Identification of a 5-protein biomarker molecular signature for predicting Alzheimer's disease

Receptor-ligand interaction controls microglial chemotaxis and amelioration of Alzheimer's disease pathology

Microglia maintain brain homeostasis through their ability to survey and phagocytose danger-associated molecular patterns (DAMPs). In Alzheimer's disease (AD), microglial phagocytic clearance regulates the turnover of neurotoxic DAMPs including amyloid beta (Aβ) and hyperphosphorylated tau. To mediate DAMP clearance, microglia express a repertoire of surface receptors to sense DAMPs; the activation of these receptors subsequently triggers a chemotaxis-to-phagocytosis functional transition in microglia. Therefore, the interaction between microglial receptors and DAMPs plays a critical role in controlling microglial DAMP clearance and AD pathogenesis. However, there is no comprehensive overview on how microglial sensome receptors interact with DAMPs and regulate various microglial functions, including chemotaxis and phagocytosis. In this review, we discuss the important axes of receptor-ligand interaction that control different microglial functions and their roles in AD pathogenesis. First, we summarize how the accumulation and structural changes of DAMPs trigger microglial functional impairment, including impaired DAMP clearance and aberrant synaptic pruning, in AD. Then, we discuss the important receptor-ligand axes that restore microglial DAMP clearance in AD and aging. These findings suggest that targeting microglial chemotaxis-the first critical step of the microglial chemotaxis-to-phagocytosis state transition-can promote microglial DAMP clearance in AD. Thus, our review highlights the importance of microglial chemotaxis in promoting microglial clearance activity in AD. Further detailed investigations are essential to identify the molecular machinery that controls microglial chemotaxis in AD.

Biomarkers in Neurodegenerative Diseases: Proteomics Spotlight on ALS and Parkinson’s Disease

Neurodegenerative diseases such as amyotrophic lateral sclerosis (ALS) and Parkinson’s disease (PD) are both characterized by pathogenic protein aggregates that correlate with the progressive degeneration of neurons and the loss of behavioral functions. Both diseases lack biomarkers for diagnosis and treatment efficacy. Proteomics is an unbiased quantitative tool capable of the high throughput quantitation of thousands of proteins from minimal sample volumes. We review recent proteomic studies in human tissues, plasma, cerebrospinal fluid (CSF), and exosomes in ALS and PD that identify proteins with potential utility as biomarkers. Further, we review disease-related post-translational modifications in key proteins TDP43 in ALS and α-synuclein in PD studies, which may serve as biomarkers. We compare relative and absolute quantitative proteomic approaches in key biomarker studies in ALS and PD and discuss recent technological advancements which may identify suitable biomarkers for the early-diagnosis treatment efficacy of these diseases.

Protein Markers for the Identification of Cork Oak Plants Infected with Phytophthora cinnamomi by Applying an (α, β)-k-Feature Set Approach

Cork oak decline in Mediterranean forests is a complex phenomenon, observed with remarkable frequency in the southern part of the Iberian Peninsula, causing the weakening and death of these woody plants. The defoliation of the canopy, the presence of dry peripheral branches, and exudations on the trunk are visible symptoms used for the prognosis of decline, complemented by the presence of Phytophthora cinnamomi identified in the rhizosphere of the trees and adjacent soils. Recently, a large proteomic dataset obtained from the leaves of cork oak plants inoculated and non-inoculated with P. cinnamomi has become available. We explored it to search for an optimal set of proteins, markers of the biological pattern of interaction with the oomycete. Thus, using published data from the cork oak leaf proteome, we mathematically modelled the problem as an α, β-k-Feature Set Problem to select molecular markers. A set of proteins (features) that represent dominant effects on the host metabolism resulting from pathogen action on roots was found. These results contribute to an early diagnosis of biochemical changes occurring in cork oak associated with P. cinnamomi infection. We hypothesize that these markers may be decisive in identifying trees that go into decline due to interactions with the pathogen, assisting the management of cork oak forest ecosystems.

Astrocytic interleukin-3 programs microglia and limits Alzheimer's disease

Communication within the glial cell ecosystem is essential for neuronal and brain health1-3. The influence of glial cells on the accumulation and clearance of β-amyloid (Aβ) and neurofibrillary tau in the brains of individuals with Alzheimer's disease (AD) is poorly understood, despite growing awareness that these are therapeutically important interactions4,5. Here we show, in humans and mice, that astrocyte-sourced interleukin-3 (IL-3) programs microglia to ameliorate the pathology of AD. Upon recognition of Aβ deposits, microglia increase their expression of IL-3Rα-the specific receptor for IL-3 (also known as CD123)-making them responsive to IL-3. Astrocytes constitutively produce IL-3, which elicits transcriptional, morphological, and functional programming of microglia to endow them with an acute immune response program, enhanced motility, and the capacity to cluster and clear aggregates of Aβ and tau. These changes restrict AD pathology and cognitive decline. Our findings identify IL-3 as a key mediator of astrocyte-microglia cross-talk and a node for therapeutic intervention in AD.

High-dimensionality Data Analysis of Pharmacological Systems Associated with Complex Diseases

It is widely accepted that molecular reductionist views of highly complex human physiologic activity, e.g., the aging process, as well as therapeutic drug efficacy are largely oversimplifications. Currently some of the most effective appreciation of biologic disease and drug response complexity is achieved using high-dimensionality (H-D) data streams from transcriptomic, proteomic, metabolomics, or epigenomic pipelines. Multiple H-D data sets are now common and freely accessible for complex diseases such as metabolic syndrome, cardiovascular disease, and neurodegenerative conditions such as Alzheimer's disease. Over the last decade our ability to interrogate these high-dimensionality data streams has been profoundly enhanced through the development and implementation of highly effective bioinformatic platforms. Employing these computational approaches to understand the complexity of age-related diseases provides a facile mechanism to then synergize this pathologic appreciation with a similar level of understanding of therapeutic-mediated signaling. For informative pathology and drug-based analytics that are able to generate meaningful therapeutic insight across diverse data streams, novel informatics processes such as latent semantic indexing and topological data analyses will likely be important. Elucidation of H-D molecular disease signatures from diverse data streams will likely generate and refine new therapeutic strategies that will be designed with a cognizance of a realistic appreciation of the complexity of human age-related disease and drug effects. We contend that informatic platforms should be synergistic with more advanced chemical/drug and phenotypic cellular/tissue-based analytical predictive models to assist in either de novo drug prioritization or effective repurposing for the intervention of aging-related diseases. SIGNIFICANCE STATEMENT: All diseases, as well as pharmacological mechanisms, are far more complex than previously thought a decade ago. With the advent of commonplace access to technologies that produce large volumes of high-dimensionality data (e.g., transcriptomics, proteomics, metabolomics), it is now imperative that effective tools to appreciate this highly nuanced data are developed. Being able to appreciate the subtleties of high-dimensionality data will allow molecular pharmacologists to develop the most effective multidimensional therapeutics with effectively engineered efficacy profiles.

Accurate Blood-Based Diagnostic Biosignatures for Alzheimer's Disease via Automated Machine Learning

Alzheimer's disease (AD) is the most common form of neurodegenerative dementia and its timely diagnosis remains a major challenge in biomarker discovery. In the present study, we analyzed publicly available high-throughput low-sample -omics datasets from studies in AD blood, by the AutoML technology Just Add Data Bio (JADBIO), to construct accurate predictive models for use as diagnostic biosignatures. Considering data from AD patients and age-sex matched cognitively healthy individuals, we produced three best performing diagnostic biosignatures specific for the presence of AD: A. A 506-feature transcriptomic dataset from 48 AD and 22 controls led to a miRNA-based biosignature via Support Vector Machines with three miRNA predictors (AUC 0.975 (0.906, 1.000)), B. A 38,327-feature transcriptomic dataset from 134 AD and 100 controls led to six mRNA-based statistically equivalent signatures via Classification Random Forests with 25 mRNA predictors (AUC 0.846 (0.778, 0.905)) and C. A 9483-feature proteomic dataset from 25 AD and 37 controls led to a protein-based biosignature via Ridge Logistic Regression with seven protein predictors (AUC 0.921 (0.849, 0.972)). These performance metrics were also validated through the JADBIO pipeline confirming stability. In conclusion, using the automated machine learning tool JADBIO, we produced accurate predictive biosignatures extrapolating available low sample -omics data. These results offer options for minimally invasive blood-based diagnostic tests for AD, awaiting clinical validation based on respective laboratory assays. They also highlight the value of AutoML in biomarker discovery.

Homocysteine Induces Inflammation in Retina and Brain

Homocysteine (Hcy) is an amino acid that requires vitamins B₁₂ and folic acid for its metabolism. Vitamins B₁₂ and folic acid deficiencies lead to hyperhomocysteinemia (HHcy, elevated Hcy), which is linked to the development of diabetic retinopathy (DR), age-related macular degeneration (AMD), and Alzheimer’s disease (AD). The goal of the current study was to explore inflammation as an underlying mechanism of HHcy-induced pathology in age related diseases such as AMD, DR, and AD. Mice with HHcy due to a lack of the enzyme cystathionine-β-synthase (CBS) and wild-type mice were evaluated for microglia activation and inflammatory markers using immuno-fluorescence (IF). Tissue lysates isolated from the brain hippocampal area from mice with HHcy were evaluated for inflammatory cytokines using the multiplex assay. Human retinal endothelial cells, retinal pigment epithelial cells, and monocyte cell lines treated with/without Hcy were evaluated for inflammatory cytokines and NFκB activation using the multiplex assay, western blot analysis, and IF. HHcy induced inflammatory responses in mouse brain, retina, cultured retinal, and microglial cells. NFκB was activated and cytokine array analysis showed marked increase in pro-inflammatory cytokines and downregulation of anti-inflammatory cytokines. Therefore, elimination of excess Hcy or reduction of inflammation is a promising intervention for mitigating damage associated with HHcy in aging diseases such as DR, AMD, and AD.

Increased inflammation in BA21 brain tissue from African Americans with Alzheimer's disease

Chronic neuroinflammation is strongly associated with AD and altered peripheral and central levels of chemokines and cytokines have been frequently described in those with AD. Given the increasing evidence of ethnicity-related differences in AD, it was of interest to determine if those altered chemokine and cytokine levels are ethnicity-related. Because African Americans exhibit a higher incidence of AD and increased symptom severity, we explored chemokine and cytokine concentrations in post-mortem brain tissue from the BA21 region of African Americans and Caucasians with AD using multiplex assays. IL-1β, MIG, TRAIL, and FADD levels were significantly increased in African Americans while levels of IL-3 and IL-8 were significantly decreased. Those effects did not interact with gender; however, overall levels of CCL25, CCL26 and CX3CL1 were significantly decreased in women. The NLRP3 inflammasome is thought to be critically involved in AD. Increased activation of this inflammasome in African Americans is consistent with the current results.

Plasma Biomarkers: Potent Screeners of Alzheimer's Disease

Alzheimer's disease (AD), a neurological disorder, is as a complex chronic disease of brain cell death that usher to cognitive decline and loss of memory. Its prevalence differs according to risk factors associated with it and necropsy performs vital role in its definite diagnosis. The stages of AD vary from preclinical to severe that proceeds to death of patient with no availability of treatment. Biomarker may be a biochemical change that can be recognized by different emerging technologies such as proteomics and metabolomics. Plasma biomarkers, 5-protein classifiers, are readily being used for the diagnosis of AD and can also predict its progression with a great accuracy, specificity, and sensitivity. In this review, upregulation or downregulation of few plasma proteins in patients with AD has also been discussed, when juxtaposed with control, and thus serves as potent biomarker in the diagnosis of AD.

GSMA: an approach to identify robust global and test Gene Signatures using Meta-Analysis

MOTIVATION

Recent advances in biomedical research have made massive amount of transcriptomic data available in public repositories from different sources. Due to the heterogeneity present in the individual experiments, identifying reproducible biomarkers for a given disease from multiple independent studies has become a major challenge. The widely used meta-analysis approaches, such as Fisher's method, Stouffer's method, minP and maxP, have at least two major limitations: (i) they are sensitive to outliers, and (ii) they perform only one statistical test for each individual study, and hence do not fully utilize the potential sample size to gain statistical power.

RESULTS

Here, we propose a gene-level meta-analysis framework that overcomes these limitations and identifies a gene signature that is reliable and reproducible across multiple independent studies of a given disease. The approach provides a comprehensive global signature that can be used to understand the underlying biological phenomena, and a smaller test signature that can be used to classify future samples of a given disease. We demonstrate the utility of the framework by constructing disease signatures for influenza and Alzheimer's disease using nine datasets including 1108 individuals. These signatures are then validated on 12 independent datasets including 912 individuals. The results indicate that the proposed approach performs better than the majority of the existing meta-analysis approaches in terms of both sensitivity as well as specificity. The proposed signatures could be further used in diagnosis, prognosis and identification of therapeutic targets.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Peripheral adaptive immunity of the triple transgenic mouse model of Alzheimer's disease

Background

Immunologic abnormalities have been described in peripheral blood and central nervous system of patients suffering from Alzheimer’s disease (AD), yet their role in the pathogenesis still remains poorly defined.

Aim and methods

We used the triple transgenic mouse model (3xTg-AD) to reproduce Aβ (amyloid plaques) and tau (neurofibrillary tangles) neuropathologies. We analyzed important features of the adaptive immune system in serum, primary (bone marrow) as well as secondary (spleen) lymphoid organs of 12-month-old 3xTg-AD mice using flow cytometry and ELISPOT. We further investigated serum cytokines of 9- and 13-month-old 3xTg-AD mice using multiplex ELISA. Results were compared to age-matched non-transgenic controls (NTg).

Results

In the bone marrow of 12-month-old 3xTg-AD mice, we detected decreased proportions of short-term reconstituting hematopoietic stem cells (0.58-fold, P = 0.0116), while lymphocyte, granulocyte, and monocyte populations remained unchanged. Our results also point to increased activation of both B and T lymphocytes. Indeed, we report elevated levels of plasma cells in bone marrow (1.3-fold, P = 0.0405) along with a 5.4-fold rise in serum IgG concentration (P < 0.0001) in 3xTg-AD animals. Furthermore, higher levels of interleukin (IL)-2 were detected in serum of 9- and 13-month-old 3xTg-AD mice (P = 0.0018). Along with increased concentrations of IL-17 (P = 0.0115) and granulocyte-macrophage colony-stimulating factor (P = 0.0085), these data support helper T lymphocyte activation with Th17 polarization.

Conclusion

Collectively, these results suggest that the 3xTg-AD model mimics modifications of the adaptive immunity changes previously observed in human AD patients and underscore the activation of both valuable and harmful pathways of immunity in AD.

Revealing Alzheimer's disease genes spectrum in the whole-genome by machine learning

Background

Alzheimer’s disease (AD) is an important, progressive neurodegenerative disease, with a complex genetic architecture. A key goal of biomedical research is to seek out disease risk genes, and to elucidate the function of these risk genes in the development of disease. For this purpose, expanding the AD-associated gene set is necessary. In past research, the prediction methods for AD related genes has been limited in their exploration of the target genome regions. We here present a genome-wide method for AD candidate genes predictions.

Methods

We present a machine learning approach (SVM), based upon integrating gene expression data with human brain-specific gene network data, to discover the full spectrum of AD genes across the whole genome.

Results

We classified AD candidate genes with an accuracy and the area under the receiver operating characteristic (ROC) curve of 84.56% and 94%. Our approach provides a supplement for the spectrum of AD-associated genes extracted from more than 20,000 genes in a genome wide scale.

Conclusions

In this study, we have elucidated the whole-genome spectrum of AD, using a machine learning approach. Through this method, we expect for the candidate gene catalogue to provide a more comprehensive annotation of AD for researchers.

Electronic supplementary material

The online version of this article (10.1186/s12883-017-1010-3) contains supplementary material, which is available to authorized users.

Alzheimer's Disease: A Journey from Amyloid Peptides and Oxidative Stress, to Biomarker Technologies and Disease Prevention Strategies-Gains from AIBL and DIAN Cohort Studies

Worldwide there are over 46 million people living with dementia, and this number is expected to double every 20 years reaching about 131 million by 2050. The cost to the community and government health systems, as well as the stress on families and carers is incalculable. Over three decades of research into this disease have been undertaken by several research groups in Australia, including work by our original research group in Western Australia which was involved in the discovery and sequencing of the amyloid-β peptide (also known as Aβ or A4 peptide) extracted from cerebral amyloid plaques. This review discusses the journey from the discovery of the Aβ peptide in Alzheimer's disease (AD) brain to the establishment of pre-clinical AD using PET amyloid tracers, a method now serving as the gold standard for developing peripheral diagnostic approaches in the blood and the eye. The latter developments for early diagnosis have been largely achieved through the establishment of the Australian Imaging Biomarker and Lifestyle research group that has followed 1,100 Australians for 11 years. AIBL has also been instrumental in providing insight into the role of the major genetic risk factor apolipoprotein E ɛ4, as well as better understanding the role of lifestyle factors particularly diet, physical activity and sleep to cognitive decline and the accumulation of cerebral Aβ.

A blood-based biomarker panel indicates IL-10 and IL-12/23p40 are jointly associated as predictors of β-amyloid load in an AD cohort

Alzheimer’s Disease (AD) is the most common form of dementia, characterised by extracellular amyloid deposition as plaques and intracellular neurofibrillary tangles of tau protein. As no current clinical test can diagnose individuals at risk of developing AD, the aim of this project is to evaluate a blood-based biomarker panel to identify individuals who carry this risk. We analysed the levels of 22 biomarkers in clinically classified healthy controls (HC), mild cognitive impairment (MCI) and Alzheimer’s participants from the well characterised Australian Imaging, Biomarker and Lifestyle (AIBL) study of aging. High levels of IL-10 and IL-12/23p40 were significantly associated with amyloid deposition in HC, suggesting that these two biomarkers might be used to detect at risk individuals. Additionally, other biomarkers (Eotaxin-3, Leptin, PYY) exhibited altered levels in AD participants possessing the APOE ε4 allele. This suggests that the physiology of some potential biomarkers may be altered in AD due to the APOE ε4 allele, a major risk factor for AD. Taken together, these data highlight several potential biomarkers that can be used in a blood-based panel to allow earlier identification of individuals at risk of developing AD and/or early stage AD for which current therapies may be more beneficial.

Altered levels of blood proteins in Alzheimer's disease longitudinal study: Results from Australian Imaging Biomarkers Lifestyle Study of Ageing cohort

INTRODUCTION

A blood-based biomarker panel to identify individuals with preclinical Alzheimer's disease (AD) would be an inexpensive and accessible first step for routine testing.

METHODS

We analyzed 14 biomarkers that have previously been linked to AD in the Australian Imaging Biomarkers lifestyle longitudinal study of aging cohort.

RESULTS

Levels of apolipoprotein J (apoJ) were higher in AD individuals compared with healthy controls at baseline and 18 months (P = .0003) and chemokine-309 (I-309) were increased in AD patients compared to mild cognitive impaired individuals over 36 months (P = .0008).

DISCUSSION

These data suggest that apoJ may have potential in the context of use (COU) of AD diagnostics, I-309 may be specifically useful in the COU of identifying individuals at greatest risk for progressing toward AD. This work takes an initial step toward identifying blood biomarkers with potential use in the diagnosis and prognosis of AD and should be validated across other prospective cohorts.

ErbB2 regulates autophagic flux to modulate the proteostasis of APP-CTFs in Alzheimer's disease

Proteolytic processing of amyloid precursor protein (APP) C-terminal fragments (CTFs) by γ-secretase underlies the pathogenesis of Alzheimer's disease (AD). An RNA interference screen using APP-CTF [99-residue CTF (C99)]- and Notch-specific γ-secretase interaction assays identified a unique ErbB2-centered signaling network that was predicted to preferentially govern the proteostasis of APP-C99. Consistently, significantly elevated levels of ErbB2 were confirmed in the hippocampus of human AD brains. We then found that ErbB2 effectively suppressed autophagic flux by physically dissociating Beclin-1 from the Vps34-Vps15 complex independent of its kinase activity. Down-regulation of ErbB2 by CL-387,785 decreased the levels of C99 and secreted amyloid-β in cellular, zebrafish, and mouse models of AD, through the activation of autophagy. Oral administration of an ErbB2-targeted CL-387,785 for 3 wk significantly improves the cognitive functions of APP/presenilin-1 (PS1) transgenic mice. This work unveils a noncanonical function of ErbB2 in modulating autophagy and establishes ErbB2 as a therapeutic target for AD.

Computer-Aided Breast Cancer Diagnosis with Optimal Feature Sets: Reduction Rules and Optimization Techniques

This chapter introduces a new method for knowledge extraction from databases for the purpose of finding a discriminative set of features that is also a robust set for within-class classification. Our method is generic and we introduce it here in the field of breast cancer diagnosis from digital mammography data. The mathematical formalism is based on a generalization of the k-Feature Set problem called (α, β)-k-Feature Set problem, introduced by Cotta and Moscato (J Comput Syst Sci 67(4):686-690, 2003). This method proceeds in two steps: first, an optimal (α, β)-k-feature set of minimum cardinality is identified and then, a set of classification rules using these features is obtained. We obtain the (α, β)-k-feature set in two phases; first a series of extremely powerful reduction techniques, which do not lose the optimal solution, are employed; and second, a metaheuristic search to identify the remaining features to be considered or disregarded. Two algorithms were tested with a public domain digital mammography dataset composed of 71 malignant and 75 benign cases. Based on the results provided by the algorithms, we obtain classification rules that employ only a subset of these features.

Apolipoprotein E4, Gender, Body Mass Index, Inflammation, Insulin Resistance, and Air Pollution Interactions: Recipe for Alzheimer's Disease Development in Mexico City Young Females

Given the epidemiological trends of increasing Alzheimer's disease (AD) and growing evidence that exposure and lifestyle factors contribute to AD risk and pathogenesis, attention should be paid to variables such as air pollution, in order to reduce rates of cognitive decline and dementia. Exposure to fine particulate matter (PM2.5) and ozone (O3) above the US EPA standards is associated with AD risk. Mexico City children experienced pre- and postnatal high exposures to PM2.5, O3, combustion-derived iron-rich nanoparticles, metals, polycyclic aromatic hydrocarbons, and endotoxins. Exposures are associated with early brain gene imbalance in oxidative stress, inflammation, innate and adaptive immune responses, along with epigenetic changes, accumulation of misfolded proteins, cognitive deficits, and brain structural and metabolic changes. The Apolipoprotein E (APOE) 4 allele, the most prevalent genetic risk for AD, plays a key role in the response to air pollution in young girls. APOE 4 heterozygous females with >75% to <94% BMI percentiles are at the highest risk of severe cognitive deficits (1.5-2 SD from average IQ). This review focused on the relationships between gender, BMI, systemic and neural inflammation, insulin resistance, hyperleptinemia, dyslipidemia, vascular risk factors, and central nervous system involvement in APOE4 urbanites exposed to PM2.5 and magnetite combustion-derived iron-rich nanoparticles that can reach the brain. APOE4 young female heterozygous carriers constitute a high-risk group for a fatal disease: AD. Multidisciplinary intervention strategies could be critical for prevention or amelioration of cognitive deficits and long-term AD progression in young individuals at high risk.

Integrated Computational Solution for Predicting Skin Sensitization Potential of Molecules

Introduction

Skin sensitization forms a major toxicological endpoint for dermatology and cosmetic products. Recent ban on animal testing for cosmetics demands for alternative methods. We developed an integrated computational solution (SkinSense) that offers a robust solution and addresses the limitations of existing computational tools i.e. high false positive rate and/or limited coverage.

Results

The key components of our solution include: QSAR models selected from a combinatorial set, similarity information and literature-derived sub-structure patterns of known skin protein reactive groups. Its prediction performance on a challenge set of molecules showed accuracy = 75.32%, CCR = 74.36%, sensitivity = 70.00% and specificity = 78.72%, which is better than several existing tools including VEGA (accuracy = 45.00% and CCR = 54.17% with ‘High’ reliability scoring), DEREK (accuracy = 72.73% and CCR = 71.44%) and TOPKAT (accuracy = 60.00% and CCR = 61.67%). Although, TIMES-SS showed higher predictive power (accuracy = 90.00% and CCR = 92.86%), the coverage was very low (only 10 out of 77 molecules were predicted reliably).

Conclusions

Owing to improved prediction performance and coverage, our solution can serve as a useful expert system towards Integrated Approaches to Testing and Assessment for skin sensitization. It would be invaluable to cosmetic/ dermatology industry for pre-screening their molecules, and reducing time, cost and animal testing.

A novel method predicting clinical response using only background clinical data in RA patients before treatment with infliximab

OBJECTIVES

The aim of the present study was to generate a novel method for predicting the clinical response to infliximab (IFX), using a machine-learning algorithm with only clinical data obtained before the treatment in rheumatoid arthritis (RA) patients.

METHODS

We obtained 32 variables out of the clinical data on the patients from two independent hospitals. Next, we selected both clinical parameters and machine-learning algorithms and decided the candidates of prediction method. These candidates were verified by clinical variables on different patients from two other hospitals. Finally, we decided the prediction method to achieve the highest score.

RESULTS

The combination of multilayer perceptron algorithm (neural network) and nine clinical parameters shows the best accuracy performance. This method could predict the good or moderate response to IFX with 92% accuracy. The sensitivity of this method was 96.7%, while the specificity was 75%.

CONCLUSIONS

We have developed a novel method for predicting the clinical response using only background clinical data in RA patients before treatment with IFX. Our method for predicting the response to IFX in RA patients may have advantages over the other previous methods in several points including easy usability, cost-effectiveness and accuracy.

Identification of Differentially Expressed Genes through Integrated Study of Alzheimer's Disease Affected Brain Regions

Background

Alzheimer’s disease (AD) is the most common form of dementia in older adults that damages the brain and results in impaired memory, thinking and behaviour. The identification of differentially expressed genes and related pathways among affected brain regions can provide more information on the mechanisms of AD. In the past decade, several studies have reported many genes that are associated with AD. This wealth of information has become difficult to follow and interpret as most of the results are conflicting. In that case, it is worth doing an integrated study of multiple datasets that helps to increase the total number of samples and the statistical power in detecting biomarkers. In this study, we present an integrated analysis of five different brain region datasets and introduce new genes that warrant further investigation.

Methods

The aim of our study is to apply a novel combinatorial optimisation based meta-analysis approach to identify differentially expressed genes that are associated to AD across brain regions. In this study, microarray gene expression data from 161 samples (74 non-demented controls, 87 AD) from the Entorhinal Cortex (EC), Hippocampus (HIP), Middle temporal gyrus (MTG), Posterior cingulate cortex (PC), Superior frontal gyrus (SFG) and visual cortex (VCX) brain regions were integrated and analysed using our method. The results are then compared to two popular meta-analysis methods, RankProd and GeneMeta, and to what can be obtained by analysing the individual datasets.

Results

We find genes related with AD that are consistent with existing studies, and new candidate genes not previously related with AD. Our study confirms the up-regualtion of INFAR2 and PTMA along with the down regulation of GPHN, RAB2A, PSMD14 and FGF. Novel genes PSMB2, WNK1, RPL15, SEMA4C, RWDD2A and LARGE are found to be differentially expressed across all brain regions. Further investigation on these genes may provide new insights into the development of AD. In addition, we identified the presence of 23 non-coding features, including four miRNA precursors (miR-7, miR570, miR-1229 and miR-6821), dysregulated across the brain regions. Furthermore, we compared our results with two popular meta-analysis methods RankProd and GeneMeta to validate our findings and performed a sensitivity analysis by removing one dataset at a time to assess the robustness of our results. These new findings may provide new insights into the disease mechanisms and thus make a significant contribution in the near future towards understanding, prevention and cure of AD.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases.

Iteratively refining breast cancer intrinsic subtypes in the METABRIC dataset

BACKGROUND

Multi-gene lists and single sample predictor models have been currently used to reduce the multidimensional complexity of breast cancers, and to identify intrinsic subtypes. The perceived inability of some models to deal with the challenges of processing high-dimensional data, however, limits the accurate characterisation of these subtypes. Towards the development of robust strategies, we designed an iterative approach to consistently discriminate intrinsic subtypes and improve class prediction in the METABRIC dataset.

FINDINGS

In this study, we employed the CM1 score to identify the most discriminative probes for each group, and an ensemble learning technique to assess the ability of these probes on assigning subtype labels using 24 different classifiers. Our analysis is comprised of an iterative computation of these methods and statistical measures performed on a set of over 2000 samples. The refined labels assigned using this iterative approach revealed to be more consistent and in better agreement with clinicopathological markers and patients' overall survival than those originally provided by the PAM50 method.

CONCLUSIONS

The assignment of intrinsic subtypes has a significant impact in translational research for both understanding and managing breast cancer. The refined labelling, therefore, provides more accurate and reliable information by improving the source of fundamental science prior to clinical applications in medicine.

Blood-Based Proteomic Biomarkers of Alzheimer's Disease Pathology

The complexity of Alzheimer’s disease (AD) and its long prodromal phase poses challenges for early diagnosis and yet allows for the possibility of the development of disease modifying treatments for secondary prevention. It is, therefore, of importance to develop biomarkers, in particular, in the preclinical or early phases that reflect the pathological characteristics of the disease and, moreover, could be of utility in triaging subjects for preventative therapeutic clinical trials. Much research has sought biomarkers for diagnostic purposes by comparing affected people to unaffected controls. However, given that AD pathology precedes disease onset, a pathology endophenotype design for biomarker discovery creates the opportunity for detection of much earlier markers of disease. Blood-based biomarkers potentially provide a minimally invasive option for this purpose and research in the field has adopted various “omics” approaches in order to achieve this. This review will, therefore, examine the current literature regarding blood-based proteomic biomarkers of AD and its associated pathology.

The Discovery of Novel Biomarkers Improves Breast Cancer Intrinsic Subtype Prediction and Reconciles the Labels in the METABRIC Data Set

BACKGROUND

The prediction of breast cancer intrinsic subtypes has been introduced as a valuable strategy to determine patient diagnosis and prognosis, and therapy response. The PAM50 method, based on the expression levels of 50 genes, uses a single sample predictor model to assign subtype labels to samples. Intrinsic errors reported within this assay demonstrate the challenge of identifying and understanding the breast cancer groups. In this study, we aim to: a) identify novel biomarkers for subtype individuation by exploring the competence of a newly proposed method named CM1 score, and b) apply an ensemble learning, as opposed to the use of a single classifier, for sample subtype assignment. The overarching objective is to improve class prediction.

METHODS AND FINDINGS

The microarray transcriptome data sets used in this study are: the METABRIC breast cancer data recorded for over 2000 patients, and the public integrated source from ROCK database with 1570 samples. We first computed the CM1 score to identify the probes with highly discriminative patterns of expression across samples of each intrinsic subtype. We further assessed the ability of 42 selected probes on assigning correct subtype labels using 24 different classifiers from the Weka software suite. For comparison, the same method was applied on the list of 50 genes from the PAM50 method.

CONCLUSIONS

The CM1 score portrayed 30 novel biomarkers for predicting breast cancer subtypes, with the confirmation of the role of 12 well-established genes. Intrinsic subtypes assigned using the CM1 list and the ensemble of classifiers are more consistent and homogeneous than the original PAM50 labels. The new subtypes show accurate distributions of current clinical markers ER, PR and HER2, and survival curves in the METABRIC and ROCK data sets. Remarkably, the paradoxical attribution of the original labels reinforces the limitations of employing a single sample classifiers to predict breast cancer intrinsic subtypes.

A New Combinatorial Optimization Approach for Integrated Feature Selection Using Different Datasets: A Prostate Cancer Transcriptomic Study

Background

The joint study of multiple datasets has become a common technique for increasing statistical power in detecting biomarkers obtained from smaller studies. The approach generally followed is based on the fact that as the total number of samples increases, we expect to have greater power to detect associations of interest. This methodology has been applied to genome-wide association and transcriptomic studies due to the availability of datasets in the public domain. While this approach is well established in biostatistics, the introduction of new combinatorial optimization models to address this issue has not been explored in depth. In this study, we introduce a new model for the integration of multiple datasets and we show its application in transcriptomics.

Methods

We propose a new combinatorial optimization problem that addresses the core issue of biomarker detection in integrated datasets. Optimal solutions for this model deliver a feature selection from a panel of prospective biomarkers. The model we propose is a generalised version of the (α,β)-k-Feature Set problem. We illustrate the performance of this new methodology via a challenging meta-analysis task involving six prostate cancer microarray datasets. The results are then compared to the popular RankProd meta-analysis tool and to what can be obtained by analysing the individual datasets by statistical and combinatorial methods alone.

Results

Application of the integrated method resulted in a more informative signature than the rank-based meta-analysis or individual dataset results, and overcomes problems arising from real world datasets. The set of genes identified is highly significant in the context of prostate cancer. The method used does not rely on homogenisation or transformation of values to a common scale, and at the same time is able to capture markers associated with subgroups of the disease.

Association of Adiposity Indices with Platelet Distribution Width and Mean Platelet Volume in Chinese Adults

Hypoxia is a prominent characteristic of inflammatory tissue lesions. It can affect platelet function. While mean platelet volume (MPV) and platelet distribution width (PDW) are sample platelet indices, they may reflect subcinical platelet activation. To investigated associations between adiposity indices and platelet indices, 17327 eligible individuals (7677 males and 9650 females) from the Dongfeng-Tongji Cohort Study (DFTJ-Cohort Study, n=27009) were included in this study, except for 9682 individuals with missing data on demographical, lifestyle, physical indicators and diseases relative to PDW and MPV. Associations between adiposity indices including waist circumstance (WC), waist-to-height ratio (WHtR), body mass index (BMI), and MPV or PDW in the participants were analyzed using multiple logistic regressions. There were significantly negative associations between abnormal PDW and WC or WHtR for both sexes (p_trend<0.001 for all), as well as abnormal MPV and WC or WHtR among female participants (p_trend<0.05 for all). In the highest BMI groups, only females with low MPV or PDW were at greater risk for having low MPV (OR=1.33, 95% CI=1.10, 1.62 p_trend<0.001) or PDW (OR=1.34, 95% CI=1.14, 1.58, p_trend<0.001) than those who had low MPV or PDW in the corresponding lowest BMI group. The change of PDW seems more sensitive than MPV to oxidative stress and hypoxia. Associations between reduced PDW and MPV values and WC, WHtR and BMI values in Chinese female adults may help us to further investigate early changes in human body.

BioAge: toward a multi-determined, mechanistic account of cognitive aging

The search for reliable early indicators of age-related cognitive decline represents a critical avenue for progress in aging research. Chronological age is a commonly used developmental index; however, it offers little insight into the mechanisms underlying cognitive decline. In contrast, biological age (BioAge), reflecting the vitality of essential biological systems, represents a promising operationalization of developmental time. Current BioAge models have successfully predicted age-related cognitive deficits. Research on aging-related cognitive function indicates that the interaction of multiple risk and protective factors across the human lifespan confers individual risk for late-life cognitive decline, implicating a multi-causal explanation. In this review, we explore current BioAge models, describe three broad yet pathologically relevant biological processes linked to cognitive decline, and propose a novel operationalization of BioAge accounting for both moderating and causal mechanisms of cognitive decline and dementia. We argue that a multivariate and mechanistic BioAge approach will lead to a greater understanding of disease pathology as well as more accurate prediction and early identification of late-life cognitive decline.

Air pollution and your brain: what do you need to know right now

Research links air pollution mostly to respiratory and cardiovascular disease. The effects of air pollution on the central nervous system (CNS) are not broadly recognized. Urban outdoor pollution is a global public health problem particularly severe in megacities and in underdeveloped countries, but large and small cities in the United States and the United Kingom are not spared. Fine and ultrafine particulate matter (UFPM) defined by aerodynamic diameter (<2.5-μm fine particles, PM2.5, and <100-nm UFPM) pose a special interest for the brain effects given the capability of very small particles to reach the brain. In adults, ambient pollution is associated to stroke and depression, whereas the emerging picture in children show significant systemic inflammation, immunodysregulation at systemic, intratechal and brain levels, neuroinflammation and brain oxidative stress, along with the main hallmarks of Alzheimer and Parkinson's diseases: hyperphosphorilated tau, amyloid plaques and misfolded α-synuclein. Animal models exposed to particulate matter components show markers of both neuroinflammation and neurodegeneration. Epidemiological, cognitive, behavioral and mechanistic studies into the association between air pollution exposures and the development of CNS damage particularly in children are of pressing importance for public health and quality of life. Primary health providers have to include a complete prenatal and postnatal environmental and occupational history to indoor and outdoor toxic hazards and measures should be taken to prevent or reduce further exposures.

Multi-analyte profile analysis of plasma immune proteins: altered expression of peripheral immune factors is associated with neuropsychiatric symptom severity in adults with and without chronic hepatitis C virus infection

BackgroundThe purpose of this study was to characterize hepatitis C virus (HCV)-associated differences in the expression of 47 inflammatory factors and to evaluate the potential role of peripheral immune activation in HCV-associated neuropsychiatric symptoms-depression, anxiety, fatigue, and pain. An additional objective was to evaluate the role of immune factor dysregulation in the expression of specific neuropsychiatric symptoms to identify biomarkers that may be relevant to the treatment of these neuropsychiatric symptoms in adults with or without HCV. MethodsBlood samples and neuropsychiatric symptom severity scales were collected from HCV-infected adults (HCV+, n = 39) and demographically similar noninfected controls (HCV-, n = 40). Multi-analyte profile analysis was used to evaluate plasma biomarkers. ResultsCompared with HCV- controls, HCV+ adults reported significantly (P < 0.050) greater depression, anxiety, fatigue, and pain, and they were more likely to present with an increased inflammatory profile as indicated by significantly higher plasma levels of 40% (19/47) of the factors assessed (21%, after correcting for multiple comparisons). Within the HCV+ group, but not within the HCV- group, an increased inflammatory profile (indicated by the number of immune factors > the LDC) significantly correlated with depression, anxiety, and pain. Within the total sample, neuropsychiatric symptom severity was significantly predicted by protein signatures consisting of 4-10 plasma immune factors; protein signatures significantly accounted for 19-40% of the variance in depression, anxiety, fatigue, and pain. ConclusionsOverall, the results demonstrate that altered expression of a network of plasma immune factors contributes to neuropsychiatric symptom severity. These findings offer new biomarkers to potentially facilitate pharmacotherapeutic development and to increase our understanding of the molecular pathways associated with neuropsychiatric symptoms in adults with or without HCV.

Analysis of sampling techniques for imbalanced data: An n = 648 ADNI study

Many neuroimaging applications deal with imbalanced imaging data. For example, in Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the mild cognitive impairment (MCI) cases eligible for the study are nearly two times the Alzheimer's disease (AD) patients for structural magnetic resonance imaging (MRI) modality and six times the control cases for proteomics modality. Constructing an accurate classifier from imbalanced data is a challenging task. Traditional classifiers that aim to maximize the overall prediction accuracy tend to classify all data into the majority class. In this paper, we study an ensemble system of feature selection and data sampling for the class imbalance problem. We systematically analyze various sampling techniques by examining the efficacy of different rates and types of undersampling, oversampling, and a combination of over and undersampling approaches. We thoroughly examine six widely used feature selection algorithms to identify significant biomarkers and thereby reduce the complexity of the data. The efficacy of the ensemble techniques is evaluated using two different classifiers including Random Forest and Support Vector Machines based on classification accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity measures. Our extensive experimental results show that for various problem settings in ADNI, (1) a balanced training set obtained with K-Medoids technique based undersampling gives the best overall performance among different data sampling techniques and no sampling approach; and (2) sparse logistic regression with stability selection achieves competitive performance among various feature selection algorithms. Comprehensive experiments with various settings show that our proposed ensemble model of multiple undersampled datasets yields stable and promising results.

Mean platelet volume and platelet distribution width in vascular dementia and Alzheimer's disease

Activated platelets play a substantial role in Alzheimer's disease (AD) and atherothrombosis. Mean platelet volume (MPV) is an early marker of platelet activation, which is linked to a variety of pro-thrombotic and pro-inflammatory diseases. This study is to examine the association between platelet indices and vascular dementia (VaD) and AD. In this cross-sectional study, we investigated the levels of platelet count, MPV, and platelet distribution width (PDW) in 150 VaD patients, 110 AD patients, and 150 non-demented controls. MPV and PDW were significantly lower in patients with VaD and AD as compared with controls. The decrease in PDW for AD patients as compared with VaD patients was also significant (p < 0.001). In addition, there was a positive correlation between Mini-Mental State Examination (MMSE) and MPV and PDW, after adjusting confounding factors (r = 0.532 for MPV and r = 0.425 for PDW, p < 0.001 for both). Multivariate regression analysis showed that MPV and PDW were significantly associated with MMSE (β = 0.366 for MPV and β = 0.273 for PDW, p < 0.001 for both). In conclusion, MPV and PDW were both decreased in VaD and AD. PDW levels were significantly lower in AD as compared to those in VaD. Our findings suggest that PDW in combination with MMSE scores could be potential indicators for distinguishing VaD from AD.

Inflammatory proteins in plasma are associated with severity of Alzheimer's disease

Markers of Alzheimer’s disease (AD) are being widely sought with a number of studies suggesting blood measures of inflammatory proteins as putative biomarkers. Here we report findings from a panel of 27 cytokines and related proteins in over 350 subjects with AD, subjects with Mild Cognitive Impairment (MCI) and elderly normal controls where we also have measures of longitudinal change in cognition and baseline neuroimaging measures of atrophy. In this study, we identify five inflammatory proteins associated with evidence of atrophy on MR imaging data particularly in whole brain, ventricular and entorhinal cortex measures. In addition, we observed six analytes that showed significant change (over a period of one year) in people with fast cognitive decline compared to those with intermediate and slow decline. One of these (IL-10) was also associated with brain atrophy in AD. In conclusion, IL-10 was associated with both clinical and imaging evidence of severity of disease and might therefore have potential to act as biomarker of disease progression.

Evaluation of Different Normalization and Analysis Procedures for Illumina Gene Expression Microarray Data Involving Small Changes

While Illumina microarrays can be used successfully for detecting small gene expression changes due to their high degree of technical replicability, there is little information on how different normalization and differential expression analysis strategies affect outcomes. To evaluate this, we assessed concordance across gene lists generated by applying different combinations of normalization strategy and analytical approach to two Illumina datasets with modest expression changes. In addition to using traditional statistical approaches, we also tested an approach based on combinatorial optimization. We found that the choice of both normalization strategy and analytical approach considerably affected outcomes, in some cases leading to substantial differences in gene lists and subsequent pathway analysis results. Our findings suggest that important biological phenomena may be overlooked when there is a routine practice of using only one approach to investigate all microarray datasets. Analytical artefacts of this kind are likely to be especially relevant for datasets involving small fold changes, where inherent technical variation-if not adequately minimized by effective normalization-may overshadow true biological variation. This report provides some basic guidelines for optimizing outcomes when working with Illumina datasets involving small expression changes.

Decreased mean platelet volume and platelet distribution width are associated with mild cognitive impairment and Alzheimer's disease

Neuroinflammation is a critical driving force underlying mild cognitive impairment (MCI) and Alzheimer's disease (AD) pathologies. Activated platelets play an important role in neuroinflammation and have been implicated in AD pathogenic mechanisms. Mean platelet volume (MPV), a marker of platelet activation, is involved in the pathophysiology of a variety of pro-inflammatory diseases. However, little research has been conducted to investigate the relationship between platelet indices and MCI and AD pathogenesis. In this cross-sectional study, we investigated the levels of platelet count, MPV and platelet distribution width (PDW) in 120 AD patients, 120 MCI patients, and 120 non-demented controls. Our study showed that MPV and PDW were significantly lower in patients with AD as compared with either MCI or controls. Moreover, MCI patients had lower MPV and PDW values compared with the controls (P < 0.001). In addition, there is a positive correlation between mini-mental state examination (MMSE) and MPV and PDW, after adjusting age, gender, and body mass index (r = 0.576, P < 0.001 for MPV; r = 0.465, P < 0.001 for PDW, respectively). Multivariate analysis showed that MPV and PDW were significantly associated with MMSE (β = 0.462; P < 0.001 for MPV; β = 0.245; P < 0.001 for PDW; respectively). In conclusion, MPV and PDW were decreased in MCI and AD patients. Further prospective research is warranted to determine the potential clinical application of MPV and PDW as biomarkers in the early diagnosis of AD.

Use of proteomic methods in the analysis of human body fluids in Alzheimer research

Proteomics is the study of the entire population of proteins and peptides in an organism or a part of it, such as a cell, tissue, or fluids like cerebrospinal fluid, plasma, serum, urine, or saliva. It is widely assumed that changes in the composition of the proteome may reflect disease states and provide clues to its origin, eventually leading to targets for new treatments. The ability to perform large-scale proteomic studies now is based jointly on recent advances in our analytical methods. Separation techniques like CE and 2DE have developed and matured. Detection methods like MS have also improved greatly in the last 5 years. These developments have also driven the fields of bioinformatics, needed to deal with the increased data production and systems biology. All these developing methods offer specific advantages but also come with certain limitations. This review describes the different proteomic methods used in the field, their limitations, and their possible pitfalls. Based on a literature search in PubMed, we identified 112 studies that applied proteomic techniques to identify biomarkers for Alzheimer disease. This review describes the results of these studies on proteome changes in human body fluids of Alzheimer patients reviewing the most important studies. We extracted a list of 366 proteins and peptides that were identified by these studies as potential targets in Alzheimer research.

Multiplex assessment of a panel of 16 serum molecules for the differential diagnosis of Alzheimer's disease

One of the current challenge in Alzheimer's disease (AD) is the identification of reliable biomarkers that might improve diagnostic accuracy, possibly correlating with the disease progression and patient's response to therapy. As the clinically validated AD biomarkers evaluate cerebrospinal fluid (CSF) parameters, the need for less invasive diagnostic markers is well evident. To this respect, blood circulating cytokines or growth factors have provided some encouraging results, even though no clinically validated to date. In 2007 Ray et al suggested a panel of 18 circulating molecules that might increase AD diagnostic accuracy. In an attempt of replicating their data, we designed a multiplex fluorimetric assay comprising 16 independent analytes and covering 15 out of the 18 described proteins. We collected serum samples from three diagnostic groups: probable AD (n=33), matched healthy controls (CNT, n=23) and non AD demented (NAD, n=14). After correction for age, we found an increased level of EGF-1 in AD in comparison to CNT and NAD, while an increase of TRAIL-R4 was found in NAD. However, evaluation of specificity/sensitivity by ROC curve analysis gave weak evidence of diagnostic accuracy (area under the curve = 0.63 and 0.66 for EGF and TRAIL-R4, respectively). Finally, we tried to find a diagnostic classifier by a multivariate algorithm. We found indication of diagnostic evidence for AD only, while NAD samples did not show a diagnostic pattern.

Triggers and effectors of oxidative stress at blood-brain barrier level: relevance for brain ageing and neurodegeneration

As fundamental research advances, it is becoming increasingly clear that a clinically expressed disease implies a mixture of intertwining molecular disturbances. Oxidative stress is one of such pathogenic pathways involved in virtually all central nervous system pathologies, infectious, inflammatory, or degenerative in nature. Since brain homeostasis largely depends on integrity of blood-brain barrier (BBB), many studies focused lately on BBB alteration in a wide spectrum of brain diseases. The proper two-way molecular transfer through BBB depends on several factors, including the functional status of its tight junction (TJ) complexes of proteins sealing neighbour endothelial cells. Although there is abundant experimental work showing that oxidative stress associates BBB permeability alteration, less is known about its implications, at molecular level, in TJ protein expression or TJ-related cell signalling. In this paper, oxidative stress is presented as a common pathway for different brain pathogenic mechanisms which lead to BBB dysregulation. We revise here oxidative-induced molecular mechanisms of BBB disruption and TJ protein expression alteration, in relation to ageing and neurodegeneration.

Predicting chemical toxicity effects based on chemical-chemical interactions

Toxicity is a major contributor to high attrition rates of new chemical entities in drug discoveries. In this study, an order-classifier was built to predict a series of toxic effects based on data concerning chemical-chemical interactions under the assumption that interactive compounds are more likely to share similar toxicity profiles. According to their interaction confidence scores, the order from the most likely toxicity to the least was obtained for each compound. Ten test groups, each of them containing one training dataset and one test dataset, were constructed from a benchmark dataset consisting of 17,233 compounds. By a Jackknife test on each of these test groups, the 1^st order prediction accuracies of the training dataset and the test dataset were all approximately 79.50%, substantially higher than the rate of 25.43% achieved by random guesses. Encouraged by the promising results, we expect that our method will become a useful tool in screening out drugs with high toxicity.

Classification of Alzheimer Diagnosis from ADNI Plasma Biomarker Data

Research into modeling the progression of Alzheimer's disease (AD) has made recent progress in identifying plasma proteomic biomarkers to identify the disease at the pre-clinical stage. In contrast with cerebral spinal fluid (CSF) biomarkers and PET imaging, plasma biomarker diagnoses have the advantage of being cost-effective and minimally invasive, thereby improving our understanding of AD and hopefully leading to early interventions as research into this subject advances. The Alzheimer's Disease Neuroimaging Initiative* (ADNI) has collected data on 190 plasma analytes from individuals diagnosed with AD as well subjects with mild cognitive impairment and cognitively normal (CN) controls. We propose an approach to classify subjects as AD or CN via an ensemble of classifiers trained and validated on ADNI data. Classifier performance is enhanced by an augmentation of a selective biomarker feature space with principal components obtained from the entire set of biomarkers. This procedure yields accuracy of 89% and area under the ROC curve of 94%.

Soluble CCL5 derived from bone marrow-derived mesenchymal stem cells and activated by amyloid β ameliorates Alzheimer's disease in mice by recruiting bone marrow-induced microglia immune responses

Microglia have the ability to eliminate amyloid β (Aβ) by a cell-specific phagocytic mechanism, and bone marrow (BM) stem cells have shown a beneficial effect through endogenous microglia activation in the brains of Alzheimer's disease (AD) mice. However, the mechanisms underlying BM-induced activation of microglia have not been resolved. Here we show that BM-derived mesenchymal stem cells (MSCs) induced the migration of microglia when exposed to Aβ in vitro. Cytokine array analysis of the BM-MSC media obtained after stimulation by Aβ further revealed elevated release of the chemoattractive factor, CCL5. We also observed that CCL5 was increased when BM-MSCs were transplanted into the brains of Aβ-deposited AD mice, but not normal mice. Interestingly, alternative activation of microglia in AD mice was associated with elevated CCL5 expression following intracerebral BM-MSC transplantation. Furthermore, by generating an AD-green fluorescent protein chimeric mouse, we ascertained that endogenous BM cells, recruited into the brain by CCL5, induced microglial activation. Additionally, we observed that neprilysin and interleukin-4 derived from the alternative microglia were associated with a reduction in Aβ deposition and memory impairment in AD mice. These results suggest that the beneficial effects observed in AD mice after intracerebral SC transplantation may be explained by alternative microglia activation. The recruitment of the alternative microglia into the brain is driven by CCL5 secretion from the transplanted BM-MSCs, which itself is induced by Aβ deposition in the AD brain.

Exploring molecular pathways of triple-negative breast cancer

Triple-negative breast cancer (TNBC) is an aggressive breast cancer subtype with a high rate of proliferation and metastasis, as well as poor prognosis for advanced-stage disease. Although TNBC was previously classified together with basal-like and BRCA1/2-related breast cancers, genomic profiling now shows that there is incomplete overlap, with important distinctions associated with each subtype. The biology of TNBC is still poorly understood; therefore, to define the relative contributions of major cellular pathways in TNBC, we have studied its molecular signature based on analysis of gene expression. Comparisons were then made with normal breast tissue. Our results suggest the existence of molecular networks in TNBC, characterized by explicit alterations in the cell cycle, DNA repair, nucleotide synthesis, metabolic pathways, NF-κB signaling, inflammatory response, and angiogenesis. Moreover, we also characterized TNBC as a cancer of mixed phenotypes, suggesting that TNBC extends beyond the basal-like molecular signature and may constitute an independent subtype of breast cancer. The data provide a new insight into the biology of TNBC.

Molecular signatures from omics data: from chaos to consensus

In the past 15 years, new "omics" technologies have made it possible to obtain high-resolution molecular snapshots of organisms, tissues, and even individual cells at various disease states and experimental conditions. It is hoped that these developments will usher in a new era of personalized medicine in which an individual's molecular measurements are used to diagnose disease, guide therapy, and perform other tasks more accurately and effectively than is possible using standard approaches. There now exists a vast literature of reported "molecular signatures". However, despite some notable exceptions, many of these signatures have suffered from limited reproducibility in independent datasets, insufficient sensitivity or specificity to meet clinical needs, or other challenges. In this paper, we discuss the process of molecular signature discovery on the basis of omics data. In particular, we highlight potential pitfalls in the discovery process, as well as strategies that can be used to increase the odds of successful discovery. Despite the difficulties that have plagued the field of molecular signature discovery, we remain optimistic about the potential to harness the vast amounts of available omics data in order to substantially impact clinical practice.