RESUMEN

Acute kidney injury (AKI) is an important clinical syndrome characterised by a sudden decline in renal function, often accompanied by renal inflammation and tubular epithelial cell damage. It has been reported that inhibiting DNA methylation significantly suppress the progression of AKI. In the current study, we investigate the effect of the DNA methyltransferase (DNMT) inhibitor RG108 in cisplatin- and hypoxia-reoxygenation-induced AKI. The expression of kidney injury molecules and inflammatory factors was examined by immunofluorescence, Western blotting and Real-time PCR. The results demonstrated that RG108 treatment significantly reduced kidney inflammation and injury. Furthermore, RNA-seq analysis was performed to reveal the regulatory mechanism of RG108 in AKI. The expression of the FOS and JUN genes, which are downstream of the MAPK pathway, were significant increased in AKI. Meanwhile, the expression of FOS and JUN were both inhibited by RG108, which is similar to what we found treatment with a specific JNK inhibitor and a specific p38 MAPK inhibitor, and thus attenuated renal inflammation and injury. In conclusion, we suggest that RG108 inhibits P38 MAPK/FOS and JNK/JUN pathways and attenuates renal injury and inflammatory responses. In these results, RG108 may become a novel MAPK pathway inhibitor and a clinical candidate for the treatment of AKI.

RESUMEN

Introduction: This study introduces the Supervised Magnitude-Altitude Scoring (SMAS) methodology, a novel machine learning-based approach for analyzing gene expression data from non-human primates (NHPs) infected with Ebola virus (EBOV). By focusing on host-pathogen interactions, this research aims to enhance the understanding and identification of critical biomarkers for Ebola infection. Methods: We utilized a comprehensive dataset of NanoString gene expression profiles from Ebola-infected NHPs. The SMAS system combines gene selection based on both statistical significance and expression changes. Employing linear classifiers such as logistic regression, the method facilitates precise differentiation between RT-qPCR positive and negative NHP samples. Results: The application of SMAS led to the identification of IFI6 and IFI27 as key biomarkers, which demonstrated perfect predictive performance with 100% accuracy and optimal Area Under the Curve (AUC) metrics in classifying various stages of Ebola infection. Additionally, genes including MX1, OAS1, and ISG15 were significantly upregulated, underscoring their vital roles in the immune response to EBOV. Discussion: Gene Ontology (GO) analysis further elucidated the involvement of these genes in critical biological processes and immune response pathways, reinforcing their significance in Ebola pathogenesis. Our findings highlight the efficacy of the SMAS methodology in revealing complex genetic interactions and response mechanisms, which are essential for advancing the development of diagnostic tools and therapeutic strategies. Conclusion: This study provides valuable insights into EBOV pathogenesis, demonstrating the potential of SMAS to enhance the precision of diagnostics and interventions for Ebola and other viral infections.

RESUMEN

BACKGROUND: Blood-brain barrier (BBB) dysfunction has been viewed as a potential underlying mechanism of neurodegenerative disorders, possibly involved in the pathogenesis and progression of Alzheimer's disease (AD). However, a relation between BBB dysfunction and dementia with Lewy bodies (DLB) has yet to be systematically investigated. Given the overlapping clinical features and neuropathology of AD and DLB, we sought to evaluate BBB permeability in the context of DLB and determine its association with plasma amyloid-ß (Aß) using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). METHODS: For this prospective study, we examined healthy controls (n = 24, HC group) and patients diagnosed with AD (n = 29) or DLB (n = 20) between December 2020 and April 2022. Based on DCE-MRI studies, mean rates of contrast agent transfer from intra- to extravascular spaces (Ktrans) were calculated within regions of interest. Spearman's correlation and multivariate linear regression were applied to analyze associations between Ktrans and specific clinical characteristics. RESULTS: In members of the DLB (vs HC) group, Ktrans values of cerebral cortex (p = 0.024), parietal lobe (p = 0.007), and occipital lobe (p = 0.014) were significantly higher; and Ktrans values of cerebral cortex (p = 0.041) and occipital lobe (p = 0.018) in the DLB group were significantly increased, relative to those of the AD group. All participants also showed increased Ktrans values of parietal ( ß  = 0.391; p = 0.001) and occipital ( ß  = 0.357; p = 0.002) lobes that were significantly associated with higher scores of the Clinical Dementia Rating, once adjusted for age and sex. Similarly, increased Ktrans values of cerebral cortex ( ß  = 0.285; p = 0.015), frontal lobe ( ß  = 0.237; p = 0.043), and parietal lobe ( ß = 0.265; p = 0.024) were significantly linked to higher plasma Aß1-42/Aß1-40 ratios, after above adjustments. CONCLUSION: BBB leakage is a common feature of DLB and possibly is even more severe than in the setting of AD for certain regions of the brain. BBB leakage appears to correlate with plasma Aß1-42/Aß1-40 ratio and dementia severity.

Asunto(s)

RESUMEN

Background: Bladder cancer carries a large societal burden, with over 570,000 newly diagnosed cases and 210,000 deaths globally each year. Platelets play vital functions in tumor progression and therapy benefits. We aimed to construct a platelet-related signature (PRS) for the clinical outcome of bladder cancer cases. Methods: Ten machine learning techniques were used in the integrative operations to build PRS using the datasets from The Cancer Genome Atlas (TCGA), gene series expression (GSE)13507, GSE31684, GSE32894 and GSE48276. A number of immunotherapy datasets and prediction scores, including GSE91061, GSE78220, and IMvigor210, were utilized to assess how well the PRS predicted the benefit of immunotherapy. Vitro experiment was performed to verify the role of α1C-tubulin (TUBA1C) in bladder cancer. Results: Enet (alpha =0.4) algorithm-based PRS had the highest average C-index of 0.73 and it was suggested as the optimal PRS. PRS acted as an independent risk factor for bladder cancer and patients with high PRS score portended a worse overall survival rate, with the area under the curve of 1-, 3- and 5-year operating characteristic curve being 0.754, 0.779 and 0.806 in TCGA dataset. A higher level of immune-activated cells, cytolytic function and T cell co-stimulation was found in the low PRS score group. Low PRS score demonstrated a higher tumor mutation burden score and programmed cell death protein 1 & cytotoxic T-lymphocyte associated protein 4 immunophenoscore, lower tumor immune dysfunction and exclusion score, intratumor heterogeneity score and immune escape score in bladder cancer, suggesting the PRS as an indicator for predicting immunotherapy benefits. Vitro experiment showed that TUBA1C was upregulated in bladder cancer and knockdown of TUBA1C obviously suppressed tumor cell proliferation. Conclusions: The present study developed an ideal PRS for bladder cancer, which may be used as a predictor of prognosis, a risk classification system, and a therapy guide.

RESUMEN

OBJECTIVE: Reconstruction of soft tissue defects after total parotidectomy requires a feasible and effective pedicled flap with sufficient volume. In this study, we introduce a modified submandibular gland flap (SMGF) for functional reconstruction of soft tissue defects resulting from total parotidectomy. MATERIALS AND METHODS: This study included 12 patients diagnosed with parotid gland carcinoma undergoing total parotidectomy and ipsilateral selective neck dissection. The modified SMGF was harvested and transferred to the parotid bed. This procedure was coupled with anastomosis between the parotid gland duct and Wharton's duct. The feasibility of the surgery, postoperative complications, facial profile restoration, and salivary secretion were assessed. RESULTS: All SMGFs pedicled only over the proximal facial artery survived without major complications. Facial profiles were well-restored, and salivary secretion was partially reserved. During the postoperative follow-up, no tumor recurrence was observed in any of the cases, and the volume of the SMGFs did not show obvious atrophy. CONCLUSIONS: The modified SMGF is a viable solution for volume restoration and functional reconstruction after total parotidectomy. CLINICAL RELEVANCE: This modified technique is simple and feasible for the functional reconstruction of soft tissue defects after total parotidectomy compared to other flaps and is worthy of clinical promotion.

RESUMEN

Retrosynthesis prediction is a fundamental problem in organic chemistry and drug synthesis. We proposed an end-to-end deep learning model called CTsynther (Contrastive Transformer for single-step retrosynthesis prediction model) that could provide single-step retrosynthesis prediction without external reaction templates or specialized knowledge. The model introduced the concept of contrastive learning in Transformer architecture and employed a contrastive learning language representation model at the SMILES sentence level to enhance model inference by learning similarities and differences between various samples. Mixed global and local attention mechanisms allow the model to capture features and dependencies between different atoms to improve generalization. We further investigated the embedding representations of SMILES learned automatically from the model. Visualization results show that the model could effectively acquire information about identical molecules and improve prediction performance. Experiments showed that the accuracy of retrosynthesis reached 53.5% and 64.4% for with and without reaction types, respectively. The validity of the predicted reactants is improved, showing competitiveness compared with semi-template methods.

RESUMEN

Using amino acid residues in peptide generation has solved several key problems, including precise control of amino acid sequence order, customized peptides for property modification, and large-scale peptide synthesis. Proteins contain unknown amino acid residues. Extracting them for the synthesis of drug-like peptides can create novel structures with unique properties, driving drug development. Computer-aided design of novel peptide drug molecules can solve the high-cost and low-efficiency problems in the traditional drug discovery process. Previous studies faced limitations in enhancing the bioactivity and drug-likeness of polypeptide drugs due to less emphasis on the connection relationships in amino acid structures. Thus, we proposed a reinforcement learning-driven generation model based on graph attention mechanisms for peptide generation. By harnessing the advantages of graph attention mechanisms, this model effectively captured the connectivity structures between amino acid residues in peptides. Simultaneously, leveraging reinforcement learning's strength in guiding optimal sequence searches provided a novel approach to peptide design and optimization. This model introduces an actor-critic framework with real-time feedback loops to achieve dynamic balance between attributes, which can customize the generation of multiple peptides for specific targets and enhance the affinity between peptides and targets. Experimental results demonstrate that the generated drug-like peptides meet specified absorption, distribution, metabolism, excretion, and toxicity properties and bioactivity with a success rate of over 90$\%$, thereby significantly accelerating the process of drug-like peptide generation.

Asunto(s)

RESUMEN

Background: Post-ischemic angiogenesis is crucial for reestablishing blood flow in conditions such as peripheral artery disease (PAD). The role of insulin-like growth factor-2 mRNA-binding protein 2 (IGF2BP2) in post-transcriptional RNA metabolism and its involvement in post-ischemic angiogenesis remains unclear. Methods: Using a human GEO database and a hind-limb ischemia (HLI) mouse model, the predominant isoform IGF2BP2 in ischemic gastrocnemius tissue was identified. Adeno-associated virus with the Tie1 promoter induced IGF2BP2 overexpression in the HLI model, evaluating the expression of vascular structural proteins (CD31 and α-SMA) and blood flow recovery after HLI. In vitro experiments with human umbilical vein endothelial cells (HUVECs) demonstrated that lentivirus-mediated IGF2BP2 overexpression upregulates cell proliferation, migration, and tube formation. GeneCards, RNAct databases, and subsequent reverse transcription quantitative polymerase chain reaction (RT-qPCR) predicted IGF2BP2 interactions with fibroblast growth factor 2 (FGF2) mRNA, and actinomycin D treatment, binding site predictions and CLIP-seq data further confirmed this interaction. Furthermore, western blotting, enzyme-linked immunosorbent assay, and RNA immunoprecipitation followed by RT-qPCR were performed to validate IGF2BP2's interaction with FGF2 mRNA and to assess its role in stabilizing FGF2 mRNA, as well as its impact on FGF2 protein expression. Results: HLI reduced IGF2BP2 expression in the gastrocnemius tissue, which gradually increased during blood flow recovery. IGF2BP2 overexpression in HLI mice accelerated blood flow recovery and increased capillary and small artery densities. The overexpression of IGF2BP2 in HUVECs stimulated proliferation, migration, and tube formation by interacting with FGF2 mRNA to increase its stability. This interaction resulted in increased levels of FGF2 protein and secretion, ultimately promoting angiogenesis. Conclusions: IGF2BP2 contributes to blood flow restoration post-ischemia in vivo and promotes angiogenesis in HUVECs by enhancing FGF2 mRNA stability and FGF2 protein expression and secretion. These findings underscore IGF2BP2's therapeutic potential in ischemic conditions, such as PAD.

RESUMEN

This study underscores the significance of precisely manipulating the morphology of the active layer in organic solar cells (OSCs). By blending polymer donors of D18 with varying molecular weights, a multiscale interpenetrating fiber network structure within the active layer is successfully created. The introduction of 10% low molecular weight D18 (LW-D18) into high molecular weight D18 (HW-D18) produces MIX-D18, which exhibits an extended exciton diffusion distance and orderly molecular stacking. Devices utilizing MIX-D18 demonstrate superior electron and hole transport, improves exciton dissociation, enhances charge collection efficiency, and reduces trap-assisted recombination compared to the other two materials. Through the use of the nonfullerene acceptor L8-BO, a remarkable power conversion efficiency (PCE) of 20.0% is achieved. This methodology, which integrates the favorable attributes of high and low molecular weight polymers, opens a new avenue for enhancing the performance of OSCs.

RESUMEN

Cross beam fracture is one of the common failures of vibrating screens, and crack is the early manifestation of fracture, which is hard to detect. In order to meet the screening requirement of the vibrating screen and improve the service life of the cracked beam, the cracked Euler-Bernoulli beam model is established to investigate the dynamics of the cross beam with a straight crack under different weights of eccentric block, processing capacities, and Rayleigh damping coefficients based on the finite element method in this paper. The local flexibility coefficients are derived from the principles of fracture mechanics and strain release energy and solved by the adaptive five-point Gaussian Legende algorithm. The stiffness matrix of the cracked beam element is calculated through the inverse method of total flexibility. The four order Runge-Kutta algorithm and MATLAB tools are used to solve the dynamic equation of the cracked cross beam. The relationship between the vibration amplitude of the cracked cross beam and the weight of the eccentric block is studied by fitting formulas using the least squares method. The influence of different weights of eccentric block, processing capacities, and Rayleigh damping coefficients on the vibration amplitude and service life of the cracked beam are discussed. The results show that the greater the weight of the eccentric block, the shorter service life of the beam. When the damping is greater, the service life of the cracked beam is longer.

RESUMEN

OBJECTIVE: Glioma is a central nervous system tumor arising from glial cells. Despite significant advances in diagnosis and treatment, most patients with high-grade gliomas have a poor prognosis. Many studies have shown that long noncoding RNAs (lncRNAs) may play important roles in the development, progression and treatment of many tumors, including gliomas. Molecularly targeted therapy may be a new direction for the adjuvant treatment of glioma. Therefore, we hope that by studying differentially expressed lncRNAs (DElncRNAs) in glioma, we can discover lncRNAs that can serve as biomarkers for glioma and provide better therapeutic modalities for glioma patients. METHODS: First, the expression of lncRNAs in 5 normal brain (NB) tissues and 10 glioma tissues was examined by RNA sequencing (RNA-seq). Next, we performed Kaplan-Meier analysis of data from The Cancer Genome Atlas (TCGA) database to assess the prognostic value of these variables. Finally, functional analysis of the DElncRNAs was performed by means of Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. RESULTS: RNA sequencing analysis revealed 85 upregulated miRNAs and 71 downregulated lncRNAs in low-grade glioma (LGG) and 50 upregulated lncRNAs and 70 downregulated lncRNAs in glioblastoma (GBM). Among them, AL355974.3 was the most upregulated lncRNA. LINC00632 was the most downregulated lncRNA. Second, LGG patients with higher AL355974.3 expression had worse overall survival according to Kaplan-Meier analysis of the TCGA database. Finally, bioinformatics analysis revealed that the target genes of these DElncRNAs were enriched in various biological processes and signaling pathways, such as cell metabolic and developmental processes. CONCLUSION: Our findings provide evidence that AL355974.3 may be a new biomarker for glioma.

RESUMEN

Background: The chronic pain arising from knee osteoarthritis (KOA) is a prevalent clinical manifestation. As a traditional Chinese approach, electroacupuncture (EA) has a positive influence in relieving chronic pain from KOA. The study aims to explore functional connectivity (FC) and effective connectivity (EC) alterations induced by EA in anterior cruciate ligament transection (ACLT) rat model of KOA using resting-state functional magnetic resonance imaging (fMRI). Methods: After the establishment of ACLT, rats were randomly divided into the EA group and the sham-EA group. The EA group received EA intervention while the sham-EA group received sham-intervention for 3 weeks. Mechanical pain threshold (MPT) assessment was performed before and after intervention, and fMRI was conducted after intervention. Results: EA intervention effectively relieved pain in post-ACLT rats. Results of rest-state functional connectivity (rs-FC) analysis revealed that compared with the sham-EA group, the EA group had higher FC between the right raphe and the left auditory cortex, the left caudate_ putamen and the left internal capsule (IC), as well as the right zona incerta (ZI) and the left piriform cortex, but lower FC between the right raphe and the left hippocampus ventral, as well as the right septum and the left septum. Furthermore, Granger causality analysis (GCA) found the altered EC between the right septum and the left septum, as well as the left IC and the right septum. Conclusion: The results confirmed the effect of EA on analgesia in post- ACLT rats. The alterations of FC and EC, mainly involving basal ganglia and limbic system neural connections, might be one of the neural mechanisms underlying the effect of EA, providing novel information about connectomics plasticity of EA following ACLT.

RESUMEN

Background: Bladder cancer is a common malignancy with high invasion and poor clinical outcome. Intratumor heterogeneity (ITH) is linked to cancer progression and metastasis and high ITH can accelerate tumor evolution. Our objective is to develop an ITH-related signature (IRS) for predicting clinical outcome and immunotherapy benefit in bladder cancer. Methods: Integrative procedure containing ten machine learning methods was applied to develop an IRS with The Cancer Genome Atlas (TCGA), gene series expression (GSE)13507, GSE31684, GSE32984 and GSE48276 datasets. To evaluate the performance of IRS in predicting the immunotherapy benefit, we also used several predicting scores and three immunotherapy datasets, including GSE91061, GSE78220 and IMvigor210. Results: The predicting model constructed with Enet (alpha =0.2) algorithm had a highest average C-index of 0.69, which was suggested as the optimal IRS. As an independent risk factor for bladder cancer, IRS had a powerful performance in predicting the overall survival (OS) rate of patients, with an area under curve of 1-, 3- and 5-year receiver operating characteristic (ROC) curve being 0.744, 0.791 and 0.816 in TCGA dataset. Bladder cancer patients with low IRS score presented with a higher level of immune-activated cells, cytolytic function and T cell co-stimulation. We also found a lower tumor immune dysfunction and exclusion (TIDE) score, lower immune escape score, higher programmed cell death protein 1 (PD-1) & cytotoxic T-lymphocyte associated protein 4 immunophenoscore, higher tumor mutation burden (TMB) score, higher response rate and better prognosis in bladder cancer with low IRS score. Bladder cancer cases with high IRS score had a higher half maximal inhibitory concentration value of common chemotherapy and targeted therapy regimens. Conclusions: The current study developed an optimal IRS for bladder cancer patients, which acted as an indicator for predicting prognosis, stratifying risk and guiding treatment for bladder cancer patients. Further analysis should be focused on the exploration the differentially expressed genes (DEGs) and related underlying mechanism mediating the development of bladder cancer in different IRS score group.

RESUMEN

BACKGROUND: Liver cancer (LC) remains a major cause of cancer death worldwide. Grasping prevalence trends is key to informing strategies for control and prevention. We analyzed the global, regional and national trends in LC prevalence and its major causes from 1990 to 2019. METHODS: We obtained LC age-standardized prevalence rate (ASPR) estimates from the Global Burden of Disease study 2019 and assessed trends using Joinpoint regression. LC cases were categorized into those due to hepatitis B virus (HBV), hepatitis C virus (HCV), alcohol use, nonalcoholic steatohepatitis (NASH) and other causes. RESULTS: While the ASPR of LC has shown a global decrease, there are specific regions where an increase in ASPR has been observed, with the highest rates in America. HBV remained the leading cause of LC (41.45 %) but significant increases occurred for HCV, alcohol use and NASH. Prevalence correlated with socioeconomic development. High-income countries had higher LC rates from HCV and alcohol but lower HBV-related LC. In high-income nations, LC prevalence climbs; the converse holds in middle- and low-income countries. CONCLUSIONS: Despite a global ASPR decrease, LC due to HCV, NASH, and alcohol is rising. Prevention strategies must prioritize HBV vaccination, HCV treatment, and alcohol regulation. IMPACT: The study informs targeted LC control policies and emphasizes the importance of continued monitoring and regional cooperation to combat LC.

RESUMEN

Calcination of MgCO3 is an important industrial reaction, but it causes significant and unfavorable CO2 production. Calcination in a reducing green hydrogen atmosphere can substantially reduce CO2 release and produce high value-added products such as CO or hydrocarbons, but the mechanism is still unclear. Here, the in situ transformation process of MgCO3 interacting with hydrogen and the specific formation mechanism of the high value-added products are thoroughly investigated based on reaction thermodynamic, ab initio molecular dynamics (AIMD) simulations, and density functional theory (DFT) calculations. The reaction thermodynamic parameters of MgCO3 coupled with hydrogen to produce CO or methane are calculated, revealing that increasing and decreasing the thermal reductive decomposition temperature favors the production of CO and methane, respectively. Kinetically, the energy barriers of each possible production pathway for the dominant products CO and methane are further calculated in conjunction with the AIMD simulation results of the transformation process. The results suggest that CO is produced via the MgO catalytic-carboxyl pathway (CO2*→ COOH*trans→ COOH*cis→ CO*→ CO), which is autocatalyzed by MgO derived from the thermal reductive decomposition of MgCO3. For the mechanism of methane formation, it prefers to be produced by the stepwise interaction of carbonates in the MgCO3 laminates with hydrogen adsorbed on their surfaces (direct conversion pathway: sur-O-CO → sur-O-HCO → sur-O-HCOH → sur-O-HC → sur-O-CH2 → sur-O-CH3 → sur-O + CH4*).

RESUMEN

We aimed to build a deep learning-based pathomics model to predict the early recurrence of non-muscle-infiltrating bladder cancer (NMIBC) in this work. A total of 147 patients from Xuzhou Central Hospital were enrolled as the training cohort, and 63 patients from Suqian Affiliated Hospital of Xuzhou Medical University were enrolled as the test cohort. Based on two consecutive phases of patch level prediction and WSI-level predictione, we built a pathomics model, with the initial model developed in the training cohort and subjected to transfer learning, and then the test cohort was validated for generalization. The features extracted from the visualization model were used for model interpretation. After migration learning, the area under the receiver operating characteristic curve for the deep learning-based pathomics model in the test cohort was 0.860 (95% CI 0.752-0.969), with good agreement between the migration training cohort and the test cohort in predicting recurrence, and the predicted values matched well with the observed values, with p values of 0.667766 and 0.140233 for the Hosmer-Lemeshow test, respectively. The good clinical application was observed using a decision curve analysis method. We developed a deep learning-based pathomics model showed promising performance in predicting recurrence within one year in NMIBC patients. Including 10 state prediction NMIBC recurrence group pathology features be visualized, which may be used to facilitate personalized management of NMIBC patients to avoid ineffective or unnecessary treatment for the benefit of patients.

Asunto(s)

RESUMEN

Herein, a practical three-component [2 + 1 + 3] cyclization of various cyclic ketones with α,ß-unsaturated aldehydes/ketones and ammonium iodide (NH4I) to access highly functional fused pyridines has been developed. The features of this transformation include mild reaction conditions, readily available starting materials, and excellent chemoselectivity. This protocol is compatible with various functional groups, and the preliminary studies on the mechanism of the reaction are also provided.

RESUMEN

The structural characteristics at the interface of bone implants can guide biological regulation. In this study, a dual-scale hierarchical microstructure is proposed and customized using hybrid machining to achieve temporal dependency osteogenic regulation. It is observed that osteoblasts induced by dual-scale hierarchical structure exhibit adequate protrusion development and rapid cell attachment through the modulation of mechanical forces in the cell growth environment, and further promot the upregulation of the cell membrane receptor PDGFR-α, which is related to cell proliferation. Afterward, transcriptomic analysis reveals that during the differentiation stage, the DSH structure regulates cellular signaling cascades primarily through integrin adhesion mechanisms and then accelerates osteogenic differentiation by activating the TGF-ß pathway and cAMP signaling pathway. Furthermore, the calcium nodules are preferentially deposited within the lower honeycomb-like channels, thereby endowing the proposed dual-scale hierarchical structure with the potential to induce oriented deposition and improve the long-term stability of the implant.

RESUMEN

Many noncoding RNAs (ncRNAs) have been identified, and many of them play vital roles in various biological processes, including gene expression regulation, epigenetic regulation, transcription, and control. Recently, a few observations revealed that ncRNAs are translated into functional peptides. Moreover, many computational methods have been developed to predict the coding potential of these transcripts, which contributes to a deeper investigation of their functions. However, most of these are used to distinguish ncRNAs and mRNAs. It is important to develop a highly accurate computational tool for identifying the coding potential of ncRNAs, thereby contributing to the discovery of novel peptides. In this Article, we propose a novel BiLSTM And Transformer encoder-based model (nBAT) with intrinsic features encoded for ncRNA coding potential prediction. In nBAT, we introduce a learnable position encoding mechanism to better obtain the embeddings of the ncRNA sequence. Moreover, we extract 43 intrinsic features from different perspectives and encode these features into the Transformer encoder by calculating their distances. Our performance comparisons show that nBAT achieves a superior performance than the state-of-the-art methods for coding potential prediction on different datasets. We also apply the method to new ncRNAs for identifying the coding potential, and the results further indicate the competitive performance of nBAT. We expect the method can be exploited as a useful tool for high-throughput coding potential prediction for ncRNAs.

Asunto(s)