scholarly journals Cross-Cell-Type Prediction of TF-Binding Site by Integrating Convolutional Neural Network and Adversarial Network

2019 ◽  
Vol 20 (14) ◽  
pp. 3425 ◽  
Author(s):  
Gongqiang Lan ◽  
Jiyun Zhou ◽  
Ruifeng Xu ◽  
Qin Lu ◽  
Hongpeng Wang
Keyword(s):  
Data Augmentation ◽  
Gene Expression Regulation ◽  
Cell Types ◽  
Cell Type ◽  
Baseline Method ◽  
Common Features ◽  
Adversarial Network ◽  
Tfbs Prediction ◽  
Feature Extractor ◽  
Different Cell Types

Transcription factor binding sites (TFBSs) play an important role in gene expression regulation. Many computational methods for TFBS prediction need sufficient labeled data. However, many transcription factors (TFs) lack labeled data in cell types. We propose a novel method, referred to as DANN_TF, for TFBS prediction. DANN_TF consists of a feature extractor, a label predictor, and a domain classifier. The feature extractor and the domain classifier constitute an Adversarial Network, which ensures that learned features are common features across different cell types. DANN_TF is evaluated on five TFs in five cell types with a total of 25 cell-type TF pairs and compared to a baseline method which does not use Adversarial Network. For both data augmentation and cross-cell-type prediction, DANN_TF performs better than the baseline method on most cell-type TF pairs. DANN_TF is further evaluated by an additional 13 TFs in the five cell types with a total of 65 cell-type TF pairs. Results show that DANN_TF achieves significantly higher AUC than the baseline method on 96.9% pairs of the 65 cell-type TF pairs. This is a strong indication that DANN_TF can indeed learn common features for cross-cell-type TFBS prediction.

scholarly journals MTTFsite: cross-cell type TF binding site prediction by using multi-task learning

2019 ◽  
Vol 35 (24) ◽  
pp. 5067-5077 ◽  
Author(s):  
Jiyun Zhou ◽  
Qin Lu ◽  
Lin Gui ◽  
Ruifeng Xu ◽  
Yunfei Long ◽  
...  
Keyword(s):  
Gene Expression ◽  
Histone Modification ◽  
Prediction Method ◽  
Cell Types ◽  
Supplementary Information ◽  
Learning Approaches ◽  
Cell Type ◽  
Baseline Method ◽  
Common Features ◽  
Task Learning

AbstractMotivationThe prediction of transcription factor binding sites (TFBSs) is crucial for gene expression analysis. Supervised learning approaches for TFBS predictions require large amounts of labeled data. However, many TFs of certain cell types either do not have sufficient labeled data or do not have any labeled data.ResultsIn this paper, a multi-task learning framework (called MTTFsite) is proposed to address the lack of labeled data problem by leveraging on labeled data available in cross-cell types. The proposed MTTFsite contains a shared CNN to learn common features for all cell types and a private CNN for each cell type to learn private features. The common features are aimed to help predicting TFBSs for all cell types especially those cell types that lack labeled data. MTTFsite is evaluated on 241 cell type TF pairs and compared with a baseline method without using any multi-task learning model and a fully shared multi-task model that uses only a shared CNN and do not use private CNNs. For cell types with insufficient labeled data, results show that MTTFsite performs better than the baseline method and the fully shared model on more than 89% pairs. For cell types without any labeled data, MTTFsite outperforms the baseline method and the fully shared model by more than 80 and 93% pairs, respectively. A novel gene expression prediction method (called TFChrome) using both MTTFsite and histone modification features is also presented. Results show that TFBSs predicted by MTTFsite alone can achieve good performance. When MTTFsite is combined with histone modification features, a significant 5.7% performance improvement is obtained.Availability and implementationThe resource and executable code are freely available at http://hlt.hitsz.edu.cn/MTTFsite/ and http://www.hitsz-hlt.com:8080/MTTFsite/.Supplementary informationSupplementary data are available at Bioinformatics online.

scholarly journals SeqEnhDL: sequence-based classification of cell type-specific enhancers using deep learning models

2020 ◽  
Author(s):  
Yupeng Wang ◽  
Rosario B. Jaime-Lara ◽  
Abhrarup Roy ◽  
Ying Sun ◽  
Xinyue Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Dna Sequences ◽  
Cell Types ◽  
Learning Models ◽  
Cell Type ◽  
Coding Sequences ◽  
Sequence Features ◽  
Cell Type Specific ◽  
Different Cell Types

AbstractWe propose SeqEnhDL, a deep learning framework for classifying cell type-specific enhancers based on sequence features. DNA sequences of “strong enhancer” chromatin states in nine cell types from the ENCODE project were retrieved to build and test enhancer classifiers. For any DNA sequence, sequential k-mer (k=5, 7, 9 and 11) fold changes relative to randomly selected non-coding sequences were used as features for deep learning models. Three deep learning models were implemented, including multi-layer perceptron (MLP), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). All models in SeqEnhDL outperform state-of-the-art enhancer classifiers including gkm-SVM and DanQ, with regard to distinguishing cell type-specific enhancers from randomly selected non-coding sequences. Moreover, SeqEnhDL is able to directly discriminate enhancers from different cell types, which has not been achieved by other enhancer classifiers. Our analysis suggests that both enhancers and their tissue-specificity can be accurately identified according to their sequence features. SeqEnhDL is publicly available at https://github.com/wyp1125/SeqEnhDL.

scholarly journals The complement of desmosomal plaque proteins in different cell types.

1985 ◽  
Vol 101 (4) ◽  
pp. 1442-1454 ◽  
Author(s):  
P Cowin ◽  
H P Kapprell ◽  
W W Franke
Keyword(s):  
Guinea Pig ◽  
Cell Types ◽  
Cardiac Cells ◽  
Myocardial Tissue ◽  
Cell Type ◽  
Wide Range ◽  
Specific Manner ◽  
A Cell ◽  
Cell Type Specific ◽  
Different Cell Types

Desmosomal plaque proteins have been identified in immunoblotting and immunolocalization experiments on a wide range of cell types from several species, using a panel of monoclonal murine antibodies to desmoplakins I and II and a guinea pig antiserum to desmosomal band 5 protein. Specifically, we have taken advantage of the fact that certain antibodies react with both desmoplakins I and II, whereas others react only with desmoplakin I, indicating that desmoplakin I contains unique regions not present on the closely related desmoplakin II. While some of these antibodies recognize epitopes conserved between chick and man, others display a narrow species specificity. The results show that proteins whose size, charge, and biochemical behavior are very similar to those of desmoplakin I and band 5 protein of cow snout epidermis are present in all desmosomes examined. These include examples of simple and pseudostratified epithelia and myocardial tissue, in addition to those of stratified epithelia. In contrast, in immunoblotting experiments, we have detected desmoplakin II only among cells of stratified and pseudostratified epithelial tissues. This suggests that the desmosomal plaque structure varies in its complement of polypeptides in a cell-type specific manner. We conclude that the obligatory desmosomal plaque proteins, desmoplakin I and band 5 protein, are expressed in a coordinate fashion but independently from other differentiation programs of expression such as those specific for either epithelial or cardiac cells.

scholarly journals Distribution and modulation of the cellular receptor for transforming growth factor-beta.

1987 ◽  
Vol 105 (2) ◽  
pp. 965-975 ◽  
Author(s):  
L M Wakefield ◽  
D M Smith ◽  
T Masui ◽  
C C Harris ◽  
M B Sporn
Keyword(s):  
Growth Factor ◽  
Transforming Growth Factor Beta ◽  
Transforming Growth Factor ◽  
Cell Types ◽  
Tgf Beta ◽  
Cell Type ◽  
Down Regulation ◽  
Growth Factor Beta ◽  
Different Cell Types

Scatchard analyses of the binding of transforming growth factor-beta (TGF-beta) to a wide variety of different cell types in culture revealed the universal presence of high affinity (Kd = 1-60 pM) receptors for TGF-beta on every cell type assayed, indicating a wide potential target range for TGF-beta action. There was a strong (r = +0.85) inverse relationship between the receptor affinity and the number of receptors expressed per cell, such that at low TGF-beta concentrations, essentially all cells bound a similar number of TGF-beta molecules per cell. The binding of TGF-beta to various cell types was not altered by many agents that affect the cellular response to TGF-beta, suggesting that modulation of TGF-beta binding to its receptor may not be a primary control mechanism in TGF-beta action. Similarly, in vitro transformation resulted in only relatively small changes in the cellular binding of TGF-beta, and for those cell types that exhibited ligand-induced down-regulation of the receptor, down-regulation was not extensive. Thus the strong conservation of binding observed between cell types is also seen within a given cell type under a variety of conditions, and receptor expression appears to be essentially constitutive. Finally, the biologically inactive form of TGF-beta, which constitutes greater than 98% of autocrine TGF-beta secreted by all of the twelve different cell types assayed, was shown to be unable to bind to the receptor without prior activation in vitro. It is proposed that this may prevent premature interaction of autocrine ligand and receptor in the Golgi apparatus.

scholarly journals Detection of cell-type-specific risk-CpG sites in epigenome-wide association studies

2018 ◽  
Author(s):  
Xiangyu Luo ◽  
Can Yang ◽  
Yingying Wei
Keyword(s):  
High Resolution ◽  
Statistical Method ◽  
Individual Cell ◽  
Association Studies ◽  
Cell Types ◽  
Cell Type ◽  
Cpg Sites ◽  
Cpg Site ◽  
Cell Type Specific ◽  
Different Cell Types

In epigenome-wide association studies, the measured signals for each sample are a mixture of methylation profiles from different cell types. The current approaches to the association detection only claim whether a cytosine-phosphate-guanine (CpG) site is associated with the phenotype or not, but they cannot determine the cell type in which the risk-CpG site is affected by the phenotype. Here, we propose a solid statistical method, HIgh REsolution (HIRE), which not only substantially improves the power of association detection at the aggregated level as compared to the existing methods but also enables the detection of risk-CpG sites for individual cell types.

scholarly journals accuEnhancer: Accurate enhancer prediction by integration of multiple cell type data with deep learning

2020 ◽  
Author(s):  
Yi-An Tung ◽  
Wen-Tse Yang ◽  
Tsung-Ting Hsieh ◽  
Yu-Chuan Chang ◽  
June-Tai Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cell Types ◽  
Regulatory Elements ◽  
Sequence Motifs ◽  
Cell Type ◽  
Enhancer Activity ◽  
Multiple Cell ◽  
Type Data ◽  
Different Cell Types ◽  
Multiple Cell Type

AbstractEnhancers are one class of the regulatory elements that have been shown to act as key components to assist promoters in modulating the gene expression in living cells. At present, the number of enhancers as well as their activities in different cell types are still largely unclear. Previous studies have shown that enhancer activities are associated with various functional data, such as histone modifications, sequence motifs, and chromatin accessibilities. In this study, we utilized DNase data to build a deep learning model for predicting the H3K27ac peaks as the active enhancers in a target cell type. We propose joint training of multiple cell types to boost the model performance in predicting the enhancer activities of an unstudied cell type. The results demonstrated that by incorporating more datasets across different cell types, the complex regulatory patterns could be captured by deep learning models and the prediction accuracy can be largely improved. The analyses conducted in this study demonstrated that the cell type-specific enhancer activity can be predicted by joint learning of multiple cell type data using only DNase data and the primitive sequences as the input features. This reveals the importance of cross-cell type learning, and the constructed model can be applied to investigate potential active enhancers of a novel cell type which does not have the H3K27ac modification data yet.AvailabilityThe accuEnhancer package can be freely accessed at: https://github.com/callsobing/accuEnhancer

scholarly journals Structural differences between plasma-membrane 5′-nucleotidase in different cell types as evidenced by antibodies

1985 ◽  
Vol 232 (3) ◽  
pp. 859-862 ◽  
Author(s):  
J Harb ◽  
K Meflah ◽  
S Bernard
Keyword(s):  
Cell Types ◽  
Antigenic Determinants ◽  
Nucleotidase Activity ◽  
Cell Type ◽  
Caudate Nuclei ◽  
The Third ◽  
Common Structure ◽  
Structural Differences ◽  
Structural Nature ◽  
Different Cell Types

Antibodies raised against bovine 5′-nucleotidase inhibit this enzyme as well as 5′-nucleotidase from other bovine tissues, showing common structure(s) between these proteins. However, an IgG fraction directed against the glucidic moiety of the liver enzyme did not cross-react with the enzyme from lymphocyte or caudate nuclei, a clear indication that within the same species the 5′-nucleotidase differs from one cell type to another. In addition, immunoblots after electrophoresis show that the previous antibodies recognize 5′-nucleotidase from human, mouse or chicken origin. However, only human 5′-nucleotidase activity can be inhibited by the antibodies. Thus at least three groups of antigenic determinants must exist on the 5′-nucleotidase: one related to the glucidic moiety of the glycoprotein whose binding inhibits the enzyme activity, another related to the catalytic site, as its binding also led to enzyme inhibition, and a last one of structural nature. It seems that the third group of determinant is common to many species, whereas the second one is more restricted.

Cell type-specific endometrial transcriptome changes during initial recognition of pregnancy in the mare

2019 ◽  
Vol 31 (3) ◽  
pp. 496 ◽  
Author(s):  
Iside Scaravaggi ◽  
Nicole Borel ◽  
Rebekka Romer ◽  
Isabel Imboden ◽  
Susanne E. Ulbrich ◽  
...  
Keyword(s):  
Gene Expression ◽  
Spatial Information ◽  
Gene Expression Regulation ◽  
Cell Types ◽  
Rna Seq ◽  
Cell Type ◽  
Expression Of Genes ◽  
Prostaglandin F ◽  
Cell Type Specific ◽  
Gene Expression Studies

Previous endometrial gene expression studies during the time of conceptus migration did not provide final conclusions on the mechanisms of maternal recognition of pregnancy (MRP) in the mare. This called for a cell type-specific endometrial gene expression analysis in response to embryo signals to improve the understanding of gene expression regulation in the context of MRP. Laser capture microdissection was used to collect luminal epithelium (LE), glandular epithelium and stroma from endometrial biopsies from Day 12 of pregnancy and Day 12 of the oestrous cycle. RNA sequencing (RNA-Seq) showed greater expression differences between cell types than between pregnant and cyclic states; differences between the pregnant and cyclic states were mainly found in LE. Comparison with a previous RNA-Seq dataset for whole biopsy samples revealed the specific origin of gene expression differences. Furthermore, genes specifically differentially expressed (DE) in one cell type were found that were not detectable as DE in biopsies. Overall, this study revealed spatial information about endometrial gene expression during the phase of initial MRP. The conceptus induced changes in the expression of genes involved in blood vessel development, specific spatial regulation of the immune system, growth factors, regulation of prostaglandin synthesis, transport prostaglandin receptors, specifically prostaglandin F receptor (PTGFR) in the context of prevention of luteolysis.

scholarly journals CARs: Beyond T Cells and T Cell-Derived Signaling Domains

2020 ◽  
Vol 21 (10) ◽  
pp. 3525 ◽  
Author(s):  
Nico M. Sievers ◽  
Jan Dörrie ◽  
Niels Schaft
Keyword(s):  
Cell Types ◽  
Antigen Binding ◽  
Cell Type ◽  
Transfected Cells ◽  
Effector Functions ◽  
Binding Domains ◽  
Specific Effector ◽  
Different Cell Types ◽  
Intracellular Domains ◽  
Signaling Domains

When optimizing chimeric antigen receptor (CAR) therapy in terms of efficacy, safety, and broadening its application to new malignancies, there are two main clusters of topics to be addressed: the CAR design and the choice of transfected cells. The former focuses on the CAR construct itself. The utilized transmembrane and intracellular domains determine the signaling pathways induced by antigen binding and thereby the cell-specific effector functions triggered. The main part of this review summarizes our understanding of common signaling domains employed in CARs, their interactions among another, and their effects on different cell types. It will, moreover, highlight several less common extracellular and intracellular domains that might permit unique new opportunities. Different antibody-based extracellular antigen-binding domains have been pursued and optimized to strike a balance between specificity, affinity, and toxicity, but these have been reviewed elsewhere. The second cluster of topics is about the cellular vessels expressing the CAR. It is essential to understand the specific attributes of each cell type influencing anti-tumor efficacy, persistence, and safety, and how CAR cells crosstalk with each other and bystander cells. The first part of this review focuses on the progress achieved in adopting different leukocytes for CAR therapy.

Transport properties of the lens

1985 ◽  
Vol 249 (3) ◽  
pp. C181-C190 ◽  
Author(s):  
R. T. Mathias ◽  
J. L. Rae
Keyword(s):  
Transport Properties ◽  
Membrane Transport ◽  
Cell Membranes ◽  
Spatial Localization ◽  
Cell Types ◽  
Physical Structure ◽  
Present Knowledge ◽  
Cell Type ◽  
Electrophysiological Properties ◽  
Different Cell Types

Many studies have shown that the lens is a multicellular syncytial tissue whose electrophysiological properties are the integrated result of membrane transport, low-resistance gap junctions interconnecting the cells, and the restricted extracellular space between cells. There are at least three structurally distinct populations of cells within the lens, and the membrane transport properties of each cell type appear to differ. Indeed, there may be subcellular specialization of membrane transport properties in the surface epithelial cells. We review the physical structure of the lens, its electrical structure, and our present knowledge of the membrane transport properties of the different cell types. Our recent work has focused on radially circulating fluxes generated by the spatial localization of membrane transport in surface cell membranes versus inner fiber cell membranes. We review this work and present some simplified models of the results with some discussion of physiological implications.

Sign in / Sign up

Export Citation Format

Share Document