降低基质效应,采用ACQUITY PREMIER HSS T3色谱柱进行分离,以甲醇和0.1%甲酸水溶液作为流动相进行梯度洗脱,采用电喷雾双喷离子源(Dual AJS ESI)正离子模式分析检测。建立了86种药物的一级精确质量数据库和二级碎片质谱库。在全扫描采集模式下,以化合物的色谱保留时间、精确质量数、同位素分布和同位素丰度比定性;在Target MS/MS采集模式下,通过二级碎片离子的匹配进一步确证化合物,以准分子离子峰的峰面积定量,实现渔药样品中多目标药物的快速定性定量分析。86种药物在各自的线性范围内均呈现良好的线性关系,相关系数均大于0.99,中草药制剂和抗生素粉剂的定量限(LOQ)范围分别为1~15 mg/kg和5~75 mg/kg,添加回收率范围为76.8%~112.1%,相对标准偏差(RSD, n=3)小于11.7%。该方法快速、简便、准确、灵敏,适用于不同种类渔药中禁限用非法添加药物的高通量筛查。将该方法应用于浙江省渔用投入品质量安全监督抽检项目中,共筛查60个样品,其中8种中草药制剂筛查出说明书中未明确标明的药物成分,1种抗生素粉剂未检出有效成分。该研究为渔药的质量安全监控提供了有效的技术手段。     

Classification of highly unbalanced CYP450 data of drugs using cost sensitive machine learning techniques

In this paper, we study the classifications of unbalanced data sets of drugs. As an example we chose a data set of 2D6 inhibitors of cytochrome P450. The human cytochrome P450 2D6 isoform plays a key role in the metabolism of many drugs in the preclinical drug discovery process. We have collected a data set from annotated public data and calculated physicochemical properties with chemoinformatics methods. On top of this data, we have built classifiers based on machine learning methods. Data sets with different class distributions lead to the effect that conventional machine learning methods are biased toward the larger class. To overcome this problem and to obtain sensitive but also accurate classifiers we combine machine learning and feature selection methods with techniques addressing the problem of unbalanced classification, such as oversampling and threshold moving. We have used our own implementation of a support vector machine algorithm as well as the maximum entropy method. Our feature selection is based on the unsupervised McCabe method. The classification results from our test set are compared structurally with compounds from the training set. We show that the applied algorithms enable the effective high throughput in silico classification of potential drug candidates.     

An Algorithm Framework for Drug-Induced Liver Injury Prediction Based on Genetic Algorithm and Ensemble Learning

In the process of drug discovery, drug-induced liver injury (DILI) is still an active research field and is one of the most common and important issues in toxicity evaluation research. It directly leads to the high wear attrition of the drug. At present, there are a variety of computer algorithms based on molecular representations to predict DILI. It is found that a single molecular representation method is insufficient to complete the task of toxicity prediction, and multiple molecular fingerprint fusion methods have been used as model input. In order to solve the problem of high dimensional and unbalanced DILI prediction data, this paper integrates existing datasets and designs a new algorithm framework, Rotation-Ensemble-GA (R-E-GA). The main idea is to find a feature subset with better predictive performance after rotating the fusion vector of high-dimensional molecular representation in the feature space. Then, an Adaboost-type ensemble learning method is integrated into R-E-GA to improve the prediction accuracy. The experimental results show that the performance of R-E-GA is better than other state-of-art algorithms including ensemble learning-based and graph neural network-based methods. Through five-fold cross-validation, the R-E-GA obtains an ACC of 0.77, an F1 score of 0.769, and an AUC of 0.842.     

Non-invasive detection of drug toxicity in rats by solid-phase extraction and MALDI-TOF analysis of urine samples

An access to fast and non-invasive techniques to infer or predict the drug-induced injury caused by newly developed drugs and to monitor therapeutic efficacy of established drugs during treatment are of the outmost importance in pharmaceutical industry and clinical diagnosis. Peptidome and low molecular weight proteome profiling is an emerging technique that allows the recognition of distinctive patterns and differentiation among diverse physiopathological conditions. In this article, we evaluated the utility of peptide/small protein profiling using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) coupled with WCX magnetic bead-based solid-phase extraction as a screening tool for drug toxicity assessment in urine samples. Given that drug-induced injury is primarily reflected in liver, three different, well-described hepatotoxic drugs were chosen for this work. These were: carbon tetrachloride (CCl₄) which induces liver fibrosis, d(+)-galactosamine as a model for acute liver injury, and Escherichia coli-derived lipopolysaccharide to study the damage caused by endotoxins. The profiles obtained with a correct clustering analysis show that this methodology can be used as a non-invasive and straightforward approach to test for potential drug toxicity. Pharmaceutical research and drug development studies could benefit from this methodology as liver injury inducer compounds could be easily detected in vivo by non-invasive means, accelerating the launch of safer drugs to the market.     

Virtual screening of novel noncovalent inhibitors for SARS-CoV 3C-like proteinase

The SARS coronavirus 3C-like proteinase is considered as a potential drug design target for the treatment of severe acute respiratory syndrome (SARS). Owing to the lack of available drugs for the treatment of SARS, the discovery of inhibitors for SARS coronavirus 3C-like proteinase that can potentially be optimized as drugs appears to be highly desirable. We have built a "flexible" three-dimensional model for SARS 3C-like proteinase by homology modeling and multicanonical molecular dynamics method and used the model for virtual screening of chemical databases. After Dock procedures, strategies including pharmocophore model, consensus scoring, and "drug-like" filters were applied in order to accelerate the process and improve the success rate of virtual docking screening hit lists. Forty compounds were purchased and tested by HPLC and colorimetric assay against SARS 3C-like proteinase. Three of them including calmidazolium, a well-known antagonist of calmodulin, were found to inhibit the enzyme with an apparent K(i) from 61 to 178 microM. These active compounds and their binding modes provide useful information for understanding the binding sites and for further selective drug design against SARS and other coronavirus.     

Synthesis of Novel Derivatives of 1,5-Dihydro-4,6-dithio-l,3,5,2-triazaphosphorine-2-oxide from N,N-bis(2-chloroethyl)diisocyanato phosphoramide

Cancer is one of the most serious disease of human beings, and studies on antitumor drugs are still challenging scientists to look for new highly active compounds with low toxicity in this field. Cyclophosphamide (Endoxan), one of the most effective antitumor agents has been widely used in cancer chemotherapy¹. However, acrolein, from its metabolysis of hepatic mixed function oxidases in the liver, is toxic to the urinary system², hence,its clinical usage is restricted. With references to our previous works^3,4,we designed and synthesized a novel type of compounds Ⅰ with a nitrogen mustard group attached to the phosphorus atom of the heterocyclic ring in which the nitrogen atom at position 5 is from a α-substituted amino acid ester.     

Exploring EZH2-Proteasome Dual-Targeting Drug Discovery through a Computational Strategy to Fight Multiple Myeloma

Multiple myeloma is an incurable plasma cell neoplastic disease representing about 10–15% of all haematological malignancies diagnosed in developed countries. Proteasome is a key player in multiple myeloma and proteasome inhibitors are the current first-line of treatment. However, these are associated with limited clinical efficacy due to acquired resistance. One of the solutions to overcome this problem is a polypharmacology approach, namely combination therapy and multitargeting drugs. Several polypharmacology avenues are currently being explored. The simultaneous inhibition of EZH2 and Proteasome 20S remains to be investigated, despite the encouraging evidence of therapeutic synergy between the two. Therefore, we sought to bridge this gap by proposing a holistic in silico strategy to find new dual-target inhibitors. First, we assessed the characteristics of both pockets and compared the chemical space of EZH2 and Proteasome 20S inhibitors, to establish the feasibility of dual targeting. This was followed by molecular docking calculations performed on EZH2 and Proteasome 20S inhibitors from ChEMBL 25, from which we derived a predictive model to propose new EZH2 inhibitors among Proteasome 20S compounds, and vice versa, which yielded two dual-inhibitor hits. Complementarily, we built a machine learning QSAR model for each target but realised their application to our data is very limited as each dataset occupies a different region of chemical space. We finally proceeded with molecular dynamics simulations of the two docking hits against the two targets. Overall, we concluded that one of the hit compounds is particularly promising as a dual-inhibitor candidate exhibiting extensive hydrogen bonding with both targets. Furthermore, this work serves as a framework for how to rationally approach a dual-targeting drug discovery project, from the selection of the targets to the prediction of new hit compounds.     

Structure-based model profiles affinity constant of drugs with hPEPT1 for rapid virtual screening of hPEPT1’s substrate

The human proton-coupled peptide transporter (hPEPT1) with broad substrates is an important route for improving the pharmacokinetic performance of drugs. Thus, it is essential to predict the affinity constant between drug molecule and hPEPT1 for rapid virtual screening of hPEPT1’s substrate during lead optimization, candidate selection and hPEPT1 prodrug design. Here, a structure-based in silico model for 114 compounds was constructed based on eight structural parameters. This model was built by the multiple linear regression method and satisfied all the prerequisites of the regression models. For the entire data set, the r² and adjusted r² values were 0.74 and 0.72, respectively. Then, this model was used to perform substrate/non-substrate classification. For 29 drugs from DrugBank database, all were correctly classified as substrates of hPEPT1. This model was also used to perform substrate/non-substrate classification for 18 drugs and their prodrugs; this QSAR model also can distinguish between the substrate and non-substrate. In conclusion, the QSAR model in this paper was validated by a large external data set, and all results indicated that the developed model was robust, stable, and can be used for rapid virtual screening of hPEPT1’s substrate in the early stage of drug discovery.