Quick and efficient quantitative predictions of androgen receptor binding affinity for screening Endocrine Disruptor Chemicals using 2D-QSAR and Chemical Read-Across

Banerjee, Arkaprava; De, Prabir; Kumar, Vinay; Kar, Supratik; Roy, Kunal

doi:10.1016/j.chemosphere.2022.136579

Cited by 32 publications

(25 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The descriptor RA f unction is a composite score based on all the selected structural and physicochemical descriptors that were initially selected using feature selection algorithms employed during the previous QSAR analysis. 13 This descriptor is like a latent variable that encodes information about all the structural and physicochemical descriptors, and thus, it has an overall positive contribution to the developed q-RASAR model. This can be exemplified in compounds like mibolerone (193) which has a higher value of RA f unction descriptor value and thus has a very high receptor binding affinity, while compounds like cortisol (63) have a lower RA function value and thus possess very little receptor binding affinity.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

“…We have used here 5 different toxicity data sets for which toxicity predictions were already reported by us in previous QSAR studies. ,− Data set 1 consists of rat androgen receptor binding affinity data of 147 compounds and 8 different structural and physicochemical descriptors, while data set 2 contains acute oral toxicity data of 128 pesticides against bobwhite quail ( C. virginianus ) with 10 different structural and physicochemical descriptors . Data set 3 contains acute contact toxicity data of plant 113 protection products against honey bees ( A. mellifera ) along with 10 different structural and physicochemical descriptors .…”

Section: Methodsmentioning

confidence: 99%

“…In this paper, they introduced the concept of the RASAR descriptors which include the novel concordance measure g m . Later on, Banerjee et al 13 performed QSAR, read-across, and q-RASAR analysis on the same data set and introduced the composite descriptor RA f unction that encodes all the features of the selected structural and physicochemical descriptors. They have shown that a univariate q-RASAR model with the descriptor "RA f unction" was the winner model due to its low MAE Test value.…”

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Some Novel Similarity-Based Functions Used in the ML-Based q-RASAR Approach for Efficient Quantitative Predictions of Selected Toxicity End Points

Banerjee

Roy

2023

Chem. Res. Toxicol.

Self Cite

View full text Add to dashboard Cite

The novel quantitative read-across structure−activity relationship (q-RASAR) approach uses read-across-derived similarity functions in the quantitative structure−activity relationship (QSAR) modeling framework in a unique way for supervised model generation. The aim of this study is to explore how this workflow enhances the external (test set) prediction quality of conventional QSAR models by the incorporation of some novel similaritybased functions as additional descriptors using the same level of chemical information. To establish this, five different toxicity data sets, for which QSAR models were reported previously, have been considered in the q-RASAR modeling exercise, which uses chemical similarity-derived measures. The identical sets of chemical features along with the same compositions of training and test sets as reported previously were used in the present analysis for ease of comparison. The RASAR descriptors were calculated based on a chosen similarity measure with the default setting of relevant hyperparameter(s) and were then clubbed with the original structural and physicochemical descriptors, and the number of selected features was further optimized by employing a grid search technique applied on the respective training sets. These features were then used to develop multiple linear regression (MLR) q-RASAR models that show enhanced predictivity as compared to the QSAR models developed previously. Moreover, various other ML algorithms like support vector machine (SVM), linear SVM, random forest, partial least squares, and ridge regression were also employed using the same feature combinations as used in the MLR models to compare the prediction qualities. The q-RASAR models for five different data sets possess at least one of the RASAR descriptors, RA f unction, g m , and average similarity, suggesting that these are important determinants of similarities that contribute to the development of predictive q-RASAR models, as also evident from the SHAP analysis of the models.

show abstract

Section: ■ Results and Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Some Novel Similarity-Based Functions Used in the ML-Based q-RASAR Approach for Efficient Quantitative Predictions of Selected Toxicity End Points

Banerjee

Roy

2023

Chem. Res. Toxicol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Virtual design and prediction of single- or multitarget inhibitors of cancer-related proteins, including aromatase is also a hot topic . A molecule able to simultaneously inhibit many different cancer cells will be better than a molecule that inhibits a few cancer cells . In addition, the heterogeneity of the tumor is also a well-established fact and varies from person to person and lays the foundation of precision medicine.…”

Section: Introductionmentioning

confidence: 99%

“… 20 A molecule able to simultaneously inhibit many different cancer cells will be better than a molecule that inhibits a few cancer cells. 21 In addition, the heterogeneity of the tumor is also a well-established fact and varies from person to person and lays the foundation of precision medicine. Of note, during the drug discovery process, we always move from one common target to a complicated multitarget strategy.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Assisted Prediction of the Biological Activity of Aromatase Inhibitors and Data Mining to Explore Similar Compounds

et al. 2022

View full text Add to dashboard Cite

Designing molecules for drugs has been a hot topic for many decades. However, it is hard and expensive to find a new molecule. Thus, the cost of the final drug is also increased. Machine learning can provide the fastest way to predict the biological activity of druglike molecules. In the present work, machine learning models are trained for the prediction of the biological activity of aromatase inhibitors. Data was collected from the literature. Molecular descriptors are calculated to be used as independent features for model training. The results showed that the R 2 values for linear regression, random forest regression, gradient boosting regression, and bagging regression are 0.58, 0.84, 0.77, and 0.80, respectively. Using these models, it is possible to predict the activity of new molecules in a short period of time and at a reasonable cost. Furthermore, Tanimoto similarity is used for similarity analysis, as well as a chemical database is mined to search for similar molecules. Nonetheless, this study provides a framework for repurposing other effective drug molecules to prevent cancer.

show abstract

In silico analysis of endocrine‐disrupting potential of triclosan, bisphenol A, and their analogs and derivatives

Đurić,

Milanović,

Drljača Lero

et al. 2024

J of Applied Toxicology

View full text Add to dashboard Cite

Owning to the increasing body of evidence about the ubiquitous exposure to endocrine disruptors (EDCs), particularly bisphenol A (BPA), and associated health effects, BPA has been gradually substituted with insufficiently tested structural analogs. The unmanaged excessive use of antimicrobial agents such as triclosan (TCS) during the COVID‐19 outbreak has also raised concerns about its possible interferences with hormonal functions. The similarity of BPA and estradiol, as well as TCS and non‐steroidal estrogens, imply that endocrine‐disrupting properties of their analogs could be predicted based on the chemical structure. Hence, this study aimed to evaluate the endocrine‐disrupting potential of BPA substitutes as well as TCS derivatives and degradation/biotransformation metabolites, in comparison to BPA and TCS based on their molecular properties, computational predictions of pharmacokinetics and binding affinities to nuclear receptors. Based on the obtained results several under‐researched BPA analogs exhibited higher binding affinities for nuclear receptors than BPA. Notable analogs included compounds detected in receipts (DD‐70, BTUM‐70, TGSA, and BisOPP‐A), along with a flame retardant, BDP. The possible health hazards linked to exposure to TCS and its mono‐hydroxylated metabolites were also found. Further research is needed in order to elucidate the health impacts of these compounds and promote better regulation practices.

show abstract

Quick and efficient quantitative predictions of androgen receptor binding affinity for screening Endocrine Disruptor Chemicals using 2D-QSAR and Chemical Read-Across

Cited by 32 publications

References 40 publications

On Some Novel Similarity-Based Functions Used in the ML-Based q-RASAR Approach for Efficient Quantitative Predictions of Selected Toxicity End Points

On Some Novel Similarity-Based Functions Used in the ML-Based q-RASAR Approach for Efficient Quantitative Predictions of Selected Toxicity End Points

Machine Learning-Assisted Prediction of the Biological Activity of Aromatase Inhibitors and Data Mining to Explore Similar Compounds

In silico analysis of endocrine‐disrupting potential of triclosan, bisphenol A, and their analogs and derivatives

Contact Info

Product

Resources

About