Multi-factorial analysis of class prediction error: estimating optimal number of biomarkers for various classification rules

Machine learning and statistical model based classifiers have increasingly been used with more complex and high dimensional biological data obtained from high-throughput technologies. Understanding the impact of various factors associated with large and complex microarray datasets on the predictive performance of classifiers is computationally intensive, under investigated, yet vital in determining the optimal number of biomarkers for various classification purposes aimed towards improved detection, diagnosis, and therapeutic monitoring of diseases. We investigate the impact of microarray based data characteristics on the predictive performance for various classification rules using simulation studies. Our investigation using Random Forest, Support Vector Machines, Linear Discriminant Analysis and k-Nearest Neighbour shows that the predictive performance of classifiers is strongly influenced by training set size, biological and technical variability, replication, fold change and correlation between biomarkers. Optimal number of biomarkers for a classification problem should therefore be estimated taking account of the impact of all these factors. A database of average generalization errors is built for various combinations of these factors. The database of generalization errors can be used for estimating the optimal number of biomarkers for given levels of predictive accuracy as a function of these factors. Examples show that curves from actual biological data resemble that of simulated data with corresponding levels of data characteristics. An R package optBiomarker implementing the method is freely available for academic use from the Comprehensive R Archive Network (http://www.cran.r-project.org/web/packages/optBiomarker/).     

Endothelin-1 drives invadopodia and interaction with mesothelial cells through ILK

1. Download : Download high-res image (174KB)
2. Download : Download full-size image

     

Levodopa-induced plasticity: a double-edged sword in Parkinson's disease?

The long-term replacement therapy with the dopamine (DA) precursor 3,4-dihydroxy-l-phenylalanine (L-DOPA) is a milestone in the treatment of Parkinson''s disease (PD). Although this drug precursor can be metabolized into the active neurotransmitter DA throughout the brain, its therapeutic benefit is due to restoring extracellular DA levels within the dorsal striatum, which lacks endogenous DA as a consequence of the neurodegenerative process induced by the disease. In the early phases of PD, L-DOPA treatment is able to restore both long-term depression (LTD) and long-term potentiation (LTP), two major forms of corticostriatal synaptic plasticity that are altered by dopaminergic denervation. However, unlike physiological DA transmission, this therapeutic approach in the advanced phase of the disease leads to abnormal peaks of DA, non-synaptically released, which are supposed to trigger behavioural sensitization, namely L-DOPA-induced dyskinesia. This condition is characterized by a loss of synaptic depotentiation, an inability to reverse previously induced LTP. In the advanced stages of PD, L-DOPA can also induce non-motor fluctuations with cognitive dysfunction and neuropsychiatric symptoms such as compulsive behaviours and impulse control disorders. Although the mechanisms underlying the role of L-DOPA in both motor and behavioural symptoms are still incompletely understood, recent data from electrophysiological and imaging studies have increased our understanding of the function of the brain areas involved and of the mechanisms implicated in both therapeutic and adverse actions of L-DOPA in PD patients.     

Comparative LCA of concrete with recycled aggregates: a circular economy mindset in Europe

Purpose

Construction and demolition waste (C&DW) is the largest waste stream in the European Union (EU) and all over the world. Proper management of C&DW and recycled materials—including the correct handling of hazardous waste—can have major benefits in terms of sustainability and the quality of life. The Waste Framework Directive 2008/98/EC aims to have 70% of C&DW recycled by 2020. However, except for a few EU countries, only about 50% of C&DW is currently being recycled. In the present research, the environmental impact of concrete with recycled aggregates and with geopolymer mixtures is analysed. The aim of the present research is to propose a comparative LCA of concrete with recycled aggregates in the context of European politics.

Methods

Life cycle assessment (LCA) methodology is applied using Simapro© software. A cradle to grave analysis is carried out. The results are analysed based on the database Ecoinvent 3.3 and Impact 2002+.

Results

Results show that the concrete with 25% recycled aggregates is the best solution from an environmental point of view. Furthermore, geopolymer mixtures could be a valid alternative to reduce the phenomenon of “global warming”; however, the production of sodium silicate and sodium hydroxide has a great environmental impact.

Conclusions

A possible future implementation of the present study is certainly to carry out an overall assessment and to determine the most cost-effective option among the different competing alternatives through the life cycle cost analysis.