A deep belief network-based method to identify proteomic risk markers for Alzheimer disease

While a large body of research has formally identified apolipoprotein E (APOE) as a major genetic risk marker for Alzheimer disease, accumulating evidence supports the notion that other risk markers may exist. The traditional Alzheimer-specific signature analysis methods, however, have not been able to make full use of rich protein expression data, especially the interaction between attributes. This paper develops a novel feature selection method to identify pathogenic factors of Alzheimer disease using the proteomic and clinical data. This approach has taken the weights of network nodes as the importance order of signaling protein expression values. After generating and evaluating the candidate subset, the method helps to select an optimal subset of proteins that achieved an accuracy greater than 90%, which is superior to traditional machine learning methods for clinical Alzheimer disease diagnosis. Besides identifying a proteomic risk marker and further reinforce the link between metabolic risk factors and Alzheimer disease, this paper also suggests that apidonectin-linked pathways are a possible therapeutic drug target.

[1]  G. Schellenberg,et al.  Early-onset Alzheimer disease in families with late-onset Alzheimer disease: a potential important subtype of familial Alzheimer disease. , 2006, Archives of neurology.

[2]  Asifullah Khan,et al.  GECC: Gene Expression Based Ensemble Classification of Colon Samples , 2014, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  Geoffrey E. Hinton Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[4]  M. Prince,et al.  World Alzheimer report 2016: improving healthcare for people living with dementia: coverage, quality and costs now and in the future , 2016 .

[5]  M. Mattson,et al.  Adiponectin protects rat hippocampal neurons against excitotoxicity , 2011, AGE.

[6]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[7]  Rebecca F. Halperin,et al.  A high-density whole-genome association study reveals that APOE is the major susceptibility gene for sporadic late-onset Alzheimer's disease. , 2007, The Journal of clinical psychiatry.

[8]  M. Kamboh,et al.  Molecular Genetics of Late‐Onset Alzheimer's Disease , 2004, Annals of human genetics.

[9]  T. Saruta,et al.  Correlation of the adipocyte-derived protein adiponectin with insulin resistance index and serum high-density lipoprotein-cholesterol, independent of body mass index, in the Japanese population. , 2002, Clinical science.

[10]  K. Blennow,et al.  Cerebrospinal fluid beta-amyloid(1-42) in Alzheimer disease: differences between early- and late-onset Alzheimer disease and stability during the course of disease. , 1999, Archives of neurology.

[11]  Oskar Hansson,et al.  CCL2 Is Associated with a Faster Rate of Cognitive Decline during Early Stages of Alzheimer's Disease , 2012, PloS one.

[12]  O. Forlenza,et al.  Decreased Levels of Circulating Adiponectin in Mild Cognitive Impairment and Alzheimer’s Disease , 2012, NeuroMolecular Medicine.

[13]  G. Schellenberg,et al.  Genetic dissection of Alzheimer disease, a heterogeneous disorder. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[14]  H. Soininen,et al.  The level of cerebrospinal fluid tau correlates with neurofibrillary tangles in Alzheimer's disease , 1997, Neuroreport.

[15]  B. Långström,et al.  The use of PET in Alzheimer disease , 2010, Nature Reviews Neurology.

[16]  W. Kukull,et al.  Epidemiology of dementia: concepts and overview. , 2000, Neurologic clinics.

[17]  Ling Li,et al.  Cholesterol as a causative factor in Alzheimer's disease: a debatable hypothesis , 2014, Journal of neurochemistry.

[18]  H. Lodish,et al.  Proteolytic cleavage product of 30-kDa adipocyte complement-related protein increases fatty acid oxidation in muscle and causes weight loss in mice. , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[19]  R. Tanzi,et al.  Alzheimer's disease: one disorder, too many genes? , 2004, Human molecular genetics.

[20]  S. Henderson Epidemiology of dementia. , 1998, Annales de medecine interne.

[21]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[22]  J. Haines,et al.  Effects of Age, Sex, and Ethnicity on the Association Between Apolipoprotein E Genotype and Alzheimer Disease: A Meta-analysis , 1997 .

[23]  K. Lam,et al.  Cross‐talk between adipose tissue and vasculature: role of adiponectin , 2011, Acta physiologica.

[24]  C. Mantzoros,et al.  Adiponectin in insulin resistance: lessons from translational research. , 2010, The American journal of clinical nutrition.

[25]  J. Couzin Once Shunned, Test for Alzheimer's Risk Headed to Market , 2008, Science.

[26]  J. Morris,et al.  The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[27]  Laura Fratiglioni,et al.  Worldwide Prevalence and Incidence of Dementia , 1999, Drugs & aging.

[28]  B. Dubois,et al.  Early-onset autosomal dominant Alzheimer disease: prevalence, genetic heterogeneity, and mutation spectrum. , 1999, American journal of human genetics.

[29]  R. Tibshirani,et al.  Classification and prediction of clinical Alzheimer's diagnosis based on plasma signaling proteins , 2007, Nature Medicine.

[30]  Geoffrey E. Hinton Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[31]  M. Birnbaum,et al.  Receptor-mediated activation of ceramidase activity initiates the pleiotropic actions of adiponectin , 2011, Nature Medicine.

[32]  A. Roses On the discovery of the genetic association of Apolipoprotein E genotypes and common late-onset Alzheimer disease. , 2006, Journal of Alzheimer's disease : JAD.

[33]  D. Gustafson Adiposity and cognitive decline: underlying mechanisms. , 2012, Journal of Alzheimer's disease : JAD.

[34]  B. Jeon,et al.  Adiponectin protects hippocampal neurons against kainic acid-induced excitotoxicity , 2009, Brain Research Reviews.

[35]  P. Deyn,et al.  Association study of cholesterol-related genes in Alzheimer’s disease , 2007, Neurogenetics.

[36]  B. Cheung,et al.  Hypoadiponectinemia as an independent predictor for the progression of carotid atherosclerosis: a 5-year prospective study. , 2014, Metabolic syndrome and related disorders.

[37]  Guangzhong Sun,et al.  A New Progressive Algorithm for a Multiple Longest Common Subsequences Problem and Its Efficient Parallelization , 2013, IEEE Transactions on Parallel and Distributed Systems.

[38]  Juan Manuel Górriz,et al.  Association rule-based feature selection method for Alzheimer's disease diagnosis , 2012, Expert Syst. Appl..

[39]  Jennifer Williamson,et al.  Genetic Aspects of Alzheimer Disease , 2009, The neurologist.

[40]  Nancy Reagan,et al.  Consensus Report of the Working Group on: "Molecular and Biochemical Markers of Alzheimer's Disease" , 1998 .

[41]  M. Halil,et al.  Adipocytokines and aging: adiponectin and leptin. , 2013, Minerva endocrinologica.

[42]  J. Haines,et al.  Gene dose of apolipoprotein E type 4 allele and the risk of Alzheimer's disease in late onset families. , 1993, Science.

[43]  J. Trojanowski,et al.  Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification , 2011, Neurobiology of Aging.

[44]  D. Selkoe Alzheimer's disease: genes, proteins, and therapy. , 2001, Physiological reviews.

[45]  Juhyun Song,et al.  Adiponectin Regulates the Polarization and Function of Microglia via PPAR-γ Signaling Under Amyloid β Toxicity , 2017, Front. Cell. Neurosci..

[46]  Animesh Nandi,et al.  Serum biomarkers for Alzheimer's disease: proteomic discovery. , 2007, Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie.

[47]  J. Massaro,et al.  Exploring the Hierarchical Influence of Cognitive Functions for Alzheimer Disease: The Framingham Heart Study , 2020, Journal of medical Internet research.

[48]  Shenghui Zhao,et al.  A Comparative Study on Human Activity Recognition Using Inertial Sensors in a Smartphone , 2016, IEEE Sensors Journal.

[49]  M. Greicius,et al.  Default-mode network activity distinguishes Alzheimer's disease from healthy aging: Evidence from functional MRI , 2004, Proc. Natl. Acad. Sci. USA.

[50]  K. Blennow,et al.  Cerebrospinal fluid tau protein as a biochemical marker for Alzheimer’s disease: a community based follow up study , 1998, Journal of neurology, neurosurgery, and psychiatry.