Dataset Information

Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources.

ABSTRACT: A generalized toxicity classification model for 7 different oxide nanomaterials is presented in this study. A data set extracted from multiple literature sources and screened by physicochemical property based quality scores were used for model development. Moreover, a few more preprocessing techniques, such as synthetic minority over-sampling technique, were applied to address the imbalanced class problem in the data set. Then, classification models using four different algorithms, such as generalized linear model, support vector machine, random forest, and neural network, were developed and their performances were compared to find the best performing preprocessing methods as well as algorithms. The neural network model built using the balanced data set was identified as the model with best predictive performance, while applicability domain was defined using k-nearest neighbours algorithm. The analysis of relative attribute importance for the built neural network model identified dose, formation enthalpy, exposure time, and hydrodynamic size as the four most important attributes. As the presented model can predict the toxicity of the nanomaterials in consideration of various experimental conditions, it has the advantage of having a broader and more general applicability domain than the existing quantitative structure-activity relationship model.

SUBMITTER: Choi JS

PROVIDER: S-EPMC5904177 | biostudies-literature | 2018 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources.

Choi Jang-Sik JS Ha My Kieu MK Trinh Tung Xuan TX Yoon Tae Hyun TH Byun Hyung-Gi HG

Scientific reports 20180417 1

A generalized toxicity classification model for 7 different oxide nanomaterials is presented in this study. A data set extracted from multiple literature sources and screened by physicochemical property based quality scores were used for model development. Moreover, a few more preprocessing techniques, such as synthetic minority over-sampling technique, were applied to address the imbalanced class problem in the data set. Then, classification models using four different algorithms, such as gener ...[more]

PMID: 29666463

Similar Datasets

Project description:Nanomaterials (NMs) display many unique and useful physico-chemical properties. However, reliable approaches are needed for risk assessment of NMs. The present study was performed in the FP7-MARINA project, with the objective to identify and evaluate in vitro test methods for toxicity assessment in order to facilitate the development of an intelligent testing strategy (ITS). Six representative oxide NMs provided by the EC-JRC Nanomaterials Repository were tested in nine laboratories. The in vitro toxicity of NMs was evaluated in 12 cellular models representing 6 different target organs/systems (immune system, respiratory system, gastrointestinal system, reproductive organs, kidney and embryonic tissues). The toxicity assessment was conducted using 10 different assays for cytotoxicity, embryotoxicity, epithelial integrity, cytokine secretion and oxidative stress. Thorough physico-chemical characterization was performed for all tested NMs. Commercially relevant NMs with different physico-chemical properties were selected: two TiO2 NMs with different surface chemistry - hydrophilic (NM-103) and hydrophobic (NM-104), two forms of ZnO - uncoated (NM-110) and coated with triethoxycapryl silane (NM-111) and two SiO2 NMs produced by two different manufacturing techniques - precipitated (NM-200) and pyrogenic (NM-203). Cell specific toxicity effects of all NMs were observed; macrophages were the most sensitive cell type after short-term exposures (24-72h) (ZnO>SiO2>TiO2). Longer term exposure (7 to 21 days) significantly affected the cell barrier integrity in the presence of ZnO, but not TiO2 and SiO2, while the embryonic stem cell test (EST) classified the TiO2 NMs as potentially 'weak-embryotoxic' and ZnO and SiO2 NMs as 'non-embryotoxic'. A hazard ranking could be established for the representative NMs tested (ZnO NM-110 > ZnO NM-111 > SiO2 NM-203 > SiO2 NM-200 > TiO2 NM-104 > TiO2 NM-103). This ranking was different in the case of embryonic tissues, for which TiO2 displayed higher toxicity compared with ZnO and SiO2. Importantly, the in vitro methodology applied could identify cell- and NM-specific responses, with a low variability observed between different test assays. Overall, this testing approach, based on a battery of cellular systems and test assays, complemented by an exhaustive physico-chemical characterization of NMs, could be deployed for the development of an ITS suitable for risk assessment of NMs. This study also provides a rich source of data for modeling of NM effects.

Project description:BackgroundInformation obtained from diverse data sources can be combined in a principled manner using various machine learning methods to increase the reliability and range of knowledge about protein function. The result is a weighted functional linkage network (FLN) in which linked neighbors share at least one function with high probability. Precision is, however, low. Aiming to provide precise functional annotation for as many proteins as possible, we explore and propose a two-step framework for functional annotation (1) construction of a high-coverage and reliable FLN via machine learning techniques (2) development of a decision rule for the constructed FLN to optimize functional annotation.ResultsWe first apply this framework to Saccharomyces cerevisiae. In the first step, we demonstrate that four commonly used machine learning methods, Linear SVM, Linear Discriminant Analysis, Naïve Bayes, and Neural Network, all combine heterogeneous data to produce reliable and high-coverage FLNs, in which the linkage weight more accurately estimates functional coupling of linked proteins than use individual data sources alone. In the second step, empirical tuning of an adjustable decision rule on the constructed FLN reveals that basing annotation on maximum edge weight results in the most precise annotation at high coverages. In particular at low coverage all rules evaluated perform comparably. At coverage above approximately 50%, however, they diverge rapidly. At full coverage, the maximum weight decision rule still has a precision of approximately 70%, whereas for other methods, precision ranges from a high of slightly more than 30%, down to 3%. In addition, a scoring scheme to estimate the precisions of individual predictions is also provided. Finally, tests of the robustness of the framework indicate that our framework can be successfully applied to less studied organisms.ConclusionWe provide a general two-step function-annotation framework, and show that high coverage, high precision annotations can be achieved by constructing a high-coverage and reliable FLN via data integration followed by applying a maximum weight decision rule.

Dataset Information

Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources.

Publications

Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets