Causal inference methods to assist in mechanistic interpretation of classification nano-SAR models

Sizochenko, Natalia; Rasulev, Bakhtiyor; Gajewicz, Agnieszka; Mokshyna, Elena; Кузьмин, В. Е.; Leszczyński, Jerzy; Puzyn, Tomasz

doi:10.1039/c5ra11399g

Cited by 17 publications

(30 citation statements)

References 39 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A set of 27 NP descriptors including element related descriptors, energy/enthalpy descriptors, size information and surface charge descriptors was also collected from Liu et al (2013b) and used as input parameters in GPTree analysis. The initial dataset was then divided into training (18 NPs, 78% of dataset) and test set (5 NPs, 22% of dataset) as recommended by (Sizochenko et al, 2015).…”

Section: Biological Data and Modellingmentioning

confidence: 99%

Accurate and interpretable nanoSAR models from genetic programming-based decision tree construction approaches

et al. 2016

View full text Add to dashboard Cite

The number of engineered nanomaterials (ENMs) being exploited commercially is growing rapidly, due to the novel properties they exhibit. Clearly, it is important to understand and ameliorate any risks to health or the environment posed by the presence of ENMs. Datadriven models that decode the relationships between the biological activities of ENMs and their physicochemical characteristics provide an attractive means of maximizing the value of scarce and expensive experimental data. Although such structure-activity relationship (SAR) methods have become very useful tools for modelling nanotoxicity endpoints (nanoSAR), they have limited robustness and predictivity, and interpretation of the models they generate can be problematic. New computational modelling tools or new ways of using existing tools are required to model the relatively sparse and sometimes lower quality data on the biological effects of ENMs. The most commonly used SAR modelling methods work best with large data sets, are not particularly good at feature selection, and may not account for nonlinearity in the structure-property relationships. To overcome these limitations, we describe the application of a novel algorithm, a genetic programming-based decision tree construction tool (GPTree) to nanoSAR modelling. We demonstrate the use of GPTree in the construction of accurate and interpretable nanoSAR models by applying it to four diverse literature datasets.We describe the algorithm and compare model results across the four studies. We show that GPTree generates models with accuracies equivalent to or superior to those of prior modelling studies on the same datasets. GPTree is a robust, automatic method for generation of accurate nanoSAR models with additional advantages that it works with small datasets, automatically selects descriptors, and provides improved interpretability of models.

show abstract

Section: Biological Data and Modellingmentioning

confidence: 99%

Accurate and interpretable nanoSAR models from genetic programming-based decision tree construction approaches

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Among the metrics mentioned, displays significantly different values from other measures including CCC, which is the most confident [131]. For binary classification, the sensitivity, specificity, accuracy, and ROC curves can be calculated [73,104]. Some of the reviewed models within the peer-reviewed literature did not demonstrate any validation metrics at all [123,127].…”

Section: Applicability Domain (Ad)mentioning

confidence: 96%

“…Sizochenko et al [104] estimated the AD based on minimum-cost-tree of variable importance values in the space of descriptors while Kar et al [46] used diverse approaches to assess AD, such as the leverage approach and distance to the model in X-space (DModX) ( Figure 5). The DModX approach is usually applied for PLS models and the basic theory is that Y and X residuals have a diagnostic value for model reliability.…”

Section: Applicability Domain (Ad)mentioning

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

“…A SVM approach, in conjunction with conduction band energy and ionic index (a parameter used to calculate the metal ion hydration energy, which is an indicator of the ability to form hydrated metal ions) descriptors, was used by Liu et al The model had a high classification accuracy of 93.74% [48]. With the data from Zhang et al, Sizochenko et al [47] built nano-SAR models for BEAS-2B and RAW 264.7 cell lines with high predictivity; they used seven and nine descriptors, respectively. The model for BEAS-2B cells included the following descriptors: Mass density, covalent index (represents interactions of NPs with protein-bound sulfhydryl and depleting glutathione), cation polarizing power (represents electrostatic interactions between NPs and cells), Wigner-Seitz radius [56], surface area-to-volume ratio and aggregation parameter (both of which are LDM-based descriptors), and tri-atomic descriptor of atomic charges (SiRMS descriptor [34,35]).…”

Section: Metal Oxidesmentioning

confidence: 99%

“…The model for RAW 264.7 cell line included the following descriptors: Mass density, molecular weight, electronegativity, covalent index, surface area, surface area-to-volume ratio, two-atomic descriptor of van der Waals interactions, tetra-atomic descriptor of atomic charges, and size. As a whole, ionic, fragmental, and LDM-based descriptors revealed the structure and characteristics of metal oxide NPs [47]. A partial least squares (PLS) regression analysis was performed by Forest et al, in which 25 nanoparticles from six metal oxides with different particle sizes and shapes were synthesized and characterized.…”

Section: Metal Oxidesmentioning

confidence: 99%

Nano-(Q)SAR for Cytotoxicity Prediction of Engineered Nanomaterials

2019

View full text Add to dashboard Cite

Although nanotechnology is a new and rapidly growing area of science, the impact of nanomaterials on living organisms is unknown in many aspects. In this regard, it is extremely important to perform toxicological tests, but complete characterization of all varying preparations is extremely laborious. The computational technique called quantitative structure-activity relationship, or QSAR, allows reducing the cost of time-and resource-consuming nanotoxicity tests. In this review, (Q)SAR cytotoxicity studies of the past decade are systematically considered. We regard here five classes of engineered nanomaterials (ENMs): Metal oxides, metal-containing nanoparticles, multi-walled carbon nanotubes, fullerenes, and silica nanoparticles. Some studies reveal that QSAR models are better than classification SAR models, while other reports conclude that SAR is more precise than QSAR. The quasi-QSAR method appears to be the most promising tool, as it allows accurately taking experimental conditions into account. However, experimental artifacts are a major concern in this case.

show abstract

Causal inference methods to assist in mechanistic interpretation of classification nano-SAR models

Cited by 17 publications

References 39 publications

Accurate and interpretable nanoSAR models from genetic programming-based decision tree construction approaches

Accurate and interpretable nanoSAR models from genetic programming-based decision tree construction approaches

Practices and Trends of Machine Learning Application in Nanotoxicology

Nano-(Q)SAR for Cytotoxicity Prediction of Engineered Nanomaterials

Contact Info

Product

Resources

About