scholarly journals Graph embedding ensemble methods based on the heterogeneous network for lncRNA-miRNA interaction prediction

BMC Genomics ◽  
2020 ◽  
Vol 21 (S13) ◽  
Author(s):  
Chengshuai Zhao ◽  
Yang Qiu ◽  
Shuang Zhou ◽  
Shichao Liu ◽  
Wen Zhang ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Heterogeneous Network ◽  
Sequence Similarity ◽  
Expression Patterns ◽  
Interaction Network ◽  
Ensemble Methods ◽  
Graph Embedding ◽  
Mirna Sequence ◽  
Interaction Prediction ◽  
Cellular Processes

Abstract Background Researchers discover LncRNA–miRNA regulatory paradigms modulate gene expression patterns and drive major cellular processes. Identification of lncRNA-miRNA interactions (LMIs) is critical to reveal the mechanism of biological processes and complicated diseases. Because conventional wet experiments are time-consuming, labor-intensive and costly, a few computational methods have been proposed to expedite the identification of lncRNA-miRNA interactions. However, little attention has been paid to fully exploit the structural and topological information of the lncRNA-miRNA interaction network. Results In this paper, we propose novel lncRNA-miRNA prediction methods by using graph embedding and ensemble learning. First, we calculate lncRNA-lncRNA sequence similarity and miRNA-miRNA sequence similarity, and then we combine them with the known lncRNA-miRNA interactions to construct a heterogeneous network. Second, we adopt several graph embedding methods to learn embedded representations of lncRNAs and miRNAs from the heterogeneous network, and construct the ensemble models using two ensemble strategies. For the former, we consider individual graph embedding based models as base predictors and integrate their predictions, and develop a method, named GEEL-PI. For the latter, we construct a deep attention neural network (DANN) to integrate various graph embeddings, and present an ensemble method, named GEEL-FI. The experimental results demonstrate both GEEL-PI and GEEL-FI outperform other state-of-the-art methods. The effectiveness of two ensemble strategies is validated by further experiments. Moreover, the case studies show that GEEL-PI and GEEL-FI can find novel lncRNA-miRNA associations. Conclusion The study reveals that graph embedding and ensemble learning based method is efficient for integrating heterogeneous information derived from lncRNA-miRNA interaction network and can achieve better performance on LMI prediction task. In conclusion, GEEL-PI and GEEL-FI are promising for lncRNA-miRNA interaction prediction.

Drug-target Interaction Prediction by Metapath2vec Node Embedding in Heterogeneous Network of Interactions

2020 ◽  
Vol 29 (01) ◽  
pp. 2050001
Author(s):  
Mina Samizadeh ◽  
Behrouz Minaei-Bidgoli
Keyword(s):  
Drug Development ◽  
Heterogeneous Network ◽  
Drug Target ◽  
Network Inference ◽  
Interaction Network ◽  
Ensemble Methods ◽  
New Drugs ◽  
Molecular Entity ◽  
Heterogeneous Interaction ◽  
Scale Down

Drug discovery is a complicated, time-consuming and expensive process. The cost for each new molecular entity (NME) is estimated at $1.8 billion. Furthermore, for a new drug to be FDA approved it often takes nearly a decade and approximately 20 new drugs being approved by the US Food and Drug Administration (FDA) each year. Accurately predicting drug-target interactions (DTIs) by computational methods is an important area of drug research, which brings about a broad prospect for fast and low-risk drug development. By accurate prediction of drugs and targets interactions scientists can scale-down huge experimental space and reduce the costs and help to faster drug development as well as predicting the side effects and potential function of new drugs. Many approaches have been taken by researchers to solve DTI problem and enhance the accuracy of methods. State-of-the-art approaches are based on various techniques, such as deep learning methods-like stacked auto-encoder-, matrix factorization, network inference, and ensemble methods. In this work, we have taken a new approach based on node embedding in a heterogeneous interaction network to obtain the representation of each node in the interaction network and then use a binary classifier such as logistic regression to solve this prominent problem in the pharmaceutical industry. Most introduced network-based methods use a homogeneous network of interactions as their input data whereas in the real word problem there exist other informative networks to help to enhance the prediction and by considering the homogeneous networks we lose some precious network information. Hence, in this work, we have tried to work on the heterogeneous network and have improved the accuracy of methods in comparison to baseline methods.

Dysregulation of HOX as a Potential Therapeutic Target in Breast Cancer

2020 ◽  
Vol 27 ◽  
Author(s):  
Ji-Yeon Lee ◽  
Myoung Hee Kim
Keyword(s):  
Breast Cancer ◽  
Hox Genes ◽  
Therapeutic Potential ◽  
Expression Patterns ◽  
Genome Structure ◽  
Control Cell ◽  
Three Dimensional ◽  
Cellular Processes ◽  
Hox Protein

: HOX genes belong to the highly conserved homeobox superfamily, responsible for the regulation of various cellular processes that control cell homeostasis, from embryogenesis to carcinogenesis. The abnormal expression of HOX genes is observed in various cancers, including breast cancer; they act as oncogenes or as suppressors of cancer, according to context. In this review, we analyze HOX gene expression patterns in breast cancer and examine their relationship, based on the three-dimensional genome structure of the HOX locus. The presence of non-coding RNAs, embedded within the HOX cluster, and the role of these molecules in breast cancer have been reviewed. We further evaluate the characteristic activity of HOX protein in breast cancer and its therapeutic potential.

scholarly journals Longitudinal stability of urinary extracellular vesicle protein patterns within and between individuals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Leyla A. Erozenci ◽  
Sander R. Piersma ◽  
Thang V. Pham ◽  
Irene V. Bijnsdorp ◽  
Connie R. Jimenez
Keyword(s):  
Expression Patterns ◽  
Interaction Network ◽  
Extracellular Vesicle ◽  
Protein Signaling ◽  
Protein Patterns ◽  
Specific Expression ◽  
Non Invasive ◽  
Data Independent Acquisition ◽  
Time Period ◽  
Using Data

AbstractThe protein content of urinary extracellular vesicles (EVs) is considered to be an attractive non-invasive biomarker source. However, little is known about the consistency and variability of urinary EV proteins within and between individuals over a longer time-period. Here, we evaluated the stability of the urinary EV proteomes of 8 healthy individuals at 9 timepoints over 6 months using data-independent-acquisition mass spectrometry. The 1802 identified proteins had a high correlation amongst all samples, with 40% of the proteome detected in every sample and 90% detected in more than 1 individual at all timepoints. Unsupervised analysis of top 10% most variable proteins yielded person-specific profiles. The core EV-protein-interaction network of 516 proteins detected in all measured samples revealed sub-clusters involved in the biological processes of G-protein signaling, cytoskeletal transport, cellular energy metabolism and immunity. Furthermore, gender-specific expression patterns were detected in the urinary EV proteome. Our findings indicate that the urinary EV proteome is stable in longitudinal samples of healthy subjects over a prolonged time-period, further underscoring its potential for reliable non-invasive diagnostic/prognostic biomarkers.

scholarly journals Genome-wide identification of the GATA transcription factor family and their expression patterns under temperature and salt stress in Aspergillus oryzae

AMB Express ◽  
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chunmiao Jiang ◽  
Gongbo Lv ◽  
Jinxin Ge ◽  
Bin He ◽  
Zhe Zhang ◽  
...  
Keyword(s):  
Salt Stress ◽  
Expression Patterns ◽  
Interaction Network ◽  
Protein Protein Interaction ◽  
Genome Wide ◽  
Gata Transcription Factor ◽  
Starting Point ◽  
Evolutionary Features ◽  
First Time

AbstractGATA transcription factors (TFs) are involved in the regulation of growth processes and various environmental stresses. Although GATA TFs involved in abiotic stress in plants and some fungi have been analyzed, information regarding GATA TFs in Aspergillusoryzae is extremely poor. In this study, we identified and functionally characterized seven GATA proteins from A.oryzae 3.042 genome, including a novel AoSnf5 GATA TF with 20-residue between the Cys-X2-Cys motifs which was found in Aspergillus GATA TFs for the first time. Phylogenetic analysis indicated that these seven A. oryzae GATA TFs could be classified into six subgroups. Analysis of conserved motifs demonstrated that Aspergillus GATA TFs with similar motif compositions clustered in one subgroup, suggesting that they might possess similar genetic functions, further confirming the accuracy of the phylogenetic relationship. Furthermore, the expression patterns of seven A.oryzae GATA TFs under temperature and salt stresses indicated that A. oryzae GATA TFs were mainly responsive to high temperature and high salt stress. The protein–protein interaction network of A.oryzae GATA TFs revealed certain potentially interacting proteins. The comprehensive analysis of A. oryzae GATA TFs will be beneficial for understanding their biological function and evolutionary features and provide an important starting point to further understand the role of GATA TFs in the regulation of distinct environmental conditions in A.oryzae.

The Expression of Sel1L and Tan-1 in Normal and Neoplastic Cells

2000 ◽  
Vol 15 (1) ◽  
pp. 26-32 ◽  
Author(s):  
M. Cattaneo ◽  
R. Orlandi ◽  
C. Ronchini ◽  
P. Granelli ◽  
G. Malferrari ◽  
...  
Keyword(s):  
Cell Function ◽  
Sequence Similarity ◽  
Expression Patterns ◽  
Negative Regulator ◽  
Chromosomal Mapping ◽  
Normal Adult ◽  
Neoplastic Cells ◽  
C Elegans ◽  
Pancreatic Cancers ◽  
Almost All

We have previously reported on the isolation and chromosomal mapping of a novel human gene (SEL1L), which shows sequence similarity to sel-1, an extragenic suppressor of C. elegans. sel-1 functions as a negative regulator of lin-12 activity, the latter being implicated in the control of diverse cellular differentiation events. In the present study we compare the expression patterns of SEL1L and TAN-1, the human ortholog of lin-12 in normal and neoplastic cells. We found that, whereas both genes are expressed in fetal tissues at similar levels, they are differentially expressed in normal adult and neoplastic cells. In normal adult cells SEL1L is generally present at very low levels; only in the cells of the pancreas does it show maximum expression. By contrast, SEL1L is generally well represented in most neoplastic cells but not in those of pancreatic and gastric carcinomas, where transcription is either downregulated or completely repressed. TAN-1 on the other hand is well represented in almost all normal and neoplastic cells, with very few exceptions. Our observations suggest that SEL1L is presumably implicated in pancreatic and gastric carcinogenesis and that, along with TAN-1, it is very important for normal cell function. Alterations in the expression of SEL1L may be used as a prognostic marker for gastric and pancreatic cancers.

pha-4 is Ce-fkh-1, a fork head/HNF-3alpha, beta, gamma homolog that functions in organogenesis of the C. elegans pharynx

Development ◽  
1998 ◽  
Vol 125 (12) ◽  
pp. 2171-2180 ◽  
Author(s):  
J.M. Kalb ◽  
K.K. Lau ◽  
B. Goszczynski ◽  
T. Fukushige ◽  
D. Moons ◽  
...  
Keyword(s):  
Early Stage ◽  
Sequence Similarity ◽  
Expression Patterns ◽  
Ectopic Expression ◽  
Specific Gene ◽  
Gata Factor ◽  
Enhancer Element ◽  
C Elegans ◽  
Fork Head ◽  
Organ Identity

The C. elegans Ce-fkh-1 gene has been cloned on the basis of its sequence similarity to the winged-helix DNA binding domain of the Drosophila fork head and mammalian HNF-3alpha, beta, gamma genes, and mutations in the zygotically active pha-4 gene have been shown to block formation of the pharynx (and rectum) at an early stage in embryogenesis. In the present paper, we show that Ce-fkh-1 and pha-4 are the same gene. We show that PHA-4 protein is present in nuclei of essentially all pharyngeal cells, of all five cell types. PHA-4 protein first appears close to the point at which a cell lineage will produce only pharyngeal cells, independently of cell type. We show that PHA-4 binds directly to a ‘pan-pharyngeal enhancer element’ previously identified in the promoter of the pharyngeal myosin myo-2 gene; in transgenic embryos, ectopic PHA-4 activates ectopic myo-2 expression. We also show that ectopic PHA-4 can activate ectopic expression of the ceh-22 gene, a pharyngeal-specific NK-2-type homeodomain protein previously shown to bind a muscle-specific enhancer near the PHA-4 binding site in the myo-2 promoter. We propose that it is the combination of pha-4 and regulatory molecules such as ceh-22 that produces the specific gene expression patterns during pharynx development. Overall, pha-4 can be described as an ‘organ identity factor’, completely necessary for organ formation, present in all cells of the organ from the earliest stages, capable of integrating upstream developmental pathways (in this case, the two distinct pathways that produce the anterior and posterior pharynx) and participating directly in the transcriptional regulation of organ specific genes. Finally, we note that the distribution of PHA-4 protein in C. elegans embryos is remarkably similar to the distribution of the fork head protein in Drosophila embryos: high levels in the foregut/pharynx and hindgut/rectum; low levels in the gut proper. Moreover, we show that pha-4 expression in the C. elegans gut is regulated by elt-2, a C. elegans gut-specific GATA-factor and possible homolog of the Drosophila gene serpent, which influences fork head expression in the fly gut. Overall, our results provide evidence for a highly conserved pathway regulating formation of the digestive tract in all (triploblastic) metazoa.

scholarly journals Transcriptomic Analysis Reveals Candidate Genes Responsive to Sclerotinia scleroterum and Cloning of the Ss-Inducible Chitinase Genes in Morus laevigata

2020 ◽  
Vol 21 (21) ◽  
pp. 8358
Author(s):  
Huanhuan Jiang ◽  
Xiaoyun Jin ◽  
Xiaofeng Shi ◽  
Yufei Xue ◽  
Jiayi Jiang ◽  
...  
Keyword(s):  
Candidate Genes ◽  
Molecular Basis ◽  
Expression Patterns ◽  
Interaction Network ◽  
Sclerotinia Stem Rot ◽  
Response Characteristics ◽  
Kegg Pathways ◽  
Cdna Sequences ◽  
Chitinase Genes ◽  
Morus Laevigata

Sclerotinia sclerotiorum (Ss) is a devastating fungal pathogen that causes Sclerotinia stem rot in rapeseed (Brassica napus), and is also detrimental to mulberry and many other crops. A wild mulberry germplasm, Morus laevigata, showed high resistance to Ss, but the molecular basis for the resistance is largely unknown. Here, the transcriptome response characteristics of M. laevigata to Ss infection were revealed by RNA-seq. A total of 833 differentially expressed genes (DEGs) were detected after the Ss inoculation in the leaf of M. laevigata. After the GO terms and KEGG pathways enrichment analyses, 42 resistance-related genes were selected as core candidates from the upregulated DEGs. Their expression patterns were detected in the roots, stems, leaves, flowers, and fruits of M. laevigata. Most of them (30/42) were specifically or mainly expressed in flowers, which was consistent with the fact that Ss mainly infects plants through floral organs, and indicated that Ss-resistance genes could be induced by pathogen inoculation on ectopic organs. After the Ss inoculation, these candidate genes were also induced in the two susceptible varieties of mulberry, but the responses of most of them were much slower with lower extents. Based on the expression patterns and functional annotation of the 42 candidate genes, we cloned the full-length gDNA and cDNA sequences of the Ss-inducible chitinase gene set (MlChi family). Phylogenetic tree construction, protein interaction network prediction, and gene expression analysis revealed their special roles in response to Ss infection. In prokaryotic expression, their protein products were all in the form of an inclusion body. Our results will help in the understanding of the molecular basis of Ss-resistance in M. laevigata, and the isolated MlChi genes are candidates for the improvement in plant Ss-resistance via biotechnology.

scholarly journals The expression of delta opioid receptor mRNA in adult male zebra finches (Taenopygia guttata)

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256599
Author(s):  
Pooja Parishar ◽  
Neha Sehgal ◽  
Soumya Iyengar
Keyword(s):  
Opioid Receptors ◽  
Sequence Similarity ◽  
Expression Patterns ◽  
Auditory Pathway ◽  
Zebra Finches ◽  
Endogenous Opioid System ◽  
Endogenous Opioid ◽  
High Sequence Similarity ◽  
Brain Functions ◽  
Song Control

The endogenous opioid system is evolutionarily conserved across reptiles, birds and mammals and is known to modulate varied brain functions such as learning, memory, cognition and reward. To date, most of the behavioral and anatomical studies in songbirds have mainly focused on μ-opioid receptors (ORs). Expression patterns of δ-ORs in zebra finches, a well-studied species of songbird have not yet been reported, possibly due to the high sequence similarity amongst different opioid receptors. In the present study, a specific riboprobe against the δ-OR mRNA was used to perform fluorescence in situ hybridization (FISH) on sections from the male zebra finch brain. We found that δ-OR mRNA was expressed in different parts of the pallium, basal ganglia, cerebellum and the hippocampus. Amongst the song control and auditory nuclei, HVC (abbreviation used as a formal name) and NIf (nucleus interfacialis nidopallii) strongly express δ-OR mRNA and stand out from the surrounding nidopallium. Whereas the expression of δ-OR mRNA is moderate in LMAN (lateral magnocellular nucleus of the anterior nidopallium), it is low in the MSt (medial striatum), Area X, DLM (dorsolateral nucleus of the medial thalamus), RA (robust nucleus of the arcopallium) of the song control circuit and Field L, Ov (nucleus ovoidalis) and MLd (nucleus mesencephalicus lateralis, pars dorsalis) of the auditory pathway. Our results suggest that δ-ORs may be involved in modulating singing, song learning as well as spatial learning in zebra finches.

A NEW ENSEMBLE LEARNING ALGORITHM USING REGIONAL CLASSIFIERS

2013 ◽  
Vol 22 (04) ◽  
pp. 1350025 ◽  
Author(s):  
BYUNGWOO LEE ◽  
SUNGHA CHOI ◽  
BYONGHWA OH ◽  
JIHOON YANG ◽  
SUNGYONG PARK
Keyword(s):  
Ensemble Learning ◽  
Learning Algorithm ◽  
Ensemble Methods ◽  
Feature Space ◽  
Training Data ◽  
Learning Method ◽  
Weighted Voting ◽  
Ensemble Learning Algorithm ◽  
Voting Scheme ◽  
Base Learner

We present a new ensemble learning method that employs a set of regional classifiers, each of which learns to handle a subset of the training data. We split the training data and generate classifiers for different regions in the feature space. When classifying an instance, we apply a weighted voting scheme among the classifiers that include the instance in their region. We used 11 datasets to compare the performance of our new ensemble method with that of single classifiers as well as other ensemble methods such as RBE, bagging and Adaboost. As a result, we found that the performance of our method is comparable to that of Adaboost and bagging when the base learner is C4.5. In the remaining cases, our method outperformed other approaches.

Sign in / Sign up

Export Citation Format

Share Document