Read-across predictions of nanoparticle hazard endpoints: a mathematical optimization approach

Varsou, Dimitra‐Danai; Afantitis, Antreas; Melagraki, Georgia; Sarimveis, Haralambos

doi:10.1039/c9na00242a

Cited by 12 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These ENMs are grouped together on the basis of defined structural similarity and differences between the substances. As a result, the toxicity end point properties will either all be similar or follow a regular pattern. , Nevertheless, the borderline between the two approaches is still vague and depends on the number of available samples. ,,, …”

Section: Introductionmentioning

confidence: 99%

“…This step can be connected to the variable selection process in predictive modeling, which aims at removing noninformative or noisy features, reducing the dimensionality and improving the reliability and the performance of the produced model. , Another crucial step in this workflow is the definition of a grouping hypothesis, which is evaluated in terms of its ability to fill data gaps. This requires a time-consuming trial-and-error process, including experimental data collection, until arriving at a successful but still nonoptimal grouping hypothesis …”

Section: Introductionmentioning

confidence: 99%

“…To address this weakness, Varsou et al , proposed an automated method that searches over the space of alternative hypotheses and determines the one providing the most accurate read-across predictions. The method selects the most important variables and defines the neighboring area around the target ENM, using single or multiple similarity criteria.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Grouping of Nanomaterials and Read-Across Prediction of Their Adverse Effects Based on Mathematical Optimization

Varsou

Koutroumpa

Sarimveis

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

In this study, a computational workflow is presented for grouping engineered nanomaterials (ENMs) and for predicting their toxicity-related end points. A mixed integer− linear optimization program (MILP) problem is formulated, which automatically filters out the noisy variables, defines the grouping boundaries, and develops specific to each group predictive models. The method is extended to the multidimensional space, by considering the ENM characterization categories (e.g., biological, physicochemical, biokinetics, image etc.) as different dimensions. The performance of the proposed method is illustrated through the application to benchmark data sets and comparison with alternative predictive modeling approaches. The trained models using the above data sets were made publicly available through a user-friendly web service.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Grouping of Nanomaterials and Read-Across Prediction of Their Adverse Effects Based on Mathematical Optimization

Varsou

Koutroumpa

Sarimveis

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…These include computational tools based on either physics‐based or data‐driven modeling approaches. Among the data‐driven computational approaches are the “classic” quantitative structure–activity relationship (QSAR) approaches often referred to as nano‐QSARs or QNARs (quantitative nanostructure–activity relationship approaches) in the nanoinformatics field, [ 166 ] while comparative–analogous models (read‐across methodologies) are also being developed. These methodologies are based on the development of statistical and machine learning (ML) algorithms to find correlations between NMs structure, physicochemical, and other properties, with their biological behavior and effects.…”

Section: Computational Approaches For Sbd Of Gbmsmentioning

confidence: 99%

Surface Functionalization of Graphene‐Based Materials: Biological Behavior, Toxicology, and Safe‐By‐Design Aspects

et al. 2021

Self Cite

View full text Add to dashboard Cite

drug delivery, bioimaging probes, antibacterial agents, and tissue engineering. [2] The advantage of GBMs over other nanomaterials (NMs) in biomedical application is their high specific surface area which allows high density functionalization and drug loading on both sides of the planar structure. [3] The π-conjugated system offers high capacity for GBMs to interact with various organic compounds with aromatic structures through π-π stacking during fabrication of graphene composites or for immobilization of biomolecules such as nucleic acids, peptides, antibodies, or other therapeutic substances. [4] The same properties may also raise concerns regarding the potential risk that GBMs may cause to human health through binding of key signaling molecules for example. GBMs may interact with biomolecules, changing the structure of protein or DNA or induce oxidative damage, and so on. [5] Therefore, prior to the widespread use of GBMs, it is imperative to evaluate their potential risk to environmental and human health and to establish a proactive approach for the safe design of these materials.In a recent review article, Fadeel et al. comprehensively examined the literature on the effects of GBMs on human health and the environment and gave an overview of the state-of-the-art of safety assessment of GBMs, highlighting the importance of The increasing exploitation of graphene-based materials (GBMs) is driven by their unique properties and structures, which ignite the imagination of scientists and engineers. At the same time, the very properties that make them so useful for applications lead to growing concerns regarding their potential impacts on human health and the environment. Since GBMs are inert to reaction, various attempts of surface functionalization are made to make them reactive. Herein, surface functionalization of GBMs, including those intentionally designed for specific applications, as well as those unintentionally acquired (e.g., protein corona formation) from the environment and biota, are reviewed through the lenses of nanotoxicity and design of safe materials (safe-by-design). Uptake and toxicity of functionalized GBMs and the underlying mechanisms are discussed and linked with the surface functionalization. Computational tools that can predict the interaction of GBMs behavior with their toxicity are discussed. A concise framing of current knowledge and key features of GBMs to be controlled for safe and sustainable applications are provided for the community.

show abstract

“…However, the user still needs to define an initial grouping/read-across hypothesis regarding the variables that will be considered important and the threshold values, that set the boundary to the neighborhoods of similar ENMs. Apellis web application updates the toxFlow methodology by automating the process of searching over the solution space in order to find the read-across hypothesis that produces the best possible results in terms of prediction accuracy and number of ENMs for which predictions are obtained [75]. To do so, a stochastic genetic algorithm that serves the selection of both the appropriate variables and the threshold values simultaneously was developed and is trained during the first step of the procedure, while the predicted toxicity endpoint is retrieved during the second part of it [75].…”

Section: Read-acrossmentioning

confidence: 99%

Transcriptomics in Toxicogenomics, Part III: Data Modelling for Risk Assessment

et al. 2020

Self Cite

View full text Add to dashboard Cite

Transcriptomics data are relevant to address a number of challenges in Toxicogenomics (TGx). After careful planning of exposure conditions and data preprocessing, the TGx data can be used in predictive toxicology, where more advanced modelling techniques are applied. The large volume of molecular profiles produced by omics-based technologies allows the development and application of artificial intelligence (AI) methods in TGx. Indeed, the publicly available omics datasets are constantly increasing together with a plethora of different methods that are made available to facilitate their analysis, interpretation and the generation of accurate and stable predictive models. In this review, we present the state-of-the-art of data modelling applied to transcriptomics data in TGx. We show how the benchmark dose (BMD) analysis can be applied to TGx data. We review read across and adverse outcome pathways (AOP) modelling methodologies. We discuss how network-based approaches can be successfully employed to clarify the mechanism of action (MOA) or specific biomarkers of exposure. We also describe the main AI methodologies applied to TGx data to create predictive classification and regression models and we address current challenges. Finally, we present a short description of deep learning (DL) and data integration methodologies applied in these contexts. Modelling of TGx data represents a valuable tool for more accurate chemical safety assessment. This review is the third part of a three-article series on Transcriptomics in Toxicogenomics.

show abstract

Read-across predictions of nanoparticle hazard endpoints: a mathematical optimization approach

Abstract: Development of a novel read-across methodology for the prediction of toxicity related endpoints of nanoparticles based on genetic algorithms.

Cited by 12 publications

References 31 publications

Automated Grouping of Nanomaterials and Read-Across Prediction of Their Adverse Effects Based on Mathematical Optimization

Automated Grouping of Nanomaterials and Read-Across Prediction of Their Adverse Effects Based on Mathematical Optimization

Surface Functionalization of Graphene‐Based Materials: Biological Behavior, Toxicology, and Safe‐By‐Design Aspects

Transcriptomics in Toxicogenomics, Part III: Data Modelling for Risk Assessment

Contact Info

Product

Resources

About