Search

A series of 3-O-β-chacotriosyl oleanane-type triterpenes have been designed, synthesized and evaluated as H5N1 entry inhibitors, based on a small molecule inhibitor, saponin 1, previously discovered by us. Detailed structure–activity relationship (SAR) studies on the aglycone of compound 1 indicated that oleanane-type triterpenes with conserved structural features as the aglycone favored the antiviral activity. The results suggested that the introduction of bulky groups onto the 28-COOH of OA was helpful for significantly improving the selectivity index while keeping the antiviral activities, which was opposite to what was found for the GA analogs. Compound 5 was selected for further mechanistic studies because of its distinguished inhibition activity and good selectivity index. Molecular simulation analysis confirmed that compound 5 stabilized the HA2 subunit of hemagglutinin (HA) by binding with amino acid residues THR-189, LYS-156, and ARG-133A, and therefore may prevent HA from undergoing conformational rearrangement, which is a critical step for viral entry.

In diagnosis of lung cancer, rapid distinction between small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) tumors is very important. Serum markers, including lactate dehydrogenase (LDH), C-reactive protein (CRP), carcino-embryonic antigen (CEA), neurone specific enolase (NSE) and Cyfra21-1, are reported to reflect lung cancer characteristics. In this study classification of lung tumors was made based on biomarkers (measured in 120 NSCLC and 60 SCLC patients) by setting up optimal biomarker joint models with a powerful computerized tool - gene expression programming (GEP). GEP is a learning algorithm that combines the advantages of genetic programming (GP) and genetic algorithms (GA). It specifically focuses on relationships between variables in sets of data and then builds models to explain these relationships, and has been successfully used in formula finding and function mining. As a basis for defining a GEP environment for SCLC and NSCLC prediction, three explicit predictive models were constructed. CEA and NSE are frequently- used lung cancer markers in clinical trials, CRP, LDH and Cyfra21-1 have significant meaning in lung cancer, basis on CEA and NSE we set up three GEP models-GEP 1(CEA, NSE, Cyfra21-1), GEP2 (CEA, NSE, LDH), GEP3 (CEA, NSE, CRP). The best classification result of GEP gained when CEA, NSE and Cyfra21-1 were combined: 128 of 135 subjects in the training set and 40 of 45 subjects in the test set were classified correctly, the accuracy rate is 94.8% in training set; on collection of samples for testing, the accuracy rate is 88.9%. With GEP2, the accuracy was significantly decreased by 1.5% and 6.6% in training set and test set, in GEP3 was 0.82% and 4.45% respectively. Serum Cyfra21-1 is a useful and sensitive serum biomarker in discriminating between NSCLC and SCLC. GEP modeling is a promising and excellent tool in diagnosis of lung cancer.

The coffee flavor compounds acquire a significant place in the improving the flavor of cigarette. In the present paper, the support vector machine is used to develop quantitative relationships between the retention time and four molecular descriptors of 52 compounds. The model of support vector machine gives good statistical results compared to those give by multiple linear regressions and support vector machine. The contribution of each descriptor to structure-retention time relationships was evaluated. It indicates the importance of the atoms number and type of parameter. The proposed method can be successfully used to predict the retention time with only four molecular descriptors which can be calculated directly from molecular structure alone.

The coffee flavor compounds acquire a significant place in the improving the flavor of cigarette. In the present paper, the gene expression programming (GEP) is used to develop quantitative relationships between the retention time (TR) and four molecular descriptors of 52 compounds. The model of GEP gives good statistical result. This method can be used to set up the good regression model.

Using the GEP,the QSAR model for anti-cancer activity of 38 compounds in 5 cancer cell lines was establish. These compounds are a novel class of anticarcinogen named tricyclic 5:7:5-fused diimidazo [4, 5-d:4, 5-f ][1, diazepines. The carcinoma cell lines involved in this research are A549 lung cancer, MCF-7 breast cancer, MDA-MB-231 breast cancer, OVCAR-3 ovarian cancer and PC-3 prostate cancer. Accuracies of these models in training group and test group are over 90%, showing perfect predictive ability. This QSAR model will be great valuable in providing guidance for future designing and synthesizing of anticancer drugs.

A novel machine learning method, gene expression programming(GEP), was employed to build quatitative structure-activity relationship(QSAR) models for predicting the enhancement effect of nitroimidazole compounds on irradiation. The models were based on descriptors which were calculated from the molecular structures. Four descriptors were selected from the pool of descriptors by best multiple linear regression(BMLR) method. After that, three regression methods, multiple linear regression(MLR), support vector machine(SVM) and GEP, were used to build QSAR models. Compared to MLR and SVM, GEP produced a better model with the square of correlation coefficient(R2), 0.9203 and 0.9014, and the root mean square error(RMSE), 0.6187 and 0.6875, for training set and test set, respectively. The results show that the GEP model has better predictive ability and more reliable than the MLR and SVM models. This indicates that GEP is a promising method on relevant researches in radiation area.

The gene expression programming, a novel machine learning algorithm, is used to develop quantitative model as a potential screening mechanism for a series of 1,4-dihydropyridine calcium channel antagonists for the first time. The heuristic method was used to search the descriptor space and select the descriptors responsible for activity. A nonlinear, six-descriptor model based on gene expression programming with mean-square errors 0.19 was set up with a predicted correlation coefficient (R2) 0.92. This paper provides a new and effective method for drug design and screening.

Quantitative structure-property relationships (QSPR) were developed to predict the pK(a) values of sulfa drugs via heuristic method (HM) and gene expression programming (GEP). The descriptors of 31 sulfa drugs were calculated by the software CODESSA, which can calculate constitutional, topological, geometrical, electrostatic, and quantum chemical descriptors. HM was also used for the preselection of 4 appropriate molecular descriptors. Linear and nonlinear QSPR models were developed based on the HM and GEP separately and two prediction models lead to a good correlation coefficient (R) of 0.90 and 0.95. The two QSPR models are tseful in predicting pK(a) during the discovery of new drugs and providing theory information for studying the new drugs.