Development of blood brain barrier permeation prediction models for organic and inorganic biocidal active substances

Shin, Hyun Kil; Lee, Sang‐Woo; Oh, Han-Mo; Yoo, Donggon; Park, Seung Min; Kim, Woo‐Keun; Kang, Myung-Gyun

doi:10.1016/j.chemosphere.2021.130330

Cited by 13 publications

(15 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…TDEi tensor options could be changed if the structural diversity of datasets is different from that of drug-like molecules. 25 , 26 …”

Section: Results and Discussionmentioning

confidence: 99%

“…In this study, experiments were performed on small drug-like compounds. TDEi tensor options could be changed if the structural diversity of datasets is different from that of drug-like molecules. , …”

Section: Results and Discussionmentioning

confidence: 99%

“…TDEi tensor options could be changed if the structural diversity of datasets is different from that of drug-like molecules. 25,26 Model Prediction Accuracy. The VGGNet was optimized with the best option of TDEi tensors in the preliminary search for each dataset (Table 2), and the goodness-of-fit of each model is shown in Figure 7.…”

Section: = − ∑ −mentioning

confidence: 99%

See 2 more Smart Citations

Topological Distance-Based Electron Interaction Tensor to Apply a Convolutional Neural Network on Drug-like Compounds

Shin

2021

ACS Omega

Self Cite

View full text Add to dashboard Cite

Deep learning (DL) models in quantitative structure–activity relationship fed the molecular structure directly to the network without using human-designed descriptors by representing molecule as a graph or string (e.g., SMILES code). However, these two representations were oversimplification of real molecules to reflect chemical properties of molecular structures. Given that the choice of molecular representation determines the architecture of the DL model to apply, a novel way of molecular representation can open a way to apply diverse DL networks developed and used in other fields. A topological distance-based electron interaction (TDEi) tensor has been developed in this study inspired by the quantum mechanical model of the molecule, which defines a molecule with electrons and protons. In the TDEi tensor, the atomic orbital (AO) of each atom is represented by an electron configuration (EC) vector, which is a bit string based on the presence and absence of electrons in each AO according to spin indicated by positive and negative signs. Interactions between EC vectors were calculated based on the topological distance between atoms in a molecule. As a molecular structure was translated into 3D array, CNN models (modified VGGNet) were applied using a TDEi tensor to predict four physicochemical properties of drug-like compound datasets: MP (275,131), Lipop (4193), Esol (1127), and Freesolv (639). Models achieved good prediction accuracy. PCA showed that a stronger correlation was observed between the extracted features and the target endpoint as features were extracted from the deeper layer.

show abstract

“…TDEi tensor options could be changed if the structural diversity of datasets is different from that of drug-like molecules. 25 , 26 …”

Section: Results and Discussionmentioning

confidence: 99%

Section: Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Topological Distance-Based Electron Interaction Tensor to Apply a Convolutional Neural Network on Drug-like Compounds

Shin

2021

ACS Omega

Self Cite

View full text Add to dashboard Cite

show abstract

“…This study shows that, in zebrafish, chlorfenapyr has a greater effect on the liver than on the brain at T21. This could be because the liver, the main organ of metabolic detoxification, is easily damaged by toxic compounds, and the blood-brain barrier prevents exogenous compounds from damaging the brain. , The blood-brain barrier is located between the blood vessels and the central nervous system (CNS) and controls the transportation of substances between the blood and the brain via special transporters, preventing toxic compounds from entering the CNS . However, there is a lack of valid data to confirm the mechanisms behind this phenomenon, which need to be explored in follow-up research.…”

Section: Discussionmentioning

confidence: 99%

Bioaccumulation, Metabolism and the Toxic Effects of Chlorfenapyr in Zebrafish (Danio rerio)

Chen

Teng

Zhang

et al. 2021

J. Agric. Food Chem.

View full text Add to dashboard Cite

Chlorfenapyr is widely used as an insecticide/miticide. Tralopyril, the active metabolite of chlorfenapyr, is used as an antifouling biocide in antifouling systems, and negatively affects aquatic environments. However, it is unclear whether tralopyril is a metabolite of chlorfenapyr in aquatic vertebrates, and there is little data on the bioaccumulation and toxicity of chlorfenapyr to aquatic vertebrates. In this study, the bioaccumulation and elimination of chlorfenapyr in zebrafish were assessed, and tralopyril, the active metabolite of chlorfenapyr, was determined. The effects of chronic exposure to chlorfenapyr on zebrafish liver and brain oxidative damage, apoptosis, immune response, and metabolome were investigated. These results showed that chlorfenapyr has a high bioaccumulation in zebrafish, with bioaccumulation factors of 864.6 and 1321.9 after exposure to 1.0 and 10 μg/L chlorfenapyr for 21 days, respectively. Chlorfenapyr at these concentrations also rapidly accumulated in zebrafish, reaching 615.5 and 10336 μg/kg on the second and third days of exposure, respectively. Chlorfenapyr was degraded to tralopyril in zebrafish; therefore, both chlorfenapyr and tralopyril should be considered when evaluating the risk of chlorfenapyr to aquatic organisms. In addition, chronic exposure caused oxidative damage, apoptosis, and immune disorders in zebrafish liver. Chronic exposure also altered the levels of endogenous metabolites in liver and brain. After 9 days of depuration, some indicators of oxidative damage, apoptosis, and immunity returned to normal levels, but the concentration of endogenous metabolites in zebrafish liver was still altered. Overall, these results provide useful information for evaluating the toxicity and environmental fate of chlorfenapyr in aquatic vertebrates.

show abstract

“…In particular, this work aims to develop a model for logBBB for biocides [12] based solely on the analysis of molecular features extracted from SMILES [17]. This approach gives the uncial possibility of extracting the similarity of endpoints in terms of structural fragments extracted from SMILES [18,19].…”

Section: Introductionmentioning

confidence: 99%

The validation of predictive potential via the system of self-consistent models: the simulation of blood-brain barrier permeation of organic compounds

Toropova

Toropov

Roncaglioni

et al. 2023

Preprint

View full text Add to dashboard Cite

In order to apply quantitative relationships "structure-endpoint" approach its reliability of prediction is necessary but sometimes challenging to achieve. Here, an attempt is made to accomplish the reliability of forecasts by creating a set of random partitions of data into training and validation sets, followed by constructing random models. A system of random models for a useful approach should be self-consistent, giving a similar or at least comparable statistical quality of the predictions for models obtained using different splits of available data into training and validation sets. Developed computer experiments aimed at obtaining blood-brain barrier permeation models showed that, in principle, such an approach can be used for the above purpose taking advantage of specific algorithms to optimize the modelling steps. Results so obtained are good, and better than what reported previously. The suggested approach to validation of models is non-identic to traditionally applied manners of the checking up models. The concept of validation can be used for arbitrary models (not only for models of the blood-brain barrier).

show abstract

Development of blood brain barrier permeation prediction models for organic and inorganic biocidal active substances

Cited by 13 publications

References 42 publications

Topological Distance-Based Electron Interaction Tensor to Apply a Convolutional Neural Network on Drug-like Compounds

Topological Distance-Based Electron Interaction Tensor to Apply a Convolutional Neural Network on Drug-like Compounds

Bioaccumulation, Metabolism and the Toxic Effects of Chlorfenapyr in Zebrafish (Danio rerio)

The validation of predictive potential via the system of self-consistent models: the simulation of blood-brain barrier permeation of organic compounds

Contact Info

Product

Resources

About