A Bayesian regression tree approach to identify the effect of nanoparticles’ properties on toxicity profiles

@article{LowKam2015ABR,
  title={A Bayesian regression tree approach to identify the effect of nanoparticles’ properties on toxicity profiles},
  author={C{\'e}cile Low-Kam and Donatello Telesca and Zhaoxia Ji and Haiyuan Zhang and Tian Xia and Jeffrey I. Zink and Andre E. Nel},
  journal={The Annals of Applied Statistics},
  year={2015},
  volume={9},
  pages={383-401}
}
We introduce a Bayesian multiple regression tree model to characterize relationships between physico-chemical properties of nanoparticles and their in-vitro toxicity over multiple doses and times of exposure. Unlike conventional models that rely on data summaries, our model solves the low sample size issue and avoids arbitrary loss of information by combining all measurements from a general exposure experiment across doses, times of exposure, and replicates. The proposed technique integrates… 
View PDF on arXiv
20 Citations
Highly Influential Citations
1
Background Citations
6
Methods Citations
4
Results Citations
1

20 Citations

A Tractable Method for Measuring Nanomaterial Risk Using Bayesian Networks

The use of Bayesian networks is demonstrated as a reliable tool for NM risk estimation and it is demonstrated how NM risk can be evaluated into a tractable, quantitative risk comparator.

BAYESIAN JOINT MODELING OF CHEMICAL STRUCTURE AND DOSE RESPONSE CURVES.

The Bayesian partially Supervised Sparse and Smooth Factor Analysis (BS3FA) model enables the prediction of chemical dose-response profiles based on chemical structure by taking advantage of a large database of chemicals that have already been tested for toxicity in HTS programs.

Application of Bayesian networks for hazard ranking of nanomaterials to support human health risk assessment

It is demonstrated that the BN may be used by different stakeholders at several stages in the risk assessment to predict certain properties of a nanomaterials of which little information is available or to prioritize nanommaterials for further screening.

Bayesian Matrix Completion for Hypothesis Testing

This model predicts bioactivity profiles of whether the dose-response curve is constant or not, using low-dimensional latent attributes of chemicals and of assay endpoints, and facilitates out-of-sample prediction of bioactivity potential for new chemicals not yet tested, while capturing heteroscedastic residuals.

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

A Bayesian model of dose-response for cancer drug studies

Bayesian tensor tensor (BTF), a hierarchical Bayesian model for dose-response modeling in multisample, mul-titreatment cancer drug studies, outperforms the current standard approach in biology and reveals potential new biomarkers of drug sensitivity in cancer.

Bayesian additive adaptive basis tensor product models for modeling high dimensional surfaces: an application to high‐throughput toxicity testing

A novel approach is proposed that models the multidimensional surface as a sum of learned basis functions formed as the tensor product of lower dimensional functions, which are themselves representable by a basis expansion learned from the data.

Bayesian Nonparametric Methods For Causal Inference And Prediction

This thesis presents novel approaches to regression and causal inference using popular Bayesian nonparametric methods and uses the EDP model to estimate incidence rates of diabetes when longitudinal laboratory values from electronic health records are used to augment diagnostic codes for outcome identification.

Relational Dose-Response Modeling for Cancer Drug Studies.

A dose-response model is built around Bayesian Tensor Filtering (BTF), a hierarchical Bayesian model of matrices of functions that captures the smoothness in each individual function while also being locally adaptive to sharp discontinuities, making it flexible enough to handle a wide variety of data.

Dose-response modeling in high-throughput cancer drug screenings: an end-to-end approach.

A hierarchical Bayesian model of how cancer cell lines respond to drugs in these experiments is proposed and a method for fitting the model to real-world high-throughput screening data is developed.

References

SHOWING 1-10 OF 38 REFERENCES

Relating Nanoparticle Properties to Biological Outcomes in Exposure Escalation Experiments.

A fundamental goal in nano-toxicology is that of identifying particle physical and chemical properties, which are likely to explain biological hazard. The first line of screening for potentially…

TOXICITY PROFILING OF ENGINEERED NANOMATERIALS VIA MULTIVARIATE DOSE-RESPONSE SURFACE MODELING.

A hierarchical structure is used to account for the multivariate nature of the data by modeling dependence between outcomes and thereby combining information across cytotoxicity pathways, and a flexible surface-response model is provided that provides inference and generalizations of various classical risk assessment parameters.

Relating nano‐particle properties to biological outcomes in exposure escalation experiments

This work discusses a modeling strategy that relates the outcome of an exposure escalation experiment to nano‐particle properties, and makes use of a hierarchical decision process to identify particles that initiate adverse biological outcomes and explain the probability of this event in terms of the particle physicochemical descriptors.

Classification NanoSAR development for cytotoxicity of metal oxide nanoparticles.

It is important to recognize that a significantly larger data set would be needed in order to expand the applicability domain and increase the confidence and reliability of data-driven nanoSARs.

Bayesian Treed Multivariate Gaussian Process With Adaptive Design: Application to a Carbon Capture Unit

A Bayesian treed multivariate Gaussian process (BTMGP) is developed as an extension of the Bayesian Treed Gaussian Process (BTGP) to model the cross-covariance function and the nonstationarity of the multivariate output and is compared with alternative approaches.

Categorical Inputs, Sensitivity Analysis, Optimization and Importance Tempering with tgp Version 2, an R Package for Treed Gaussian Process Models

The topics covered include methods for dealing with categorical inputs and excluding inputs from the tree or GP part of the model; fully Bayesian sensitivity analysis for inputs/covariates; sequential optimization of black-box functions; and a new Monte Carlo method for inference in multi-modal posterior distributions that combines simulated tempering and importance sampling.

BART: Bayesian Additive Regression Trees

We develop a Bayesian "sum-of-trees" model where each tree is constrained by a regularization prior to be a weak learner, and fitting and inference are accomplished via an iterative Bayesian…

A Partially Linear Tree‐based Regression Model for Multivariate Outcomes

A novel tree‐based model provides a formal statistical testing framework for the evaluation of the association between a multivariate outcome and a set of candidate predictors, such as markers within a gene or pathway, while accommodating adjustment for other covariates.

MULTIVARIATE REGRESSION TREES: A NEW TECHNIQUE FOR MODELING SPECIES–ENVIRONMENT RELATIONSHIPS

Multivariate regression trees (MRT) are a new statistical technique that can be used to explore, describe, and predict relationships between multispecies data and environmental characteristics. MRT…

Bayesian CART: Prior Specification and Posterior Simulation

The core computational innovations involve a novel Metropolis–Hastings method that can dramatically improve the convergence and mixing properties of MCMC methods of Bayesian CART analysis.