Dataset Information

Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets.

ABSTRACT: The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure-Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for?>?10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F₁ score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman's aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g.,?>?28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

SUBMITTER: Idakwo G

PROVIDER: S-EPMC7592558 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets.

Idakwo Gabriel G Thangapandian Sundar S Luttrell Joseph J Li Yan Y Wang Nan N Zhou Zhaoxian Z Hong Huixiao H Yang Bei B Zhang Chaoyang C Gong Ping P

Journal of cheminformatics 20201027 1

The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure-Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxican ...[more]

PMID: 33372637

Similar Datasets

Project description:Cervical cell classification has important clinical significance in cervical cancer screening at early stages. However, there are fewer public cervical cancer smear cell datasets, the weights of each classes' samples are unbalanced, the image quality is uneven, and the classification research results based on CNN tend to overfit. To solve the above problems, we propose a cervical cell image generation model based on taming transformers (CCG-taming transformers) to provide high-quality cervical cancer datasets with sufficient samples and balanced weights, we improve the encoder structure by introducing SE-block and MultiRes-block to improve the ability to extract information from cervical cancer cells images; we introduce Layer Normlization to standardize the data, which is convenient for the subsequent non-linear processing of the data by the ReLU activation function in feed forward; we also introduce SMOTE-Tomek Links to balance the source data set and the number of samples and weights of the images we use Tokens-to-Token Vision Transformers (T2T-ViT) combing transfer learning to classify the cervical cancer smear cell image dataset to improve the classification performance. Classification experiments using the model proposed in this paper are performed on three public cervical cancer datasets, the classification accuracy in the liquid-based cytology Pap smear dataset (4-class), SIPAKMeD (5-class), and Herlev (7-class) are 98.79%, 99.58%, and 99.88%, respectively. The quality of the images we generated on these three data sets is very close to the source data set, the final averaged inception score (IS), Fréchet inception distance (FID), Recall and Precision are 3.75, 0.71, 0.32 and 0.65 respectively. Our method improves the accuracy of cervical cancer smear cell classification, provides more cervical cell sample images for cervical cancer-related research, and assists gynecologists to judge and diagnose different types of cervical cancer cells and analyze cervical cancer cells at different stages, which are difficult to distinguish. This paper applies the transformer to the generation and recognition of cervical cancer cell images for the first time.Supplementary informationThe online version contains supplementary material available at 10.1007/s11042-022-12670-0.

Project description:BackgroundInhibition of acetylcholinesterase (AChE), a biomarker of organophosphorous and carbamate exposure in environmental and occupational human health, has been commonly used to identify potential safety liabilities. So far, many environmental chemicals, including drug candidates, food additives, and industrial chemicals, have not been thoroughly evaluated for their inhibitory effects on AChE activity. AChE inhibitors can have therapeutic applications (e.g., tacrine and donepezil) or neurotoxic consequences (e.g., insecticides and nerve agents).ObjectivesThe objective of the current study was to identify environmental chemicals that inhibit AChE activity using in vitro and in silico models.MethodsTo identify AChE inhibitors rapidly and efficiently, we have screened the Toxicology in the 21st Century (Tox21) 10K compound library in a quantitative high-throughput screening (qHTS) platform by using the homogenous cell-based AChE inhibition assay and enzyme-based AChE inhibition assays (with or without microsomes). AChE inhibitors identified from the primary screening were further tested in monolayer or spheroid formed by SH-SY5Y and neural stem cell models. The inhibition and binding modes of these identified compounds were studied with time-dependent enzyme-based AChE inhibition assay and molecular docking, respectively.ResultsA group of known AChE inhibitors, such as donepezil, ambenonium dichloride, and tacrine hydrochloride, as well as many previously unreported AChE inhibitors, such as chelerythrine chloride and cilostazol, were identified in this study. Many of these compounds, such as pyrazophos, phosalone, and triazophos, needed metabolic activation. This study identified both reversible (e.g., donepezil and tacrine) and irreversible inhibitors (e.g., chlorpyrifos and bromophos-ethyl). Molecular docking analyses were performed to explain the relative inhibitory potency of selected compounds.ConclusionsOur tiered qHTS approach allowed us to generate a robust and reliable data set to evaluate large sets of environmental compounds for their AChE inhibitory activity. https://doi.org/10.1289/EHP6993.

Dataset Information

Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets.

Publications

Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets