scholarly journals Predicting Long non-coding RNAs through feature ensemble learning

BMC Genomics ◽  
2020 ◽  
Vol 21 (S13) ◽  
Author(s):  
Yanzhen Xu ◽  
Xiaohan Zhao ◽  
Shuai Liu ◽  
Wen Zhang
Keyword(s):  
Learning Strategies ◽  
Ensemble Learning ◽  
Feature Space ◽  
Prediction Methods ◽  
General Sequence ◽  
Sequencing Technologies ◽  
Different Types ◽  
Non Coding Rnas ◽  
Deep Learning Model ◽  
Fold Cross Validation

Abstract Background Many transcripts have been generated due to the development of sequencing technologies, and lncRNA is an important type of transcript. Predicting lncRNAs from transcripts is a challenging and important task. Traditional experimental lncRNA prediction methods are time-consuming and labor-intensive. Efficient computational methods for lncRNA prediction are in demand. Results In this paper, we propose two lncRNA prediction methods based on feature ensemble learning strategies named LncPred-IEL and LncPred-ANEL. Specifically, we encode sequences into six different types of features including transcript-specified features and general sequence-derived features. Then we consider two feature ensemble strategies to utilize and integrate the information in different feature types, the iterative ensemble learning (IEL) and the attention network ensemble learning (ANEL). IEL employs a supervised iterative way to ensemble base predictors built on six different types of features. ANEL introduces an attention mechanism-based deep learning model to ensemble features by adaptively learning the weight of individual feature types. Experiments demonstrate that both LncPred-IEL and LncPred-ANEL can effectively separate lncRNAs and other transcripts in feature space. Moreover, comparison experiments demonstrate that LncPred-IEL and LncPred-ANEL outperform several state-of-the-art methods when evaluated by 5-fold cross-validation. Both methods have good performances in cross-species lncRNA prediction. Conclusions LncPred-IEL and LncPred-ANEL are promising lncRNA prediction tools that can effectively utilize and integrate the information in different types of features.

Predicting the interaction biomolecule types for lncRNA: an ensemble deep learning approach

2020 ◽  
Author(s):  
Yu Zhang ◽  
Cangzhi Jia ◽  
Chee Keong Kwoh
Keyword(s):  
Deep Learning ◽  
Molecular Mechanisms ◽  
Operating Characteristic ◽  
Cross Validation ◽  
Characteristic Curve ◽  
Published Data ◽  
Different Types ◽  
Precision Recall Curve ◽  
Deep Learning Model ◽  
Fold Cross Validation

Abstract Long noncoding RNAs (lncRNAs) play significant roles in various physiological and pathological processes via their interactions with biomolecules like DNA, RNA and protein. The existing in silico methods used for predicting the functions of lncRNA mainly rely on calculating the similarity of lncRNA or investigating whether an lncRNA can interact with a specific biomolecule or disease. In this work, we explored the functions of lncRNA from a different perspective: we presented a tool for predicting the interaction biomolecule type for a given lncRNA. For this purpose, we first investigated the main molecular mechanisms of the interactions of lncRNA–RNA, lncRNA–protein and lncRNA–DNA. Then, we developed an ensemble deep learning model: lncIBTP (lncRNA Interaction Biomolecule Type Prediction). This model predicted the interactions between lncRNA and different types of biomolecules. On the 5-fold cross-validation, the lncIBTP achieves average values of 0.7042 in accuracy, 0.7903 and 0.6421 in macro-average area under receiver operating characteristic curve and precision–recall curve, respectively, which illustrates the model effectiveness. Besides, based on the analysis of the collected published data and prediction results, we hypothesized that the characteristics of lncRNAs that interacted with DNA may be different from those that interacted with only RNA.

scholarly journals Non-Coding RNAs and their Integrated Networks

2019 ◽  
Vol 16 (3) ◽  
Author(s):  
Peijing Zhang ◽  
Wenyi Wu ◽  
Qi Chen ◽  
Ming Chen
Keyword(s):  
Gene Regulatory Networks ◽  
Regulatory Networks ◽  
Protein Coding ◽  
Integrated Networks ◽  
Cellular Processes ◽  
Sequencing Technologies ◽  
Different Types ◽  
Gene Regulatory ◽  
Non Coding Rnas ◽  
Eukaryotic Genomes

AbstractEukaryotic genomes are pervasively transcribed. Besides protein-coding RNAs, there are different types of non-coding RNAs that modulate complex molecular and cellular processes. RNA sequencing technologies and bioinformatics methods greatly promoted the study of ncRNAs, which revealed ncRNAs’ essential roles in diverse aspects of biological functions. As important key players in gene regulatory networks, ncRNAs work with other biomolecules, including coding and non-coding RNAs, DNAs and proteins. In this review, we discuss the distinct types of ncRNAs, including housekeeping ncRNAs and regulatory ncRNAs, their versatile functions and interactions, transcription, translation, and modification. Moreover, we summarize the integrated networks of ncRNA interactions, providing a comprehensive landscape of ncRNAs regulatory roles.

MicroRNAs and their role in hematological malignant diseases

2012 ◽  
Vol 153 (52) ◽  
pp. 2051-2059 ◽  
Author(s):  
Zsuzsanna Gaál ◽  
Éva Oláh
Keyword(s):  
Target Genes ◽  
Lymphoblastic Leukemia ◽  
Cancer Tissue ◽  
Altered Expression ◽  
Diagnosis And Prognosis ◽  
Oncologic Patients ◽  
Different Types ◽  
Non Coding Rnas ◽  
Success Of Treatment ◽  
Posttranscriptional Level

MicroRNAs are a class of small non-coding RNAs regulating gene expression at posttranscriptional level. Their target genes include numerous regulators of cell cycle, cell proliferation as well as apoptosis. Therefore, they are implicated in the initiation and progression of cancer, tissue invasion and metastasis formation as well. MicroRNA profiles supply much information about both the origin and the differentiation state of tumours. MicroRNAs also have a key role during haemopoiesis. An altered expression level of those have often been observed in different types of leukemia. There are successful attempts to apply microRNAs in the diagnosis and prognosis of acute lymphoblastic leukemia and acute myeloid leukemia. Measurement of the expression levels may help to predict the success of treatment with different kinds of chemotherapeutic drugs. MicroRNAs are also regarded as promising therapeutic targets, and can contribute to a more personalized therapeutic approach in haemato-oncologic patients. Orv. Hetil., 2012, 153, 2051–2059.

scholarly journals Investigation of long non-coding RNAs as regulatory players of grapevine response to powdery and downy mildew infection

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Garima Bhatia ◽  
Santosh K. Upadhyay ◽  
Anuradha Upadhyay ◽  
Kashmir Singh
Keyword(s):  
Downy Mildew ◽  
Plasmopara Viticola ◽  
Defense Responses ◽  
Protein Coding ◽  
Functional Roles ◽  
Real Time Quantitative Pcr ◽  
Transcriptional Reprogramming ◽  
Sequencing Technologies ◽  
Non Coding Rnas ◽  
Fungal Phytopathogens

Abstract Background Long non-coding RNAs (lncRNAs) are regulatory transcripts of length > 200 nt. Owing to the rapidly progressing RNA-sequencing technologies, lncRNAs are emerging as considerable nodes in the plant antifungal defense networks. Therefore, we investigated their role in Vitis vinifera (grapevine) in response to obligate biotrophic fungal phytopathogens, Erysiphe necator (powdery mildew, PM) and Plasmopara viticola (downy mildew, DM), which impose huge agro-economic burden on grape-growers worldwide. Results Using computational approach based on RNA-seq data, 71 PM- and 83 DM-responsive V. vinifera lncRNAs were identified and comprehensively examined for their putative functional roles in plant defense response. V. vinifera protein coding sequences (CDS) were also profiled based on expression levels, and 1037 PM-responsive and 670 DM-responsive CDS were identified. Next, co-expression analysis-based functional annotation revealed their association with gene ontology (GO) terms for ‘response to stress’, ‘response to biotic stimulus’, ‘immune system process’, etc. Further investigation based on analysis of domains, enzyme classification, pathways enrichment, transcription factors (TFs), interactions with microRNAs (miRNAs), and real-time quantitative PCR of lncRNAs and co-expressing CDS pairs suggested their involvement in modulation of basal and specific defense responses such as: Ca2+-dependent signaling, cell wall reinforcement, reactive oxygen species metabolism, pathogenesis related proteins accumulation, phytohormonal signal transduction, and secondary metabolism. Conclusions Overall, the identified lncRNAs provide insights into the underlying intricacy of grapevine transcriptional reprogramming/post-transcriptional regulation to delay or seize the living cell-dependent pathogen growth. Therefore, in addition to defense-responsive genes such as TFs, the identified lncRNAs can be further examined and leveraged to candidates for biotechnological improvement/breeding to enhance fungal stress resistance in this susceptible fruit crop of economic and nutritional importance.

scholarly journals Ensemble-Based Out-of-Distribution Detection

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 567
Author(s):  
Donghun Yang ◽  
Kien Mai Mai Ngoc ◽  
Iksoo Shin ◽  
Kyong-Ha Lee ◽  
Myunggwon Hwang
Keyword(s):  
Detection Method ◽  
State Of The Art ◽  
Metric Learning ◽  
Feature Space ◽  
Confidence Score ◽  
Distance Metric Learning ◽  
Current State ◽  
Overall Performance ◽  
Deep Learning Model

To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on the Mahalanobis distance in a feature space. Although it outperformed the previous approaches, the results were sensitive to the quality of the trained model and the dataset complexity. Herein, we propose a novel OOD detection method that can train more efficient feature space for OOD detection. The proposed method uses an ensemble of the features trained using the softmax-based classifier and the network based on distance metric learning (DML). Through the complementary interaction of these two networks, the trained feature space has a more clumped distribution and can fit well on the Gaussian distribution by class. Therefore, OOD data can be efficiently detected by setting a threshold in the trained feature space. To evaluate the proposed method, we applied our method to various combinations of image datasets. The results show that the overall performance of the proposed approach is superior to those of other methods, including the state-of-the-art approach, on any combination of datasets.

scholarly journals The Crosstalk Between Long Non-Coding RNAs and Various Types of Death in Cancer Cells

2021 ◽  
Vol 20 ◽  
pp. 153303382110330
Author(s):  
Wenwen Tang ◽  
Shaomi Zhu ◽  
Xin Liang ◽  
Chi Liu ◽  
Linjiang Song
Keyword(s):  
Cell Death ◽  
Cancer Cell ◽  
Causes Of Death ◽  
Vital Role ◽  
Cancer Cell Proliferation ◽  
Biological Targets ◽  
Cancer Cell Death ◽  
Different Types ◽  
Non Coding Rnas ◽  
Tumor Death

With the increasing aging population, cancer has become one of the leading causes of death worldwide, and the number of cancer cases and deaths is only anticipated to grow further. Long non-coding RNAs (lncRNAs), which are closely associated with the expression level of downstream genes and various types of bioactivity, are regarded as one of the key regulators of cancer cell proliferation and death. Cell death, including apoptosis, necrosis, autophagy, pyroptosis, and ferroptosis, plays a vital role in the progression of cancer. A better understanding of the regulatory relationships between lncRNAs and these various types of cancer cell death is therefore urgently required. The occurrence and development of tumors can be controlled by increasing or decreasing the expression of lncRNAs, a method which confers broad prospects for cancer treatment. Therefore, it is urgent for us to understand the influence of lncRNAs on the development of different modes of tumor death, and to evaluate whether lncRNAs have the potential to be used as biological targets for inducing cell death and predicting prognosis and recurrence of chemotherapy. The purpose of this review is to provide an overview of the various forms of cancer cell death, including apoptosis, necrosis, autophagy, pyroptosis, and ferroptosis, and to describe the mechanisms of different types of cancer cell death that are regulated by lncRNAs in order to explore potential targets for cancer therapy.

scholarly journals The Role of Non-Coding RNAs in the Regulation of the Proto-Oncogene MYC in Different Types of Cancer

Biomedicines ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 921
Author(s):  
Ekaterina Mikhailovna Stasevich ◽  
Matvey Mikhailovich Murashko ◽  
Lyudmila Sergeevna Zinevich ◽  
Denis Eriksonovich Demin ◽  
Anton Markovich Schwartz
Keyword(s):  
Malignant Tumors ◽  
Current Data ◽  
Cellular Processes ◽  
Cell Divisions ◽  
Specific Tumor ◽  
Different Types ◽  
Myc Gene ◽  
Non Coding Rnas ◽  
Tumor Types

Alterations in the expression level of the MYC gene are often found in the cells of various malignant tumors. Overexpressed MYC has been shown to stimulate the main processes of oncogenesis: uncontrolled growth, unlimited cell divisions, avoidance of apoptosis and immune response, changes in cellular metabolism, genomic instability, metastasis, and angiogenesis. Thus, controlling the expression of MYC is considered as an approach for targeted cancer treatment. Since c-Myc is also a crucial regulator of many cellular processes in healthy cells, it is necessary to find ways for selective regulation of MYC expression in tumor cells. Many recent studies have demonstrated that non-coding RNAs play an important role in the regulation of the transcription and translation of this gene and some RNAs directly interact with the c-Myc protein, affecting its stability. In this review, we summarize current data on the regulation of MYC by various non-coding RNAs that can potentially be targeted in specific tumor types.

scholarly journals Epigenomic regulation of heart failure: integrating histone marks, long noncoding RNAs, and chromatin architecture

F1000Research ◽  
2018 ◽  
Vol 7 ◽  
pp. 1713 ◽  
Author(s):  
Timothy A. McKinsey ◽  
Thomas M. Vondriska ◽  
Yibin Wang
Keyword(s):  
Heart Failure ◽  
Therapeutic Potential ◽  
Noncoding Rnas ◽  
Loss Of Function ◽  
Sequencing Technologies ◽  
Recent Developments ◽  
Non Coding Rnas ◽  
Epigenomic Regulation ◽  
Generation Sequencing ◽  
Epigenetic Processes

Epigenetic processes are known to have powerful roles in organ development across biology. It has recently been found that some of the chromatin modulatory machinery essential for proper development plays a previously unappreciated role in the pathogenesis of cardiac disease in adults. Investigations using genetic and pharmacologic gain- and loss-of-function approaches have interrogated the function of distinct epigenetic regulators, while the increased deployment of the suite of next-generation sequencing technologies have fundamentally altered our understanding of the genomic targets of these chromatin modifiers. Here, we review recent developments in basic and translational research that have provided tantalizing clues that may be used to unlock the therapeutic potential of the epigenome in heart failure. Additionally, we provide a hypothesis to explain how signal-induced crosstalk between histone tail modifications and long non-coding RNAs triggers chromatin architectural remodeling and culminates in cardiac hypertrophy and fibrosis.

scholarly journals Prediction of Merchandise Sales on E-Commerce Platforms Based on Data Mining and Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Xiaoting Yin ◽  
Xiaosha Tao
Keyword(s):  
Data Mining ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Research Process ◽  
Deep Learning Algorithm ◽  
Sales Prediction ◽  
Different Types ◽  
Online Business ◽  
Product Sales ◽  
Deep Learning Model

Online business has grown exponentially during the last decade, and the industries are focusing on online business more than before. However, just setting up an online store and starting selling might not work. Different machine learning and data mining techniques are needed to know the users’ preferences and know what would be best for business. According to the decision-making needs of online product sales, combined with the influencing factors of online product sales in various industries and the advantages of deep learning algorithm, this paper constructs a sales prediction model suitable for online products and focuses on evaluating the adaptability of the model in different types of online products. In the research process, the full connection model is compared with the training results of CNN, which proves the accuracy and generalization ability of CNN model. By selecting the non-deep learning model as the comparison baseline, the performance advantages of CNN model under different categories of products are proved. In addition, the experiment concludes that the unsupervised pretrained CNN model is more effective and adaptable in sales forecasting.

scholarly journals Opinion mining using combinational approach for different domains

2019 ◽  
Vol 9 (4) ◽  
pp. 3307
Author(s):  
Jyoti Sandesh Deshmukh ◽  
Amiya Kumar Tripathy ◽  
Dilendra Hiran
Keyword(s):  
Maximum Entropy ◽  
Cross Validation ◽  
Opinion Mining ◽  
Domain Adaptation ◽  
Online Reviews ◽  
Research Area ◽  
Source Domain ◽  
Different Types ◽  
Fold Cross Validation ◽  
Target Data

An increase in use of web produces large content of information about products. Online reviews are used to make decision by peoples. Opinion mining is vast research area in which different types of reviews are analyzed. Several issues are existing in this area. Domain adaptation is emerging issue in opinion mining. Labling of data for every domain is time consuming and costly task. Hence the need arises for model that train one domain and applied it on other domain reducing cost aswell as time. This is called domain adaptation which is addressed in this paper. Using maximum entropy and clustering technique source domains data is trained. Trained data from source domain is applied on target data to labeling purpose A result shows moderate accuracy for 5 fold cross validation and combination of source domains for Blitzer et al (2007) multi domain product dataset.

Sign in / Sign up

Export Citation Format

Share Document