multiple linear regression

Online determination of the elemental composition of tissues near the Bragg peak is a challenge in proton therapy related studies. In the present work, an analysis method based on the whole spectral information is presented for the quantitative determination of the elemental composition (weight %) of an irradiated target from its emitted Prompt Gamma (PG) spectrum.

To address this issue, four test phantoms with different weights (%) of 12C, 16O, 20Ca, and 14N elements were considered. The simulated PG spectra were recorded using 3 × 3 inch NaI detectors. A library consisting of the spectra of single-element phantoms as well as the spectra of test-irradiated phantoms was produced for 30, 70, and 150 MeV incident protons using the Geant4 Monte Carlo toolkit. The elemental analysis was performed using the information of the whole spectrum by applying two methods, including the well-known Genetic Algorithm (GA) and Multiple Linear Regression (MLR).

The results show that the proposed method estimates the oxygen concentration accurately. Furthermore, the estimated weights of other elements, with both methods, agree well with nominal values in each test phantom, for the considered energies.

The proposed quantitative elemental analysis of proton-bombarded phantoms using their induced PG spectrum is expected to be beneficial in treatment planning and treatment verification studies.

In this study, the pharmacological activity of 33 compounds of furopyrimidine and thienopyrimidine as vascular endothelial growth factor receptor 2 (VEGFR-2) inhibitors to inhibit cancer was investigated. The most important angiogenesis inducer is VEGF endothelial growth factor, which exerts its activity by binding to two tyrosine kinase receptors called VEGFR-1 and VEGFR-2. Due to the critical role of VEGF in the pathological angiogenesis of this molecule, it is a valuable therapeutic target for antiangiogenesis therapies.

After calculating descriptors using SPSS software and stepwise selection method, 5 descriptors were used for modeling in multiple linear regression (MLR) and artificial neural network (ANN). The calibration series and the test series in this study included 26 and 7 combinations, respectively.

The performance evaluation of models was determined by the R2 , RMSE, and Q2 statistic parameters. The R2 values of MLR and ANN models were 0.889 and 0.998, respectively. Also, the value of RMSE in the ANN model was lower and its Q2 value was higher than the MLR model.

The results were evaluated by different statistical methods and it was concluded that the nonlinear neural network method is powerful to predict the pharmacological activity of similar compounds, and because of the complex and nonlinear relationships, the MLR was not capable of establishing a good model with high predictive power.

With an aim to design a validated two‑dimensional quantitative structure–activity relationship (2D QSAR) model, a probe was executed on a series of reported c‑Jun NH2‑terminal kinase‑1 (JNK1) inhibitors, exhibiting selectivity toward JNKs (and not other members of MAPK family).

The present work focused on obtaining valuable insights from the structural architecture of the selected compounds and their effects on JNK1 inhibitory activity. The present work deciphers the importance of descriptive variables, namely Verloop L (Subst. 1), Bond Dipole Moment (Subst. 2), LogP (Subst. 1), Balaban Topological index (Subst. 1), and  VAMP Total Dipole (whole molecule), in molecules possessing JNK1 inhibitory profile.

These explanatory variables, obtained after iteratively reducing the data, did not only provide us with the substantial evidence pertaining to the dependence of bioactivity on the structural features of molecules, but also suggested the measures to optimize the selected compounds so as to obtain potent JNK1 inhibitors with good selectivity profile. Based on these distinct descriptors, exhibiting no apparent intercorrelation and manifesting good correlation with biological activity, a 2D QSAR model was generated.

Robustness of the developed model was evaluated by performing multiple linear regression, partial least square, and artificial neural network studies. The reliability and predictive ability of the developed model was ascertained through the values of standard statistical parameters, such as s = 0.38, F = 97.22, r = 0.95, r2 = 0.90, and r2cv = 0.88, for the training set compounds. The generated model was validated through the test set compounds, as well as by leave one out method

  Identification of ground waters contaminated by arsenic using surface soil parameters and modeling this relationship in two models including artificial neural network and multiple linear regression can be useful in managing the water resources of the region.
Material & The purpose of the present study was to estimate the potential of arsenic pollution in the Sanandaj ground waters using multiple linear regression (MLR) and artificial neural
network (ANN) models. In this regards, 35 number of wells were selected among the permissible wells with considering watershed area, appropriate distribution, and different geological structure. The water samples stored in polyethylene bottles and kept at 4°C until transferred to the laboratory. For consideration of the relationship between the soils characteristics around the wells and ground water, the soil samples were collected from 0-20 cm of topsoil with composite sampling technique. The soil samples were air-dried and prepared for analysis. For long term storage of water samples nitric acid were added and the concentration of arsenic in water samples were measured by graphite furnace atomic absorption analyzer. Physical and chemical characteristics of the soil samples including: arsenic, arsenate, arsenite, phosphate, nitrate, total iron, amorphous iron, total manganese, amorphous manganese, clay, sand, silt, organic matter, pH and CEC were measured. Then all water and soil data were normalized and finally, accuracy of the MLP and ANN models was assessed to investigate the relationship between arsenic of water and soil parameters. Results showed that the arsenic concentration of ground waters were lower than the standard level in the study area. This can be due to high concentration of arsenate in the study area soils
compared arsenite and increasing the cationic exchange capacity of soil under the influence of clay particles, organic matter and free iron oxides. Compression of models accuracy result showed that ANN model with R=0.835, RMSE=0.156 and MAE =0.118 in the training phase and R =0.816, RMSE=0.177 and MAE=0.158 in the testing phase has higher accuracy and lower errors in the estimation of ground waters arsenic contamination than MLP model

The purpose of this work is to promote and facilitate forensic profiling and chemical analysis of illicit drug samples in order to determine their origin, methods of production and transfer through the country. The article is based on the gas chromatography analysis of heroin samples seized from three different locations in Serbia. Chemometric approach with appropriate statistical tools (multiple-linear regression (MLR), hierarchical cluster analysis (HCA) and Wald-Wolfowitz run (WWR) test) were applied on chromatographic data of heroin samples in order to correlate and examine the geographic origin of seized heroin samples. The best MLR models were further validated by leave-one-out technique as well as by the calculation of basic statistical parameters for the established models. To confirm the predictive power of the models, external set of heroin samples was used. High agreement between experimental and predicted values of acetyl thebaol and diacetyl morphine peak ratio, obtained in the validation procedure, indicated the good quality of derived MLR models. WWR test showed which examined heroin samples come from the same population, and HCA was applied in order to overview the similarities among the studied heroine samples.

A robust and reliable quantitative structure-property relationship (QSPR) study was established to forecast the melting points (MPs) of a diverse and long set including 250 drug-like compounds. Based on the calculated descriptors by Dragon software package, to detect homogeneities and to split the whole dataset into training and test sets, a principal component analysis (PCA) approach was used. Accordingly, there was no outlier in the constructed cluster. Afterwards, the genetic algorithm (GA) feature selection strategy was used to select the most impressive descriptors resulting in the best-fitted models. In addition, multiple linear regression (MLR) and support vector machine (SVM) were used to develop linear and non-linear models correlating the molecular descriptors and the melting points. The validation of the obtained models was confirmed applying cross validation, chance correlation along with statistical features associated with external test set. Our computational study exactly showed a determination coefficient and of 0.853 and a root mean square error (RMSE) of 11.082, which are better than those MLR model (R2=0.712, RMSE 15.042%) accounting for higher capability of SVM-based model in prediction of the theoretical values related to melting points. In fact, using the GA approach resulted in selection of powerful descriptors having useful information concerning effective variables on MPs, which can be utilized in further designing of drug like compounds with desired melting points.

This paper describes 3D-QSAR analysis and biological evaluation of 1,5-benzodiazepine analogues. Benzodiazepine nucleus with its simple structure gives a good opportunity for further modification regarding an increase of its antimicrobial activity. We synthesized a series of benzodiazepine analogues from condensation of various chalcones and halo substituted o-phenelynene diamines. All compounds were assayed in vitro against, E. coli, P. aeruginosa, S. aureus. The models were generated on the Vlife MDS 3.5; selected models showed a correlation coefficient (r2) above 0.9 with cross-validated correlation coefficient (q2) above 0.8, respectively, for all the selected organisms. The 3D-QSAR models generated were externally validated for all models using a test set of 6 molecules for which the predictive r2 (r2-pred) was found to be above 0.45. The results of 3D-QSAR indicate that contours can be used to design some potent antibacterial agents.