Neural Networks in 3D QSAR

Livingstone, David J.; Manallack, David T.

doi:10.1002/qsar.200310003

Cited by 15 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative structure-property relationship (QSPR) modeling has long been used in drug discovery [17]. This approach was translated into predicting biological response to polymeric biomaterials.…”

Section: Introductionmentioning

confidence: 99%

Predicting biomaterial property-dendritic cell phenotype relationships from the multivariate analysis of responses to polymethacrylates

et al. 2012

View full text Add to dashboard Cite

Dendritic cells (DCs) play a critical role in orchestrating the host responses to a wide variety of foreign antigens and are essential in maintaining immune tolerance. Distinct biomaterials have been shown to differentially affect the phenotype of DCs, which suggested that biomaterials may be used to modulate immune response towards the biologic component in combination products. The elucidation of biomaterial property-DC phenotype relationships is expected to inform rational design of immuno-modulatory biomaterials. In this study, DC response to a set of 12 polymethacrylates (pMAs) was assessed in terms of surface marker expression and cytokine profile. Principal component analysis (PCA) determined that surface carbon correlated with enhanced DC maturation, while surface oxygen was associated with an immature DC phenotype. Partial square linear regression, a multivariate modeling approach, was implemented and successfully predicted biomaterial-induced DC phenotype in terms of surface marker expression from biomaterial properties with R2prediction = 0.76. Furthermore, prediction of DC phenotype was effective based on only theoretical chemical composition of the bulk polymers with R2prediction = 0.80. These results demonstrated that immune cell response can be predicted from biomaterial properties, and computational models will expedite future biomaterial design and selection.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting biomaterial property-dendritic cell phenotype relationships from the multivariate analysis of responses to polymethacrylates

et al. 2012

View full text Add to dashboard Cite

show abstract

“…Recently there are modified PLS methods for SAR modeling [Bennett et al, 2003;Rosipal and Krämer, 2006b], in which kernel partial least squares (kernel PLS) is a kernel method for PLS that introduces on-linear mapping through kernels [Lapinsh et al, 2005;Deng et al, 2004]. Many other learning algorithms are applcable for SAR modeling and include Neural Networks (NN) [Tetko et al, 2001;Livingstone and Manallack, 2003;Guha and Jurs, 2005], Decision Tree [Sussman et al, 2003], Recursive Partitioning [Chen et al, 1998;Rusinko et al, 1999;An and Wang, 2001], Linear Discriminant Analysis (LDA) [Otto, 1999], Bayesian models [Xia et al, 2004;Mccallum and Nigam, 1998], and Random Forest [Zhang and Aires-de Sousa, 2007;Breiman, 2001]. Hughes-Oliver et al [2008] implement and compare many popular learning methods for SAR modeling.…”

Section: Machine Learning Algorithms For Conventional In Silico Modelsmentioning

confidence: 99%

In silico structure‐activity‐relationship (SAR) models from machine learning: a review

Ning

Karypis

2010

Drug Development Research

View full text Add to dashboard Cite

In this article, we review the recent development for in silico Structure-Activity-Relationship (SAR) models using machine-learning techniques. The review focuses on the following topics: machine-learning algorithms for computational SAR models, single-target-oriented SAR methodologies, Chemogenomics, and future trends. We try to provide the state-of-the-art SAR methods as well as the most up-to-date advancement, in order for the researchers to have a general overview at this area. Drug Dev Res 72:138-146, 2011.

show abstract

“…Translating the QSPR modeling approach [80] used in drug discovery to the biomaterials field, Smith et al [81][82][83][84] pioneered the concept of predicting biological response for polymeric biomaterials by introducing surrogate models which combine machine learning algorithms, molecular modeling and an artificial neural network (ANN) to predict cell-material interactions at the surfaces of biodegradable polymers for tissue-engineering applications. To the best of our knowledge, this is the only group to date that focused on predicting cell growth and protein adsorption on polymeric biomaterial surfaces using surrogate models and their work and its limitations are presented bellow.…”

Section: Surrogate Modeling Approachmentioning

confidence: 99%