Entity

Time filter

Source Type


Oksel C.,University of Leeds | Winkler D.A.,CSIRO | Winkler D.A.,Monash Institute of Pharmaceutical Sciences | Winkler D.A.,Latrobe Institute for Molecular Science | And 4 more authors.
Nanotoxicology | Year: 2016

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 minimize any risks to health or the environment posed by the presence of ENMs. Data-driven 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, most importantly, interpretation of the models they generate is often very difficult. 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 datasets, are not particularly good at feature selection, can be relatively opaque to interpretation, 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 important advantages that it works with small datasets, automatically selects descriptors, and provides significantly improved interpretability of models. © 2016 Informa UK Limited, trading as Taylor & Francis Group. Source


Winkler D.A.,CSIRO | Winkler D.A.,Monash Institute of Pharmaceutical Sciences | Winkler D.A.,Latrobe Institute for Molecular Science | Winkler D.A.,Flinders University | And 2 more authors.
Pharmacology and Therapeutics | Year: 2016

The noble gases represent an intriguing scientific paradox. They are extremely inert chemically but display a remarkable spectrum of clinically useful biological properties. Despite a relative paucity of knowledge of their mechanisms of action, some of the noble gases have been used successfully in the clinic. Studies with xenon have suggested that the noble gases as a class may exhibit valuable biological properties such as anaesthesia; amelioration of ischemic damage; tissue protection prior to transplantation; analgesic properties; and a potentially wide range of other clinically useful effects. Xenon has been shown to be safe in humans, and has useful pharmacokinetic properties such as rapid onset, fast wash out etc. The main limitations in wider use are that: many of the fundamental biochemical studies are still lacking; the lighter noble gases are likely to manifest their properties only under hyperbaric conditions, impractical in surgery; and administration of xenon using convectional gaseous anaesthesia equipment is inefficient, making its use very expensive. There is nonetheless a significant body of published literature on the biochemical, pharmacological, and clinical properties of noble gases but no comprehensive reviews exist that summarize their properties and the existing knowledge of their models of action at the molecular (atomic) level. This review provides such an up-to-date summary of the extensive, useful biological properties of noble gases as drugs and prospects for wider application of these atoms. © 2016 Published by Elsevier Inc. All rights reserved. Source


Burden F.R.,CSIRO | Burden F.R.,Monash Institute of Pharmaceutical Sciences | Winkler D.A.,CSIRO | Winkler D.A.,Monash Institute of Pharmaceutical Sciences | And 2 more authors.
Journal of Chemical Information and Modeling | Year: 2015

Sparse machine learning methods have provided substantial benefits to quantitative structure property modeling, as they make model interpretation simpler and generate models with improved predictivity. Sparsity is usually induced via Bayesian regularization using sparsity-inducing priors and by the use of expectation maximization algorithms with sparse priors. The focus to date has been on using sparse methods to model continuous data and to carry out sparse feature selection. We describe the relevance vector machine (RVM), a sparse version of the support vector machine (SVM) that is one of the most widely used classification machine learning methods in QSAR and QSPR. We illustrate the superior properties of the RVM by modeling eight data sets using SVM, RVM, and another sparse Bayesian machine learning method, the Bayesian regularized artificial neural network with Laplacian prior (BRANNLP). We show that RVM models are substantially sparser than the SVM models and have similar or superior performance to them. (Figure Presented). © 2015 American Chemical Society. Source


Le T.C.,CSIRO | Yan B.,Shandong University | Winkler D.A.,CSIRO | Winkler D.A.,Monash Institute of Pharmaceutical Sciences | And 2 more authors.
Advanced Functional Materials | Year: 2015

Nanomaterials are used increasingly in diagnostics and therapeutics, particularly for malignancies. Efficient targeting of nanoparticles to specific cells is an important requirement for the development of successful nanoparticle-based theranostics and personalized medicines. Gold nanoparticles are surface modified using a library of small organic molecules, and optionally folate, to investigate their ability to target four cell lines from common cancers, three having high levels of folate receptors expression. Uptake of these nanoparticles varies widely with surface chemistriy and cell lines. Sparse machine learning methods are used to computationally model surface chemistry-uptake relationships, to make quantitative predictions of uptake for new nanoparticle surface chemistries, and to elucidate molecular aspects of the interactions. The combination of combinatorial surface chemistry modification and machine learning models will facilitate the rapid development of targeted theranostics. Efficient targeting of nanoparticles to specific cells is an important requirement for the development of successful nanoparticle-based cancer theranostics and personalized medicines. The cancer cell targeting ability of gold nanoparticles coated with a library of small organic molecules plus folate is modeled. Computational models can predict the degree of uptake of the nanoparticles as a function of surface chemistry. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim. Source


Ebert G.,Walter and Eliza Hall Institute of Medical Research | Ebert G.,University of Melbourne | Preston S.,Walter and Eliza Hall Institute of Medical Research | Preston S.,University of Melbourne | And 25 more authors.
Proceedings of the National Academy of Sciences of the United States of America | Year: 2015

Hepatitis B virus (HBV) infection can result in a spectrum of outcomes from immune-mediated control to disease progression, cirrhosis, and liver cancer. The host molecular pathways that influence and contribute to these outcomes need to be defined. Using an immuno-competent mouse model of chronic HBV infection, we identified some of the host cellular and molecular factors that impact on infection outcomes. Here, we show that cellular inhibitor of apoptosis proteins (cIAPs) attenuate TNF signaling during hepatitis B infection, and they restrict the death of infected hepatocytes, thus allowing viral persistence. Animals with a liver-specific cIAP1 and total cIAP2 deficiency efficiently control HBV infection compared with WT mice. This phenotype was partly recapitulated in mice that were deficient in cIAP2 alone. These results indicate that antagonizing the function of cIAPs may promote the clearance of HBV infection. © 2015, National Academy of Sciences. All rights reserved. Source

Discover hidden collaborations