Structure–activity relationship studies of miniproteins targeting the androgen receptor–coactivator interaction

MedChemComm ◽  
2013 ◽  
Vol 4 (1) ◽  
pp. 187-192 ◽  
Author(s):  
Marta Dominguez Seoane ◽  
Katja Petkau-Milroy ◽  
Belen Vaz ◽  
Sabine Möcklinghoff ◽  
Simon Folkertsma ◽  
...  
Keyword(s):  
Androgen Receptor ◽  
Point Mutations ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Receptor Affinity ◽  
Structure Activity

Miniproteins featuring a stable α-helical motif allow exploring point mutations in and around FXXLF motifs to improve androgen receptor affinity.

scholarly journals Deep learning-based structure-activity relationship modeling for multi-category toxicity classification : a case study of 10K Tox21 chemicals with high-throughput cell-based androgen receptor bioassay data

2021 ◽  
Author(s):  
Gabriel Idakwo ◽  
Sundar Thangapandian ◽  
Joseph Luttrell ◽  
Zhaoxian Zhou ◽  
Chaoyang Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Androgen Receptor ◽  
Learning Algorithms ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Chemical Toxicity ◽  
Toxicity Prediction ◽  
Predictive Toxicology ◽  
Structure Activity

Deep learning (DL) has attracted the attention of computational toxicologists as it offers a potentially greater power for in silico predictive toxicology than existing shallow learning algorithms. However, contradicting reports have been documented. To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program. A nested double-loop cross-validation approach was adopted along with a stratified sampling strategy for partitioning chemicals of multiple AR activity classes (i.e., agonist, antagonist, inactive, and inconclusive) at the same distribution rates amongst the training, validation and test subsets. Deep neural networks (DNN) and random forest (RF), representing deep and shallow learning algorithms, respectively, were chosen to carry out structure-activity relationship-based chemical toxicity prediction. Results suggest that DNN significantly outperformed RF (p < 0.001, ANOVA) by 22–27% for four metrics (precision, recall, F-measure, and AUPRC) and by 11% for another (AUROC). Further in-depth analyses of chemical scaffolding shed insights on structural alerts for AR agonists/antagonists and inactive/inconclusive compounds, which may aid in future drug discovery and improvement of toxicity prediction modeling.

Structure-Activity Relationship Studies of Novel Pyrazolo[1,5-c][1,3]benzoxazines: Synthesis and Benzodiazepine Receptor Affinity

1996 ◽  
Vol 329 (12) ◽  
pp. 529-534 ◽  
Author(s):  
Flavia Varano ◽  
Daniela Catarzi ◽  
Vittoria Colotta ◽  
Lucia Cecchi ◽  
Guido Filacchioni ◽  
...  
Keyword(s):  
Benzodiazepine Receptor ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Receptor Affinity ◽  
Structure Activity

scholarly journals Development and Validation of Quantitative Structure-Activity Relationship Models for Compounds Acting on Serotoninergic Receptors

2012 ◽  
Vol 2012 ◽  
pp. 1-11 ◽  
Author(s):  
Grażyna Żydek ◽  
Elżbieta Brzezińska
Keyword(s):  
Regression Analysis ◽  
Physicochemical Parameters ◽  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Receptor Interaction ◽  
Regression Equations ◽  
Quantitative Structure ◽  
Receptor Affinity ◽  
Structure Activity

A quantitative structure-activity relationship (QSAR) study has been made on 20 compounds with serotonin (5-HT) receptor affinity. Thin-layer chromatographic (TLC) data and physicochemical parameters were applied in this study. RP2 TLC 60F254plates (silanized) impregnated with solutions of propionic acid, ethylbenzene, 4-ethylphenol, and propionamide (used as analogues of the key receptor amino acids) and their mixtures (denoted as S1–S7 biochromatographic models) were used in two developing phases as a model of drug-5-HT receptor interaction. The semiempirical method AM1 (HyperChem v. 7.0 program) and ACD/Labs v. 8.0 program were employed to calculate a set of physicochemical parameters for the investigated compounds. Correlation and multiple linear regression analysis were used to search for the best QSAR equations. The correlations obtained for the compounds studied represent their interactions with the proposed biochromatographic models. The good multivariate relationships (R2=0.78–0.84) obtained by means of regression analysis can be used for predicting the quantitative effect of biological activity of different compounds with 5-HT receptor affinity. “Leave-one-out” (LOO) and “leave-N-out” (LNO) cross-validation methods were used to judge the predictive power of final regression equations.

Sign in / Sign up

Export Citation Format

Share Document