Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important problem. While one can potentially exploit the latent-space back-projection GANs to cluster, we demonstrate that cluster structure not retained GAN latent space. In this paper, propose ClusterGAN as a new mechanism for using GANs. By sampling variables from mixture of one-hot encoded continuous variables, coupled with inverse network (which...

In the wake of recent advances in scientific research, personalized medicine using deep learning techniques represents a new paradigm. this work, our goal was to establish models which distinguish responders from non-responders, and also predict possible antidepressant treatment outcomes major depressive disorder (MDD). To uncover relationships between responsiveness biomarkers, we developed prediction approach resulting analysis genetic clinical factors such as single nucleotide...

Abstract Background Single-cell RNA sequencing (scRNA-seq) is an emerging technology that can assess the function of individual cell and cell-to-cell variability at single level in unbiased manner. Dimensionality reduction essential first step downstream analysis scRNA-seq data. However, data are challenging for traditional methods due to their high dimensional measurements as well abundance dropout events (that is, zero expression measurements). Results To overcome these difficulties, we...

Depression is associated with various environmental risk factors such as stress, childhood maltreatment experiences, and stressful life events. Current approaches to assess the pathophysiology of depression, epigenetics gene-environment (GxE) interactions, have been widely leveraged determine plausible markers, genes, variants for developing depression.We focus on most recent developments genomic research in GxE interactions.In this review, we first survey a variety association studies...

Abstract Increased risk of developing metabolic syndrome (MetS) has been associated with the APOA5 , APOC1 BRAP BUD13 CETP LIPA LPL PLCG1 and ZPR1 genes. In this replication study, we reassessed whether these genes are MetS its individual components independently and/or through complex interactions in a Taiwanese population. We also analyzed between environmental factors influencing components. A total 3,000 subjects were assessed study. Metabolic traits such as waist circumference,...

In the studies of genomics, it is essential to select a small number genes that are more significant than others for association disease susceptibility. this work, our goal was compare computational tools with and without feature selection predicting chronic fatigue syndrome (CFS) using genetic factors such as single nucleotide polymorphisms (SNPs).We employed dataset original previous study by CDC Chronic Fatigue Syndrome Research Group. To uncover relationships between CFS SNPs, we applied...

Brain-derived neurotrophic-factor (BDNF) and its receptor neurotrophic tyrosine kinase 2 (NTRK2) have been implicated in both major depression cognitive function. This study examines the main effects of single loci multilocus interactions to test hypothesis that BDNF NTRK2 genes may contribute etiology geriatric independently and/or through complex interactions. We genotyped gene Val66Met (rs6265) polymorphism four single-nucleotide polymorphisms (SNPs) (including rs1187323, rs1187329,...

The transforming growth factor-β (TGF-β) signaling pathway and its relevant genes have been correlated with an increased risk of developing various hallmarks metabolic syndrome (MetS). In this study, we assessed whether the TGF-β pathway-associated SMAD family member 2 (SMAD2), SMAD3, SMAD4, factor beta 1 (TGFB1), TGFB2, TGFB3, receptor (TGFBR1), TGFBR2 are associated MetS individual components independently, through complex interactions, or both in a Taiwanese population. A total 3,000...

Abstract It has been suggested that the relationship between cognitive function and functional outcome in schizophrenia is mediated by clinical symptoms, while assessed Quality of Life Scale (QLS) Global Assessment Functioning (GAF) Scale. To determine QLS GAF, we established a bagging ensemble framework with feature selection algorithm resulting from analysis factors such as 3 symptom scales 11 scores 302 patients Taiwanese population. We compared our other state-of-the-art algorithms...

Machine learning has been proposed to utilize d-amino acid oxidase (DAO) and DAO activator (DAOA [or pLG72]) protein levels ascertain disease status in schizophrenia. However, it remains unclear whether machine can effectively evaluate clinical features relation DAOA schizophrenia patients. We employed an interpretable (IML) framework including linear regression, least absolute shrinkage selection operator (Lasso) models, generalized additive models (GAMs) analyze DAO/DAOA using 380...

Genome-wide association studies and meta-analyses implicated that increased risk of developing Alzheimer's diseases (AD) has been associated with the ABCA7, APOE, BIN1, CASS4, CD2AP, CD33, CELF1, CLU, CR1, DSG2, EPHA1, FERMT2, HLA-DRB1, HLA-DRB4, INPP5D, MEF2C, MS4A4A, MS4A4E, MS4A6E, NME8, PICALM, PLD3, PTK2B, RIN3, SLC24A4, SORL1, ZCWPW1 genes. In this study, we assessed whether single nucleotide polymorphisms (SNPs) within these 27 AD-associatedgenes are linked cognitive aging...