Jiansong Fang

Predictions of BuChE Inhibitors Using Support Vector Machine and Naive Bayesian Classification Techniques in Drug Discovery

Butyrylcholinesterase (BuChE, EC 3.1.1.8) is an important pharmacological target for Alzheimers disease (AD) treatment. However, the currently available BuChE inhibitor screening assays are expensive, labor-intensive, and compound-dependent. It is necessary to develop robust in silico methods to predict the activities of BuChE inhibitors for the lead identification. In this investigation, support vector machine (SVM) models and naive Bayesian models were built to discriminate BuChE inhibitors (BuChEIs) from the noninhibitors. Each molecule was initially represented in 1870 structural descriptors (1235 from ADRIANA.Code, 334 from MOE, and 301 from Discovery studio). Correlation analysis and stepwise variable selection method were applied to figure out activity-related descriptors for prediction models. Additionally, structural fingerprint descriptors were added to improve the predictive ability of models, which were measured by cross-validation, a test set validation with 1001 compounds and an external test set validation with 317 diverse chemicals. The best two models gave Matthews correlation coefficient of 0.9551 and 0.9550 for the test set and 0.9132 and 0.9221 for the external test set. To demonstrate the practical applicability of the models in virtual screening, we screened an in-house data set with 3601 compounds, and 30 compounds were selected for further bioactivity assay. The assay results showed that 10 out of 30 compounds exerted significant BuChE inhibitory activities with IC50 values ranging from 0.32 to 22.22 μM, at which three new scaffolds as BuChE inhibitors were identified for the first time. To our best knowledge, this is the first report on BuChE inhibitors using machine learning approaches. The models generated from SVM and naive Bayesian approaches successfully predicted BuChE inhibitors. The study proved the feasibility of a new method for predicting bioactivities of ligands and discovering novel lead compounds.

Discovery of multitarget-directed ligands against Alzheimer's disease through systematic prediction of chemical-protein interactions.

To determine chemical-protein interactions (CPI) is costly, time-consuming, and labor-intensive. In silico prediction of CPI can facilitate the target identification and drug discovery. Although many in silico target prediction tools have been developed, few of them could predict active molecules against multitarget for a single disease. In this investigation, naive Bayesian (NB) and recursive partitioning (RP) algorithms were applied to construct classifiers for predicting the active molecules against 25 key targets toward Alzheimers disease (AD) using the multitarget-quantitative structure-activity relationships (mt-QSAR) method. Each molecule was initially represented with two kinds of fingerprint descriptors (ECFP6 and MACCS). One hundred classifiers were constructed, and their performance was evaluated and verified with internally 5-fold cross-validation and external test set validation. The range of the area under the receiver operating characteristic curve (ROC) for the test sets was from 0.741 to 1.0, with an average of 0.965. In addition, the important fragments for multitarget against AD given by NB classifiers were also analyzed. Finally, the validated models were employed to systematically predict the potential targets for six approved anti-AD drugs and 19 known active compounds related to AD. The prediction results were confirmed by reported bioactivity data and our in vitro experimental validation, resulting in several multitarget-directed ligands (MTDLs) against AD, including seven acetylcholinesterase (AChE) inhibitors ranging from 0.442 to 72.26 μM and four histamine receptor 3 (H3R) antagonists ranging from 0.308 to 58.6 μM. To be exciting, the best MTDL DL0410 was identified as an dual cholinesterase inhibitor with IC50 values of 0.442 μM (AChE) and 3.57 μM (BuChE) as well as a H3R antagonist with an IC50 of 0.308 μM. This investigation is the first report using mt-QASR approach to predict chemical-protein interaction for a single disease and discovering highly potent MTDLs. This protocol may be useful for in silico multitarget prediction of other diseases.

Inhibition of acetylcholinesterase by two genistein derivatives: kinetic analysis, molecular docking and molecular dynamics simulation.

In this study two genistein derivatives (G1 and G2) are reported as inhibitors of acetylcholinesterase (AChE) and butyrylcholinesterase (BuChE), and differences in the inhibition of AChE are described. Although they differ in structure by a single methyl group, the inhibitory effect of G1 (IC50=264 nmol/L) on AChE was 80 times stronger than that of G2 (IC50=21,210 nmol/L). Enzyme-kinetic analysis, molecular docking and molecular dynamics (MD) simulations were conducted to better understand the molecular basis for this difference. The results obtained by kinetic analysis demonstrated that G1 can interact with both the catalytic active site and peripheral anionic site of AChE. The predicted binding free energies of two complexes calculated by the molecular mechanics/generalized born surface area (MM/GBSA) method were consistent with the experimental data. The analysis of the individual energy terms suggested that a difference between the net electrostatic contributions (ΔEele+ΔGGB) was responsible for the binding affinities of these two inhibitors. Additionally, analysis of the molecular mechanics and MM/GBSA free energy decomposition revealed that the difference between G1 and G2 originated from interactions with Tyr124, Glu292, Val294 and Phe338 of AChE. In conclusion, the results reveal significant differences at the molecular level in the mechanism of inhibition of AChE by these structurally related compounds.

Network pharmacology-based study on the mechanism of action for herbal medicines in Alzheimer treatment.

ETHNOPHARMACOLOGICAL RELEVANCE Alzheimers disease (AD), as the most common type of dementia, has brought a heavy economic burden to healthcare system around the world. However, currently there is still lack of effective treatment for AD patients. Herbal medicines, featured as multiple herbs, ingredients and targets, have accumulated a great deal of valuable experience in treating AD although the exact molecular mechanisms are still unclear. MATERIALS AND METHODS In this investigation, we proposed a network pharmacology-based method, which combined large-scale text-mining, drug-likeness filtering, target prediction and network analysis to decipher the mechanisms of action for the most widely studied medicinal herbs in AD treatment. RESULTS The text mining of PubMed resulted in 10 herbs exhibiting significant correlations with AD. Subsequently, after drug-likeness filtering, 1016 compounds were remaining for 10 herbs, followed by structure clustering to sum up chemical scaffolds of herb ingredients. Based on target prediction results performed by our in-house protocol named AlzhCPI, compound-target (C-T) and target-pathway (T-P) networks were constructed to decipher the mechanism of action for anti-AD herbs. CONCLUSIONS Overall, this approach provided a novel strategy to explore the mechanisms of herbal medicine from a holistic perspective.

Ameliorative effects of baicalein in MPTP-induced mouse model of Parkinson's disease: A microarray study

Baicalein, a flavonoid from Scutellaria baicalensis Georgi, has been shown to possess neuroprotective properties. The purpose of this study was to explore the effects of baicalein on motor behavioral deficits and gene expression in N-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP)-induced mice model of Parkinsons disease (PD). The behavioral results showed that baicalein significantly improves the abnormal behaviors in MPTP-induced mice model of PD, as manifested by shortening the total time for climbing down the pole, prolonging the latent periods of rotarod, and increasing the vertical movements. Using cDNA microarray and subsequent bioinformatic analyses, it was found that baicalein significantly promotes the biological processes including neurogenesis, neuroblast proliferation, neurotrophin signaling pathway, walking and locomotor behaviors, and inhibits dopamine metabolic process through regulation of gene expressions. Based on analysis of gene co-expression networks, the results indicated that the regulation of genes such as LIMK1, SNCA and GLRA1 by baicalein might play central roles in the network. Our results provide experimental evidence for the potential use of baicalein in the treatment of PD, and revealed gene expression profiles, biological processes and pathways influenced by baicalein in MPTP-treated mice.

In vitro antiviral effects and 3D QSAR study of resveratrol derivatives as potent inhibitors of influenza H1N1 neuraminidase.

The anti‐influenza virus activities of 50 resveratrol (RV: 3, 5, 4′‐trihydroxy‐trans‐stilbene) derivatives were evaluated using a neuraminidase (NA) activity assay. The results showed that 35 compounds exerted an inhibitory effect on the NA activity of the influenza virus strain A/PR/8/34 (H1N1) with 50% inhibitory concentration (IC50) values ranging from 3.56 to 186.1 μm. Next, the 35 RV derivatives were used to develop 3D quantitative structure–activity relationship (3D QSAR) models for understanding the chemical–biological interactions governing their activities against NA. The comparative molecular field analysis (CoMFA r2 = 0.973, q2 = 0.620, qtest2 = 0.661) and the comparative molecular similarity indices analysis (CoMSIA r2 = 0.956, q2 = 0.610, qtest2 = 0.531) were applied. Afterward, molecular docking was performed to study the molecular interactions between the RV derivatives and NA. Finally, a cytopathic effect (CPE) reduction assay was used to evaluate the antiviral effects of the RV derivatives in vitro. Time‐of‐addition studies demonstrated that the RV derivatives might have a direct effect on viral particle infectivity. Our results indicate that the RV derivatives are potentially useful antiviral compounds for new drug design and development for influenza treatment.

DL0410 can reverse cognitive impairment, synaptic loss and reduce plaque load in APP/PS1 transgenic mice.

Cholinesterase inhibitors are first-line therapy for Alzheimers disease (AD). DL0410 is an AChE/BuChE dual inhibitor with a novel new structural scaffold. It has been demonstrated that DL0410 could improve memory deficits in both Aβ1-42-induced and scopolamine-induced amnesia in mice. In the present study, the therapeutic effect of DL0410 and its action mechanism were investigated in APP/PS1 transgenic mice. Six-month old APP/PS1 transgenic mice were orally administered with DL0410 (3, 10, 30 mg/kg/day). After 60 days, several behavioural tests, including the Morris water maze and step-down tests, were used to investigate the effects of DL0410 on mice behaviours. All the behavioural experimental results showed that DL0410 significantly ameliorated memory deficits. Meanwhile, DL0410 attenuated neural cell damage and reduced senile plaques significantly in the hippocampus of APP/PS1 transgenic mice. In addition, DL0410 significantly decreased Aβ plaques, while increasing the number of synapses and the thickness of PSD in the hippocampus. We also found DL0410 decreased the expression of APP, NMDAR1B and the phosphorylation level of NMDAR2B, and increased the phosphorylation level of CAMKII and the expression of PSD-95. In this study, the results of behavioural tests demonstrated for the first time that DL0410 could improve learning and memory dysfunction in APP/PS1 transgenic mice. The mechanism of its beneficial effects might be related to cholinesterase inhibition, Aβ plaques inhibition, improvement of synapse loss by regulating of expression of proteins related to synapses. As a result, DL0410 could be considered as a candidate drug for the therapy of AD.

In silico Target Fishing for the Potential Targets and Molecular Mechanisms of Baicalein as an Antiparkinsonian Agent: Discovery of the Protective Effects on NMDA Receptor-Mediated Neurotoxicity

The flavonoid baicalein has been proven effective in animal models of parkinsons disease; however, the potential biological targets and molecular mechanisms underlying the antiparkinsonian action of baicalein have not been fully clarified. In the present study, the potential targets of baicalein were predicted by in silico target fishing approaches including database mining, molecular docking, structure‐based pharmacophore searching, and chemical similarity searching. A consensus scoring formula has been developed and validated to objectively rank the targets. The top two ranked targets catechol‐O‐methyltransferase (COMT) and monoamine oxidase B (MAO‐B) have been proposed as targets of baicalein by literatures. The third‐ranked one (N‐methyl‐d‐aspartic acid receptor, NMDAR) with relatively low consensus score was further experimentally tested. Although our results suggested that baicalein significantly attenuated NMDA‐induced neurotoxicity including cell death, intracellular nitric oxide (NO) and reactive oxygen species (ROS) generation, extracellular NO reduction in human SH‐SY5Y neuroblastoma cells, baicalein exhibited no inhibitory effect on [3H]MK‐801 binding study, indicating that NMDAR might not be the target of baicalein. In conclusion, the results indicate that in silico target fishing is an effective method for drug target discovery, and the protective role of baicalein against NMDA‐induced neurotoxicity supports our previous research that baicalein possesses antiparkinsonian activity.

Discovery of neuroprotective compounds by machine learning approaches

Neuronal cell death from oxidative stress is a strong factor of many neurodegenerative diseases. To tackle these problems, phenotypic drug screening assays are a possible alternative strategy. The aim of this study is to develop the neuroprotective models against glutamate or H2O2-induced neurotoxicity by machine learning approaches, which helps in discovering neuroprotective compounds. Four different single classifiers (neural network, k nearest neighbors, classification tree and random forest) were constructed based on two large datasets containing 1260 and 900 known active or inactive compounds, which were integrated to develop the combined Bayesian models to obtain superior performance. Our results showed that both of the Bayesian models (combined-NB-1 and combined-NB-2) outperformed the corresponding four single classifiers. Additionally, structural fingerprint descriptors were added to improve the predictive ability of the models, resulting in the two best models NB-1-LPFP4 and NB-2-LCFP6. The best two models gave Matthews correlation coefficients of 0.972 and 0.956 for 5-fold cross validation as well as 0.953 and 0.902 for the test set, respectively. To illustrate the practical applications of the two models, NB-1-LPFP4 and NB-2-LCFP6 were used to perform virtual screening for discovering neuroprotective compounds, and 70 compounds were selected for further cell-based assay. The assay results showed that 28 compounds exhibited neuroprotective effects against glutamate-induced and H2O2-induced neurotoxicity simultaneously. Our results suggested the method that integrated single classifiers into combined Bayesian models could be feasible to predict neuroprotective compounds.

Discovery of the neuroprotective effects of alvespimycin by computational prioritization of potential anti‐parkinson agents

Based on public gene expression data, we propose a computational approach to optimize gene expression signatures for the use with Connectivity Map (CMap) to reposition drugs or discover lead compounds for Parkinsons disease. This approach integrates genetic information from the Gene Expression Omnibus (GEO) database, the Parkinsons disease gene expression database (ParkDB), the Online Mendelian Inheritance in Man (OMIM) database and the Comparative Toxicogenomics Database (CTD), with the aim of identifying a set of interesting genes for use in computational drug screening via CMap. The results showed that CMap, using the top 20 differentially expressed genes identified by our approach as a gene expression signature, outperformed the same method using all differentially expressed genes (n = 535) as a signature. Utilizing this approach, the candidate compound alvespimycin (17‐DMAG) was selected for experimental evaluation in a model of rotenone‐induced toxicity in human SH‐SY5Y neuroblastoma cells and isolated rat brain mitochondria. The results showed that 17‐DMAG significantly attenuated rotenone‐induced toxicity, as reflected by the increase of cell viability, the reduction of intracellular reactive oxygen species generation and a reduction in mitochondrial respiratory dysfunction. In conclusion, this computational method provides an effective systematic approach for drug repositioning or lead compound discovery for Parkinsons disease, and the discovery of the neuroprotective effects of 17‐DMAG supports the practicability of this method.