Discriminative models using molecular descriptors for predicting increased serum ALT levels in repeated-dose toxicity studies of rats

Takeshita, Jun-ichi; Nakayama, Hideki; Kitsunai, Yoko; Tanabe, Misako; Oki, Hitomi; Sasaki, Takuma; Yoshinari, Kouichi

doi:10.1016/j.comtox.2017.05.002

Cited by 6 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SMOTE can conduct over- and undersampling based on the same chemical categories using the nearest neighbors method. Components of synthesized chemicals by SMOTE are similar to original data sets on the basis of the concept of SMOTE technique [ 27 ]. The number of chemicals was set to the maximum number of the three categories (=150).…”

Section: Methodsmentioning

confidence: 99%

In Silico Model for Chemical-Induced Chromosomal Damages Elucidates Mode of Action and Irrelevant Positives

Fujita

Morita

Honda

2020

Genes

View full text Add to dashboard Cite

In silico tools to predict genotoxicity have become important for high-throughput screening of chemical substances. However, current in silico tools to evaluate chromosomal damage do not discriminate in vitro-specific positives that can be followed by in vivo tests. Herein, we establish an in silico model for chromosomal damages with the following approaches: (1) re-categorizing a previous data set into three groups (positives, negatives, and misleading positives) according to current reports that use weight-of-evidence approaches and expert judgments; (2) utilizing a generalized linear model (Elastic Net) that uses partial structures of chemicals (organic functional groups) as explanatory variables of the statistical model; and (3) interpreting mode of action in terms of chemical structures identified. The accuracy of our model was 85.6%, 80.3%, and 87.9% for positive, negative, and misleading positive predictions, respectively. Selected organic functional groups in the models for positive prediction were reported to induce genotoxicity via various modes of actions (e.g., DNA adduct formation), whereas those for misleading positives were not clearly related to genotoxicity (e.g., low pH, cytotoxicity induction). Therefore, the present model may contribute to high-throughput screening in material design or drug discovery to verify the relevance of estimated positives considering their mechanisms of action.

show abstract

Section: Methodsmentioning

confidence: 99%

In Silico Model for Chemical-Induced Chromosomal Damages Elucidates Mode of Action and Irrelevant Positives

Fujita

Morita

Honda

2020

Genes

View full text Add to dashboard Cite

show abstract

“…The number of clusters is set by the level of undersampling. Few extensions of this work include [41], [42]. Zhao er al.…”

Section: A Previous Work On Undersamplingmentioning

confidence: 99%

“…[41] applied an unsupervised learning algorithm that transforms the classification problem into several classification sub-problems. K-medoids based undersampling approach is applied in [42] and only the cluster centers are considered as sampled data. Again, all these approaches can't ensure retaining of most informative data as they replaces the real-samples with the cluster centers.…”

Section: A Previous Work On Undersamplingmentioning

confidence: 99%

A Method for Handling Multi-class Imbalanced Data by Geometry based Information Sampling and Class Prioritized Synthetic Data Generation (GICaPS)

Majumder¹,

Dutta²,

Kumar³

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper looks into the problem of handling imbalanced data in a multi-label classification problem. The problem is solved by proposing two novel methods that primarily exploit the geometric relationship between the feature vectors. The first one is an undersampling algorithm that uses angle between feature vectors to select more informative samples while rejecting the less informative ones. A suitable criterion is proposed to define the informativeness of a given sample. The second one is an oversampling algorithm that uses a generative algorithm to create new synthetic data that respects all class boundaries. This is achieved by finding no man's land based on Euclidean distance between the feature vectors. The efficacy of the proposed methods is analyzed by solving a generic multi-class recognition problem based on mixture of Gaussians. The superiority of the proposed algorithms is established through comparison with other state-of-the-art methods, including SMOTE and ADASYN, over ten different publicly available datasets exhibiting high-toextreme data imbalance. These two methods are combined into a single data processing framework and is labeled as "GICaPS" to highlight the role of geometry-based information (GI) sampling and Class-Prioritized Synthesis (CaPS) in dealing with multi-class data imbalance problem, thereby making a novel contribution in this field.

show abstract

Computational Approaches for Drug-Induced Liver Injury (DILI) Prediction: State of the Art and Challenges

et al. 2021

View full text Add to dashboard Cite

show abstract

Discriminative models using molecular descriptors for predicting increased serum ALT levels in repeated-dose toxicity studies of rats

Cited by 6 publications

References 8 publications

In Silico Model for Chemical-Induced Chromosomal Damages Elucidates Mode of Action and Irrelevant Positives

In Silico Model for Chemical-Induced Chromosomal Damages Elucidates Mode of Action and Irrelevant Positives

A Method for Handling Multi-class Imbalanced Data by Geometry based Information Sampling and Class Prioritized Synthetic Data Generation (GICaPS)

Computational Approaches for Drug-Induced Liver Injury (DILI) Prediction: State of the Art and Challenges

Contact Info

Product

Resources

About