Curation of datasets, assessment of their quality and completeness, and nanoSAR classification model development for metallic nanoparticles

Trinh, Tung X.; Ha, My Kieu; Choi, Jang Sik; Byun, Hyung‐Gi; Yoon, Tae Hyun

doi:10.1039/c8en00061a

Cited by 33 publications

(47 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the experimental protocols were not taken under consideration. Future studies may integrate weighting scoring rules for each published article based on the measurement methods to evaluate the quality of the p-chem data as displayed in [21].…”

Section: Discussionmentioning

confidence: 99%

“…Surface area appeared as either important or not, probably largely affected by low data completeness. NP type is found to be both highly and lowly influencing; Trinh, Ha, Choi, Byun and Yoon [21] had only one or two types of metal NP in their dataset, and this could explain why this variable provided little information in building the models. Particle size appeared as significant across all studies, highlighting the importance of size in the manifestation of toxicological effects.…”

Section: Refmentioning

confidence: 99%

“…However, due to low completeness, we integrated the variables into a single one. Only one study specified the medium in which zeta potential and hydrodynamic size were measured [21]. Besides p-chem properties, one study included quantum chemical properties in their dataset such as formation enthalpy, conduction band energy etc.…”

Section: Refmentioning

confidence: 99%

See 2 more Smart Citations

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Furxhi¹,

Murphy²

2020

IJMS

View full text Add to dashboard Cite

The practice of non-testing approaches in nanoparticles hazard assessment is necessary to identify and classify potential risks in a cost effective and timely manner. Machine learning techniques have been applied in the field of nanotoxicology with encouraging results. A neurotoxicity classification model for diverse nanoparticles is presented in this study. A data set created from multiple literature sources consisting of nanoparticles physicochemical properties, exposure conditions and in vitro characteristics is compiled to predict cell viability. Pre-processing techniques were applied such as normalization methods and two supervised instance methods, a synthetic minority over-sampling technique to address biased predictions and production of subsamples via bootstrapping. The classification model was developed using random forest and goodness-of-fit with additional robustness and predictability metrics were used to evaluate the performance. Information gain analysis identified the exposure dose and duration, toxicological assay, cell type, and zeta potential as the five most important attributes to predict neurotoxicity in vitro. This is the first tissue-specific machine learning tool for neurotoxicity prediction caused by nanoparticles in in vitro systems. The model performs better than non-tissue specific models.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Refmentioning

confidence: 99%

See 1 more Smart Citation

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Furxhi¹,

Murphy²

2020

IJMS

View full text Add to dashboard Cite

show abstract

“…Furthermore, 8% of the studies mention that their dataset had equal outcome classes, while, on the other hand, 4% of studies tackled the imbalance issue by resampling the training dataset. Resampling can be done by applying the Synthetic Minority Oversampling Technique (SMOTE), which is a supervised instance algorithm that oversamples the minority instances using the k-nearest-neighbor (kNN) [60,67,77]. This method balances the dataset by generating more data points.…”

Section: Class Balancingmentioning

confidence: 99%

“…Class imbalance reflects an unequal distribution of class values within a dataset and poses a challenging problem because classifiers exhibit biases of the results. This has been rarely accounted for properly during training [60,67,72,74]. The most common technique used was SMOTE.…”

Section: The Frameworkmentioning

confidence: 99%

Practices and Trends of Machine Learning Application in Nanotoxicology

et al. 2020

View full text Add to dashboard Cite

Machine Learning (ML) techniques have been applied in the field of nanotoxicology with very encouraging results. Adverse effects of nanoforms are affected by multiple features described by theoretical descriptors, nano-specific measured properties, and experimental conditions. ML has been proven very helpful in this field in order to gain an insight into features effecting toxicity, predicting possible adverse effects as part of proactive risk analysis, and informing safe design. At this juncture, it is important to document and categorize the work that has been carried out. This study investigates and bookmarks ML methodologies used to predict nano (eco)-toxicological outcomes in nanotoxicology during the last decade. It provides a review of the sequenced steps involved in implementing an ML model, from data pre-processing, to model implementation, model validation, and applicability domain. The review gathers and presents the step-wise information on techniques and procedures of existing models that can be used readily to assemble new nanotoxicological in silico studies and accelerates the regulation of in silico tools in nanotoxicology. ML applications in nanotoxicology comprise an active and diverse collection of ongoing efforts, although it is still in their early steps toward a scientific accord, subsequent guidelines, and regulation adoption. This study is an important bookend to a decade of ML applications to nanotoxicology and serves as a useful guide to further in silico applications.

show abstract

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

et al. 2021

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

Curation of datasets, assessment of their quality and completeness, and nanoSAR classification model development for metallic nanoparticles

Abstract: Workflow for curation of datasets, assessment of their quality and completeness, and nanoSAR model development.

Cited by 33 publications

References 42 publications

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

Practices and Trends of Machine Learning Application in Nanotoxicology

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

Contact Info

Product

Resources

About