ABSTRACT
Existing matrix factorization methods face challenges, including the cold start problem and global nonlinear data loss during similarity learning, particularly in predicting associations between long noncoding RNAs (LncRNAs) and diseases. To overcome these issues, we introduce HPTRMF, a matrix factorization approach incorporating high-order perturbation and flexible trifactor regularization. HPTRMF constructs a high-order correlation matrix utilizing the known association matrix, leveraging high-order perturbation to effectively address the cold start problem caused by data sparsity. Additionally, HPTRMF incorporates a flexible trifactor regularization term to capture similarity information on LncRNAs and diseases, enabling the effective handling of global nonlinear data loss by capturing such data in the similarity matrix. Experimental results demonstrate the superiority of HPTRMF over nine state-of-the-art algorithms in Leave-One-Out Cross-Validation (LOOCV) and Five-Fold Cross-Validation (5-Fold CV) on three data sets.HPTRMF and data sets are available in https://github.com/Llvvvv/HPTRMF.
ABSTRACT
Medical image segmentation is a compelling fundamental problem and an important auxiliary tool for clinical applications. Recently, the Transformer model has emerged as a valuable tool for addressing the limitations of convolutional neural networks by effectively capturing global relationships and numerous hybrid architectures combining convolutional neural networks (CNNs) and Transformer have been devised to enhance segmentation performance. However, they suffer from multilevel semantic feature gaps and fail to account for multilevel dependencies between space and channel. In this paper, we propose a hierarchical dependency Transformer for medical image segmentation, named HD-Former. First, we utilize a Compressed Bottleneck (CB) module to enrich shallow features and localize the target region. We then introduce the Dual Cross Attention Transformer (DCAT) module to fuse multilevel features and bridge the feature gap. In addition, we design the broad exploration network (BEN) that cascades convolution and self-attention from different percepts to capture hierarchical dense contextual semantic features locally and globally. Finally, we exploit uncertain multitask edge loss to adaptively map predictions to a consistent feature space, which can optimize segmentation edges. The extensive experiments conducted on medical image segmentation from ISIC, LiTS, Kvasir-SEG, and CVC-ClinicDB datasets demonstrate that our HD-Former surpasses the state-of-the-art methods in terms of both subjective visual performance and objective evaluation. Code: https://github.com/barcelonacontrol/HD-Former.
Subject(s)
Neural Networks, Computer , Humans , Image Processing, Computer-Assisted/methods , AlgorithmsABSTRACT
HBV-associated hepatocellular carcinoma (HCC) represents the prevalent form of HCC, with HBx protein being a crucial oncoprotein. Numerous members of the protein tyrosine phosphatase non-receptor (PTPN) family have been confirmed to be significantly associated with the occurrence and progression of malignant tumors. Our group has previously identified the involvement of PTPN13 in HCC. However, the roles of other PTPNs in HCC still requires further investigation. In this study, we found PTPN18 expression was significantly downregulated within HCC tissues compared to that in adjacent non-tumor tissues and normal liver tissues. Functionally, PTPN18 exerted inhibitory effects on the proliferation, migration, invasion, and sphere-forming capability of HCC cells, while concurrently promoting apoptotic processes. Through phospho-protein microarray screening followed by subsequent validation experiments, we identified that PTPN18 could activate the p53 signaling pathway and suppress the AKT/FOXO1 signaling cascade in HCC cells. Moreover, we found that the HBx protein mediated the repression of PTPN18 expression by upregulating miR-128-3p. Collectively, our study unveiled the role of PTPN18 as a tumor suppressor in HBV-related HCC. Implications: Our findings revealed PTPN18 might serve as a potential diagnostic and therapeutic target for HBV-related HCC.
ABSTRACT
PURPOSE: Our research aims to compare the predictive performance of decision tree algorithms (DT) and logistic regression analysis (LR) in constructing models, and develop a Post-Thrombotic Syndrome (PTS) risk stratification tool. METHODS: We retrospectively collected and analyzed relevant case information of 618 patients diagnosed with DVT from January 2012 to December 2021 in three different tertiary hospitals in Jiangxi Province as the modeling group. Additionally, we used the case information of 212 patients diagnosed with DVT from January 2022 to January 2023 in two tertiary hospitals in Hubei Province and Guangdong Province as the validation group. We extracted electronic medical record information including general patient data, medical history, laboratory test indicators, and treatment data for analysis. We established DT and LR models and compared their predictive performance using receiver operating characteristic (ROC) curves and confusion matrices. Internal and external validations were conducted. Additionally, we utilized LR to generate nomogram charts, calibration curves, and decision curves analysis (DCA) to assess its predictive accuracy. RESULTS: Both DT and LR models indicate that Year, Residence, Cancer, Varicose Vein Operation History, DM, and Chronic VTE are risk factors for PTS occurrence. In internal validation, DT outperforms LR (0.962 vs 0.925, z = 3.379, P < 0.001). However, in external validation, there is no significant difference in the area under the ROC curve between the two models (0.963 vs 0.949, z = 0.412, P = 0.680). The validation results of calibration curves and DCA demonstrate that LR exhibits good predictive accuracy and clinical effectiveness. A web-based calculator software of nomogram (https://sunxiaoxuan.shinyapps.io/dynnomapp/) was utilized to visualize the logistic regression model. CONCLUSIONS: The combination of decision tree and logistic regression models, along with the web-based calculator software of nomogram, can assist healthcare professionals in accurately assessing the risk of PTS occurrence in individual patients with lower limb DVT.
Subject(s)
Postthrombotic Syndrome , Venous Thrombosis , Humans , Venous Thrombosis/diagnosis , Postthrombotic Syndrome/diagnosis , Postthrombotic Syndrome/etiology , Female , Male , Middle Aged , Risk Assessment/methods , Retrospective Studies , Lower Extremity/blood supply , Risk Factors , Logistic Models , Adult , Decision Trees , Aged , ROC Curve , Algorithms , NomogramsABSTRACT
DNA 4 mC plays a crucial role in the genetic expression process of organisms. However, existing deep learning algorithms have shortcomings in the ability to represent DNA sequence features. In this paper, we propose a 4 mC site identification algorithm, DNABert-4mC, based on a fusion of the pruned pre-training DNABert-Pruning model and artificial feature encoding to identify 4 mC sites. The algorithm prunes and compresses the DNABert model, resulting in the pruned pre-training model DNABert-Pruning. This model reduces the number of parameters and removes redundancy from output features, yielding more precise feature representations while upholding accuracy.Simultaneously, the algorithm constructs an artificial feature encoding module to assist the DNABert-Pruning model in feature representation, effectively supplementing the information that is missing from the pre-trained features. The algorithm also introduces the AFF-4mC fusion strategy, which combines artificial feature encoding with the DNABert-Pruning model, to improve the feature representation capability of DNA sequences in multi-semantic spaces and better extract 4 mC sites and the distribution of nucleotide importance within the sequence. In experiments on six independent test sets, the DNABert-4mC algorithm achieved an average AUC value of 93.81%, outperforming seven other advanced algorithms with improvements of 2.05%, 5.02%, 11.32%, 5.90%, 12.02%, 2.42% and 2.34%, respectively.
Subject(s)
Algorithms , DNA , DNA/genetics , NucleotidesABSTRACT
Computational approaches employed for predicting potential microbe-disease associations often rely on similarity information between microbes and diseases. Therefore, it is important to obtain reliable similarity information by integrating multiple types of similarity information. However, existing similarity fusion methods do not consider multi-order fusion of similarity networks. To address this problem, a novel method of linear neighborhood label propagation with multi-order similarity fusion learning (MOSFL-LNP) is proposed to predict potential microbe-disease associations. Multi-order fusion learning comprises two parts: low-order global learning and high-order feature learning. Low-order global learning is used to obtain common latent features from multiple similarity sources. High-order feature learning relies on the interactions between neighboring nodes to identify high-order similarities and learn deeper interactive network structures. Coefficients are assigned to different high-order feature learning modules to balance the similarities learned from different orders and enhance the robustness of the fusion network. Overall, by combining low-order global learning with high-order feature learning, multi-order fusion learning can capture both the shared and unique features of different similarity networks, leading to more accurate predictions of microbe-disease associations. In comparison to six other advanced methods, MOSFL-LNP exhibits superior prediction performance in the leave-one-out cross-validation and 5-fold validation frameworks. In the case study, the predicted 10 microbes associated with asthma and type 1 diabetes have an accuracy rate of up to 90% and 100%, respectively.
Subject(s)
Algorithms , Humans , Computational Biology/methods , Machine LearningABSTRACT
Salvianolic acids (SA), such as rosmarinic acid (RA), danshensu (DSS), and their derivative salvianolic acid B (SAB), etc. widely existed in Lamiaceae and Boraginaceae families, are of interest due to medicinal properties in the pharmaceutical industries. Hundreds of studies in past decades described that 4-coumaroyl-CoA and 4-hydroxyphenyllactic acid (4-HPL) are common substrates to biosynthesize SA with participation of rosmarinic acid synthase (RAS) and cytochrome P450 98A (CYP98A) subfamily enzymes in different plants. However, in our recent study, several acyl donors and acceptors included DSS as well as their ester-forming products all were determined in SA-rich plants, which indicated that previous recognition to SA biosynthesis is insufficient. Here, we used Salvia miltiorrhiza, a representative important medicinal plant rich in SA, to elucidate the diversity of SA biosynthesis. Various acyl donors as well as acceptors are catalysed by SmRAS to form precursors of RA and two SmCYP98A family members, SmCYP98A14 and SmCYP98A75, are responsible for different positions' meta-hydroxylation of these precursors. SmCYP98A75 preferentially catalyses C-3' hydroxylation, and SmCYP98A14 preferentially catalyses C-3 hydroxylation in RA generation. In addition, relative to C-3' hydroxylation of the acyl acceptor moiety in RA biosynthesis, SmCYP98A75 has been verified as the first enzyme that participates in DSS formation. Furthermore, SmCYP98A enzymes knockout resulted in the decrease and overexpression leaded to dramatic increase of SA accumlation. Our study provides new insights into SA biosynthesis diversity in SA-abundant species and versatility of CYP98A enzymes catalytic preference in meta-hydroxylation reactions. Moreover, CYP98A enzymes are ideal metabolic engineering targets to elevate SA content.
Subject(s)
Cytochrome P-450 Enzyme System , Salvia miltiorrhiza , Hydroxylation , Cytochrome P-450 Enzyme System/metabolism , Cytochrome P-450 Enzyme System/genetics , Salvia miltiorrhiza/metabolism , Salvia miltiorrhiza/genetics , Salvia miltiorrhiza/enzymology , Polyphenols/metabolism , Polyphenols/biosynthesis , Plant Proteins/metabolism , Plant Proteins/genetics , AlkenesABSTRACT
Most existing graph neural network-based methods for predicting miRNA-disease associations rely on initial association matrices to pass messages, but the sparsity of these matrices greatly limits performance. To address this issue and predict potential associations between miRNAs and diseases, we propose a method called strengthened hypergraph convolutional autoencoder (SHGAE). SHGAE leverages multiple layers of strengthened hypergraph neural networks (SHGNN) to obtain robust node embeddings. Within SHGNN, we design a strengthened hypergraph convolutional network module (SHGCN) that enhances original graph associations and reduces matrix sparsity. Additionally, SHGCN expands node receptive fields by utilizing hyperedge features as intermediaries to obtain high-order neighbor embeddings. To improve performance, we also incorporate attention-based fusion of self-embeddings and SHGCN embeddings. SHGAE predicts potential miRNA-disease associations using a multilayer perceptron as the decoder. Across multiple metrics, SHGAE outperforms other state-of-the-art methods in five-fold cross-validation. Furthermore, we evaluate SHGAE on colon and lung neoplasms cases to demonstrate its ability to predict potential associations. Notably, SHGAE also performs well in the analysis of gastric neoplasms without miRNA associations.
Subject(s)
MicroRNAs , MicroRNAs/genetics , Algorithms , Neural Networks, Computer , Computational Biology/methodsABSTRACT
[S U M M A R Y] Many miRNA-disease association prediction models incorporate Gaussian interaction profile kernel similarity (GIPS). However, the GIPS fails to consider the specificity of the miRNA-disease association matrix, where matrix elements with a value of 0 represent miRNA and disease relationships that have not been discovered yet. To address this issue and better account for the impact of known and unknown miRNA-disease associations on similarity, we propose a method called vector projection similarity-based method for miRNA-disease association prediction (VPSMDA). In VPSMDA, we introduce three projection rules and combined with logistic functions for the miRNA-disease association matrix and propose a vector projection similarity measure for miRNAs and diseases. By integrating the vector projection similarity matrix with the original one, we obtain the improved miRNA and disease similarity matrix. Additionally, we construct a weight matrix using different numbers of neighbors to reduce the noise in the similarity matrix. In performance evaluation, both LOOCV and 5-fold CV experiments demonstrate that VPSMDA outperforms seven other state-of-the-art methods in AUC. Furthermore, in a case study, VPSMDA successfully predicted 10, 9, and 10 out of the top 10 associations for three important human diseases, respectively, and these predictions were confirmed by recent biomedical resources.
Subject(s)
MicroRNAs , Humans , MicroRNAs/genetics , MicroRNAs/metabolism , Genetic Predisposition to Disease , Algorithms , Models, Genetic , Area Under Curve , Computational Biology/methodsABSTRACT
Background: Our previous study demonstrated that digital diabetes care model (DDCM) created by multidisciplinary care team (MDCT) can improve glycemic control for patients with diabetes than usual care. Therefore, we aimed to explore long-term glycemic control with DDCM and influencing factors in type 2 diabetic cohort, in order to make a portrait for diabetes with goal-achieved HbA1c in clinics. Methods: A total of 1198 outpatients with type 2 diabetes using DDCM for at least 12 months were recruited as a cohort. Medical records and specific DDCM indexes were collected. The influencing factors for glycemic control were explored by multivariate logistic regression analysis, followed by an internal and external validation. Results: A total of 887 patients were finally included. HbA1c target-achieving rate was increased from 39.83% at baseline to 71.79% after 3-month follow-up. A shorter duration of diabetes, more frequent self-monitoring of blood glucose, lower HbA1c level at baseline, and less frequent emergency out-of-hospital follow-ups were influencing factors for HbA1c <7% at 12-month follow-up. AUC of the prediction model was 0.790, with a sensitivity of 69.7% and specificity of 76.1%. Internal and external validation in patients using the DDCM monitored by MDCT indicated that the DDCM was robust (AUC =0.783 and 0.723, respectively). Conclusion: Our findings made a portrait for T2DM with goal-achieved HbA1c in our DDCM. It is important to recognize associated factors for health providers to make personalized intervention in clinical practice.
ABSTRACT
Accumulating evidence suggests that long non-coding RNAs (lncRNAs) are associated with various complex human diseases. They can serve as disease biomarkers and hold considerable promise for the prevention and treatment of various diseases. The traditional random walk algorithms generally exclude the effect of non-neighboring nodes on random walking. In order to overcome the issue, the neighborhood constraint (NC) approach is proposed in this study for regulating the direction of the random walk by computing the effects of both neighboring nodes and non-neighboring nodes. Then the association matrix is updated by matrix multiplication for minimizing the effect of the false negative data. The heterogeneous lncRNA-disease network is finally analyzed using an unbalanced random walk method for predicting the potential lncRNA-disease associations. The LUNCRW model is therefore developed for predicting potential lncRNA-disease associations. The area under the curve (AUC) values of the LUNCRW model in leave-one-out cross-validation and five-fold cross-validation were 0.951 and 0.9486 ± 0.0011, respectively. Data from published case studies on three diseases, including squamous cell carcinoma, hepatocellular carcinoma, and renal cell carcinoma, confirmed the predictive potential of the LUNCRW model. Altogether, the findings indicated that the performance of the LUNCRW method is superior to that of existing methods in predicting potential lncRNA-disease associations.
Subject(s)
Kidney Neoplasms , RNA, Long Noncoding , Humans , RNA, Long Noncoding/genetics , Algorithms , Area Under Curve , WalkingABSTRACT
AIM: The purpose of this study was to explore the relationships among perceptions of decent work, psychological empowerment, and work immersion among nurses, hypothesizing that psychological empowerment mediates the relationship between perceptions of decent work and work immersion. BACKGROUND: At present, there are many studies on nurses' perceptions of decent labor and work immersion in China, but the relationship between them has not been discussed from a psychological perspective. METHODS: The sample consisted of clinical nurses in Jiangxi, Zhejiang, Hubei, and Guangdong provinces, China, and the nurses' general information, decent labor perception, psychological empowerment, and work immersion scores were assessed using the General Information Scale, Decent Labor Perception Scale, Psychological Empowerment Scale, and Work Immersion Scale, respectively. Pearson correlation analysis and structural equation modeling were used to analyze the data. RESULTS: The total scores of nurses' perceptions of decent work, psychological empowerment, and work immersion were at a moderate level. The total nurse work immersion score and each dimension score were positively correlated with the total nurse decent work perception score and the total psychological empowerment score. Decent work perception and psychological empowerment directly and positively predicted work immersion; decent work perception also indirectly acted on work immersion through psychological empowerment. CONCLUSIONS AND IMPLICATIONS FOR NURSING AND HEALTH POLICY: Nurses' work immersion was moderate, and this study explored the mechanisms by which perceptions of decent work affect nurses' work immersion from a psychological perspective, validating the mediating role of psychological empowerment. This study emphasizes that nursing managers should fully understand the importance of nurses' work immersion, continuously improve nurses' decent labor perceptions, enhance their psychological empowerment level, improve their work immersion, and enhance the quality of nursing services.
ABSTRACT
BACKGROUND: The rising cancer incidence in patients with oral leukoplakia (OL) highlights the importance of identifying potential biomarkers for high-risk individuals and lesions because these biomarkers are useful in developing personalized management strategies for OL patients. This study systematically searched and analyzed the literature on potential saliva and serum biomarkers for OL malignant transformation. METHODS: PubMed and Scopus were searched for studies published up to April 2022. The primary outcome of this study was the difference in biomarker concentrations in saliva or serum samples from healthy control (HC), OL and oral cancer (OC) populations. Cohen's d with 95% credible interval was calculated and pooled using the inverse variance heterogeneity method. RESULTS: A total of seven saliva biomarkers were analyzed in this paper, including interleukin-1alpha, interleukin-6 (IL-6), interleukin-6-8, tumor necrosis factor alpha (TNF-α), copper, zinc, and lactate dehydrogenase. IL-6 and TNF-α exhibited statistically significant deviations in comparisons between HC versus OL and OL versus OC. A total of 13 serum biomarkers were analyzed, including IL-6, TNF-α, C-reactive protein, total cholesterol, triglycerides, high-density lipoproteins, low-density lipoproteins, albumin, protein, ß2-microglobulin, fucose, lipid-bound sialic acid (LSA), and total sialic acid (TSA). LSA and TSA exhibited statistically significant deviations in comparisons between HC versus OL and OL versus OC. CONCLUSION: IL-6 and TNF-α in saliva have strong predictive values for OL deterioration, and LSA and TSA concentration levels in serum also have the potential to serve as biomarkers for OL deterioration.
Subject(s)
Interleukin-6 , Mouth Neoplasms , Humans , Tumor Necrosis Factor-alpha/metabolism , N-Acetylneuraminic Acid , Leukoplakia, Oral/metabolism , Leukoplakia, Oral/pathology , Biomarkers/metabolism , Mouth Neoplasms/metabolism , Cell Transformation, NeoplasticABSTRACT
The ability of knowledge, attitude, and practice of intensive care unit (ICU) nurses to perform medical device-related pressure injuries (MDRPIs) can affect the incidence of MDRPI in ICU patients. Therefore, in order to improve ICU nurses' understanding and nursing ability of MDRPIs, we investigated the non-linear relationship (synergistic and superimposed relationships) between the factors influencing ICU nurses' ability of knowledge, attitude, and practice. A Clinical Nurses' Knowledge, Attitude, and Practice Questionnaire for the Prevention of MDRPI in Critically Ill Patients was administered to 322 ICU nurses from tertiary hospitals in China from January 1, 2022 to June 31, 2022. After the questionnaire was distributed, the data were collected and sorted out, and the corresponding statistical analysis and modelling software was used to analyse the data. IBM SPSS 25.0 software was used to conduct Single factor analysis and Logistic regression analysis on the data, so as to screen the statistically significant influencing factors. IBM SPSS Modeler18.0 software was used to construct a decision tree model of the factors influencing MDRPI knowledge, attitude, and practice of ICU nurses, and ROC curves were plotted to analyse the accuracy of the model. The results showed that the overall passing rate of ICU nurses' knowledge, attitude, and practice score was 72%. The statistically significant predictor variables ranked in importance were education background (0.35), training (0.31), years of working (0.24), and professional title (0.10). AUC = 0.718, model prediction performance is good. There is a synergistic and superimposed relationship between high education background, attended training, high years of working and high professional title. Nurses with the above factors have strong MDRPI knowledge, attitude, and practice ability. Therefore, nursing managers can develop a reasonable and effective scheduling system and MDRPI training program based on the study results. The ultimate goal is to improve the ability of ICU nurses to know and act on MDRPI and to reduce the incidence of MDRPI in ICU patients.
Subject(s)
Nurses , Pressure Ulcer , Humans , Pressure Ulcer/etiology , Pressure Ulcer/prevention & control , Pressure Ulcer/epidemiology , Health Knowledge, Attitudes, Practice , Clinical Competence , Cross-Sectional Studies , Intensive Care Units , Surveys and QuestionnairesABSTRACT
Recent studies have revealed that long noncoding RNAs (lncRNAs) are closely linked to several human diseases, providing new opportunities for their use in detection and therapy. Many graph propagation and similarity fusion approaches can be used for predicting potential lncRNA-disease associations. However, existing similarity fusion approaches suffer from noise and self-similarity loss in the fusion process. To address these problems, a new prediction approach, termed SSMF-BLNP, based on organically combining selective similarity matrix fusion (SSMF) and bidirectional linear neighborhood label propagation (BLNP), is proposed in this paper to predict lncRNA-disease associations. In SSMF, self-similarity networks of lncRNAs and diseases are obtained by selective preprocessing and nonlinear iterative fusion. The fusion process assigns weights to each initial similarity network and introduces a unit matrix that can reduce noise and compensate for the loss of self-similarity. In BLNP, the initial lncRNA-disease associations are employed in both lncRNA and disease directions as label information for linear neighborhood label propagation. The propagation was then performed on the self-similarity network obtained from SSMF to derive the scoring matrix for predicting the relationships between lncRNAs and diseases. Experimental results showed that SSMF-BLNP performed better than seven other state of-the-art approaches. Furthermore, a case study demonstrated up to 100% and 80% accuracy in 10 lncRNAs associated with hepatocellular carcinoma and 10 lncRNAs associated with renal cell carcinoma, respectively. The source code and datasets used in this paper are available at: https://github.com/RuiBingo/SSMF-BLNP.
Subject(s)
RNA, Long Noncoding , Humans , Algorithms , Computational Biology/methods , RNA, Long Noncoding/genetics , Software , Carcinoma, Hepatocellular/genetics , Carcinoma, Renal Cell/genetics , Liver Neoplasms/genetics , Kidney Neoplasms/geneticsABSTRACT
BACKGROUND: Increasing evidence has suggested inositol polyphosphate 5-phosphatase family contributes to tumorigenesis and tumor progression. However, the role of INPP5F in hepatocellular carcinoma (HCC) and its underlying mechanisms is unclear. METHODS: The expression of INPP5F in HCC was analyzed in public databases and our clinical specimens. The biological functions of INPP5F were investigated in vitro and vivo. The molecular mechanism of INPP5F in regulating tumor growth were studied by transcriptome-sequencing analysis, mass spectrometry analysis, immunoprecipitation assay and immunofluorescence assay. RESULTS: High expression of INPP5F was found in HCC tissues and was associated with poor prognosis in HCC patients. Overexpression of INPP5F promoted HCC cell proliferation, and vice versa. Knockdown of INPP5F suppressed tumor growth in vivo. Results from transcriptome-sequencing analysis showed INPP5F not only regulated a series of cell cycle related genes expression (c-MYC and cyclin E1), but also promoted many aerobic glycolysis related genes expression. Further studies confirmed that INPP5F could enhance lactate production and glucose consumption in HCC cell. Mechanistically, INPP5F activated Notch signaling pathway and upregulated c-MYC and cyclin E1 in HCC via interacting with ASPH. Interestingly, INPP5F was commonly nuclear-located in cells of adjacent non-tumor tissues, while in HCC, cytoplasm-located was more common. LMB (nuclear export inhibitor) treatment restricted INPP5F in nucleus and was associated with inhibition of Notch signaling and cell proliferation. Sequence of nuclear localization signals (NLSs) and nuclear export signals (NESs) in INPP5F aminoacidic sequence were then identified. Alteration of the NLSs or NESs influenced the localization of INPP5F and the expression of its downstream molecules. Furthermore, we found INPP5F interacted with both exportin and importin through NESs and NLSs, respectively, but the interaction with exportin was stronger, leading to cytoplasmic localization of INPP5F in HCC. CONCLUSION: These findings indicate that INPP5F functions as an oncogene in HCC via a translocation mechanism and activating ASPH-mediated Notch signaling pathway. INPP5F may serve as a potential therapeutic target for HCC patients.
Subject(s)
Calcium-Binding Proteins/metabolism , Carcinoma, Hepatocellular/genetics , Inositol Polyphosphate 5-Phosphatases/metabolism , Liver Neoplasms/genetics , Membrane Proteins/metabolism , Mixed Function Oxygenases/metabolism , Muscle Proteins/metabolism , Animals , Carcinoma, Hepatocellular/pathology , Cell Line, Tumor , Cell Proliferation , Gene Expression Regulation, Neoplastic , Humans , Liver Neoplasms/pathology , Male , Mice , Signal TransductionABSTRACT
Accumulating evidence has demonstrated various associations of long non-coding RNAs (lncRNAs) with human diseases, such as abnormal expression due to microbial influences that cause disease. Gaining a deeper understanding of lncRNA-disease associations is essential for disease diagnosis, treatment, and prevention. In recent years, many matrix decomposition methods have also been used to predict potential lncRNA-disease associations. However, these methods do not consider the use of microbe-disease association information to enrich disease similarity, and also do not make more use of similarity information in the decomposition process. To address these issues, we here propose a correction-based similarity-constrained probability matrix decomposition method (SCCPMD) to predict lncRNA-disease associations. The microbe-disease associations are first used to enrich the disease semantic similarity matrix, and then the logistic function is used to correct the lncRNA and disease similarity matrix, and then these two corrected similarity matrices are added to the probability matrix decomposition as constraints to finally predict the potential lncRNA-disease associations. The experimental results show that SCCPMD outperforms the five advanced comparison algorithms. In addition, SCCPMD demonstrated excellent prediction performance in a case study for breast cancer, lung cancer, and renal cell carcinoma, with prediction accuracy reaching 80, 100, and 100%, respectively. Therefore, SCCPMD shows excellent predictive performance in identifying unknown lncRNA-disease associations.
ABSTRACT
Hepatitis B x protein (HBx) affects cellular protein expression and participates in the tumorigenesis and progression of hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC). Metabolic reprogramming contributed to the HCC development, but its role in HBV-related HCC remains largely unclear. Tyrosine-protein phosphatase nonreceptor type 13 (PTPN13) is a significant regulator in tumor development, however, its specific role in hepatocarcinogenesis remains to be explored. Here, we found that decreased PTPN13 expression was associated with HBV/HBx. Patients with low PTPN13 expression showed a poor prognosis. Functional assays revealed that PTPN13 inhibited proliferation and tumorigenesis in vitro and in vivo. Further mechanistic studies indicated that HBx inhibited PTPN13 expression by upregulating the expression of DNMT3A and interacting with DNMT3A. Furthermore, we found that DNMT3A bound to the PTPN13 promoter (-343 to -313 bp) in an epigenetically controlled manner associated with elevated DNA methylation and then inhibited PTPN13 transcription. In addition, we identified IGF2BP1 as a novel PTPN13-interacting gene and demonstrated that PTPN13 influences c-Myc expression by directly and competitively binding to IGF2BP1 to decrease the intracellular concentration of functional IGF2BP1. Overexpressing PTPN13 promoted c-Myc mRNA degradation independent of the protein tyrosine phosphatase (PTP) activity of PTPN13. Importantly, we discovered that the PTPN13-IGF2BP1-c-Myc axis was important for cancer cell growth through promoting metabolic reprogramming. We verified the significant negative correlations between PTPN13 expression and c-Myc, PSPH, and SLC7A1 expression in clinical HCC tissue samples. In summary, our findings demonstrate that PTPN13 is a novel regulator of HBV-related hepatocarcinogenesis and may play an important role in HCC. PTPN13 may serve as a prognostic marker and therapeutic target in HBV-related HCC patients.
Subject(s)
Carcinoma, Hepatocellular/pathology , Hepatitis B/complications , Liver Neoplasms/pathology , Protein Tyrosine Phosphatase, Non-Receptor Type 13/genetics , RNA-Binding Proteins/genetics , Trans-Activators/metabolism , Viral Regulatory and Accessory Proteins/metabolism , Animals , Biomarkers, Tumor/genetics , Carcinoma, Hepatocellular/genetics , Carcinoma, Hepatocellular/metabolism , Carcinoma, Hepatocellular/virology , Cell Proliferation , Cohort Studies , DNA (Cytosine-5-)-Methyltransferases/metabolism , DNA Methylation , DNA Methyltransferase 3A , Disease Progression , Down-Regulation , Epigenesis, Genetic , Gene Expression Regulation, Neoplastic , Hepatitis B/genetics , Hepatitis B/metabolism , Humans , Liver Neoplasms/genetics , Liver Neoplasms/metabolism , Liver Neoplasms/virology , Mice , Neoplasm Transplantation , Prognosis , Promoter Regions, Genetic , Proto-Oncogene Proteins c-myc/genetics , RNA StabilityABSTRACT
BACKGROUND: The overall prognosis of oral cancer remains poor because over half of patients are diagnosed at advanced-stages. Previously reported screening and earlier detection methods for oral cancer still largely rely on health workers' clinical experience and as yet there is no established method. We aimed to develop a rapid, non-invasive, cost-effective, and easy-to-use deep learning approach for identifying oral cavity squamous cell carcinoma (OCSCC) patients using photographic images. METHODS: We developed an automated deep learning algorithm using cascaded convolutional neural networks to detect OCSCC from photographic images. We included all biopsy-proven OCSCC photographs and normal controls of 44,409 clinical images collected from 11 hospitals around China between April 12, 2006, and Nov 25, 2019. We trained the algorithm on a randomly selected part of this dataset (development dataset) and used the rest for testing (internal validation dataset). Additionally, we curated an external validation dataset comprising clinical photographs from six representative journals in the field of dentistry and oral surgery. We also compared the performance of the algorithm with that of seven oral cancer specialists on a clinical validation dataset. We used the pathological reports as gold standard for OCSCC identification. We evaluated the algorithm performance on the internal, external, and clinical validation datasets by calculating the area under the receiver operating characteristic curves (AUCs), accuracy, sensitivity, and specificity with two-sided 95% CIs. FINDINGS: 1469 intraoral photographic images were used to validate our approach. The deep learning algorithm achieved an AUC of 0·983 (95% CI 0·973-0·991), sensitivity of 94·9% (0·915-0·978), and specificity of 88·7% (0·845-0·926) on the internal validation dataset (n = 401), and an AUC of 0·935 (0·910-0·957), sensitivity of 89·6% (0·847-0·942) and specificity of 80·6% (0·757-0·853) on the external validation dataset (n = 402). For a secondary analysis on the internal validation dataset, the algorithm presented an AUC of 0·995 (0·988-0·999), sensitivity of 97·4% (0·932-1·000) and specificity of 93·5% (0·882-0·979) in detecting early-stage OCSCC. On the clinical validation dataset (n = 666), our algorithm achieved comparable performance to that of the average oral cancer expert in terms of accuracy (92·3% [0·902-0·943] vs 92.4% [0·912-0·936]), sensitivity (91·0% [0·879-0·941] vs 91·7% [0·898-0·934]), and specificity (93·5% [0·909-0·960] vs 93·1% [0·914-0·948]). The algorithm also achieved significantly better performance than that of the average medical student (accuracy of 87·0% [0·855-0·885], sensitivity of 83·1% [0·807-0·854], and specificity of 90·7% [0·889-0·924]) and the average non-medical student (accuracy of 77·2% [0·757-0·787], sensitivity of 76·6% [0·743-0·788], and specificity of 77·9% [0·759-0·797]). INTERPRETATION: Automated detection of OCSCC by deep-learning-powered algorithm is a rapid, non-invasive, low-cost, and convenient method, which yielded comparable performance to that of human specialists and has the potential to be used as a clinical tool for fast screening, earlier detection, and therapeutic efficacy assessment of the cancer.
ABSTRACT
Objective: Gallbladder cancer (GBC) is one of the most aggressive malignant tumors, and there is no effective and convenient method for predicting cancer-specific survival (CSS). We aim to develop a novel nomogram staging system based on the positive lymph node ratio (pLNR) for GBC patients. Methods:A total of 1,356 patients enrolled in the study. We evaluated the prognostic value of the pLNR and built a prognostic nomogram staging system based on the pLNR in the training cohort. The concordance index and calibration plots were used to evaluate model discrimination. The predictive accuracy and clinical value of the nomograms were measured by decision curve analysis (DCA). The CSS nomogram was further validated in an internal validation cohort. Results:The pLNR was an independent prognostic factor for CSS based on Cox regression analyses. A prognostic nomogram that combined T classification, pLNR, M classification, histologic grade, live metastasis, and tumor size was formulated with a c-index of 0.763 (95% CI, 0.728-0.798), while the c-indexes for the staging system of AJCC 8th, 7th, and 6th for CSS prediction were 0.718, 0.718, and 0.717, respectively. The calibration curves showed perfect agreement. The DCA showed that the nomogram provided substantial clinical value. The nomogram (the AUCs for 1, 3, and 5 years were 0.693, 0.716, and 0.726, respectively,) showed high prognostic accuracy. Conclusion:We have developed a formulated nomogram staging system based on the pLNR that allows more accurate individualized predictions of CSS for resected GBC patients than the AJCC staging systems.