Computational identification of preservatives with potential neuronal cytotoxicity

Kan, Hung-Lin; Lin, Ying; Tung, Chun Wei

doi:10.1016/j.yrtph.2020.104815

Cited by 9 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The consensus chemical space was determined by using a decision tree-based method 12 , 13 ) to derive classification rules for the exclusion of chemicals outside of the consensus chemical space. To avoid overfitting problems, the determination of the consensus chemical space was derived solely from the training dataset and independently tested using the test dataset.…”

Section: Methodsmentioning

confidence: 99%

“…The 143 pesticides were randomly divided into a training dataset and a test dataset at a 2 : 1 ratio. Exclusion rules for chemicals outside of the consensus chemical space were derived by using a decision tree-based algorithm 12 , 13 ) with nine different fingerprints based on the training dataset, and their predictive performance was evaluated using the test dataset. The test result showed that the proposed method using standard fingerprints is effective in identifying non-sensitizers with a high concordance of 100%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconfiguring the online tool of SkinSensPred for predicting skin sensitization of pesticides

et al. 2022

Self Cite

View full text Add to dashboard Cite

Adverse outcome pathway (AOP)-based computational models provide state-of-the-art prediction for human skin sensitizers and are promising alternatives to animal testing. However, little is known about their applicability to pesticides due to scarce pesticide data for evaluation. Moreover, pesticides traditionally have been tested on animals without human data, making validation difficult. Direct application of AOP-based models to pesticides may be inappropriate since their original applicability domains were designed to maximize reliability for human response prediction on diverse chemicals but not pesticides. This study proposed to identify a consensus chemical space with concordant human responses predicted by the SkinSensPred online tool and animal testing data to reduce animal testing. The identified consensus chemical space for non-sensitizers achieved high concordance of 85% and 100% for the cross-validation and independent test, respectively. The reconfigured SkinSensPred can be applied as the first-tier tool for identifying non-sensitizers to reduce. animal testing for pesticides by 19.6%.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reconfiguring the online tool of SkinSensPred for predicting skin sensitization of pesticides

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…A majority vote of outputs from all decision trees was applied to make the final prediction. Random forest is shown to be effective and robust for small datasets [41][42][43][44][45] and is considered suitable for this study. The percentage of stable prediction was utilized as the prediction score ranging from 1 (stable) to 0 (unstable).…”

Section: Model Developmentmentioning

confidence: 99%

A Machine Learning Classifier for Predicting Stable MCI Patients Using Gene Biomarkers

Lin

Tung

2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a neurodegenerative disorder with an insidious onset and irreversible condition. Patients with mild cognitive impairment (MCI) are at high risk of converting to AD. Early diagnosis of unstable MCI patients is therefore vital for slowing the progression to AD. However, current diagnostic methods are either highly invasive or expensive, preventing their wide applications. Developing low-invasive and cost-efficient screening methods is desirable as the first-tier approach for identifying unstable MCI patients or excluding stable MCI patients. This study developed feature selection and machine learning algorithms to identify blood-sample gene biomarkers for predicting stable MCI patients. Two datasets obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database were utilized to conclude 29 genes biomarkers (31 probes) for predicting stable MCI patients. A random forest-based classifier performed well with area under the receiver operating characteristic curve (AUC) values of 0.841 and 0.775 for cross-validation and test datasets, respectively. For patients with a prediction score greater than 0.9, an excellent concordance of 97% was obtained, showing the usefulness of the proposed method for identifying stable MCI patients. In the context of precision medicine, the proposed prediction model is expected to be useful for identifying stable MCI patients and providing medical doctors and patients with new first-tier diagnosis options.

show abstract

“…Furthermore, in that review, state‐of‐the‐art molecular toxicity‐based prioritization studies making use of, for example, the ToxCast database, were not discussed (see Hartman et al, 2018; Rogers et al, 2021). In addition, there have been no summaries or interpretations of several key prioritization studies employing novel screening approaches such as in vitro neuronal cytotoxicity and (anti‐)estrogenic activity published during 2018–2022 (see Pinto et al, 2019; Kan et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

What Approaches Should be Used to Prioritize Pharmaceuticals and Personal Care Products for Research on Environmental and Human Health Exposure and Effects?

Guo

Iwata

et al. 2022

Enviro Toxic and Chemistry

View full text Add to dashboard Cite

Pharmaceuticals and personal care products (PPCPs) are released from multiple anthropogenic sources and thus have a ubiquitous presence in the environment. The environmental exposure and potential effects of PPCPs on biota and humans has aroused concern within the scientific community and the public. Risk assessments are commonly conducted to evaluate the likelihood of chemicals including PPCPs that pose health threats to organisms inhabiting various environmental compartments and humans. Because thousands of PPCPs are currently used, it is impractical to assess the environmental risk of all of them due to data limitations; in addition, new PPCPs are continually being produced. Prioritization approaches, based either on exposure, hazard, or risk, provide a possible means by which those PPCPs that are likely to pose the greatest risk to the environment are identified, thereby enabling more effective allocation of resources in environmental monitoring programs in specific geographical locations and ecotoxicological investigations. In the present review, the importance and current knowledge concerning PPCP occurrence and risk are discussed and priorities for future research are proposed, in terms of PPCP exposure (e.g., optimization of exposure modeling in freshwater ecosystems and more monitoring of PPCPs in the marine environment) or hazard (e.g., differential risk of PPCPs to lower vs. higher trophic level species and risks to human health). Recommended research questions for the next 10 years are also provided, which can be answered by future studies on prioritization of PPCPs. Environ Toxicol Chem 2022;00:1–14. © 2022 SETAC

show abstract

Computational identification of preservatives with potential neuronal cytotoxicity

Cited by 9 publications

References 39 publications

Reconfiguring the online tool of SkinSensPred for predicting skin sensitization of pesticides

Reconfiguring the online tool of SkinSensPred for predicting skin sensitization of pesticides

A Machine Learning Classifier for Predicting Stable MCI Patients Using Gene Biomarkers

What Approaches Should be Used to Prioritize Pharmaceuticals and Personal Care Products for Research on Environmental and Human Health Exposure and Effects?

Contact Info

Product

Resources

About