circRNA Prediction Research Articles

Circular RNA expression in turkey skeletal muscle satellite cells is significantly altered by thermal challenge.

Understanding the genetic mechanisms behind muscle growth and development is crucial for improving the efficiency of animal protein production. Recent poultry studies have identified genes related to muscle development and explored how environmental stressors, such as temperature extremes, affect protein production and meat quality. Non-coding RNAs, including circular RNAs (circRNAs), play crucial roles in modulating gene expression and regulating the translation of mRNAs into proteins. This study examined circRNA expression in turkey skeletal muscle stem cells under thermal stress. The objectives were to identify and quantify circRNAs, assess circRNA abundance following RNAse R depletion, identify differentially expressed circRNAs (DECs), and predict potential microRNA (miRNA) targets for DECs and their associated genes. Cultured cells from two genetic lines (Nicholas commercial turkey and The Ohio State Random Bred Control 2) under three thermal treatments: cold (33°C), control (38°C), and hot (43°C) were compared at both the proliferation and differentiation stages. CircRNA prediction and differential expression and splicing analyses were conducted using the CIRIquant pipeline for both the untreated and RNase R depletion treated libraries. Predicted interactions between DECs and miRNAs, as well as the potential impact of circRNA secondary structure on these interactions, were investigated. A total of 11,125 circRNAs were predicted within the treatment groups, between both untreated and RNase R treated libraries. Differential expression analyses indicated that circRNA expression was significantly altered by thermal treatments and the genetic background of the stem cells. A total of 140 DECs were identified across the treatment comparisons. In general, more DECs within temperature treatment comparisons were identified in the proliferation stage and more DECs within genetic line comparisons were identified in the differentiation stage. This study highlights the significant impact of environmental stressors on non-coding RNAs and their role in gene regulation. Elucidating the role of non-coding RNAs in gene regulation can help further our understanding of muscle development and poultry production, underscoring the broader implications of this research for enhancing animal protein production efficiency.

CircRNA identification and feature interpretability analysis

BackgroundCircular RNAs (circRNAs) can regulate microRNA activity and are related to various diseases, such as cancer. Functional research on circRNAs is the focus of scientific research. Accurate identification of circRNAs is important for gaining insight into their functions. Although several circRNA prediction models have been developed, their prediction accuracy is still unsatisfactory. Therefore, providing a more accurate computational framework to predict circRNAs and analyse their looping characteristics is crucial for systematic annotation.ResultsWe developed a novel framework, CircDC, for classifying circRNAs from other lncRNAs. CircDC uses four different feature encoding schemes and adopts a multilayer convolutional neural network and bidirectional long short-term memory network to learn high-order feature representation and make circRNA predictions. The results demonstrate that the proposed CircDC model is more accurate than existing models. In addition, an interpretable analysis of the features affecting the model is performed, and the computational framework is applied to the extended application of circRNA identification.ConclusionsCircDC is suitable for the prediction of circRNA. The identification of circRNA helps to understand and delve into the related biological processes and functions. Feature importance analysis increases model interpretability and uncovers significant biological properties. The relevant code and data in this article can be accessed for free at https://github.com/nmt315320/CircDC.git.

Identification of a lncRNA/circRNA-miRNA-mRNA ceRNA Network in Alzheimer's Disease.

Alzheimer's disease (AD) occurs in the elderly and pre-elderly, characterized by decline of memory, cognitive dysfunction, impairment of learning capacity, and motor dysfunction. Recently a competitive endogenous RNA (ceRNA) network has been found to be related to AD progression, but there is still little understanding of the ceRNA regulatory network in AD. This study aims to explore the important regulatory mechanisms of ceRNA regulatory networks containing long non-coding RNAs (lncRNAs), circular RNAs (circRNAs), microRNAs (miRNAs), and messenger RNAs (mRNAs) in AD. Data from the gene expression omnibus (GEO) database were used for the analysis. To study enrichment function for the upregulated and downregulated mRNAs, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed using the Metascape database, respectively. Based on the STRING database and Cytoscape software 3.9.1, a protein-protein interaction (PPI) network was constructed. The hub genes in this network were identified utilizing the CytoHubba plugin in Cytoscape. The TargetScan, miRWalk, and miRDB were selected to calculate the regulatory interaction between miRNAs and the hub genes. LncRNAs were predicted using RNA22. Additionally, circRNA prediction was executed using the circBank database. 711 downregulated and 670 upregulated overlapping mRNAs were identified between AD and control samples. 32 downregulated and 340 upregulated miRNAs were obtained from AD samples compared with control samples. 78 upregulated and 205 downregulated circRNAs were screened. 275 upregulated lncRNAs and 209 downregulated lncRNAs were found between AD samples and control samples. The PPI network constructed consists of 1016 nodes and 13,946 edges. Ten hub genes were selected to identify target miRNAs and ceRNAs. On the basis of the ceRNA hypothesis, a circRNA/lncRNA-miRNA-mRNA network was established. It included five lncRNAs (TRHDE-AS1, SNHG10, OIP5-AS, LINC00926 and LINC00662), 26 circRNAs, five miRNAs (hsa-miR-3158-3p, hsa-miR-4435, hsa-let-7d-3p, hsa-miR-330-5p and hsa-miR-3605-3p), and ten mRNAs (RPL11, RPL34, RPL21, RPL22, RPL6, RPL32, RPL24, RPL35, RPL31, and RPL35A). RPL35 and RPL35A were found to be significantly associated with AD pathology in tau and Aβ line AD models by the AlzData database. The study discovered the significance of several lncRNA-miRNA-mRNA axes and circRNA-miRNA-mRNA axes that included RPL35A and RPL35. ceRNAs were found to be important regulators in the development of AD and provide potential biological therapy targets for AD management.

Identification and Functional Prediction of CircRNAs Involved in Drought Responses in Sugar Beet (Beta vulgaris L.)

Identification and Functional Prediction of CircRNAs Involved in Drought Responses in Sugar Beet (Beta vulgaris L.)

Collaborative deep learning improves disease-related circRNA prediction based on multi-source functional information.

Emerging studies have shown that circular RNAs (circRNAs) are involved in a variety of biological processes and play a key role in disease diagnosing, treating and inferring. Although many methods, including traditional machine learning and deep learning, have been developed to predict associations between circRNAs and diseases, the biological function of circRNAs has not been fully exploited. Some methods have explored disease-related circRNAs based on different views, but how to efficiently use the multi-view data about circRNA is still not well studied. Therefore, we propose a computational model to predict potential circRNA-disease associations based on collaborative learning with circRNA multi-view functional annotations. First, we extract circRNA multi-view functional annotations and build circRNA association networks, respectively, to enable effective network fusion. Then, a collaborative deep learning framework for multi-view information is designed to get circRNA multi-source information features, which can make full use of the internal relationship among circRNA multi-view information. We build a network consisting of circRNAs and diseases by their functional similarity and extract the consistency description information of circRNAs and diseases. Last, we predict potential associations between circRNAs and diseases based on graph auto encoder. Our computational model has better performance in predicting candidate disease-related circRNAs than the existing ones. Furthermore, it shows the high practicability of the method that we use several common diseases as case studies to find some unknown circRNAs related to them. The experiments show that CLCDA can efficiently predict disease-related circRNAs and are helpful for the diagnosis and treatment of human disease.

Identification and Functional Prediction of CircRNAs in Leaves of F1 Hybrid Poplars with Different Growth Potential and Their Parents.

Circular RNAs (CircRNAs) regulate plant growth and development; however, their role in poplar heterosis is unclear. We identified 3722 circRNAs in poplar leaves, most of which were intergenic (57.2%) and exonic (40.2%). The expression of circRNAs in F1 hybrids with high growth potential was higher than that in those with low growth potential. Non-additive expression of circRNAs and single-parent expression of circRNAs (SPE-circRNAs) might regulate poplar heterosis through microRNA sponging and protein translation, respectively. DECs among F1 hybrids with different growth potentials might regulate the growth potential of poplar via microRNA sponging. Correlation analysis between circRNA expression and its parent gene expression showed that SPE-M circRNA (circRNAs expressed by male parent only) might regulate poplar heterosis by inhibiting parent gene expression, while other circRNAs might regulate poplar heterosis by enhancing parent gene expression. Weighted correlation network analysis of gene/circRNA expression showed that circRNAs mainly regulate poplar heterosis via carbohydrate metabolism, amino acid metabolism, energy metabolism, and material transport. In addition, we identified seven circRNAs that positively or negatively regulate poplar heterosis. Thus, non-additively expressed circRNAs and SPE circRNAs are involved in regulating poplar heterosis, and DECs among F1 hybrids with different growth potentials were involved in regulating poplar growth potential.

StackCirRNAPred: computational classification of long circRNA from other lncRNA based on stacking strategy

BackgroundCircRNAs are essential for the regulation of post-transcriptional gene expression, including as miRNA sponges, and play an important role in disease development. Some computational tools have been proposed recently to predict circRNA, since only one classifier is used, there is still much that can be done to improve the performance.ResultsStackCirRNAPred was proposed, the computational classification of long circRNA from other lncRNA based on stacking strategy. In order to cope with the potential problem that a single feature might not be able to distinguish circRNA well from other lncRNA, we first extracted features from different sources, including nucleic acid composition, sequence spatial features and physicochemical properties, Alu and tandem repeats. We innovatively apply the stacking strategy to integrate the more advantageous classifiers of RF, LightGBM, XGBoost. This allows the model to incorporate these features more flexibly. StackCirRNAPred was found to be significantly better than other tools, with precision, accuracy, F1, recall and MCC of 0.843, 0.833, 0.831, 0.819 and 0.666 respectively. We tested it directly on the mouse dataset. StackCirRNAPred was still significantly better than other methods, with precision, accuracy, F1, recall and MCC of 0.837, 0.839, 0.839, 0.841, 0.677.ConclusionsWe proposed StackCirRNAPred based on stacking strategy to distinguish long circRNAs from other lncRNAs. With the test results demonstrating the validity and robustness of StackCirRNAPred, we hope StackCirRNAPred will complement existing circRNA prediction methods and is helpful in down-stream research.

Identification and functional prediction of CircRNAs of developing seeds in high oleic acid sunflower (Helianthus annuus L.)

Identification and functional prediction of CircRNAs of developing seeds in high oleic acid sunflower (Helianthus annuus L.)

Association prediction of CircRNAs and diseases using multi-homogeneous graphs and variational graph auto-encoder

As a non-coding RNA molecule with closed-loop structure, circular RNA (circRNA) is tissue-specific and cell-specific in expression pattern. It regulates disease development by modulating the expression of disease-related genes. Therefore, exploring the circRNA-disease relationship can reveal the molecular mechanism of disease pathogenesis. Biological experiments for detecting circRNA-disease associations are time-consuming and laborious. Constrained by the sparsity of known circRNA-disease associations, existing algorithms cannot obtain relatively complete structural information to represent features accurately. To this end, this paper proposes a new predictor, VGAERF, combining Variational Graph Auto-Encoder (VGAE) and Random Forest (RF). Firstly, circRNA homogeneous graph structure and disease homogeneous graph structure are constructed by Gaussian interaction profile (GIP) kernel similarity, semantic similarity, and known circRNA-disease associations. VGAEs with the same structure are employed to extract the higher-order features by the encoding and decoding of input graph structures. To further increase the completeness of the network structure information, the deep features acquired from the two VGAEs are summed, and then train the RF with sparse data processing capability to perform the prediction task. On the independent test set, the Area Under ROC Curve (AUC), accuracy, and Area Under PR Curve (AUPR) of the proposed method reach up to 0.9803, 0.9345, and 0.9894, respectively. On the same dataset, the AUC, accuracy, and AUPR of VGAERF are 2.09%, 5.93%, and 1.86% higher than the best-performing method (AEDNN). It is anticipated that VGAERF will provide significant information to decipher the molecular mechanisms of circRNA-disease associations, and promote the diagnosis of circRNA-related diseases.

In Silico Identification and Characterization of circRNAs During Host-Pathogen Interactions.

Circular RNAs (circRNAs) are a class of non-coding RNAs that are formed via back-splicing. These circRNAs are predominantly studied for their roles as regulators of various biological processes. Notably, emerging evidence demonstrates that host circRNAs can be differentially expressed (DE) upon infection withpathogens (e.g., influenza and coronaviruses), suggesting a role for circRNAs in regulating host innate immune responses. However, investigations on the role of circRNAs during pathogenic infections are limited by the knowledge and skills required to carry out the necessary bioinformatic analysis to identify DE circRNAs from RNA sequencing (RNA-seq) data. Bioinformatics prediction and identification of circRNAs is crucial before any verification, and functional studies using costly and time-consuming wet-lab techniques. To solve this issue, a step-by-step protocol of in silico prediction and characterization of circRNAs using RNA-seq data is provided in this manuscript. The protocol can be divided into four steps: 1) Prediction and quantification of DE circRNAs via the CIRIquant pipeline; 2) Annotation via circBase and characterization of DE circRNAs; 3) CircRNA-miRNA interaction prediction through Circr pipeline; 4) functional enrichment analysis of circRNA parental genes using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG). This pipeline will be useful in driving future in vitro and in vivo research to further unravel the role of circRNAs in host-pathogen interactions.

Functional prediction and profiling of exosomal circRNAs derived from seminal plasma for the diagnosis and treatment of oligoasthenospermia.

Oligoasthenospermia (OAZ) is the most common element contributing to male infertility. However, the etiology of OAZ remains unknown in the majority of cases. Growing evidence indicates that exosomal circular (circ)RNAs may exhibit potential as biological markers for the detection of various disorders. The available information on exosomes derived from seminal plasma is limited. The present study investigated the composition and role of circRNAs in exosomes isolated from seminal plasma of patients with OAZ. Exosomes were isolated from the seminal plasma of 12 patients with OAZ and 12 matched healthy controls. Thereafter, RNA sequencing was performed using exosomes from both groups to identify circRNAs associated with OAZ. The sequencing data revealed a total of 14,991 circRNAs. Among these, 7,635 were upregulated and 7,356 were downregulated in patients with OAZ. Gene Ontology functional enrichment analysis revealed that the differentially expressed exosomal circRNAs were primarily enriched in ‘protein binding’, ‘intracellular organelles’ and ‘cellular metabolism’. Kyoto Encyclopedia of Genes and Genomes pathway analysis revealed that the differentially expressed exosomal circRNAs were enriched in ‘ubiquitin-mediated proteolysis’, ‘endocytosis’ and ‘RNA transport’, which are involved in spermatogenesis-related pathways. Then seven differentially expressed circRNAs were predicted and validated as putative upstream targets and their target genes also were detected by reverse transcription-quantitative PCR. CircRNA-microRNA-mRNA network was constructed to predict their potential functions. The findings provide a preliminary foundation for identifying the potential diagnostic value of critical exosomal circRNAs involved in OAZ.

Identification of Potential Biomarkers of Platelet RNA in Glioblastoma by Bioinformatics Analysis.

Objective Glioblastoma is one of the most common and fatal malignancies in adults. Current treatment is still not optimistic. Glioblastoma (GBM) transports RNA to platelets in the blood system via microvesicles, suggesting that platelet RNA can be a potential diagnostic and therapeutic target. The roles of specific platelet RNAs in treatment of GBM are not well understood. Methods Platelet RNA profiling of 8 GBM and 12 normal samples were downloaded from the GEO database. Differentially expressed genes (DEGs) were identified between tumors and normal samples. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to elucidate the functions of up- and downregulated genes. miRNA was predicted by miRTarBase, TargetScan, and miRDB databases. circBase and circBank were used for circRNA prediction. ceRNA (circRNA-mRNA-miRNA) network was constructed to investigate the potential interactions. Results 22 genes were upregulated and 9 genes were downregulated. There are only two genes (CCR7 and FAM102A) that connect to miRNAs (hsa-let-7a-5p, hsa-miR-1-3p). We assessed the overall survival rates by Kaplan-Meier plotter, and relative expression of GBM and subtypes for overlapped mRNA (CCR7 and FAM102A) were evaluated, and further, we obtained circRNAs (has-circ-0015164, hsa-circ-0003243) by circBank and circBase and bind sites through the CSCD database. Finally, a ceRNA network (circRNA-mRNA-miRNA) was constructed based on 2 miRNAs, 2 mRNAs, and 2 circRNAs by Cytoscape. This study focused on potential mRNA and ceRNA biomarkers to targeted treatment of GBM and provided ideas for clinical treatment through the combination of hematology and oncology. Conclusion The findings of this study contribute to better understand the relationship between GBM and the blood system (platelets) and might lay a solid foundation for improving GBM molecule and gene diagnosis and prognosis.

Genome-wide identification of circular RNAs in adult Schistosoma japonicum

Circular RNAs (circRNAs) are a class of novel, widespread, covalently closed RNAs that have played an essential role in animal gene regulation. To systematically explore circRNAs in the blood fluke Schistosoma japonicum, we performed RNA sequencing and bioinformatics analysis, and found that hundreds of circRNAs showed gender-associated expression. Among these identified circRNAs, more than 77.54% and 74.73% were putatively derived from the exon region of the genome and some circRNAs showed gender-associated expressions. The functional prediction of circRNAs (circ_003826 and circ_004690) showed potential binding sites and possibly acted as the sponge to regulate microRNAs (miRNAs) sja-miR-1, sja-miR-133 and sja-miR-3504. Altogether, these findings demonstrated that S. japonicum also contains circRNAs, which may have potential regulatory roles during schistosome development.

Identification of lncRNA/circRNA-miRNA-mRNA ceRNA Network as Biomarkers for Hepatocellular Carcinoma.

Background: Hepatocellular carcinoma (HCC) accounts for the majority of liver cancer, with the incidence and mortality rates increasing every year. Despite the improvement of clinical management, substantial challenges remain due to its high recurrence rates and short survival period. This study aimed to identify potential diagnostic and prognostic biomarkers in HCC through bioinformatic analysis. Methods: Datasets from GEO and TCGA databases were used for the bioinformatic analysis. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were carried out by WebGestalt website and clusterProfiler package of R. The STRING database and Cytoscape software were used to establish the protein-protein interaction (PPI) network. The GEPIA website was used to perform expression analyses of the genes. The miRDB, miRWalk, and TargetScan were employed to predict miRNAs and the expression levels of the predicted miRNAs were explored via OncomiR database. LncRNAs were predicted in the StarBase and LncBase while circRNA prediction was performed by the circBank. ROC curve analysis and Kaplan-Meier (KM) survival analysis were performed to evaluate the diagnostic and prognostic value of the gene expression, respectively. Results: A total of 327 upregulated and 422 downregulated overlapping DEGs were identified between HCC tissues and noncancerous liver tissues. The PPI network was constructed with 89 nodes and 178 edges and eight hub genes were selected to predict upstream miRNAs and ceRNAs. A lncRNA/circRNA-miRNA-mRNA network was successfully constructed based on the ceRNA hypothesis, including five lncRNAs (DLGAP1-AS1, GAS5, LINC00665, TYMSOS, and ZFAS1), six circRNAs (hsa_circ_0003209, hsa_circ_0008128, hsa_circ_0020396, hsa_circ_0030051, hsa_circ_0034049, and hsa_circ_0082333), eight miRNAs (hsa-miR-150-5p, hsa-miR-19b-3p, hsa-miR-23b-3p, hsa-miR-26a-5p, hsa-miR-651-5p, hsa-miR-10a-5p, hsa-miR-214-5p and hsa-miR-486-5p), and five mRNAs (CDC6, GINS1, MCM4, MCM6, and MCM7). The ceRNA network can promote HCC progression via cell cycle, DNA replication, and other pathways. Clinical diagnostic and survival analyses demonstrated that the ZFAS1/hsa-miR-150-5p/GINS1 ceRNA regulatory axis had a high diagnostic and prognostic value. Conclusion: These results revealed that cell cycle and DNA replication pathway could be potential pathways to participate in HCC development. The ceRNA network is expected to provide potential biomarkers and therapeutic targets for HCC management, especially the ZFAS1/hsa-miR-150-5p/GINS1 regulatory axis.

CRAFT: a bioinformatics software for custom prediction of circular RNA functions.

Circular RNAs (circRNAs), transcripts generated by backsplicing, are particularly stable and pleiotropic molecules, whose dysregulation drives human diseases and cancer by modulating gene expression and signaling pathways. CircRNAs can regulate cellular processes by different mechanisms, including interaction with microRNAs (miRNAs) and RNA-binding proteins (RBP), and encoding specific peptides. The prediction of circRNA functions is instrumental to interpret their impact in diseases, and to prioritize circRNAs for functional investigation. Currently, circRNA functional predictions are provided by web databases that do not allow custom analyses, while self-standing circRNA prediction tools are mostly limited to predict only one type of function, mainly focusing on the miRNA sponge activity of circRNAs. To solve these issues, we developed CRAFT (CircRNA Function prediction Tool), a freely available computational pipeline that predicts circRNA sequence and molecular interactions with miRNAs and RBP, along with their coding potential. Analysis of a set of circRNAs with known functions has been used to appraise CRAFT predictions and to optimize its setting. CRAFT provides a comprehensive graphical visualization of the results, links to several knowledge databases, and extensive functional enrichment analysis. Moreover, it originally combines the predictions for different circRNAs. CRAFT is a useful tool to help the user explore the potential regulatory networks involving the circRNAs of interest and generate hypotheses about the cooperation of circRNAs into the modulation of biological processes.

Differential Expression Profiles and Functional Prediction of circRNAs in Necrotizing Enterocolitis.

Circular RNAs (circRNAs), a novel type of noncoding RNAs, have been demonstrated to behave as microRNA (miRNA) sponges to exert their effects during pathological processes of diseases. However, the roles of circRNAs have not been explored in necrotizing enterocolitis (NEC). This study sought to identify differentially expressed circRNAs and predict their potential biological functions in NEC. circRNA expression profiles in terminal ileum from newborn rats with NEC and normal controls were explored using next-generation sequencing. In the NEC group, 53 circRNAs were significantly differentially expressed, including 9 upregulated and 44 downregulated. Gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses were conducted, and circRNA-miRNA interaction networks were generated to predict the potential roles of circRNAs in NEC progression. Further investigation revealed that most circRNAs include miRNA binding sites and that some are implicated in NEC development. In conclusion, this study's findings demonstrate that differentially expressed circRNAs are involved in NEC development via their interactions with miRNAs, making them prospective targets for NEC diagnosis and treatment.

JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites

MotivationCircular RNA (circRNA) is a novel class of long non-coding RNAs that have been broadly discovered in the eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backspliced to an upstream acceptor site. These circRNA sequences are conserved across species. More importantly, rising evidence suggests their vital roles in gene regulation and association with diseases. As the fundamental effort toward elucidating their functions and mechanisms, several computational methods have been proposed to predict the circular structure from the primary sequence. Recently, advanced computational methods leverage deep learning to capture the relevant patterns from RNA sequences and model their interactions to facilitate the prediction. However, these methods fail to fully explore positional information of splice junctions and their deep interaction.ResultsWe present a robust end-to-end framework, Junction Encoder with Deep Interaction (JEDI), for circRNA prediction using only nucleotide sequences. JEDI first leverages the attention mechanism to encode each junction site based on deep bidirectional recurrent neural networks and then presents the novel cross-attention layer to model deep interaction among these sites for backsplicing. Finally, JEDI can not only predict circRNAs but also interpret relationships among splice sites to discover backsplicing hotspots within a gene region. Experiments demonstrate JEDI significantly outperforms state-of-the-art approaches in circRNA prediction on both isoform level and gene level. Moreover, JEDI also shows promising results on zero-shot backsplicing discovery, where none of the existing approaches can achieve.Availability and implementationThe implementation of our framework is available at https://github.com/hallogameboy/JEDI.Supplementary information Supplementary data are available at Bioinformatics online.

PCirc: random forest-based plant circRNA identification software

BackgroundCircular RNA (circRNA) is a novel type of RNA with a closed-loop structure. Increasing numbers of circRNAs are being identified in plants and animals, and recent studies have shown that circRNAs play an important role in gene regulation. Therefore, identifying circRNAs from increasing amounts of RNA-seq data is very important. However, traditional circRNA recognition methods have limitations. In recent years, emerging machine learning techniques have provided a good approach for the identification of circRNAs in animals. However, using these features to identify plant circRNAs is infeasible because the characteristics of plant circRNA sequences are different from those of animal circRNAs. For example, plants are extremely rich in splicing signals and transposable elements, and their sequence conservation in rice, for example is far less than that in mammals. To solve these problems and better identify circRNAs in plants, it is urgent to develop circRNA recognition software using machine learning based on the characteristics of plant circRNAs.ResultsIn this study, we built a software program named PCirc using a machine learning method to predict plant circRNAs from RNA-seq data. First, we extracted different features, including open reading frames, numbers of k-mers, and splicing junction sequence coding, from rice circRNA and lncRNA data. Second, we trained a machine learning model by the random forest algorithm with tenfold cross-validation in the training set. Third, we evaluated our classification according to accuracy, precision, and F1 score, and all scores on the model test data were above 0.99. Fourth, we tested our model by other plant tests, and obtained good results, with accuracy scores above 0.8. Finally, we packaged the machine learning model built and the programming script used into a locally run circular RNA prediction software, Pcirc (https://github.com/Lilab-SNNU/Pcirc).ConclusionBased on rice circRNA and lncRNA data, a machine learning model for plant circRNA recognition was constructed in this study using random forest algorithm, and the model can also be applied to plant circRNA recognition such as Arabidopsis thaliana and maize. At the same time, after the completion of model construction, the machine learning model constructed and the programming scripts used in this study are packaged into a localized circRNA prediction software Pcirc, which is convenient for plant circRNA researchers to use.

Prediction of disease-associated circRNAs via circRNA–disease pair graph and weighted nuclear norm minimization

Circular RNA (circRNA) is a special single-stranded, non-coding RNA molecule. A variety of circRNAs are widely distributed in organisms and can regulate gene expression by adsorbing miRNAs and proteins. Therefore, abnormal expression of circRNAs can reflect a variety of diseases. In this study, from a computational perspective, potential circRNA–disease relationships are predicted by a novel method named PDC-PGWNNM. A pair graph of circRNA–disease is designed using the interactions of circRNAs with miRNAs and regulatory relationship of miRNAs in diseases. After extracting a reliable negative set, the original observation set is expanded, and a weighted nuclear norm minimization model is used to predict the potential circRNA–disease associations. Experimental results show that PDC-PGWNNM has better performance than existing methods. At the same time, the rationality of the pair graph is explored. The regulatory information of miRNAs and the expression profiles of circRNAs are used to analyse the predicted disease–circRNAs. Special cases are discussed for glioma, colorectal cancer and coronary heart disease.

Possible immune regulation mechanisms for the progression of chronic thromboembolic pulmonary hypertension

PurposeThis study aimed to screen key genes significantly associated with chronic thromboembolic pulmonary hypertension (CTEPH) and predicted suitable drugs for the treatment of CTEPH from the perspective of immune cells. MethodsThe dataset GSE130391 was used for this analysis. Differentially expressed genes (DEGs) between the CTEPH and control groups were screened. Abundance of infiltrating immune cells was analyzed and immune-related DEGs were identified. Next, the circular RNA (circRNA)-micro RNA (miRNA)-mRNA network was constructed, followed by functional enrichment analysis. Then, the protein-protein interaction (PPI) network was constructed and drug-gene interactions were predicted. Finally, miRNA and circRNA prediction results were verified by our previously published studies. ResultsFive key immune cell-related DEGs [CD83 molecule (CD83), complement c5a receptor 1 (C5AR1), atypical chemokine receptor 1 (ACKR1), profilin 2 (PFN2), and solute carrier family 2 member 3 (SLC2A3)] were identified. Several circRNA-miRNA-mRNA interactions were obtained, including circ_0022342miR-503-5pSLC2A3 and circ_0002062miR-92b-3p/miR-92a-3pmannosidase alpha class 2A member 1 (MAN2A1). Immune cell for SLC2A3 was eosinophils and for MAN2A1 was regulatory T cells (Tregs). Additionally, Glufosfamide and Kifunensine might be suitable as candidate drugs for CTEPH treatment. ConclusionsSLC2A3 and MAN2A1 may be important genes for the pathogenesis of CTEPH. Possible immune regulation mechanisms in CTEPH may be circ_0022342miR-503-5pSLC2A3 and circ_0002062miR-92b-3p/miR-92a-3pMAN2A1. These results may be helpful for the diagnosis and treatment of CTEPH from the perspective of immunology.