Identifying Cancer-Specific circRNA-RBP Binding Sites Based on Deep Learning

CRIECNN: Ensemble convolutional neural network and advanced feature extraction methods for the precise forecasting of circRNA-RBP binding sites

Circular RNAs (circRNAs) have surfaced as important non-coding RNA molecules in biology. Understanding interactions between circRNAs and RNA-binding proteins (RBPs) is crucial in circRNA research. Existing prediction models suffer from limited availability and accuracy, necessitating advanced approaches. In this study, we propose CRIECNN (Circular RNA-RBP Interaction predictor using an Ensemble Convolutional Neural Network), a novel ensemble deep learning model that enhances circRNA-RBP binding site prediction accuracy. CRIECNN employs advanced feature extraction methods and evaluates four distinct sequence datasets and encoding techniques (BERT, Doc2Vec, KNF, EIIP). The model consists of an ensemble convolutional neural network, a BiLSTM, and a self-attention mechanism for feature refinement. Our results demonstrate that CRIECNN outperforms state-of-the-art methods in accuracy and performance, effectively predicting circRNA-RBP interactions from both full-length sequences and fragments. This novel strategy makes an enormous advancement in the prediction of circRNA-RBP interactions, improving our understanding of circRNAs and their regulatory roles.

Predicting circRNA-RBP Binding Sites Using a Hybrid Deep Neural Network

Circular RNAs (circRNAs) are non-coding RNAs generated by reverse splicing. They are involved in biological process and human diseases by interacting with specific RNA-binding proteins (RBPs). Due to traditional biological experiments being costly, computational methods have been proposed to predict the circRNA-RBP interaction. However, these methods have problems of single feature extraction. Therefore, we propose a novel model called circ-FHN, which utilizes only circRNA sequences to predict circRNA-RBP interactions. The circ-FHN approach involves feature coding and a hybrid deep learning model. Feature coding takes into account the physicochemical properties of circRNA sequences and employs four coding methods to extract sequence features. The hybrid deep structure comprises a convolutional neural network (CNN) and a bidirectional gated recurrent unit (BiGRU). The CNN learns high-level abstract features, while the BiGRU captures long-term dependencies in the sequence. To assess the effectiveness of circ-FHN, we compared it to other computational methods on 16 datasets and conducted ablation experiments. Additionally, we conducted motif analysis. The results demonstrate that circ-FHN exhibits exceptional performance and surpasses other methods. circ-FHN is freely available at https://github.com/zhaoqi106/circ-FHN .

Circular RNA and its potential diagnostic and therapeutic values in breast cancer

Breast cancer (BC) is one of the most common malignant tumors in women and still poses a significant threat to women worldwide. Recurrence of BC in situ, metastasis to distant organs, and resistance to chemotherapy are all attached to high mortality in patients with BC. Non-coding RNA (ncRNA) of the type known as "circRNA" links together from one end to another to create a covalently closed, single-stranded circular molecule. With characteristics including plurality, evolutionary conservation, stability, and particularity, they are extensively prevalent in various species and a range of human cells. CircRNAs are new and significant contributors to several kinds of disorders, including cardiovascular disease, multiple organ inflammatory responses and malignancies. Recent studies have shown that circRNAs play crucial roles in the occurrence of breast cancer by interacting with miRNAs to regulate gene expression at the transcriptional or post-transcriptional levels. CircRNAs offer the potential to be therapeutic targets for breast cancer treatment as well as prospective biomarkers for early diagnosis and prognosis of BC. Here, we are about to present an overview of the functions of circRNAs in the proliferation, invasion, migration, and resistance to medicines of breast cancer cells and serve as a promising resource for future investigations on the pathogenesis and therapeutic strategies.

CircNetVis: an interactive web application for visualizing interaction networks of circular RNAs

Analyzing the interactions of circular RNAs (circRNAs) is a crucial step in understanding their functional impacts. While there are numerous visualization tools available for investigating circRNA interaction networks, these tools are typically limited to known circRNAs from specific databases. Moreover, these existing tools usually require complex installation procedures which can be time-consuming and challenging for users. There is a lack of a user-friendly web application that facilitates interactive exploration and visualization of circRNA interaction networks. CircNetVis is an interactive online web application to enhance the analysis of human/mouse circRNA interactions. The tool allows three different input formats of circRNAs including circRNA IDs from CircBase, circRNA coordinates (chromosome, start position, end position), and circRNA sequences in the FASTA format. It integrates multiple interaction networks for visualization and investigation of the interplay between circRNA, microRNAs, mRNAs and RNA binding proteins. CircNetVis also enables users to interactively explore the interactions of unknown circRNAs which are not reported from previous databases. The tool can generate interactive plots and allows users to save results as output files for offline usage. CircNetVis is implemented as a web application using R-shiny and freely available for academic use at https://www.meb.ki.se/shiny/truvu/CircNetVis/ .

CircSI-SSL: circRNA-binding site identification based on self-supervised learning

MOTIVATION

In recent years, circular RNAs (circRNAs), the particular form of RNA with a closed-loop structure, have attracted widespread attention due to their physiological significance (they can directly bind proteins), leading to the development of numerous protein site identification algorithms. Unfortunately, these studies are supervised and require the vast majority of labeled samples in training to produce superior performance. But the acquisition of sample labels requires a large number of biological experiments and is difficult to obtain.

RESULTS

To resolve this matter that a great deal of tags need to be trained in the circRNA-binding site prediction task, a self-supervised learning binding site identification algorithm named CircSI-SSL is proposed in this article. According to the survey, this is unprecedented in the research field. Specifically, CircSI-SSL initially combines multiple feature coding schemes and employs RNA_Transformer for cross-view sequence prediction (self-supervised task) to learn mutual information from the multi-view data, and then fine-tuning with only a few sample labels. Comprehensive experiments on six widely used circRNA datasets indicate that our CircSI-SSL algorithm achieves excellent performance in comparison to previous algorithms, even in the extreme case where the ratio of training data to test data is 1:9. In addition, the transplantation experiment of six linRNA datasets without network modification and hyperparameter adjustment shows that CircSI-SSL has good scalability. In summary, the prediction algorithm based on self-supervised learning proposed in this article is expected to replace previous supervised algorithms and has more extensive application value.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/cc646201081/CircSI-SSL.

The emerging role of circRNAs on skeletal muscle development in economical animals

CircRNAs are a novel type of closed circular molecules formed through a covalent bond lacking a 5'cap and 3' end tail, which mainly arise from mRNA precursor. They are widely distributed in plants and animals and are characterized by stable structure, high conservativeness in cells or tissues, and showed the expression specificity at different stages of development in different tissues. CircRNAs have been gradually attracted wide attention with the development of RNA sequencing, which become a new research hotspot in the field of RNA. CircRNAs play an important role in gene expression regulation. Presently, the related circRNAs research in the regulation of animal muscle development is still at the initial stage. In this review, the formation, properties, biological functions of circRNAs were summarized. The recent research progresses of circRNAs in skeletal muscle growth and development from economic animals including livestock, poultry and fishes were introduced. Finally, we proposed a prospective for further studies of circRNAs in muscle development, and we hope our research could provide new ideas, some theoretical supports and helps for new molecular genetic markers exploitation and animal genetic breeding in future.

Nucleotide-level prediction of CircRNA-protein binding based on fully convolutional neural network

Introduction: CircRNA-protein binding plays a critical role in complex biological activity and disease. Various deep learning-based algorithms have been proposed to identify CircRNA-protein binding sites. These methods predict whether the CircRNA sequence includes protein binding sites from the sequence level, and primarily concentrate on analysing the sequence specificity of CircRNA-protein binding. For model performance, these methods are unsatisfactory in accurately predicting motif sites that have special functions in gene expression. Methods: In this study, based on the deep learning models that implement pixel-level binary classification prediction in computer vision, we viewed the CircRNA-protein binding sites prediction as a nucleotide-level binary classification task, and use a fully convolutional neural networks to identify CircRNA-protein binding motif sites (CPBFCN). Results: CPBFCN provides a new path to predict CircRNA motifs. Based on the MEME tool, the existing CircRNA-related and protein-related database, we analysed the motif functions discovered by CPBFCN. We also investigated the correlation between CircRNA sponge and motif distribution. Furthermore, by comparing the motif distribution with different input sequence lengths, we found that some motifs in the flanking sequences of CircRNA-protein binding region may contribute to CircRNA-protein binding. Conclusion: This study contributes to identify circRNA-protein binding and provides help in understanding the role of circRNA-protein binding in gene expression regulation.

CircSSNN: circRNA-binding site prediction via sequence self-attention neural networks with pre-normalization

BACKGROUND

Circular RNAs (circRNAs) play a significant role in some diseases by acting as transcription templates. Therefore, analyzing the interaction mechanism between circRNA and RNA-binding proteins (RBPs) has far-reaching implications for the prevention and treatment of diseases. Existing models for circRNA-RBP identification usually adopt convolution neural network (CNN), recurrent neural network (RNN), or their variants as feature extractors. Most of them have drawbacks such as poor parallelism, insufficient stability, and inability to capture long-term dependencies.

METHODS

In this paper, we propose a new method completely using the self-attention mechanism to capture deep semantic features of RNA sequences. On this basis, we construct a CircSSNN model for the cirRNA-RBP identification. The proposed model constructs a feature scheme by fusing circRNA sequence representations with statistical distributions, static local contexts, and dynamic global contexts. With a stable and efficient network architecture, the distance between any two positions in a sequence is reduced to a constant, so CircSSNN can quickly capture the long-term dependencies and extract the deep semantic features.

RESULTS

Experiments on 37 circRNA datasets show that the proposed model has overall advantages in stability, parallelism, and prediction performance. Keeping the network structure and hyperparameters unchanged, we directly apply the CircSSNN to linRNA datasets. The favorable results show that CircSSNN can be transformed simply and efficiently without task-oriented tuning.

CONCLUSIONS

In conclusion, CircSSNN can serve as an appealing circRNA-RBP identification tool with good identification performance, excellent scalability, and wide application scope without the need for task-oriented fine-tuning of parameters, which is expected to reduce the professional threshold required for hyperparameter tuning in bioinformatics analysis.

Upregulated circ_0002141 facilitates oral squamous cell carcinoma progression via the miR-1231/EGFR axis

OBJECTIVES

The dysregulation of circular RNAs (circRNAs) is implicated in the progression of various cancers. This study was aimed at expounding the role and mechanism of hsa_circ_0002141 in the OSCC progression.

MATERIALS AND METHODS

Circ_0002141 expression was examined in 52 pairs of OSCC tissues and matched adjacent tissue samples by quantitative real-time polymerase chain reaction (qRT-PCR) assay. After circ_0002141 was overexpressed or knocked down in OSCC cell lines, cell counting kit-8 (CCK-8) assay, Transwell assay, flow cytometry, and Western blotting were conducted to detect the changes in the growth, migration, invasion and apoptosis of OSCC cells. Western blot assay, qRT-PCR and dual-luciferase reporter assay were performed to clarify the interplay among circ_0002141, miR-1231, and epidermal growth factor receptor (EGFR).

RESULTS

Circ_0002141 expression was significantly upregulated in OSCC tissues and cell lines. Circ_0002141 overexpression markedly promoted the proliferation, migration, and invasion of OSCC cells whereas reduced the apoptotic of OSCC cells. Also, circ_0002141 knockdown suppressed the malignant characteristics of OSCC cells. EGFR was validated as the target of miR-1231. Besides, circ_0002141 could sponge miR-1231 and upregulate EGFR expression in OSCC cells.

CONCLUSION

Circ_0002141/miR-1231/EGFR axis is involved in the progression of OSCC.

Involvement of circRNAs in the Development of Heart Failure

In recent years, interest in non-coding RNAs as important physiological regulators has grown significantly. Their participation in the pathophysiology of cardiovascular diseases is extremely important. Circular RNA (circRNA) has been shown to be important in the development of heart failure. CircRNA is a closed circular structure of non-coding RNA fragments. They are formed in the nucleus, from where they are transported to the cytoplasm in a still unclear mechanism. They are mainly located in the cytoplasm or contained in exosomes. CircRNA expression varies according to the type of tissue. In the brain, almost 12% of genes produce circRNA, while in the heart it is only 9%. Recent studies indicate a key role of circRNA in cardiomyocyte hypertrophy, fibrosis, autophagy and apoptosis. CircRNAs act mainly by interacting with miRNAs through a "sponge effect" mechanism. The involvement of circRNA in the development of heart failure leads to the suggestion that they may be promising biomarkers and useful targets in the treatment of cardiovascular diseases. In this review, we will provide a brief introduction to circRNA and up-to-date understanding of their role in the mechanisms leading to the development of heart failure.

A pseudo-Siamese framework for circRNA-RBP binding sites prediction integrating BiLSTM and soft attention mechanism

Circular RNAs (circRNAs) are widely expressed in tissues and play a key role in diseases through interacting with RNA binding proteins (RBPs). Since the high cost of traditional technology, computational methods are developed to identify the binding sites between circRNAs and RBPs. Unfortunately, these methods suffer from the insufficient learning of features and the single classification of output. To address these limitations, we propose a novel method named circ-pSBLA which constructs a pseudo-Siamese framework integrating Bi-directional long short-term memory (BiLSTM) network and soft attention mechanism for circRNA-RBP binding sites prediction. Softmax function and CatBoost are adopted to classify, respectively, and then a pseudo-Siamese framework is constructed. circ-pSBLA combines them to get final output. To validate the effectiveness of circ-pSBLA, we compare it with other state-of-the-art methods and carry out an ablation experiment on 17 sub-datasets. Moreover, we do motif analysis on 3 sub-datasets. The results show that circ-pSBLA achieves superior performance and outperforms other methods. All supporting source codes can be downloaded from https://github.com/gyj9811/circ-pSBLA.

A web server for identifying circRNA-RBP variable-length binding sites based on stacked generalization ensemble deep learning network

Circular RNA (circRNA) can exert biological functions by interacting with RNA-binding protein (RBP), and some deep learning-based methods have been developed to predict RBP binding sites on circRNA. However, most of these methods identify circRNA-RBP binding sites are only based on single data resource and cannot provide exact binding sites, only providing the probability value of a sequence fragment. To solve these problems, we propose a binding sites localization algorithm that fuses binding sites from multiple databases, and further design a stacked generalization ensemble deep learning model named CirRBP to identify RBP binding sites on circRNA. The CirRBP is trained by combining the binding sites from multiple databases and makes predictions by weighted aggregating the predictions of each sub-model. The results show that the CirRBP outperforms any sub-model and existing online prediction model. For better access to our research results, we develop an open-source web application called CRWS (CircRNA-RBP Web Server). Its back-end learning model of the CRWS is a stacked generalization ensemble learning model CirRBP based on different deep learning frameworks. Given a full-length circRNA or fragment sequence and a target RBP, the CRWS can analyze and provide the exact potential binding sites of the target RBP on the given sequence through the binding sites localization algorithm, and visualize it. In addition, the CRWS can discover the most widely distributed motif in each RBP dataset. Up to now, CRWS is the first significant online tool that uses multi-source data to train models and predict exact binding sites. CRWS is now publicly and freely available without login requirement at: http://www.bioinformatics.team.

Genomics enters the deep learning era

The tremendous amount of biological sequence data available, combined with the recent methodological breakthrough in deep learning in domains such as computer vision or natural language processing, is leading today to the transformation of bioinformatics through the emergence of deep genomics, the application of deep learning to genomic sequences. We review here the new applications that the use of deep learning enables in the field, focusing on three aspects: the functional annotation of genomes, the sequence determinants of the genome functions and the possibility to write synthetic genomic sequences.

Circular RNAs in hepatocellular carcinoma: Recent advances

Circular RNAs (circRNAs) have covalently closed loop structures at both ends, exhibiting characteristics dissimilar to those of linear RNAs. Emerging evidence suggests that aberrantly expressed circRNAs play crucial roles in hepatocellular carcinoma (HCC) by affecting the proliferation, apoptosis and invasive capacity of HCC cells. Certain circRNAs may be used as biomarkers to diagnose and predict the prognosis of HCC. Therefore, circRNAs are expected to become novel biomarkers and therapeutic targets for HCC. Herein, we briefly review the characteristics and biological functions of circRNAs, focusing on their roles in HCC to provide new insights for the early diagnosis and targeted therapy of HCC.

Circular RNA: A novel and potential regulator in pathophysiology of schizophrenia

Circular RNAs (CircRNAs) are a sub-class of non-coding RNA, which are covalently closed at the ends through a non-canonical process called, backsplicing from the precursor linear RNAs. These molecules are involved in several biological phenomena including regulation of gene expression, synaptic plasticity, and cognition. Several studies have shown that circRNA are present abundantly inside the mammalian brain and they are believed to be associated with the development of neurons and neuronal functions. It is also evident that alterations in intracellular and extracellular levels of circRNAs are linked with various neurological and neuropsychiatric disorders including schizophrenia (SZ). Detailed studies of circRNAs are required to decode the molecular mechanism behind the onset of SZ and the related biological activities during disease progression. This can help unravel their role in this neurobehavioral disorder and develop effective therapeutics against the disease. The present review mainly focuses on the expression and activities of the circRNAs in the post-mortem brain, peripheral blood, and exosomes. It also gives an insight into the role of circRNA interaction with RNA binding proteins (RBPs) and nucleotide modification and their therapeutic potential in the context of schizophrenia.

Circular RNA circ_0006089 regulates the IGF1R expression by targeting miR-143-3p to promote gastric cancer proliferation, migration and invasion

Circular RNAs (circRNAs) figure prominently in regulating the progression of a variety of human malignancies. This study was performed to probe how circ_0006089 functioned in gastric cancer (GC). CircRNA expression profile GSE83521 was downloaded from Gene Expression Omnibus (GEO) database, and circRNAs and analyzed. Quantitative real-time polymerase chain reaction (qRT-PCR) was used to measure circ_0006089, microRNA-143-3p (miR-143-3p) and insulin-like growth factor 1 receptor (IGF1R) mRNA expressions in GC tissues and cell lines. Kaplan-Meier curves were used to detect the relationship between circ_0006089 expression and overall survival time of GC patients. Cell counting kit-8 (CCK-8) and 5-bromo-2-deoxyuridine (BrdU) assays were employed to detect the proliferative ability of GC cells after circ_0006089 was overexpressed or knocked down. Wound healing assay and Transwell assay were executed to examine the migration and invasion ability of GC cells. Western blot was adopted to detect IGF1R protein expressions. Circ_0006089 expression was up-regulated in GC samples and cell lines. And high circ_0006089 expression was associated with shorter survival time in GC patients. Circ_0006089 overexpression in GC cells significantly accelerated GC cell proliferation, migration and invasion, whereas circ_0006089 knockdown resulted in the opposite effects. Additionally, miR-143-3p was validated as a downstream target of circ_0006089, and circ_0006089 could positively regulate IGF1R expression via repressing miR-143-3p. Circ_0006089 is highly expressed in GC, and it promotes the malignancy of GC cells via modulating miR-143-3p/IGF1R axis, suggesting that circ_0006089 may serve as a promising therapeutic target for GC.

HCRNet: high-throughput circRNA-binding event identification from CLIP-seq data using deep temporal convolutional network

Identifying genome-wide binding events between circular RNAs (circRNAs) and RNA-binding proteins (RBPs) can greatly facilitate our understanding of functional mechanisms within circRNAs. Thanks to the development of cross-linked immunoprecipitation sequencing technology, large amounts of genome-wide circRNA binding event data have accumulated, providing opportunities for designing high-performance computational models to discriminate RBP interaction sites and thus to interpret the biological significance of circRNAs. Unfortunately, there are still no computational models sufficiently flexible to accommodate circRNAs from different data scales and with various degrees of feature representation. Here, we present HCRNet, a novel end-to-end framework for identification of circRNA-RBP binding events. To capture the hierarchical relationships, the multi-source biological information is fused to represent circRNAs, including various natural language sequence features. Furthermore, a deep temporal convolutional network incorporating global expectation pooling was developed to exploit the latent nucleotide dependencies in an exhaustive manner. We benchmarked HCRNet on 37 circRNA datasets and 31 linear RNA datasets to demonstrate the effectiveness of our proposed method. To evaluate further the model's robustness, we performed HCRNet on a full-length dataset containing 740 circRNAs. Results indicate that HCRNet generally outperforms existing methods. In addition, motif analyses were conducted to exhibit the interpretability of HCRNet on circRNAs. All supporting source code and data can be downloaded from https://github.com/yangyn533/HCRNet and https://doi.org/10.6084/m9.figshare.16943722.v1. And the web server of HCRNet is publicly accessible at http://39.104.118.143:5001/.

CRBPDL: Identification of circRNA-RBP interaction sites using an ensemble neural network approach

Circular RNAs (circRNAs) are non-coding RNAs with a special circular structure produced formed by the reverse splicing mechanism. Increasing evidence shows that circular RNAs can directly bind to RNA-binding proteins (RBP) and play an important role in a variety of biological activities. The interactions between circRNAs and RBPs are key to comprehending the mechanism of posttranscriptional regulation. Accurately identifying binding sites is very useful for analyzing interactions. In past research, some predictors on the basis of machine learning (ML) have been presented, but prediction accuracy still needs to be ameliorated. Therefore, we present a novel calculation model, CRBPDL, which uses an Adaboost integrated deep hierarchical network to identify the binding sites of circular RNA-RBP. CRBPDL combines five different feature encoding schemes to encode the original RNA sequence, uses deep multiscale residual networks (MSRN) and bidirectional gating recurrent units (BiGRUs) to effectively learn high-level feature representations, it is sufficient to extract local and global context information at the same time. Additionally, a self-attention mechanism is employed to train the robustness of the CRBPDL. Ultimately, the Adaboost algorithm is applied to integrate deep learning (DL) model to improve prediction performance and reliability of the model. To verify the usefulness of CRBPDL, we compared the efficiency with state-of-the-art methods on 37 circular RNA data sets and 31 linear RNA data sets. Moreover, results display that CRBPDL is capable of performing universal, reliable, and robust. The code and data sets are obtainable at https://github.com/nmt315320/CRBPDL.git.

More and more evidences show that circular RNA can directly bind to proteins and participate in countless different biological processes. The calculation method can quickly and accurately predict the binding site of circular RNA and RBP. In order to identify the interaction of circRNA with 37 different types of circRNA binding proteins, we developed an integrated deep learning network based on hierarchical network, called CRBPDL. It can effectively learn high-level feature representations. The performance of the model was verified through comparative experiments of different feature extraction algorithms, different deep learning models and classifier models. Moreover, the CRBPDL model was applied to 31 linear RNAs, and the effectiveness of our method was proved by comparison with the results of current excellent algorithms. It is expected that the CRBPDL model can effectively predict the binding site of circular RNA-RBP and provide reliable candidates for further biological experiments.

Hsa_circ_0008259 modulates miR-21-5p and PDCD4 expression to restrain osteosarcoma progression

BACKGROUND

Osteosarcoma (OS) is one of the most common primary bone tumors in children and adolescents. However, the molecular mechanism of OS tumorigenesis is still little known. Circular RNA (circRNA) is a key player in the progression of many cancers. This study is performed to decipher the role and mechanism of circ_0008259 in the progression of OS.

METHODS

A differentially expressed circRNA, circ_0008259, was screened out by analyzing the expression profile of circRNA in OS tissue. Circ_0008259, miR-21-5p and programmable cell death 4 (PDCD4) mRNA expression levels in OS tissues and cells were detected by qRT-PCR. Cell viability, metastatic potential and apoptosis were evaluated by cell counting kit-8 assay, Transwell and flow cytometry. The targeting relationship between circ_0008259 and miR-21-5p, and miR-21-5p and PDCD4 mRNA was analyzed and probed by bioinformatics analysis and dual-luciferase reporter assay, RNA-binding protein immunoprecipitation assay and RNA-pull down assay. The regulatory effects of circ_0008259 and miR-21-5p on PDCD4 protein expression in OS cells were detected by Western blot assay.

RESULTS

Circ_0008259 expression and PDCD4 expression were down-regulated and miR-21-5p expression was elevated in the OS tissues and cells. Functional experiments showed that circ_0008259 overexpression significantly inhibited the proliferation and metastatic potential of OS cells and promoted the apoptosis. Besides, PDCD4 was validated as the target gene of miR-21-5p, and circ_0008259 could competitively bind to miR-21-5p, thus up-regulating PDCD4 expression in OS cells.

CONCLUSIONS

Circ_0008259 suppresses OS progression via regulating miR-21-5p/PDCD4 axis.

CircSERPINA3 regulates SERPINA3-mediated apoptosis, autophagy and aerobic glycolysis of prostate cancer cells by competitively binding to MiR-653-5p and recruiting BUD13

BACKGROUND

Prostate cancer (PCa) belongs to an epithelial malignancy that occurs in the prostate gland and is the most common malignancy of the male genitourinary system. Referring to related literature, circSERPINA3 has been reported to be up-regulated in PCa. However, its biological function remains unclear.

PURPOSE

This study aimed to reveal the specific role and relevant molecular mechanism of circSERPINA3 in PCa.

METHODS

RT-qPCR was used to examine gene expression and functional analyses were conducted to verify the effect of circSERPINA3 on cell apoptosis, autophagy and aerobic glycolysis in PCa cells. Mechanism assays were applied to evaluate the relationship among circSERPINA3/miR-653-5p/SERPINA3/BUD13.

RESULTS

CircSERPINA3 was verified to be up-regulated in PCa cells and to inhibit cell apoptosis while promoting aerobic glycolysis and autophagy in PCa cells. CircSERPINA3 and SERPINA3 were also testified to bind to miR-653-5p through a line of mechanism experiments. Moreover, it was discovered that circSERPINA3 could stabilize SERPINA3 mRNA via recruiting BUD13. Additionally, SERPINA3 was verified to inhibit cell apoptosis, while promoting aerobic glycolysis and autophagy in PCa cells.

CONCLUSIONS

Our study suggested that circSERPINA3 regulated apoptosis, autophagy and aerobic glycolysis of PCa cells by competitively binding to miR-653-5p and recruiting BUD13.

Circular RNA hsa_circ_0002360 promotes non-small cell lung cancer progression through upregulating matrix metalloproteinase 16 and sponging multiple micorRNAs

Dysregulated circular RNAs (circRNAs) are involved in the progression of non-small cell lung cancer (NSCLC). However, the role of has_circ_0002360 (circ_0002360) in NSCLC has rarely been reported. In this study, circ_0002360 expression in NSCLC tissues and cell lines was measured using microarray data and quantitative real-time PCR (qRT-PCR). After gain-of-function and loss-of-function, cell models were established; 5-bromo-2-deoxyuridine (BrdU) and transwell assays were conducted to detect NSCLC cell growth, migration, and invasion. What is more, bioinformatic analysis and dual-luciferase reporter assay were adopted to show how circ_0002360, microRNAs (miR-127-5p, miR-145-5p, miR-585-3p, and miR-758-3p), and matrix metalloproteinase 16 (MMP16) 3ʹUTR interact with each other. Western blotting was executed to probe the regulatory effects of circ_0002360 and these miRNAs on MMP16 protein expression in NSCLC cells. We found that circ_0002360 expression was raised in NSCLC tissues. High circ_0002360 expression predicted a short overall survival time for NSCLC patients. Circ_0002360 overexpression promoted NSCLC cell proliferative, migrative, and invasive abilities, and circ_0002360 depletion worked oppositely. MiR-127-5p, miR-145-5p, miR-585-3p, and miR-758-3p were the targets of circ_0002360, and circ_0002360 could regulate MMP16 expression by competitively binding with the above miRNAs. In summary, circ_0002360 serves as a competitive endogenous RNA to raise MMP16 expressions by competitively binding to miR-127-5p, miR-145-5p, miR-585-3p, and miR-758-3p, thereby promoting NSCLC progression.

Prediction of RBP binding sites on circRNAs using an LSTM-based deep sequence learning architecture

Circular RNAs (circRNAs) are widely expressed in highly diverged eukaryotes. Although circRNAs have been known for many years, their function remains unclear. Interaction with RNA-binding protein (RBP) to influence post-transcriptional regulation is considered to be an important pathway for circRNA function, such as acting as an oncogenic RBP sponge to inhibit cancer. In this study, we design a deep learning framework, CRPBsites, to predict the binding sites of RBPs on circRNAs. In this model, the sequences of variable-length binding sites are transformed into embedding vectors by word2vec model. Bidirectional LSTM is used to encode the embedding vectors of binding sites, and then they are fed into another LSTM decoder for decoding and classification tasks. To train and test the model, we construct four datasets that contain sequences of variable-length binding sites on circRNAs, and each set corresponds to an RBP, which is overexpressed in bladder cancer tissues. Experimental results on four datasets and comparison with other existing models show that CRPBsites has superior performance. Afterwards, we found that there were highly similar binding motifs in the four binding site datasets. Finally, we applied well-trained CRPBsites to identify the binding sites of IGF2BP1 on circCDYL, and the results proved the effectiveness of this method. In conclusion, CRPBsites is an effective prediction model for circRNA-RBP interaction site identification. We hope that CRPBsites can provide valuable guidance for experimental studies on the influence of circRNA on post-transcriptional regulation.

Improved Predicting of The Sequence Specificities of RNA Binding Proteins by Deep Learning

RNA-binding proteins (RBPs) have a significant role in various regulatory tasks. However, the mechanism by which RBPs identify the subsequence target RNAs is still not clear. In recent years, several machine and deep learning-based computational models have been proposed for understanding the binding preferences of RBPs. These methods required integrating multiple features with raw RNA sequences such as secondary structure and their performances can be further improved. In this paper, we propose an efficient and simple convolution neural network, RBPCNN, that relies on the combination of the raw RNA sequence and evolutionary information. We show that conservation scores (evolutionary information) for the RNA sequences can significantly improve the overall performance of the proposed predictor. In addition, the automatic extraction of the binding sequence motifs can enhance our understanding of the binding specificities of RBPs. The experimental results show that RBPCNN outperforms significantly the current state-of-the-art methods. More specifically, the average area under the receiver operator curve was improved by 2.67 percent and the mean average precision was improved by 8.03 percent. The datasets and results can be downloaded from https://home.jbnu.ac.kr/NSCL/RBPCNN.htm.

Circular RNA hsa_circ_0000730 restrains cell proliferation, migration, and invasion in cervical cancer through miR-942-5p/PTEN axis

Circular RNAs (circRNAs) play prominent roles in regulating the progression of cancers. This study is aimed to decipher the role of hsa_circ_0000730 in cervical cancer (CC).The differentially expressed circRNAs of CC were screened out from the Gene Expression Omnibus database. qRT-PCR was used to detect circ_0000730 expression in CC tissues and cell lines, and the Kaplan-Meier curve was adopted to figure out the relationship between circ_000730 expression and the overall survival time of CC patients. BrdU assay and Tanswell assay were utilized to examine the proliferation, migration, and invasion of CC cells. Western blot was adopted to detect PTEN protein expression. Bioinformatics analysis and dual-luciferase reporter assay were used to examine the target relationship between miR-942-5p and circ_0000730 or PTEN, respectively.Circ_0000730 was among the differentially expressed circRNAs in CC. Circ_0000730 was significantly down-regulated in the cancer tissues of 50 CC patients and CC cell lines. Additionally, underexpression of circ_0000730 was associated with the shorter survival time of CC patients. Gain- and loss-of-function assays highlighted that circ_0000730 significantly inhibited the proliferation, migration, and invasion of CC cells. Mechanistically, miR-942-5p was identified as a downstream target of circ_0000730, and circ_0000730 could positively regulate PTEN expression via repressing miR-942-5p in CC cells.Circ_0000730 inhibits the proliferation, migration, and invasion of CC cells via regulating miR-942-5p/PTEN axis. Circ_0000730 probably acts as a tumor suppressor in CC, and it may be a candidate target for the treatment of CC.

CircRNA pappalysin 1 facilitates prostate cancer development through miR-515-5p/FKBP1A axis

The role of circular RNA (circRNA) pappalysin 1 (circ-PAPPA; hsa_circ_0088233) in prostate cancer (PCa) cells was explored in the current study. Circ-PAPPA abundance was markedly enhanced in PCa. Circ-PAPPA interference restrained cell viability, proliferation, motility and glycolysis while elevated the apoptosis rate of PCa cells. Circ-PAPPA negatively regulated microRNA-515-5p (miR-515-5p) abundance. MiR-515-5p silencing largely diminished circ-PAPPA knockdown-mediated effects in PCa cells. MiR-515-5p directly bound to FKBP prolyl isomerase 1A (FKBP1A). MiR-515-5p overexpression-mediated impacts were partly counteracted by FKBP1A overexpression. Circ-PAPPA silencing reduced FKBP1A protein level partly by elevating miR-515-5p expression. Circ-PAPPA knockdown significantly restrained the tumour growth in vivo. Circ-PAPPA elevated the malignant phenotypes of PCa cells by sequestering miR-515-5p to induce the expression of FKBP1A.

Identification of RNA binding protein interacting with circular RNA and hub candidate network for hepatocellular carcinoma

The interaction between RNA binding protein (RBP) and circular RNA (circRNA) is important for the regulation of tumor progression. This study aimed to identify the RBP-circRNA network in hepatocellular carcinoma (HCC). 22 differentially expressed (DE) circRNAs in HCC were screened out from Gene Expression Omnibus (GEO) database and their binding RBPs were predicted by Circular RNA Interactome. Among them, 17 DERBPs, which were commonly dysregulated in HCC from The Clinical Proteomic Tumor Analysis Consortium (CPTAC), The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) projects, were utilized to construct the RBP-circRNA network. Through survival analysis, we found TARDBP was the only prognostic RBP for HCC in CPTAC, TCGA and ICGC projects. High expression of TARDBP was correlated with high grade, advanced stage and low macrophage infiltration of HCC. Additionally, gene set enrichment analysis showed that dysregulated TARDBP might be involved in some pathways related to the HCC pathogenesis. Therefore, a hub RBP-circRNA network was generated based on TARDBP. RNA immunoprecipitation and RNA pull-down confirmed that hsa_circ_0004913 binds to TARDBP. These findings indicated certain RBP-circRNA regulatory network potentially involved in the pathogenesis of HCC, which provides novel insights into the mechanism study and biomarker identification for HCC.

Circular RNAs and Cardiovascular Regeneration

circular RNAs (circRNAs) are a type of non-coding RNAs that are widely present in eukaryotic cells. They have the characteristics of stable structure, high abundance, and cell or tissue specific expression. circRNAs are single-stranded RNAs that are covalently back spliced to form closed circular loops. They may participate in gene expression and regulation through a variety of action modes. circRNAs can encode proteins or function by acting as miRNA sponges for protein translation. Since 2016, a growing number of research studies have shown that circRNAs play important role in the pathogenesis of cardiovascular disease. With the construction of circRNA database, the differential expression of circRNAs in the heart tissue samples from different species and the gradual elucidation of its mode of action in disease may become an ideal diagnosis biomarker and an effective therapeutic target. What can be expected surely has a broader application prospect. In this review, we summarize recent publications on circRNA biogenesis, expression profiles, functions, and the most recent studies of circRNAs in the field of cardiovascular diseases with special emphasis on cardiac regeneration.

CircRNA-Mediated Regulation of Angiogenesis: A New Chapter in Cancer Biology

Angiogenesis is necessary for carcinoma progression and is regulated by a variety of pro- and anti-angiogenesis factors. CircRNAs are RNA molecules that do not have a 5'-cap or a 3'-polyA tail and are involved in a variety of biological functions. While circRNA-mediated regulation of tumor angiogenesis has received much attention, the detailed biological regulatory mechanism remains unclear. In this review, we investigated circRNAs in tumor angiogenesis from multiple perspectives, including its upstream and downstream factors. We believe that circRNAs have natural advantages and great potential for the diagnosis and treatment of tumors, which deserves further exploration.

The Biogenesis and Functions of circRNAs and Their Roles in Breast Cancer

Recent statistics show that breast cancer is among the most frequent cancers in clinical practice. It is also the second-leading cause of cancer-related deaths among women worldwide. CircRNAs are a new class of endogenous regulatory RNA molecules whose 5’ end and 3’ end are connected together to form a covalently closed single-stranded loop by back-splicing. CircRNAs present the advantages of disease-specific expression and excellent expression stability, and they can modulate gene expression at posttranscriptional and transcriptional levels. CircRNAs are abnormally expressed in multiple cancers, such as breast cancer, and drive the initiation and progression of cancer. In this review, we describe current knowledge about the functions of circRNAs and generalize their roles in various aspects of breast cancer, including cell proliferation, cell cycle, apoptosis, invasion and metastasis, autophagy, angiogenesis, drug resistance, and tumor immunity, and their prognostic and diagnostic value. This may add to a better understanding of the functions and roles of circRNAs in breast cancer, which may become new diagnostic and predictive biomarkers of breast cancer.

A comprehensive survey on computational methods of non-coding RNA and disease association prediction

The studies on relationships between non-coding RNAs and diseases are widely carried out in recent years. A large number of experimental methods and technologies of producing biological data have also been developed. However, due to their high labor cost and production time, nowadays, calculation-based methods, especially machine learning and deep learning methods, have received a lot of attention and been used commonly to solve these problems. From a computational point of view, this survey mainly introduces three common non-coding RNAs, i.e. miRNAs, lncRNAs and circRNAs, and the related computational methods for predicting their association with diseases. First, the mainstream databases of above three non-coding RNAs are introduced in detail. Then, we present several methods for RNA similarity and disease similarity calculations. Later, we investigate ncRNA-disease prediction methods in details and classify these methods into five types: network propagating, recommend system, matrix completion, machine learning and deep learning. Furthermore, we provide a summary of the applications of these five types of computational methods in predicting the associations between diseases and miRNAs, lncRNAs and circRNAs, respectively. Finally, the advantages and limitations of various methods are identified, and future researches and challenges are also discussed.

Circ_0057553/miR-515-5p Regulates Prostate Cancer Cell Proliferation, Apoptosis, Migration, Invasion and Aerobic Glycolysis by Targeting YES1

Background

Prostate cancer (PCa) is one of the most common malignant cancer in males worldwide. Circular RNAs (CircRNAs) are novel type of non-coding RNAs. Recently, circRNAs have been reported participating in various cancers, including prostate cancer. However, the function and mechanism of circ_0057553 remain to be elucidated.

Methods and Materials

The RNA expression levels of circ_0057553, miR-515-5p, YES proto-oncogene 1 (YES1) and glycolytic genes mRNA were detected by qRT-PCR in PCa tissues or cells. Western blotting was performed to analyze YES1 protein level. Cell viability, migration and invasion and cell apoptosis were assessed by cell counting kit-8 (CCK-8) assay, transwell assay and flow cytometry. In addition, the effects of cell glycolysis were evaluated by measuring lactate production, glucose consumption and adenosine triphosphate (ATP) level. Moreover, dual-luciferase reporter assay was used to detect the target sites of circ_0057553 and miR-515-5p, miR-515-5p and YES1. RNA immunoprecipitation (RIP) was conducted to evaluate the target relationship between circ_0057553 and miR-515-5p. Xenograft mouse model was conducted to measure tumor formation in vivo.

Results

Circ_0057553 was significantly up-regulated in PCa tissues and cells. Knockdown of circ_0057553 inhibited cell viability, migration, invasion and glycolysis and facilitated apoptosis in PCa cells. Furthermore, circ_0057553 bound to miR-515-5p and miR-515-5p directly targeted YES1. Interestingly, miR-515-5p inhibitor partially rescued the function of circ_0057553 knockdown, while YES1 restored the effects of miR-515-5p overexpression. Circ_0057553 down-regulation remarkably decreased tumor volume and weight in vivo.

Conclusion

Circ_0057553 affected PCa cell viability, migration, invasion, apoptosis and glycolysis through miR-515-5p/YES1 axis.

iCircRBP-DHN: identification of circRNA-RBP interaction sites using deep hierarchical network

Circular RNAs (circRNAs) are widely expressed in eukaryotes. The genome-wide interactions between circRNAs and RNA-binding proteins (RBPs) can be probed from cross-linking immunoprecipitation with sequencing data. Therefore, computational methods have been developed for identifying RBP binding sites on circRNAs. Unfortunately, those computational methods often suffer from the low discriminative power of feature representations, numerical instability and poor scalability. To address those limitations, we propose a novel computational method called iCircRBP-DHN using deep hierarchical network for discriminating circRNA-RBP binding sites. The network architecture can be regarded as a deep multi-scale residual network followed by bidirectional gated recurrent units (BiGRUs) with the self-attention mechanism, which can simultaneously extract local and global contextual information. Meanwhile, we propose novel encoding schemes by integrating CircRNA2Vec and the K-tuple nucleotide frequency pattern to represent different degrees of nucleotide dependencies. To validate the effectiveness of our proposed iCircRBP-DHN, we compared its performance with other computational methods on 37 circRNAs datasets and 31 linear RNAs datasets, respectively. The experimental results reveal that iCircRBP-DHN can achieve superior performance over those state-of-the-art algorithms. Moreover, we perform motif analysis on circRNAs bound by those different RBPs, demonstrating that our proposed CircRNA2Vec encoding scheme can be promising. The iCircRBP-DHN method is made available at https://github.com/houzl3416/iCircRBP-DHN.

Circular RNA hsa_circ_0000282 contributes to osteosarcoma cell proliferation by regulating miR-192/XIAP axis

Background

Circular RNAs (circRNAs) have emerged as a novel category of non-coding RNA, which exhibit a pivotal effect on regulating gene expression and biological functions, yet how circRNAs function in osteosarcoma (OSA) still demands further investigation. This study aimed at probing into the function of hsa_circ_0000282 in OSA.

Methods

The expressions of circ_0000282 and miR-192 in OSA tissues and cell lines were examined by quantitative real-time polymerase chain reaction (qRT-PCR), and the correlation between the expression level of circ_0000282 and clinicopathological features of OSA patients was analyzed. The expressions of X-linked inhibitor of apoptosis protein (XIAP), B-cell lymphoma-2 (Bcl-2) and Bcl-2 associated X protein (Bax) in OSA cells were assayed by Western blot. The proliferation and apoptosis of OSA cells were examined by CCK-8, BrdU and flow cytometry, respectively. Bioinformatics analysis, dual-luciferase reporter gene assay and RIP experiments were employed to predict and validate the targeting relationships between circ_0000282 and miR-192, and between miR-192 and XIAP, respectively.

Results

Circ_0000282 was highly expressed in OSA tissues and cell lines, which represented positive correlation with Enneking stage of OSA patients and negative correlation with tumor differentiation degree. In vitro experiments confirmed that overexpression of circ_0000282 markedly facilitated OSA cell proliferation and repressed cancer cell apoptosis in comparison to control group. Besides, knockdown of circ_0000282 repressed OSA cell proliferation and promoted apoptosis. Additionally, the binding relationships between circ_0000282 and miR-192, and between miR-192 and XIAP were validated. Circ_0000282 indirectly up-regulated XIAP expression by adsorbing miR-192, thereby playing a role in promoting cancer in OSA.

Conclusion

Circ_0000282 was a novel oncogenic circRNA in OSA. Circ_0000282/miR-192/XIAP axis regulated OSA cell proliferation apoptosis with competitive endogenous RNA mechanism.

Non-coding RNAs in Brain Tumors, the Contribution of lncRNAs, circRNAs, and snoRNAs to Cancer Development-Their Diagnostic and Therapeutic Potential

Brain tumors are one of the most frightening ailments that afflict human beings worldwide. They are among the most lethal of all adult and pediatric solid tumors. The unique cell-intrinsic and microenvironmental properties of neural tissues are some of the most critical obstacles that researchers face in the diagnosis and treatment of brain tumors. Intensifying the search for potential new molecular markers in order to develop new effective treatments for patients might resolve this issue. Recently, the world of non-coding RNAs (ncRNAs) has become a field of intensive research since the discovery of their essential impact on carcinogenesis. Some of the most promising diagnostic and therapeutic regulatory RNAs are long non-coding RNAs (lncRNAs), circular RNAs (circRNAs), and small nucleolar RNAs (snoRNAs). Many recent reports indicate the important role of these molecules in brain tumor development, as well as their implications in metastasis. In the following review, we summarize the current state of knowledge about regulatory RNAs, namely lncRNA, circRNAs, and snoRNAs, and their impact on the development of brain tumors in children and adults with particular emphasis on malignant primary brain tumors-gliomas and medulloblastomas (MB). We also provide an overview of how these different ncRNAs may act as biomarkers in these tumors and we present their potential clinical implications.

Prioritizing CircRNA-Disease Associations With Convolutional Neural Network Based on Multiple Similarity Feature Fusion

Accumulating evidence shows that circular RNAs (circRNAs) have significant roles in human health and in the occurrence and development of diseases. Biological researchers have identified disease-related circRNAs that could be considered as potential biomarkers for clinical diagnosis, prognosis, and treatment. However, identification of circRNA–disease associations using traditional biological experiments is still expensive and time-consuming. In this study, we propose a novel method named MSFCNN for the task of circRNA–disease association prediction, involving two-layer convolutional neural networks on a feature matrix that fuses multiple similarity kernels and interaction features among circRNAs, miRNAs, and diseases. First, four circRNA similarity kernels and seven disease similarity kernels are constructed based on the biological or topological properties of circRNAs and diseases. Subsequently, the similarity kernel fusion method is used to integrate the similarity kernels into one circRNA similarity kernel and one disease similarity kernel, respectively. Then, a feature matrix for each circRNA–disease pair is constructed by integrating the fused circRNA similarity kernel and fused disease similarity kernel with interactions and features among circRNAs, miRNAs, and diseases. The features of circRNA–miRNA and disease–miRNA interactions are selected using principal component analysis. Finally, taking the constructed feature matrix as an input, we used two-layer convolutional neural networks to predict circRNA–disease association labels and mine potential novel associations. Five-fold cross validation shows that our proposed model outperforms conventional machine learning methods, including support vector machine, random forest, and multilayer perception approaches. Furthermore, case studies of predicted circRNAs for specific diseases and the top predicted circRNA–disease associations are analyzed. The results show that the MSFCNN model could be an effective tool for mining potential circRNA–disease associations.

Circ09863 Regulates Unsaturated Fatty Acid Metabolism by Adsorbing miR-27a-3p in Bovine Mammary Epithelial Cells

Fatty acid composition plays a key role in regulating flavor and quality of milk. Therefore, in order to improve milk quality, it is particularly important to investigate regulatory mechanisms of milk fatty acid metabolism. Circular RNAs (circRNAs) regulate expression genes associated with several biological processes including fatty acid metabolism. In this study, high-throughput sequencing was used to detect differentially expressed genes in bovine mammary tissue at early lactation and peak lactation. Circ09863 profiles were influenced by the lactation stage. Functional studies in bovine mammary epithelial cells (BMECs) revealed that circ09863 promotes triglyceride (TAG) synthesis together with increased content of unsaturated fatty acids (C16:1 and C18:1). These results suggested that circ09863 is partly responsible for modulating fatty acid metabolism. Additionally, software prediction identified a miR-27a-3p binding site in the circ09863 sequence. Overexpression of miR-27a-3p in BMECs led to decreased TAG synthesis. However, overexpression of circ09863 (pcDNA-circ09863) in BMECs significantly reduced expression of miR-27a-3p and enhanced gene expression of fatty acid synthase (FASN), a target of miR-27a-3p. Overall, data suggest that circ09863 relieves the inhibitory effect of miR-27a-3p on FASN expression by binding miR-27a-3p and subsequently regulating TAG synthesis and fatty acid composition. Together, these mechanisms provide new research avenues and theoretical bases to improve milk quality.

Identifying Circular RNA and Predicting Its Regulatory Interactions by Machine Learning

Circular RNA (circRNA) is a closed long non-coding RNA (lncRNA) formed by covalently closed loops through back-splicing. Emerging evidence indicates that circRNA can influence cellular physiology through various molecular mechanisms. Thus, accurate circRNA identification and prediction of its regulatory information are critical for understanding its biogenesis. Although several computational tools based on machine learning have been proposed for circRNA identification, the prediction accuracy remains to be improved. Here, first we present circLGB, a machine learning-based framework to discriminate circRNA from other lncRNAs. circLGB integrates commonly used sequence-derived features and three new features containing adenosine to inosine (A-to-I) deamination, A-to-I density and the internal ribosome entry site. circLGB categorizes circRNAs by utilizing a LightGBM classifier with feature selection. Second, we introduce circMRT, an ensemble machine learning framework to systematically predict the regulatory information for circRNA, including their interactions with microRNA, the RNA binding protein, and transcriptional regulation. Feature sets including sequence-based features, graph features, genome context, and regulatory information features were modeled in circMRT. Experiments on public and our constructed datasets show that the proposed algorithms outperform the available state-of-the-art methods. circLGB is available at http://www.circlgb.com. Source codes are available at https://github.com/Peppags/circLGB-circMRT.

The emerging landscape of circular RNAs in immunity: breakthroughs and challenges

Circular RNAs (circRNAs) are covalently linked RNAs that exhibit individual strand with a closed-loop framework compared with a conserving, steady and abundant linear counterpart. In recent years, as high-throughput sequencing advancement has been developing, functional circRNAs have been increasingly recognized, and more extensive analyses expounded their effect on different diseases. However, the study on the function of circRNAs in the immune system remains insufficient. This study discusses the basic principles of circRNAs regulation and the systems involved in physiology-related and pathology-related processes. The effect of circRNAs on immune regulation is elucidated. The ongoing development of circRNAs and basic immunology has multiplied their potential in treating diseases. Such perspective will summarize the status and effect of circRNAs on various immune cells in cancer, autoimmune diseases and infections. Moreover, this study will primarily expound the system of circRNAs in T lymphocytes, macrophages and other immune cells, which creates a novel perspective and lay a theoretical basis for treating diseases.

Matrix factorization with neural network for predicting circRNA-RBP interactions

Background

Circular RNA (circRNA) has been extensively identified in cells and tissues, and plays crucial roles in human diseases and biological processes. circRNA could act as dynamic scaffolding molecules that modulate protein-protein interactions. The interactions between circRNA and RNA Binding Proteins (RBPs) are also deemed to an essential element underlying the functions of circRNA. Considering cost-heavy and labor-intensive aspects of these biological experimental technologies, instead, the high-throughput experimental data has enabled the large-scale prediction and analysis of circRNA-RBP interactions.

Results

A computational framework is constructed by employing Positive Unlabeled learning (P-U learning) to predict unknown circRNA-RBP interaction pairs with kernel model MFNN (Matrix Factorization with Neural Networks). The neural network is employed to extract the latent factors of circRNA and RBP in the interaction matrix, the P-U learning strategy is applied to alleviate the imbalanced characteristics of data samples and predict unknown interaction pairs. For this purpose, the known circRNA-RBP interaction data samples are collected from the circRNAs in cancer cell lines database (CircRic), and the circRNA-RBP interaction matrix is constructed as the input of the model. The experimental results show that kernel MFNN outperforms the other deep kernel models. Interestingly, it is found that the deeper of hidden layers in neural network framework does not mean the better in our model. Finally, the unlabeled interactions are scored using P-U learning with MFNN kernel, and the predicted interaction pairs are matched to the known interactions database. The results indicate that our method is an effective model to analyze the circRNA-RBP interactions.

Conclusion

For a poorly studied circRNA-RBP interactions, we design a prediction framework only based on interaction matrix by employing matrix factorization and neural network. We demonstrate that MFNN achieves higher prediction accuracy, and it is an effective method.

Critical function of circular RNAs in lung cancer

Lung cancer is one of the main causes of cancer-related death in the world, especially due to its frequency and ineffective therapeutically approaches in the late stages of the disease. Despite the recent advent of promising new targeted therapies, lung cancer diagnostic strategies still have difficulty in identifying the disease at an early stage. Therefore, the characterizations of more sensible and specific cancer biomarkers have become an important goal for clinicians. Circular RNAs (circRNAs), a type of RNA with covalently closed continuous loop structures that display high structural resistance and tissue specificity pointed toward a potential biomarker role. Current investigations have identified that circRNAs have a prominent function in the regulation of oncogenic pathways, by regulating gene expression both at transcriptional and post-transcriptional level. The aim of this review is to provide novel information regarding the implications of circRNAs in lung cancer, with an emphasis on the role in disease development and progression. Initially, we explored the potential utility of circRNAs as biomarkers, focusing on function, mechanisms, and correlation with disease progression in lung cancer. Further, we will describe the interaction between circRNAs and other non-coding species of RNA (particularly microRNA) and their biological significance in lung cancer. Describing the nature of these interactions and their therapeutic potential will provide additional insight regarding the altered molecular landscape of lung cancer and consolidate the potential clinical value of these circular transcripts. This article is categorized under: RNA Structure and Dynamics > Influence of RNA Structure in Biological Systems RNA in Disease and Development > RNA in Disease RNA in Disease and Development > RNA in Development.