Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Epigenetic signature of human induced pluripotent stem cells identified with the linear machine learning model

ABSTRACT: Human induced pluripotent stem cells (iPSCs) were established as an artificial embryonic stem cells (ESCs) to avoid immune rejection, for ethical issues in regenerative medicine, and for biological research. Comparison analyses in previous studies revealed that there is no hot spot that distinguishes iPSCs from ESCs. We herewith established a learning model using Jubatus, as a machine learning platform, with linear model for classification to distinguish human iPSCs from ESCs based on DNA methylation profiles. We found that the linear model classification is most suitable for the analysis of human iPSCs whose line number is practically 10 to 100. The learning models discriminated ESCs and iPSCs with an accuracy of ≥ 85.71 % and ≥ 90.91 %, respectively. In addition, the epigenetic signature of iPSCs was identified by component analysis of the learning models. The iPSC-specific fluctuated methylation regions were abundant at chromosome 7, 8, 12, and 22. The method can be utilized with comprehensive data and can also be widely applied to many aspects of molecular biology research.

ORGANISM(S): Homo sapiens

PROVIDER: GSE141521 | GEO | 2019/12/06

REPOSITORIES: GEO

ACCESS DATA

Json Xml

Similar Datasets

Epigenetic signature of human induced pluripotent stem cells identified with the linear machine learning model

Project description:Epigenetic signature of human induced pluripotent stem cells identified with the linear machine learning model

| PRJNA593774 | ENA

Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data [Methylomics]

Project description:We experimented how well various supervised machine learning methods such as decision tree, partial least squares discriminant analysis (PLSDA), support vector machine and random forest perform in classifying endometriosis from the control samples trained on both transcriptomics and methylomics data. The assessment was done from two different perspectives for improving classification performances: (a) implication of three different normalization techniques, and (b) implication of differential analysis using the generalized linear model (GLM). We concluded that an appropriate machine learning diagnostic pipeline for endometriosis should use TMM normalization for transcriptomics data, and quantile or voom normalization for methylomics data, GLM for feature space reduction and classification performance maximization.

2019-07-18 | GSE134052 | GEO

Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data [Transcriptomics]

2019-07-18 | GSE134056 | GEO

Multiple Firings in Double-stapled Colorectal Anastomosis

Project description:Multiple linear stapler firings during double stapling technique (DST) is associated with anastomotic leakage (AL) after laparoscopic low anterior resection (LAR). We aim to investigate the risk factors and then to develop a deep learning model to predict the usage of ≥3 linear stapler cartridges during DST anastomosis.

| 2744994 | ecrin-mdr-crc

Validation Study of Linear Quantification of CD3+ Cells in Localized Colorectal Carcinomas

Project description:The purpose of this study is to confirm that linear quantification of CD3+ cells is a prognostic biomarker in localized colorectal carcinomas.

| 2183880 | ecrin-mdr-crc

Induced Pluripotent Cells Derived from Differentiated Rod Photoreceptors Undergo Efficient Retinogenesis in Three-Dimensional Cultures

Project description:"Embryonic stem cells (ESCs) and induced pluripotent stem cells (iPSCs) are used to study lineage-specific differentiation in culture. We developed a standardized quantitative protocol called STEM-RET to compare eye field specification, optic cup formation, and retinal differentiation across stem cell populations. We reprogrammed individual rod photoreceptors into iPSCs by inducible expression of Oct3/4, Klf4, Sox2, and Myc. We also developed ESC lines from rods by somatic cell nuclear transfer. Using the STEM-RET protocol, we compared the abilities of ESCs, fibroblast-derived iPSCs (f-iPSCs), rod photoreceptor-derived iPSCs (r-iPSCs), and rod photoreceptorderived ESCs to form retinae using STEM-RET. r-iPSCs were the most efficient at producing differentiated retina. Retinae derived from f-iPSCs lacked an inner nuclear layer (INL) and had a concomitant reduction in amacrine cells and other INL cell populations. The INL-specific LIM homeobox gene, Lhx9, was hypermethylated in fiPSCs and concomitantly downregulated in retinae derived from those stem cells. ChIP-seq analysis for H3K36me3, H3K4me1, H3K4me3, H3K9/14Ac, H3K27me3, H3K9me3, CTCF and 5 hydroxymethyl cytosine showed that the major difference between the r-iPSCs and the f-iPSCs were in the genes marked by the CTCF insulator protein. Importantly, CTCF binding enrichment at rod photoreceptor specific genes was at least 10-fold higher in r-iPSCs relative to f-iPSCs. Taken together, our data suggest that both inhibitory and permissive epigenetic marks important for retinal development can be retained in iPSCs and such marks can be exploited to select the most favorable stem cell population to study retinal development or produce photoreceptor precursors for cell transplantation."

| EGAS00001001288 | EGA

Excised linear introns regulate growth in yeast

Project description:Excised linear introns regulate growth in yeast

| PRJNA498397 | ENA

Compartmentalization of HP1 proteins in pluripotency acquisition and maintenance

Project description:Embryonic stem cells (ESCs) have a hyperdynamic chromatin structure characterized by fewer discrete foci of heterochromatin protein 1 family of proteins (HP1) compared to somatic cells. During reprogramming of somatic cells, depletion of HP1γ early, reduced, while depletion later, enhanced the generation of induced pluripotent stem cells (iPSCs); concomitant with a change from a centromeric to nucleoplasmic localization. To identify the interactome of HP1γ in different biochemical environment in ESCs, we compared protein complexes of HP1γ at 0.42M salt (Dignam et al, 1983), with micrococcal nuclease (MCN) digestion with 0.3M NaCl, and MCN with 0.5M NaCl. To understand the effectors of the change in localization, we isolated protein complexes containing HP1γ in ESCs and compared the profile to that in partially reprogrammed intermediates called pre-iPSCs. Given the differential distribution of the HP1 family in ESCs, we also compared the protein interactome of HP1γ in ESCs with that of HP1α and HP1β. In addition, we probed histone associations of HP1γ in ESCs further by querying the histone post-translational modifications that were detectable. The HP1 proteins themselves are decorated with multiple PTMs, several of which we have found to be novel. Taken together our results reveal the complex contribution of the HP1 proteins to pluripotency.

2017-12-13 | PXD006817 | Pride

Urinary Proteomic Spectra Analysis Based on Machine Learning for Classification of Kidney Diseases

Project description:To extract urinary proteome spectral features based on advanced mass spectrometer and machine learning algorithms, it could get more accurate reporting results for disease classification. We tried to establish a novel diagnosis model of kidney diseases by combining machine learning XGBoost algorithm with complete urinary proteomic information.

2022-09-13 | PXD018996 | Pride

mRNA expression data from iPSCs, ntESCs and iPSC-nt-ESCs

Project description:We generated three kinds of genetically identical mouse reprogrammed cells: induced pluripotent stem cells (iPSCs), nuclear transfer embryonic stem cells (ntESCs) and iPSC-nt-ESCs that are established after successively reprogramming of iPSCs by nuclear transfer (NT). NtESCs show better developmental potential than iPSCs, whereas iPSC-nt-ESCs display worse developmental potential than iPSCs. We used microarrays to distinguish the gene expression differences among three pluriptoent stem cells and identified that imprinted genes had a similar expression pattern in iPSCs and iPSC-nt-ESCs.

2011-05-31 | GSE24705 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data