RNA-binding proteins (RBPs) are essential for post-transcriptional gene regulation in eukaryotes, including splicing control, mRNA transport and decay. Thus, accurate identification of RBPs is important to understand gene expression and regulation of cell state. In order to detect RBPs, a number of computational models have been developed. These methods made use of datasets from several eukaryotic species, specifically from mice and humans. Although some models have been tested on Arabidopsis, these techniques fall short of correctly identifying RBPs for other plant species. Therefore, the development of a powerful computational model for identifying plant-specific RBPs is needed. In this study, we presented a novel computational model for locating RBPs in plants. Five deep learning models and ten shallow learning algorithms were utilized for prediction with 20 sequence-derived and 20 evolutionary feature sets. The highest repeated five-fold cross-validation accuracy, 91.24% AU-ROC and 91.91% AU-PRC, was achieved by light gradient boosting machine. While evaluated using an independent dataset, the developed approach achieved 94.00% AU-ROC and 94.50% AU-PRC. The proposed model achieved significantly higher accuracy for predicting plant-specific RBPs as compared to the currently available state-of-art RBP prediction models. Despite the fact that certain models have already been trained and assessed on the model organism Arabidopsis, this is the first comprehensive computer model for the discovery of plant-specific RBPs. The web server RBPLight was also developed, which is publicly accessible at https://iasri-sg.icar.gov.in/rbplight/, for the convenience of researchers to identify RBPs in plants.

Most SNPs associated with complex diseases seem to lie in non-coding regions of the genome; however, their contribution to gene expression and disease phenotype remains poorly understood. Here, we established a workflow to provide assistance in prioritising the functional relevance of non-coding SNPs of candidate genes as susceptibility loci in polygenic neurological disorders. To illustrate the applicability of our workflow, we considered the multifactorial disorder migraine as a model to follow our step-by-step approach. We annotated the overlap of selected SNPs with regulatory elements and assessed their potential impact on gene expression based on publicly available prediction algorithms and functional genomics information. Some migraine risk loci have been hypothesised to reside in non-coding regions and to be implicated in the neurotransmission pathway. In this study, we used a set of 22 non-coding SNPs from neurotransmission and synaptic machinery-related genes previously suggested to be involved in migraine susceptibility based on our candidate gene association studies. After prioritising these SNPs, we focused on non-reported ones that demonstrated high regulatory potential: (1) VAMP2_rs1150 (3' UTR) was predicted as a target of hsa-mir-5010-3p miRNA, possibly disrupting its own gene expression; (2) STX1A_rs6951030 (proximal enhancer) may affect the binding affinity of zinc-finger transcription factors (namely ZNF423) and disturb TBL2 gene expression; and (3) SNAP25_rs2327264 (distal enhancer) expected to be in a binding site of ONECUT2 transcription factor. This study demonstrated the applicability of our practical workflow to facilitate the prioritisation of potentially relevant non-coding SNPs and predict their functional impact in multifactorial neurological diseases.

The chromatin loops in the three-dimensional (3D) structure of chromosomes are essential for the regulation of gene expression. Despite the fact that high-throughput chromatin capture techniques can identify the 3D structure of chromosomes, chromatin loop detection utilizing biological experiments is arduous and time-consuming. Therefore, a computational method is required to detect chromatin loops. Deep neural networks can form complex representations of Hi-C data and provide the possibility of processing biological datasets. Therefore, we propose a bagging ensemble one-dimensional convolutional neural network (Be-1DCNN) to detect chromatin loops from genome-wide Hi-C maps. First, to obtain accurate and reliable chromatin loops in genome-wide contact maps, the bagging ensemble learning method is utilized to synthesize the prediction results of multiple 1DCNN models. Second, each 1DCNN model consists of three 1D convolutional layers for extracting high-dimensional features from input samples and one dense layer for producing the prediction results. Finally, the prediction results of Be-1DCNN are compared to those of the existing models. The experimental results indicate that Be-1DCNN predicts high-quality chromatin loops and outperforms the state-of-the-art methods using the same evaluation metrics. The source code of Be-1DCNN is available for free at https://github.com/HaoWuLab-Bioinformatics/Be1DCNN.

Post-translational modifications (PTMs) either enhance a protein's activity in various sub-cellular processes, or degrade their activity which leads toward failure of intracellular processes. Tyrosine nitration (NT) modification degrades protein's activity that initiates and propagates various diseases including neurodegenerative, cardiovascular, autoimmune diseases and carcinogenesis. Identification of NT modification supports development of novel therapies and drug discoveries for associated diseases. Identification of NT modification in biochemical labs is expensive, time consuming and error-prone. To supplement this process, several computational approaches have been proposed. However these approaches fail to precisely identify NT modification, due to the extraction of irrelevant, redundant and less discriminative features from protein sequences. This paper presents the NTpred framework that is competent in extracting comprehensive features from raw protein sequences using four different sequence encoders. To reap the benefits of different encoders, it generates four additional feature spaces by fusing different combinations of individual encodings. Furthermore, it eradicates irrelevant and redundant features from eight different feature spaces through a Recursive Feature Elimination process. Selected features of four individual encodings and four feature fusion vectors are used to train eight different Gradient Boosted Tree classifiers. The probability scores from the trained classifiers are utilized to generate a new probabilistic feature space, which is used to train a Logistic Regression classifier. On the BD1 benchmark dataset, the proposed framework outperforms the existing best-performing predictor in 5-fold cross validation and independent test evaluation with combined improvement of 13.7% in MCC and 20.1% in AUC. Similarly, on the BD2 benchmark dataset, the proposed framework outperforms the existing best-performing predictor with combined improvement of 5.3% in MCC and 1.0% in AUC. NTpred is publicly available for further experimentation and predictive use at: https://sds_genetic_analysis.opendfki.de/PredNTS/.

Following the central dogma of molecular biology, gene expression heterogeneity can aid in predicting and explaining the wide variety of protein products, functions and, ultimately, heterogeneity in phenotypes. There is currently overlapping terminology used to describe the types of diversity in gene expression profiles, and overlooking these nuances can misrepresent important biological information. Here, we describe transcriptome diversity as a measure of the heterogeneity in (1) the expression of all genes within a sample or a single gene across samples in a population (gene-level diversity) or (2) the isoform-specific expression of a given gene (isoform-level diversity). We first overview modulators and quantification of transcriptome diversity at the gene level. Then, we discuss the role alternative splicing plays in driving transcript isoform-level diversity and how it can be quantified. Additionally, we overview computational resources for calculating gene-level and isoform-level diversity for high-throughput sequencing data. Finally, we discuss future applications of transcriptome diversity. This review provides a comprehensive overview of how gene expression diversity arises, and how measuring it determines a more complete picture of heterogeneity across proteins, cells, tissues, organisms and species.

Determining cell types by single-cell transcriptomics data is fundamental for downstream analysis. However, cell clustering and data imputation still face the computation challenges, due to the high dropout rate, sparsity and dimensionality of single-cell data. Although some deep learning based solutions have been proposed to handle these challenges, they still can not leverage gene attribute information and cell topology in a sensible way to explore the consistent clustering. In this paper, we present scDeepFC, a deep information fusion-based single-cell data clustering method for cell clustering and data imputation. Specifically, scDeepFC uses a deep auto-encoder (DAE) network and a deep graph convolution network to embed high-dimensional gene attribute information and high-order cell-cell topological information into different low-dimensional representations, and then fuses them to generate a more comprehensive and accurate consensus representation via a deep information fusion network. In addition, scDeepFC integrates the zero-inflated negative binomial (ZINB) into DAE to model the dropout events. By jointly optimizing the ZINB loss and cell graph reconstruction loss, scDeepFC generates a salient embedding representation for clustering cells and imputing missing data. Extensive experiments on real single-cell datasets prove that scDeepFC outperforms other popular single-cell analysis methods. Both the gene attribute and cell topology information can improve the cell clustering.

Primary hyperparathyroidism is caused by solitary parathyroid adenomas (PTAs) in most cases (⁓85%), and it has been previously reported that PTAs are associated with cardiovascular disease (CVD) and type-2 diabetes (T2D). To understand the molecular basis of PTAs, we have investigated the genetic association amongst PTAs, CVD and T2D through an integrative network-based approach and observed a remarkable resemblance. The current study proposed to compare the PTAs-associated proteins with the overlapping proteins of CVD and T2D to determine the disease relationship. We constructed the protein-protein interaction network by integrating curated and experimentally validated interactions in humans. We found the $11$ highly clustered modules in the network, which contain a total of $13$ hub proteins (TP53, ESR1, EGFR, POTEF, MEN1, FLNA, CDKN2B, ACTB, CTNNB1, CAV1, MAPK1, G6PD and CCND1) that commonly co-exist in PTAs, CDV and T2D and reached to network's hierarchically modular organization. Additionally, we implemented a gene-set over-representation analysis over biological processes and pathways that helped to identify disease-associated pathways and prioritize target disease proteins. Moreover, we identified the respective drugs of these hub proteins. We built a bipartite network that helps decipher the drug-target interaction, highlighting the influential roles of these drugs on apparently unrelated targets and pathways. Targeting these hub proteins by using drug combinations or drug-repurposing approaches will improve the clinical conditions in comorbidity, enhance the potency of a few drugs and give a synergistic effect with better outcomes. This network-based analysis opens a new horizon for more personalized treatment and drug-repurposing opportunities to investigate new targets and multi-drug treatment and may be helpful in further analysis of the mechanisms underlying PTA and associated diseases.

A standard model that is able to generalize data on myriad involvement of the immune system in organismal physio-pathology and to provide a unified evolutionary teleology for immune functions in multicellular organisms remains elusive. A number of such 'general theories of immunity' have been proposed based on contemporaneously available data, starting with the usual description of self-nonself discrimination, followed by the 'danger model' and the more recent 'discontinuity theory.' More recent data deluge on involvement of immune mechanisms in a wide variety of clinical contexts, a number of which fail to get readily accommodated into the available teleologic standard models, makes deriving a standard model of immunity more challenging. But technological advances enabling multi-omics investigations into an ongoing immune response, covering genome, epigenome, coding and regulatory transcriptome, proteome, metabolome and tissue-resident microbiome, bring newer opportunities for developing a more integrative insight into immunocellular mechanisms within different clinical contexts. The new ability to map the heterogeneity of composition, trajectory and endpoints of immune responses, in both health and disease, also necessitates incorporation into the potential standard model of immune functions, which again can only be achieved through multi-omics probing of immune responses and integrated analyses of the multi-dimensional data.

Ion channels, in particular transient-receptor potential (TRP) channels, are essential genes that play important roles in many physiological processes. Emerging evidence has demonstrated that TRP genes are involved in a number of diseases, including various cancer types. However, we still lack knowledge about the expression alterations landscape of TRP genes across cancer types. In this review, we comprehensively reviewed and summarised the transcriptomes from more than 10 000 samples in 33 cancer types. We found that TRP genes were widespreadly transcriptomic dysregulated in cancer, which was associated with clinical survival of cancer patients. Perturbations of TRP genes were associated with a number of cancer pathways across cancer types. Moreover, we reviewed the functions of TRP family gene alterations in a number of diseases reported in recent studies. Taken together, our study comprehensively reviewed TRP genes with extensive transcriptomic alterations and their functions will directly contribute to cancer therapy and precision medicine.

Abnormalities of DNA modifications are closely related to the pathogenesis and prognosis of pancreatic cancer. The development of third-generation sequencing technology has brought opportunities for the study of new epigenetic modification in cancer. Here, we screened the N6-methyladenine (6mA) and 5-methylcytosine (5mC) modification in pancreatic cancer based on Oxford Nanopore Technologies sequencing. The 6mA levels were lower compared with 5mC and upregulated in pancreatic cancer. We developed a novel method to define differentially methylated deficient region (DMDR), which overlapped 1319 protein-coding genes in pancreatic cancer. Genes screened by DMDRs were more significantly enriched in the cancer genes compared with the traditional differential methylation method (P < 0.001 versus P = 0.21, hypergeometric test). We then identified a survival-related signature based on DMDRs (DMDRSig) that stratified patients into high- and low-risk groups. Functional enrichment analysis indicated that 891 genes were closely related to alternative splicing. Multi-omics data from the cancer genome atlas showed that these genes were frequently altered in cancer samples. Survival analysis indicated that seven genes with high expression (ADAM9, ADAM10, EPS8, FAM83A, FAM111B, LAMA3 and TES) were significantly associated with poor prognosis. In addition, the distinction for pancreatic cancer subtypes was determined using 46 subtype-specific genes and unsupervised clustering. Overall, our study is the first to explore the molecular characteristics of 6mA modifications in pancreatic cancer, indicating that 6mA has the potential to be a target for future clinical treatment.

G-quadruplex (G4), a non-classical deoxyribonucleic acid structure, is widely distributed in the genome and involved in various biological processes. In vivo, high-throughput sequencing has indicated that G4s are significantly enriched at functional regions in a cell-type-specific manner. Therefore, the prediction of G4s based on computational methods is necessary instead of the time-consuming and laborious experimental methods. Recently, G4 CUT&Tag has been developed to generate higher-resolution sequencing data than ChIP-seq, which provides more accurate training samples for model construction. In this paper, we present a new dataset construction method based on G4 CUT&Tag sequencing data and an XGBoost prediction model based on the machine learning boost method. The results show that our model performs well within and across cell types. Furthermore, sequence analysis indicates that the formation of G4 structure is greatly affected by the flanking sequences, and the GC content of the G4 flanking sequences is higher than non-G4. Moreover, we also identified G4 motifs in the high-resolution dataset, among which we found several motifs for known transcription factors (TFs), such as SP2 and BPC. These TFs may directly or indirectly affect the formation of the G4 structure.

Third-generation sequencing (TGS) technologies have revolutionized genome science in the past decade. However, the long-read data produced by TGS platforms suffer from a much higher error rate than that of the previous technologies, thus complicating the downstream analysis. Several error correction tools for long-read data have been developed; these tools can be categorized into hybrid and self-correction tools. So far, these two types of tools are separately investigated, and their interplay remains understudied. Here, we integrate hybrid and self-correction methods for high-quality error correction. Our procedure leverages the inter-similarity between long-read data and high-accuracy information from short reads. We compare the performance of our method and state-of-the-art error correction tools on Escherichia coli and Arabidopsis thaliana datasets. The result shows that the integration approach outperformed the existing error correction methods and holds promise for improving the quality of downstream analyses in genomic research.

With the global pandemic of COVID-19, the research on influenza virus has entered a new stage, but it is difficult to elucidate the pathogenesis of influenza disease. Genome-wide association studies (GWASs) have greatly shed light on the role of host genetic background in influenza pathogenesis and prognosis, whereas single-cell RNA sequencing (scRNA-seq) has enabled unprecedented resolution of cellular diversity and in vivo following influenza disease. Here, we performed a comprehensive analysis of influenza GWAS and scRNA-seq data to reveal cell types associated with influenza disease and provide clues to understanding pathogenesis. We downloaded two GWAS summary data, two scRNA-seq data on influenza disease. After defining cell types for each scRNA-seq data, we used RolyPoly and LDSC-cts to integrate GWAS and scRNA-seq. Furthermore, we analyzed scRNA-seq data from the peripheral blood mononuclear cells (PBMCs) of a healthy population to validate and compare our results. After processing the scRNA-seq data, we obtained approximately 70 000 cells and identified up to 13 cell types. For the European population analysis, we determined an association between neutrophils and influenza disease. For the East Asian population analysis, we identified an association between monocytes and influenza disease. In addition, we also identified monocytes as a significantly related cell type in a dataset of healthy human PBMCs. In this comprehensive analysis, we identified neutrophils and monocytes as influenza disease-associated cell types. More attention and validation should be given in future studies.

Tumor mutational burden (TMB) is a significant predictive biomarker for selecting patients that may benefit from immune checkpoint inhibitor therapy. Whole exome sequencing is a common method for measuring TMB; however, its clinical application is limited by the high cost and time-consuming wet-laboratory experiments and bioinformatics analysis. To address this challenge, we downloaded multimodal data of 326 gastric cancer patients from The Cancer Genome Atlas, including histopathological images, clinical data and various molecular data. Using these data, we conducted a comprehensive analysis to investigate the relationship between TMB, clinical factors, gene expression and image features extracted from hematoxylin and eosin images. We further explored the feasibility of predicting TMB levels, i.e. high and low TMB, by utilizing a residual network (Resnet)-based deep learning algorithm for histopathological image analysis. Moreover, we developed a multimodal fusion deep learning model that combines histopathological images with omics data to predict TMB levels. We evaluated the performance of our models against various state-of-the-art methods using different TMB thresholds and obtained promising results. Specifically, our histopathological image analysis model achieved an area under curve (AUC) of 0.749. Notably, the multimodal fusion model significantly outperformed the model that relied only on histopathological images, with the highest AUC of 0.971. Our findings suggest that histopathological images could be used with reasonable accuracy to predict TMB levels in gastric cancer patients, while multimodal deep learning could achieve even higher levels of accuracy. This study sheds new light on predicting TMB in gastric cancer patients.

Esophageal cancer (ESCA) has a bad prognosis. Long non-coding RNA (lncRNA) impacts on cell proliferation. However, the prognosis function of N6-methyladenosine (m6A)-associated lncRNAs (m6A-lncRNAs) in ESCA remains unknown. Univariate Cox analysis was applied to investigate prognosis related m6A-lncRNAs, based on which the samples were clustered. Wilcoxon rank and Chi-square tests were adopted to compare the clinical traits, survival, pathway activity and immune infiltration in different clusters where overall survival, clinical traits (N stage), tumor-invasive immune cells and pathway activity were found significantly different. Through least absolute shrinkage and selection operator and proportional hazard (Lasso-Cox) model, five m6A-lncRNAs were selected to construct the prognostic signature (m6A-lncSig) and risk score. To investigate the link between risk score and clinical traits or immunological microenvironments, Chi-square test and Spearman correlation analysis were utilized. Risk score was found connected with N stage, tumor stage, different clusters, macrophages M2, B cells naive and T cells CD4 memory resting. Risk score and tumor stage were found as independent prognostic variables. And the constructed nomogram model had high accuracy in predicting prognosis. The obtained m6A-lncSig could be taken as potential prognostic biomarker for ESCA patients. This study offers a theoretical foundation for clinical diagnosis and prognosis of ESCA.

In recent years, the emergence and development of single-cell sequencing technologies have provided unprecedented opportunities to analyze deoxyribonucleic acid, ribonucleic acid and proteins at single-cell resolution. The advancements and reduced costs of high-throughput technologies allow for parallel sequencing of multiple molecular layers from a single cell, providing a comprehensive insight into the biological state and behavioral mechanisms of cells through the integration of genomics, transcriptomics, epigenomics and proteomics information. Researchers are actively working to further improve the cost-effectiveness, stability and high-throughput capabilities of single-cell multi-omics sequencing technologies and exploring their potential in precision medicine through clinical diagnostics. This review aims to survey the cutting-edge advancements in single-cell multi-omics sequencing, summarizing the representative technologies and their applications in profiling complex diseases, with a particular focus on tumors.

Language models have shown the capacity to learn complex molecular distributions. In the field of molecular generation, they are designed to explore the distribution of molecules, and previous studies have demonstrated their ability to learn molecule sequences. In the early times, recurrent neural networks (RNNs) were widely used for feature extraction from sequence data and have been used for various molecule generation tasks. In recent years, the attention mechanism for sequence data has become popular. It captures the underlying relationships between words and is widely applied to language models. The Transformer-Layer, a model based on a self-attentive mechanism, also shines the same as the RNN-based model. In this research, we investigated the difference between RNNs and the Transformer-Layer to learn a more complex distribution of molecules. For this purpose, we experimented with three different generative tasks: the distributions of molecules with elevated scores of penalized LogP, multimodal distributions of molecules and the largest molecules in PubChem. We evaluated the models on molecular properties, basic metrics, Tanimoto similarity, etc. In addition, we applied two different representations of the molecule, SMILES and SELFIES. The results show that the two language models can learn complex molecular distributions and SMILES-based representation has better performance than SELFIES. The choice between RNNs and the Transformer-Layer needs to be based on the characteristics of dataset. RNNs work better on data focus on local features and decreases with multidistribution data, while the Transformer-Layer is more suitable when meeting molecular with larger weights and focusing on global features.

We identified 11 conserved stretches in over 6.3 million SARS-CoV-2 genomes including all the major variants of concerns. Each conserved stretch is ≥100 nucleotides in length with ≥99.9% conservation at each nucleotide position. Interestingly, six of the eight conserved stretches in ORF1ab overlapped significantly with well-folded experimentally verified RNA secondary structures. Furthermore, two of the conserved stretches were mapped to regions within the S2-subunit that undergo dynamic structural rearrangements during viral fusion. In addition, the conserved stretches were significantly depleted for zinc-finger antiviral protein (ZAP) binding sites, which facilitated the recognition and degradation of viral RNA. These highly conserved stretches in the SARS-CoV-2 genome were poorly conserved at the nucleotide level among closely related β-coronaviruses, thus representing ideal targets for highly specific and discriminatory diagnostic assays. Our findings highlight the role of structural constraints at both RNA and protein levels that contribute to the sequence conservation of specific genomic regions in SARS-CoV-2.

Single-cell clustering is the most significant part of single-cell RNA sequencing (scRNA-seq) data analysis. One main issue facing the scRNA-seq data is noise and sparsity, which poses a great challenge for the advance of high-precision clustering algorithms. This study adopts cellular markers to identify differences between cells, which contributes to feature extraction of single cells. In this work, we propose a high-precision single-cell clustering algorithm-SCMcluster (single-cell cluster using marker genes). This algorithm integrates two cell marker databases(CellMarker database and PanglaoDB database) with scRNA-seq data for feature extraction and constructs an ensemble clustering model based on the consensus matrix. We test the efficiency of this algorithm and compare it with other eight popular clustering algorithms on two scRNA-seq datasets derived from human and mouse tissues, respectively. The experimental results show that SCMcluster outperforms the existing methods in both feature extraction and clustering performance. The source code of SCMcluster is available for free at https://github.com/HaoWuLab-Bioinformatics/SCMcluster.

The expression and activity of transcription factors, which directly mediate gene transcription, are strictly regulated to control numerous normal cellular processes. In cancer, transcription factor activity is often dysregulated, resulting in abnormal expression of genes related to tumorigenesis and development. The carcinogenicity of transcription factors can be reduced through targeted therapy. However, most studies on the pathogenic and drug-resistant mechanisms of ovarian cancer have focused on the expression and signaling pathways of individual transcription factors. To improve the prognosis and treatment of patients with ovarian cancer, multiple transcription factors should be evaluated simultaneously to determine the effects of their protein activity on drug therapies. In this study, the transcription factor activity of ovarian cancer samples was inferred from virtual inference of protein activity by enriched regulon algorithm using mRNA expression data. Patients were clustered according to their transcription factor protein activities to investigate the association of transcription factor activities of different subtypes with prognosis and drug sensitivity for filtering subtype-specific drugs. Meanwhile, master regulator analysis was utilized to identify master regulators of differential protein activity between clustering subtypes, thereby identifying transcription factors associated with prognosis and assessing their potential as therapeutic targets. Master regulator risk scores were then constructed for guiding patients' clinical treatment, providing new insights into the treatment of ovarian cancer at the level of transcriptional regulation.