Currently, bioactivity analysis and AdMET property analysis of compound molecules in drug discovery are time-consuming and labor-intensive, so the approach of building compound bioactivity prediction models is usually...
详细信息
ISBN:
(纸本)9781450385053
Currently, bioactivity analysis and AdMET property analysis of compound molecules in drug discovery are time-consuming and labor-intensive, so the approach of building compound bioactivity prediction models is usually used to screen potentially active compounds, especially the rapiddevelopment of data mining and machine learning methods has greatly facilitated this process. The aim of this paper is to construct quantitative prediction models for the bioactivity of compounds ERα. Firstly, 12moleculardescriptors that are strongly correlated with bioactivity and independent of each other were screened from 729 moleculardescriptors to construct a quantitative prediction model of compound ERα bioactivity based on BP neural network, decision tree and random forest, respectively. Finally, the three models were evaluated with four evaluation metrics - variance, standarddeviation, mean absolute error, and root mean square error. According to the comparison results, the best prediction model is the random forest model, which can be used to predict new compound molecules with better ERα bioactivity in the future.
Currently, bioactivity analysis and AdMET property analysis of compound molecules in drug discovery are time-consuming and labor-intensive, so the approach of building compound bioactivity prediction models is usually...
详细信息
Currently, bioactivity analysis and AdMET property analysis of compound molecules in drug discovery are time-consuming and labor-intensive, so the approach of building compound bioactivity prediction models is usually used to screen potentially active compounds, especially the rapiddevelopment of data mining and machine learning methods has greatly facilitated this process. The aim of this paper is to construct quantitative prediction models for the bioactivity of compounds ERα. Firstly, 12moleculardescriptors that are strongly correlated with bioactivity and independent of each other were screened from 729 moleculardescriptors to construct a quantitative prediction model of compound ERα bioactivity based on BP neural network, decision tree and random forest,respectively. Finally, the three models were evaluated with four evaluation metrics-variance, standarddeviation, mean absolute error, and root mean square error. According to the comparison results, the best prediction model is the random forest model, which can be used to predict new compound molecules with better ERαbioactivity in the future.
JNK3 signaling pathway is gaining interest due to its involvement in many neurological disorders. The purpose of this study was to explore for the first time the use of a large anddiverse dataset in combination with ...
详细信息
JNK3 signaling pathway is gaining interest due to its involvement in many neurological disorders. The purpose of this study was to explore for the first time the use of a large anddiverse dataset in combination with binary QSAR methodology for predicting JNK3 activity class. data were extracted from Aureus Pharma' AurSCOPE Kinase knowledge database and active or inactive classes were assigned to ligands based on IC50 biological activity. Two sets of 2d molecular descriptors (P_VSA and BCUT) were used to build models using different biological activity thresholds. The design of the models was preceded by the evaluation of the chemical space covered by the datasets and an assessment of its chemical diversity. The best model was found using a 100 nM IC50 threshold with surface-based P_VSA descriptors. This binary QSAR model reached an overall accuracy of 98% and a leave-one-out cross-validated accuracy of 94%. Most relevant descriptors were found to encode size and hydrophobic interactions. These derived models can be useful for screening chemical libraries in the search for new JNK3 inhibitors. (C) 2007 Elsevier Ltd. All rights reserved.
Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered the...
详细信息
Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered therapeutic agent. The purpose of this study is to develop in silica model that can effectively distinguish human CYP3A4 inhibitors from non-inhibitors. Structural diversity of the drug-like compounds CYP3A4 inhibitors and non-inhibitors was obtained from Fujitsu database and Korea Research Institute of Chemical Technology (KRICT) as training and test sets, respectively. Recursive Partitioning (RP) method was introduced for the classification of inhibitor and non-inhibitor of CYP3A4 because it is an easy and quick classification method to implement. The 2d molecular descriptors were used to classify the compounds into respective inhibitors and non-inhibitors by calculation of the physicochemical properties of CYP3A4 inhibitors such as molecular weights and fractions of 2d VSA chargeable groups. The RP tree model reached 72.33% of accuracy and exceeded this percentage for the sensitivity (75.82%) parameter. This model is further validated by the test set where both accuracy and sensitivity were 72.58% and 82.64%, respectively. The accuracy of the random forest model was increased to 73.8%. The 2ddescriptors sufficiently represented the molecular features of CYP3A4 inhibitors. Our model can be used for the prediction of either CYP3A4 inhibitors or non-inhibitors in the early stages of the drug discovery process. (C) 2008 Elsevier Masson SAS. All rights reserved.
暂无评论