lncRNA-protein Interactions Research Articles

Quantitative proteomics reveals that long non-coding RNA MALAT1 interacts with DBC1 to regulate p53 acetylation

Metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) is a broadly expressed lncRNA involved in many aspects of cellular processes. To further delineate the underlying molecular mechanism, we employed a high-throughput strategy to characterize the interacting proteins of MALAT1 by combining RNA pull-down, quantitative proteomics, bioinformatics, and experimental validation. Our approach identified 127 potential MALAT1-interacting proteins and established a highly connected MALAT1 interactome network consisting of 788 connections. Gene ontology annotation and network analysis showed that MALAT1 was highly involved in five biological processes: RNA processing; gene transcription; ribosomal proteins; protein degradation; and metabolism regulation. The interaction between MALAT1 and depleted in breast cancer 1 (DBC1) was validated using RNA pull-down and RNA immunoprecipitation. Further mechanistic studies reveal that MALAT1 binding competes with the interaction between sirtuin1 (SIRT1) and DBC1, which then releases SIRT1 and enhances its deacetylation activity. Consequently, the deacetylation of p53 reduces the transcription of a spectrum of its downstream target genes, promotes cell proliferation and inhibits cell apoptosis. Our results uncover a novel mechanism by which MALAT1 regulates the activity of p53 through the lncRNA–protein interaction.

Prediction of lncRNA-protein interactions using HeteSim scores based on heterogeneous networks

Massive studies have indicated that long non-coding RNAs (lncRNAs) are critical for the regulation of cellular biological processes by binding with RNA-related proteins. However, only a few experimentally supported lncRNA-protein associations have been reported. Existing network-based methods are typically focused on intrinsic features of lncRNA and protein but ignore the information implicit in the topologies of biological networks associated with lncRNAs. Considering the limitations in previous methods, we propose PLPIHS, an effective computational method for Predicting lncRNA-Protein Interactions using HeteSim Scores. PLPIHS uses the HeteSim measure to calculate the relatedness score for each lncRNA-protein pair in the heterogeneous network, which consists of lncRNA-lncRNA similarity network, lncRNA-protein association network and protein-protein interaction network. An SVM classifier to predict lncRNA-protein interactions is built with the HeteSim scores. The results show that PLPIHS performs significantly better than the existing state-of-the-art approaches and achieves an AUC score of 0.97 in the leave-one-out validation test. We also compare the performances of networks with different connectivity density and find that PLPIHS performs well across all the networks. Furthermore, we use the proposed method to identify the related proteins for lncRNA MALAT1. Highly-ranked proteins are verified by the biological studies and demonstrate the effectiveness of our method.

Proteomic Analysis of Chicken Skeletal Muscle during Embryonic Development.

Embryonic growth and development of skeletal muscle is a major determinant of muscle mass, and has a significant effect on meat production in chicken. To assess the protein expression profiles during embryonic skeletal muscle development, we performed a proteomics analysis using isobaric tags for relative and absolute quantification (iTRAQ) in leg muscle tissues of female Xinghua chicken at embryonic age (E) 11, E16, and 1-day post hatch (D1). We identified 3,240 proteins in chicken embryonic muscle and 491 of them were differentially expressed (fold change ≥ 1.5 or ≤ 0.666 and p < 0.05). There were 19 up- and 32 down-regulated proteins in E11 vs. E16 group, 238 up- and 227 down-regulated proteins in E11 vs. D1 group, and 13 up- and 5 down-regulated proteins in E16 vs. D1 group. Protein interaction network analyses indicated that these differentially expressed proteins were mainly involved in the pathway of protein synthesis, muscle contraction, and oxidative phosphorylation. Integrative analysis of proteome and our previous transcriptome data found 189 differentially expressed proteins that correlated with their mRNA level. The interactions between these proteins were also involved in muscle contraction and oxidative phosphorylation pathways. The lncRNA-protein interaction network found four proteins DMD, MYL3, TNNI2, and TNNT3 that are all involved in muscle contraction and may be lncRNA regulated. These results provide several candidate genes for further investigation into the molecular mechanisms of chicken embryonic muscle development, and enable us to better understanding their regulation networks and biochemical pathways.

Abstract P1-04-05: RNA immunoprecipitation reveals lncRNA-protein interactions in basal-like breast cancer

Abstract Interactions between long non-coding RNAs (lncRNAs) and proteins contribute to the epigenetic regulation of gene expression, and defects in such interactions have been implicated in several diseases, including cancer. Basal-like breast cancer accounts for approximately 15% of all breast cancer and is a major clinical problem given its poor survival and lack of responsiveness to targeted breast cancer treatments. DNA methylation is non-random and is much more pronounced in basal-like breast cancer (BLBC) compared to other molecular subtypes of breast cancer, raising the possibility that hypermethylation could be important in the genesis of BLBCs. LncRNAs are aberrantly expressed in multiple subtypes of breast cancer, including BLBC, and are considered to have significant prognostic potential. In order to explore the potential roles of DNA methylation and lncRNAs in BLBC, we investigated lncRNA-protein interactions using bioinformatics and molecular techniques, focusing on proteins that actively perform DNA methylation - the DNA methyltransferase (DNMT) family. Our novel bioinformatic methods revealed that BLBC may be sub-classified according to methylation profile in a way that could predict disease survival. We then identified candidate lncRNAs that are over-expressed in BLBC and statistically predicted to interact with DNMT proteins. Using RNA immunoprecipitation of BLBC cell lines, we have identified potential lncRNA-protein interactions that may be involved in epigenetic remodelling in BLBC. The role of these lncRNAs in epigenetic gene regulation and BLBC is currently being explored. Citation Format: Northwood K, Saunus J, Milevskiy M, Lakhani S, Brown M. RNA immunoprecipitation reveals lncRNA-protein interactions in basal-like breast cancer [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P1-04-05.

Comprehensive Analysis of lncRNA and mRNA Expression Profiles in Lung Cancer.

Lung cancer is one of the most common malignancies across the world. Long noncoding RNAs (lncRNAs) play an important role in the pathology. This study was to compare the lncRNA and mRNA of lung cancer. The aim of this study was to compare the lncRNA and mRNA expression profiles, their related biological functions, and pathways in lung cancer. Human lung cancer mRNA expression datasets were searched and downloaded from NCBI-GEO. LncRNA expression profiles in lung cancer were detected by the Agilent Human LncRNA Microarray V3.0. Differential expression analysis was conducted between cases and controls in mRNA and lncRNA. The starBase web server v2.0 was used to decipher lncRNA-protein interactions. DAVID Bioinformatics Resources 6.7 was used to perform GO Biological Processes and KEGG pathway enrichment analysis of these dysregulated mRNA and lncRNA target genes. The study showed that differentially expressed lncRNA target genes included almost all of the differential expression genes from mRNA. Furthermore, these dysregulated lncRNAs reflected more comprehensive impairment in functional enrichment than dysregulated mRNAs. In addition, five top downregulated lncRNAs had more remarkable fold changes than top downregulated mRNAs, especially FENDRR. Amount of lncRNAs and mRNAs were differentially expressed in lung cancer. The degrees of difference in lncRNAs were more than mRNAs. It may provide valuable help for an effective strategy in diagnosis and prevention.

LncRNA expression in the auditory forebrain during postnatal development

The biological processes governing brain development and maturation depend on complex patterns of gene and protein expression, which can be influenced by many factors. One of the most overlooked is the long noncoding class of RNAs (lncRNAs), which are known to play important regulatory roles in an array of biological processes. Little is known about the distribution of lncRNAs in the sensory systems of the brain, and how lncRNAs interact with other mechanisms to guide the development of these systems. In this study, we profiled lncRNA expression in the mouse auditory forebrain during postnatal development at time points before and after the onset of hearing (P7, P14, P21, adult). First, we generated lncRNA profiles of the primary auditory cortex (A1) and medial geniculate body (MG) at each age. Then, we determined the differential patterns of expression by brain region and age. These analyses revealed that the lncRNA expression profile was distinct between both brain regions and between each postnatal age, indicating spatial and temporal specificity during maturation of the auditory forebrain. Next, we explored potential interactions between functionally-related lncRNAs, protein coding RNAs (pcRNAs), and associated proteins. The maturational trajectories (P7 to adult) of many lncRNA – pcRNA pairs were highly correlated, and predictive analyses revealed that lncRNA-protein interactions tended to be strong. A user-friendly database was constructed to facilitate inspection of the expression levels and maturational trajectories for any lncRNA or pcRNA in the database. Overall, this study provides an in-depth summary of lncRNA expression in the developing auditory forebrain and a broad-based foundation for future exploration of lncRNA function during brain development.

IPMiner: hidden ncRNA-protein interaction sequential pattern mining with stacked autoencoder for accurate computational prediction.

BackgroundNon-coding RNAs (ncRNAs) play crucial roles in many biological processes, such as post-transcription of gene regulation. ncRNAs mainly function through interaction with RNA binding proteins (RBPs). To understand the function of a ncRNA, a fundamental step is to identify which protein is involved into its interaction. Therefore it is promising to computationally predict RBPs, where the major challenge is that the interaction pattern or motif is difficult to be found.ResultsIn this study, we propose a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling. One of the IPMiner’s typical merits is that it is able to mine the hidden sequential interaction patterns from sequence composition features of protein and RNA sequences using stacked autoencoder, and then the learned hidden features are fed into random forest models. Finally, stacked ensembling is used to integrate different predictors to further improve the prediction performance. The experimental results indicate that IPMiner achieves superior performance on the tested lncRNA-protein interaction dataset with an accuracy of 0.891, sensitivity of 0.939, specificity of 0.831, precision of 0.945 and Matthews correlation coefficient of 0.784, respectively. We further comprehensively investigate IPMiner on other RNA-protein interaction datasets, which yields better performance than the state-of-the-art methods, and the performance has an increase of over 20 % on some tested benchmarked datasets. In addition, we further apply IPMiner for large-scale prediction of ncRNA-protein network, that achieves promising prediction performance.ConclusionBy integrating deep neural network and stacked ensembling, from simple sequence composition features, IPMiner can automatically learn high-level abstraction features, which had strong discriminant ability for RNA-protein detection. IPMiner achieved high performance on our constructed lncRNA-protein benchmark dataset and other RNA-protein datasets. IPMiner tool is available at http://www.csbio.sjtu.edu.cn/bioinf/IPMiner.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-016-2931-8) contains supplementary material, which is available to authorized users.

Relevance search for predicting lncRNA–protein interactions based on heterogeneous network

lncRNA plays important roles in many biological and pathological processes. lncRNA–protein interaction is the most common way of lncRNA performing their functions. Thus, predicting lncRNA–protein interaction is very significant to understand the nature of lncRNA. Earlier methods to predict RNA–protein interaction always adopt classification algorithms using features extracted from RNA and protein themselves. But their performance is not good enough in lncRNA–protein interaction prediction because of lncRNA’s low conservation. In this paper, we try to use information implicit in the topologies of biological network associated with lncRNA to solve this problem. Firstly we construct a heterogeneous lncRNA–protein network which incorporate protein interaction information. We use an algorithm called HeteSim which can evaluate relevance between heterogeneous objects to perform relevance search in the lncRNA and protein heterogeneous network. The relevance search results are used to help the identification of lncRNA–protein interactions.

A text feature-based approach for literature mining of lncRNA–protein interactions

Long non-coding RNAs (lncRNAs) play important roles in regulating transcriptional and post-transcriptional levels. Currently, Knowledge of lncRNA and protein interactions (LPIs) is crucial for biomedical researches that are related to lncRNA. Many freshly discovered LPIs are stored in biomedical literature. With over one million new biomedical journal articles published every year, just keeping up with the novel finding requires automatically extracting information by text mining. To address this issue, we apply a text feature-based text mining approach to efficiently extract LPIs from biomedical literatures. Our approach consists of four steps. By employ natural language processing (NLP) technologies, this approach extracts text features from sentences that can precisely reflect the real LPIs. Our approach involves four steps including data collection, text pre-processing, structured representation, features extraction and training model and classification. The F-score performance of our approach achieves 79.5%, and the results indicate that the proposed approach can efficiently extract LPIs from biomedical literature.

Abstract A36: A systematic network-based approach to prioritizing lncRNA drivers in cancers

Abstract Introduction: Decades of efforts have been made to have a better understanding about the human genome, which encodes ~20,000 protein-coding genes as well as an astounding number of transcriptionally active noncoding RNAs. Among these noncoding RNAs, long-noncoding RNAs (lncRNAs) have been increasingly recognized to play essential roles in tumorigenesis, representing a new focus in cancer research. Analogous to the identification of protein-coding cancer driver genes, it is a crucial task in cancer research to identify lncRNA drivers and elucidate their functions in various cancer types. Methods: We first downloaded TCGA RNA-seq BAM files (&amp;gt;60TB) across 20 cancer types from the UCSC Cancer Genomic Hub (CGHub) and quantified the lncRNA expression based on GENCODE lncRNA annotation. To identify lncRNA drivers, we focused on identifying the functional relevant lncRNA-protein pairs through their expression profiling data. To prevent acquiring more false positives from conventional correlation analysis, we applied the context likelihood of relatedness (CLR) algorithm on evaluating co-expressed lncRNA and protein pairs based on RNA-seq and reverse-phase protein array (RPPA) data. In addition, to further increase the clinical relevance of the potential lncRNA drivers, we conducted survival analysis and tumor/normal differential analysis to boost the prediction power of our systematic computational approach. Results: In this study, we integrated lncRNA expression, protein expression and patient survival data to nominate lncRNA drivers in 20 cancers. Among ~4 million lncRNA-protein pairs, we have identified 9 lncRNA drivers and 16 potential lncRNA-protein interaction pairs linked with them. To validate our findings, we selected 3 lncRNAs with high confidence and performed knockdown experiments in multiple cell lines, in which 2 lncRNAs (TMPO-AS1 and HCP5) showed functional relevance with protein-coding genes MSH6 and LCK respectively. Both of the pairs have the same direction of correlations (positive or negative) as we predicted. Our results indicate that the identified lncRNAs may functionally interact with their protein partners identified by our network-based approach, which will further provide the molecular foundation for investigating cancer mechanisms, identifying prognostic lncRNA markers and characterizing additional therapeutic targets. Citation Format: Jun Li, Zhicheng Zhou, Han Liang. A systematic network-based approach to prioritizing lncRNA drivers in cancers. [abstract]. In: Proceedings of the AACR Special Conference on Noncoding RNAs and Cancer: Mechanisms to Medicines ; 2015 Dec 4-7; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2016;76(6 Suppl):Abstract nr A36.

A Bipartite Network-based Method for Prediction of Long Non-coding RNA–protein Interactions

As one large class of non-coding RNAs (ncRNAs), long ncRNAs (lncRNAs) have gained considerable attention in recent years. Mutations and dysfunction of lncRNAs have been implicated in human disorders. Many lncRNAs exert their effects through interactions with the corresponding RNA-binding proteins. Several computational approaches have been developed, but only few are able to perform the prediction of these interactions from a network-based point of view. Here, we introduce a computational method named lncRNA–protein bipartite network inference (LPBNI). LPBNI aims to identify potential lncRNA–interacting proteins, by making full use of the known lncRNA–protein interactions. Leave-one-out cross validation (LOOCV) test shows that LPBNI significantly outperforms other network-based methods, including random walk (RWR) and protein-based collaborative filtering (ProCF). Furthermore, a case study was performed to demonstrate the performance of LPBNI using real data in predicting potential lncRNA–interacting proteins.

Methods to Study Long Noncoding RNA Biology in Cancer.

Thousands of long noncoding RNAs (lncRNAs) have been discovered in recent years. The functions of lncRNAs range broadly from regulating chromatin structure and gene expression in the nucleus to controlling messenger RNA (mRNA) processing, mRNA posttranscriptional regulation, cellular signaling, and protein activity in the cytoplasm. Experimental and computational techniques have been developed to characterize lncRNAs in high-throughput scale, to study the lncRNA function in vitro and in vivo, to map lncRNA binding sites on the genome, and to capture lncRNA-protein interactions with the identification of lncRNA-binding partners, binding sites, and interaction determinants. In this chapter, we will discuss these technologies and their applications in decoding the functions of lncRNAs. Understanding these techniques including their advantages and disadvantages and developing them in the future will be essential to elaborate the roles of lncRNAs in cancer and other diseases.

Long non-coding RNAs in colorectal cancer.

Colorectal cancer (CRC) is one of the leading causes of cancer-related death worldwide. Despite substantial progress in understanding the molecular mechanisms and treatment of CRC in recent years, the overall survival rate of CRC patients has not improved dramatically. The development of CRC is multifactor and multistep processes, in which abnormal gene expression may play an important role. With the advance of human tumor molecular biology, a series of studies have highlighted the role of long non-coding RNAs (lncRNAs) in the development of CRC. CRC-related lncRNAs have been demonstrated to regulate the genes by various mechanisms, including epigenetic modifications, lncRNA-miRNA and lncRNA-protein interactions, and by their actions as miRNA precursors or pseudogenes. Since some lncRNAs can be detected in human body fluid and have good specificity and accessibility, they have been suggested to be used as novel potential biomarkers for CRC diagnosis and prognosis as well as in the prediction of the response to therapy. Therefore, in this review, we will focus on lncRNAs in CRC development, the mechanisms and biomarkers of lncRNAs in CRC.

Unveiling the hidden function of long non-coding RNA by identifying its major partner-protein.

Tens of thousands of long non-coding RNAs (lncRNAs) have been discovered in eukarya, but their functions are largely unknown. Fortunately, lncRNA–protein interactions may offer details of how lncRNAs play important roles in various biological processes, thus identifying proteins associated with lncRNA is critical. Here we review progress of molecular archetypes that lncRNAs execute as guides, scaffolds, or decoys for protein, focusing on advantages, shortcomings and applications of various conventional and emerging technologies to probe lncRNAs and protein interactions, including protein-centric biochemistry approaches such as nRIP and CLIP, and RNA-centric biochemistry approaches such as ChIRP, CHART and RAP. Overall, this review provides strategies for probing interactions between lncRNAs and protein.

Screening for Small-Molecule Modulators of Long Noncoding RNA-Protein Interactions Using AlphaScreen

Long non–protein coding RNAs (lncRNAs) are an important class of molecules that help orchestrate key cellular events. Although their functional roles in cells are not well understood, thousands of lncRNAs and a number of possible mechanisms by which they act have been reported. LncRNAs can exert their regulatory function in cells by interacting with epigenetic enzymes. In this study, we developed a tool to study lncRNA-protein interactions for high-throughput screening of small-molecule modulators using AlphaScreen technology. We tested the interaction of two lncRNAs: brain-derived neurotrophic factor antisense (BDNF-AS) and Hox transcript antisense RNA (HOTAIR), with Enhancer of zeste homolog 2 (EZH2), a histone methyltransferase against a phytochemical library, to look for small-molecule inhibitors that can alter the expression of downstream target genes. We identified ellipticine, a compound that up-regulates BDNF transcription. Our study shows the feasibility of using high-throughput screening to identify modulators of lncRNA-protein interactions and paves the road for targeting lncRNAs that are dysregulated in human disorders using small-molecule therapies.

IDH1 mutation-associated long non-coding RNA expression profile changes in glioma.

Isocitrate dehydrogenase 1 (IDH1) mutation is an important prognostic marker in glioma. However, its downstream effect remains incompletely understood. Long non-coding RNAs (lncRNAs) are emerging as important regulators of tumorigenesis in a number of human malignancies, including glioma. Here, we investigated whether and how lncRNA expression profiles would differ between gliomas with or without IDH1 mutation. By using our previously reported lncRNA mining approach, we performed lncRNA profiling in three public glioma microarray datasets. The differential lncRNA expression analysis was then conducted between mutant-type and wild-type IDH1 glioma samples. Comparison analysis identified 14 and 9 lncRNA probe sets that showed significantly altered expressions in astrocytic and oligodendroglial tumors, respectively (fold change ≥ 1.5, false discovery rate ≤ 0.1). Moreover, the differential expressions of these lncRNAs could be confirmed in the independent testing sets. Functional exploration of the lncRNAs by analyzing the lncRNA-protein interactions revealed that these IDH1 mutation-associated lncRNAs were involved in multiple tumor-associated cellular processes, including metabolism, cell growth and apoptosis. Our data suggest the potential roles of lncRNA in gliomagenesis, and may help to understand the pathogenesis of gliomas associated with IDH1 mutation.

Identification of novel long non-coding RNAs in clear cell renal cell carcinoma.

BackgroundLong non-coding RNAs (lncRNA) play an important role in carcinogenesis; knowledge on lncRNA expression in renal cell carcinoma is rudimental. As a basis for biomarker development, we aimed to explore the lncRNA expression profile in clear cell renal cell carcinoma (ccRCC) tissue.ResultsMicroarray experiments were performed to determine the expression of 32,183 lncRNA transcripts belonging to 17,512 lncRNAs in 15 corresponding normal and malignant renal tissues. Validation was performed using quantitative real-time PCR in 55 ccRCC and 52 normal renal specimens. Computational analysis was performed to determine lncRNA-microRNA (MiRTarget2) and lncRNA-protein (catRAPID omics) interactions. We identified 1,308 dysregulated transcripts (expression change >2-fold; upregulated: 568, downregulated: 740) in ccRCC tissue. Among these, aberrant expression was validated using PCR: lnc-BMP2-2 (mean expression change: 37-fold), lnc-CPN2-1 (13-fold), lnc-FZD1-2 (9-fold), lnc-ITPR2-3 (15-fold), lnc-SLC30A4-1 (15-fold), and lnc-SPAM1-6 (10-fold) were highly overexpressed in ccRCC, whereas lnc-ACACA-1 (135-fold), lnc-FOXG1-2 (19-fold), lnc-LCP2-2 (2-fold), lnc-RP3-368B9 (19-fold), and lnc-TTC34-3 (314-fold) were downregulated. There was no correlation between lncRNA expression with clinical-pathological parameters. Computational analyses revealed that these lncRNAs are involved in RNA-protein networks related to splicing, binding, transport, localization, and processing of RNA. Small interfering RNA (siRNA)-mediated knockdown of lnc-BMP2-2 and lnc-CPN2-1 did not influence cell proliferation.ConclusionsWe identified many novel lncRNA transcripts dysregulated in ccRCC which may be useful for novel diagnostic biomarkers.Electronic supplementary materialThe online version of this article (doi:10.1186/s13148-015-0047-7) contains supplementary material, which is available to authorized users.

Targeting colon cancer metabolism through a long noncoding RNA.

604 Background: Long non-coding RNAs (lncRNAs) have gained massive attention in recent years as a potentially new and crucial layer of gene regulation. We studied the function of the lncRNA HOTAIR in colorectal cancer, one of the most common causes of cancer mortality worldwide. Methods: Molecular profiling was performed in colonic normal (40) and cancer (160) tissues. Gene expression was evaluated by qRT-PCR and gene expression arrays. LncRNA-protein interactions were investigated by RNA-immunoprecipitation, mass spectrometry and mutational analyses. Chromatin immunoprecipitation followed by DNA sequencing (ChIP-Seq) was employed for the histone acetylome analysis. Subcutaneous xenograft mouse models were used to evaluate tumor growth in vivo. Results: HOTAIR is significantly upregulated (&gt;30 fold) in colon cancer and inversely correlates with patient survival. Molecular profiling revealed a gene signature downstream of HOTAIR that links metabolic pathways to colon cancer cell growth and invasiveness. RNA immunoprecipitation/mass spectrometry analysis revealed the interaction of HOTAIR with the histone acetyltransferase PCAF. Mutational analyses identified the domains of both the lincRNA and acetyltransferase responsible for their interaction and function. Histone acetylome analysis demonstrated that HOTAIR is required for the recruitment and activity of PCAF towards a set of genes involved in the mTOR/insulin receptor/PI3K-Akt pathways. In specific, 44 genes involved in these pathways are regulated by Lysine 27 histone H3 acetylation, catalyzed by PCAF only when recruited by HOTAIR. Genome-wide profiling of colon cancer and normal colonic tissues revealed that the expression of this gene set correlates positively with HOTAIR levels and inversely with patient survival. Knockdown of either HOTAIR or PCAF sensitized colon cancer cells to dietary restriction and inhibited tumor growth in subcutaneous xenograft mouse models. Conclusions: Our results provide the mechanistic link between an lncRNA, a transcription activating chromatin mark and metabolic signaling in colorectal cancer. In conclusion, we identified a novel RNA-protein complex that affects growth factor/metabolic pathways essential for colon oncogenesis.

Predicting Long Noncoding RNA and Protein Interactions Using Heterogeneous Network Model.

Recent study shows that long noncoding RNAs (lncRNAs) are participating in diverse biological processes and complex diseases. However, at present the functions of lncRNAs are still rarely known. In this study, we propose a network-based computational method, which is called lncRNA-protein interaction prediction based on Heterogeneous Network Model (LPIHN), to predict the potential lncRNA-protein interactions. First, we construct a heterogeneous network by integrating the lncRNA-lncRNA similarity network, lncRNA-protein interaction network, and protein-protein interaction (PPI) network. Then, a random walk with restart is implemented on the heterogeneous network to infer novel lncRNA-protein interactions. The leave-one-out cross validation test shows that our approach can achieve an AUC value of 96.0%. Some lncRNA-protein interactions predicted by our method have been confirmed in recent research or database, indicating the efficiency of LPIHN to predict novel lncRNA-protein interactions.

Extracting LncRNA-protein Interactions from Literature Using a Text Feature-based Approach

Long non-coding RNAs (lncRNAs) play important roles in regulating transcriptional and posttranscriptional levels. Knowledge of lncRNA-protein interactions (LPIs) is crucial for biologists to explain biological mechanism and guide experiments. Since most freshly discovered LPIs can be extracted from biomedical literature, LPIs extraction by text mining is highly relevant. In this study, we apply a feature-based text mining method to extract LPIs from biomedical literatures. Our method is composed of three steps. Firstly, we operate text pre-processing to convert text from three databases into structured representations. Secondly, we extract a set of features from structured representation sentences. And these features are utilized to generate feature vectors for candidate LPIs pairs. Finally, a random forest classifier is trained by the feature vectors. When we evaluate the method on our dataset, the performance of our method achieves F-score of 79.3%, and the results suggest that as the first text mining approach, the proposed method can efficiently extract LPIs from biomedical literature