Linear QSAR regression models for the prediction of bioconcentration factors by physicochemical properties and structural theoretical molecular descriptors

Chemosphere ◽  
2007 ◽  
Vol 67 (2) ◽  
pp. 351-358 ◽  
Author(s):  
E. Papa ◽  
J.C. Dearden ◽  
P. Gramatica
Keyword(s):  
Physicochemical Properties ◽  
Regression Models ◽  
Molecular Descriptors ◽  
Bioconcentration Factors

scholarly journals Predicting the DPP-IV Inhibitory ActivitypIC50Based on Their Physicochemical Properties

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Tianhong Gu ◽  
Xiaoyan Yang ◽  
Minjie Li ◽  
Milin Wu ◽  
Qiang Su ◽  
...  
Keyword(s):  
Feature Selection ◽  
Physicochemical Properties ◽  
Inhibitory Activity ◽  
Molecular Descriptors ◽  
Feature Selection Method ◽  
Development Program ◽  
Support Vector ◽  
Training Set ◽  
Second Development ◽  
Dpp Iv

The second development program developed in this work was introduced to obtain physicochemical properties of DPP-IV inhibitors. Based on the computation of molecular descriptors, a two-stage feature selection method called mRMR-BFS (minimum redundancy maximum relevance-backward feature selection) was adopted. Then, the support vector regression (SVR) was used in the establishment of the model to map DPP-IV inhibitors to their corresponding inhibitory activity possible. The squared correlation coefficient for the training set of LOOCV and the test set are 0.815 and 0.884, respectively. An online server for predicting inhibitory activity pIC50of the DPP-IV inhibitors as described in this paper has been given in the introduction.

scholarly journals In silico prediction of chemical neurotoxicity using machine learning

2020 ◽  
Vol 9 (3) ◽  
pp. 164-172
Author(s):  
Changsheng Jiang ◽  
Piaopiao Zhao ◽  
Weihua Li ◽  
Yun Tang ◽  
Guixia Liu
Keyword(s):  
Machine Learning ◽  
Regression Models ◽  
Cross Validation ◽  
Prediction Models ◽  
Drug Withdrawal ◽  
Molecular Descriptors ◽  
Computational Prediction ◽  
Machine Learning Algorithms ◽  
Training Set ◽  
Data Set

Abstract Neurotoxicity is one of the main causes of drug withdrawal, and the biological experimental methods of detecting neurotoxic toxicity are time-consuming and laborious. In addition, the existing computational prediction models of neurotoxicity still have some shortcomings. In response to these shortcomings, we collected a large number of data set of neurotoxicity and used PyBioMed molecular descriptors and eight machine learning algorithms to construct regression prediction models of chemical neurotoxicity. Through the cross-validation and test set validation of the models, it was found that the extra-trees regressor model had the best predictive effect on neurotoxicity (${q}_{\mathrm{test}}^2$ = 0.784). In addition, we get the applicability domain of the models by calculating the standard deviation distance and the lever distance of the training set. We also found that some molecular descriptors are closely related to neurotoxicity by calculating the contribution of the molecular descriptors to the models. Considering the accuracy of the regression models, we recommend using the extra-trees regressor model to predict the chemical autonomic neurotoxicity.

Study of drug-drug combinations based on molecular descriptors and physicochemical properties

2016 ◽  
Vol 19 (2) ◽  
pp. 153-160 ◽  
Author(s):  
Bing Niu ◽  
Zhihao Xing ◽  
Manman Zhao ◽  
Haizhong Huo ◽  
Guohua Huang ◽  
...  
Keyword(s):  
Physicochemical Properties ◽  
Molecular Descriptors ◽  
Drug Combinations

scholarly journals Zagreb-Type Indices of R-Vertex Join and R-Edge Join of Graphs

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Jianxin Wei ◽  
Muhammad Imran ◽  
Muhamamd Azhar Iqbal ◽  
Muhammad Asad Zaighum
Keyword(s):  
Physicochemical Properties ◽  
Molecular Descriptors ◽  
Molecular Structures ◽  
Connectivity Index ◽  
Chemical Databases ◽  
Randic Index ◽  
Zagreb Indices ◽  
Mathematical Chemistry ◽  
Join Of Graphs ◽  
Arbitrary Graphs

There are various methods available which are used to search large chemical databases and to predict the physicochemical properties of molecular structures. Using molecular descriptors for this purpose is the simplest of these methods. The Zagreb indices are amongst the oldest molecular descriptors, and their properties have been extensively studied and applied in QSAR/QSPR studies. The Zagreb coindices were recently introduced, attracting the attention of researchers in mathematical chemistry. In this paper, we study Zagreb indices and several other Zagreb-type indices including the general Randić index, sum-connectivity index, F-index, and Zagreb coindices of R-vertex and edge join of two arbitrary graphs.

scholarly journals Computation of Vertex Degree-Based Molecular Descriptors of Hydrocarbon Structure

2022 ◽  
Vol 2022 ◽  
pp. 1-15
Author(s):  
Zeeshan Saleem Mufti ◽  
Rukhshanda Anjum ◽  
Ayesha Abbas ◽  
Shahbaz Ali ◽  
Muhammad Afzal ◽  
...  
Keyword(s):  
Melting Point ◽  
Physicochemical Properties ◽  
Organic Compounds ◽  
Topological Index ◽  
Unsolved Problem ◽  
Molecular Descriptors ◽  
Topological Indices ◽  
Physical Chemical ◽  
Point Density ◽  
Biological Attributes

Topological indices are such numbers or set of numbers that describe topology of structures. Nearly 400 topological indices are calculated so far. The prognostication of physical, chemical, and biological attributes of organic compounds is an important and still unsolved problem of computational chemistry. Topological index is the tool to predict the physicochemical properties such as boiling point, melting point, density, viscosity, and polarity of organic compounds. In this study, some degree-based molecular descriptors of hydrocarbon structure are calculated.

Sign in / Sign up

Export Citation Format

Share Document