Machine learning prediction of nanoparticle in vitro toxicity: A comparative study of classifiers and ensemble-classifiers using the Copeland Index

Furxhi, Irini; Murphy, Finbarr; Mullins, Martin; Poland, Craig A.

doi:10.1016/j.toxlet.2019.05.016

Cited by 45 publications

(30 citation statements)

References 86 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These variables take values of 0 or 1 depending on whether a particular nano-feature or experimental endpoint is absent or present [56,71]. Studies used one-hot encoding in models where categories cannot be used, such as in linear regression [60,72]. Within the reviewed articles, one hot encoding was applied in 7% of the studies.…”

Section: Normalization and Discretizationmentioning

confidence: 99%

“…While assessing data quality and completeness, nano-specific filling in of missing values using manufacturer's specifications and/or estimations [60,64] was suggested within the Safe and Sustainable Nanotechnology (S2NANO) (http://portal.s2nano.org/ (Webpage accessed autumn 2019)) database. Furxhi et al [72] investigated the robustness of several ML tools on generated versions of the dataset by removing values artificially. Recently, an integration of two data gap filling techniques to predict neurotoxicity for non-NMs was implemented, which demonstrated the capacity of integrating methodologies [81].…”

Section: Missing Valuesmentioning

confidence: 99%

“…However, the tool is presently valid only for MLR models. Furxhi et al [72] proposed a composite score based on a Copeland index to rank classifiers according to their performance on diverse datasets, validation stages, and performance metrics. Tamvakis et al [133] proposed a dissimilarity performance index based on their voting performance to recommend the optimal ensemble combination.…”

Section: Ranking Of Classifiersmentioning

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%

“…They showed excellent predictivity with small or large datasets, which performed well even with missing values. Furxhi et al [72] demonstrated that RF ranks first among individual classifiers and compete with meta-algorithms. RF is highly tolerant of overfitting, as it combines a number of simple models and has the ability to deal with special issues, such as descriptors counting higher than observations [40].…”

Section: The Algorithmsmentioning

confidence: 99%

See 4 more Smart Citations

Practices and Trends of Machine Learning Application in Nanotoxicology

et al. 2020

Self Cite

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