Predicting miRNA-disease associations using an ensemble learning framework with resampling method.

MOTIVATION: Accumulating evidences have indicated that microRNA (miRNA) plays a crucial role in the pathogenesis and progression of various complex diseases. Inferring disease-associated miRNAs is significant to explore the etiology, diagnosis and treatment of human diseases. As the biological experiments are time-consuming and labor-intensive, developing effective computational methods has become indispensable to identify associations between miRNAs and diseases. RESULTS: We present an Ensemble learning framework with Resampling method for MiRNA-Disease Association (ERMDA) prediction to discover potential disease-related miRNAs. Firstly, the resampling strategy is proposed for building multiple different balanced training subsets to address the challenge of sample imbalance within the database. Then, ERMDA extracts miRNA and disease feature representations by integrating miRNA-miRNA similarities, disease-disease similarities and experimentally verified miRNA-disease association information. Next, the feature selection approach is applied to reduce the redundant information and increase the diversity among these subsets. Lastly, ERMDA constructs an individual learner on each subset to yield primitive outcomes, and the soft voting method is introduced for making the final decision based on the prediction results of individual learners. A series of experimental results demonstrates that ERMDA outperforms other state-of-the-art methods on both balanced and unbalanced testing sets. Besides, case studies conducted on the three human diseases further confirm the ERMDA's prediction capability for identifying potential disease-related miRNAs. In conclusion, these experimental results demonstrate that our method can serve as an effective and reliable tool for researchers to explore the regulatory role of miRNAs in complex diseases.

GraphCDA: a hybrid graph representation learning framework based on GCN and GAT for predicting disease-associated circRNAs.

MOTIVATION: CircularRNA (circRNA) is a class of noncoding RNA with high conservation and stability, which is considered as an important disease biomarker and drug target. Accumulating pieces of evidence have indicated that circRNA plays a crucial role in the pathogenesis and progression of many complex diseases. As the biological experiments are time-consuming and labor-intensive, developing an accurate computational prediction method has become indispensable to identify disease-related circRNAs. RESULTS: We presented a hybrid graph representation learning framework, named GraphCDA, for predicting the potential circRNA-disease associations. Firstly, the circRNA-circRNA similarity network and disease-disease similarity network were constructed to characterize the relationships of circRNAs and diseases, respectively. Secondly, a hybrid graph embedding model combining Graph Convolutional Networks and Graph Attention Networks was introduced to learn the feature representations of circRNAs and diseases simultaneously. Finally, the learned representations were concatenated and employed to build the prediction model for identifying the circRNA-disease associations. A series of experimental results demonstrated that GraphCDA outperformed other state-of-the-art methods on several public databases. Moreover, GraphCDA could achieve good performance when only using a small number of known circRNA-disease associations as the training set. Besides, case studies conducted on several human diseases further confirmed the prediction capability of GraphCDA for predicting potential disease-related circRNAs. In conclusion, extensive experimental results indicated that GraphCDA could serve as a reliable tool for exploring the regulatory role of circRNAs in complex diseases.

Efficacy of rTMS in treating functional impairment in post-stroke patients: a systematic review and meta-analysis.

BACKGROUND: Most stroke patients suffer from an imbalance in blood supply, which causes severe brain damage leading to functional deficits in motor, sensory, swallowing, cognitive, emotional, and speech functions. Repetitive transcranial magnetic stimulation (rTMS) is thought to restore functions impaired during the stroke process and improve the quality of life of stroke patients. However, the efficacy of rTMS in treating post-stroke function impairment varies significantly. Therefore, we conducted a meta-analysis of the number of patients with effective rTMS in treating post-stroke dysfunction. METHODS: The PubMed, Embase, and Cochrane Library databases were searched. Screening and full-text review were performed by three investigators. Single-group rate meta-analysis was performed on the extracted data using a random variable model. Then subgroup analyses were performed at the levels of stroke acuity (acute, chronic, or subacute); post-stroke symptoms (including upper and lower limb motor function, dysphagia, depression, aphasia); rTMS stimulation site (affected side, unaffected side); and whether or not it was a combination therapy. RESULTS: We obtained 8955 search records, and finally 33 studies (2682 patients) were included in the meta-analysis. The overall analysis found that effective strength (ES) of rTMS was 0.53. In addition, we found that the ES of rTMS from acute/subacute/chronic post-stroke was 0.69, 0.45, and 0.52. We also found that the ES of rTMS using high-frequency stimulation was 0.56, while the ES of rTMS using low-frequency stimulation was 0.53. From post-stroke symptoms, we found that the ES of rTMS in sensory aspects, upper limb functional aspects, swallowing function, and aphasia was 0.50, 0.52, 0.51, and 0.54. And from the site of rTMS stimulation, we found that the ES of rTMS applied to the affected side was 0.51, while the ES applied to the unaffected side was 0.54. What's more, we found that the ES of rTMS applied alone was 0.53, while the ES of rTMS applied in conjunction with other therapeutic modalities was 0.53. CONCLUSIONS: By comparing the results of the data, we recommend rTMS as a treatment option for rehabilitation of functional impairment in patients after stroke. We also recommend that rehabilitation physicians or clinicians use combination therapy as one of the options for patients.

Adversarial neural network with sentiment-aware attention for detecting adverse drug reactions.

Adverse drug reaction (ADR) detection is an important issue in drug safety. ADRs are health threats caused by medication. Identifying ADRs in a timely manner can reduce harm to patients and can also assist doctors in the rational use of drugs. Many studies have investigated potential ADRs based on social media due to the openness and timeliness of this resource; however, they have ignored the fine-grained emotional expression in social media text. In addition, the benchmark datasets from social media are usually small, which can result in the problem of over-fitting. In this paper, we propose the Adversarial Neural Network with Sentiment-aware Attention (ANNSA) model, which enhances the sentimental element in social media and improves the performance of neural networks via data augmentation. Specifically, a sentiment-aware attention mechanism is proposed to extract the word-level sentiment features associated with sentiment words and learn task-related information by optimizing a task-specific loss. For low-resource datasets, we use an adversarial training approach to generate perturbations of the word embeddings via an implicit regularization technique. ANNSA was tested on three social media ADR detection datasets, namely, Twitter, TwiMed (Twitter) and CADEC. The experimental results indicated the ability to achieve F1 values of 48.84%, 64.18% and 83.06%, respectively, comparable to the best results reported for state-of-the-art methods. Our study demonstrates that sentiment words are highly correlated with ADRs and that word-level sentiment features can assist in detecting ADRs from social media datasets.

Influence of collateral circulation on cerebral blood flow and frontal lobe cognitive function in patients with severe internal carotid artery stenosis.

BACKGROUND: This study aimed to investigate the cerebral blood flow (CBF) and frontal lobe cognitive function in severe internal carotid artery (ICA) stenosis patients with different types of collateral circulation. METHODS: One hundred twenty-six patients with severe unilateral ICA stenosis were enrolled. Digital subtraction angiography (DSA) was performed to recruit patients with one of three common types of collateral circulation: anterior communicating artery (AcoA), posterior communicating artery (PcoA) and ophthalmic artery (OA). The hemodynamic parameters of the middle cerebral artery (MCA) were measured using transcranial Doppler (TCD), and the individual frontal lobe cognitive attention functions were evaluated using Word Fluency Test, Trail-Making Test (TMT), Digit Span, and Stroop Color Word Test (SCWT). The correlation between hemodynamic changes and the scores of all tasks was analyzed. RESULTS: On the side of arterial stenosis, the CBF velocities were highest in AcoA group and lowest in the OA group. All patients performed worse in TMT and Digit Span than the matched normal controls. The AcoA group exhibited a lower pulsatility index (PI) and a longer response time in the Stroop task, but had a higher accuracy rate in the Stroop task and higher scores in Word Fluency Test than the PcoA and OA groups. In all the three groups, PI was positively correlated with the accuracy rate for Stroop interference effects. CONCLUSIONS: Our findings suggested that the frontal lobe cognitive function of patients with ICA was impaired, and AcoA collaterals may be beneficial for selective attention functions, whereas OA collaterals may be associated with impairment of selective attention functions. Additionally, a high PI may be an indicator for identifying impaired selective attention in patients with severe ICA stenosis.

Cyclodextrin Modulated Type I Collagen Self-Assembly to Engineer Biomimetic Cornea Implants.

Collagen-rich tissues in the cornea exhibit unique and highly organized extracellular matrix ultrastructures, which contribute to its high load-bearing capacity and light transmittance. Corneal collagen fibrils are controlled during development by small leucine-rich proteoglycans (SLRPs) that regulate the fibril diameter and spacing in order to achieve the unique optical transparency. Cyclodextrins (CDs) of varying size and chemical functionality for their ability to regulate collagen assembly during vitrification process are screened in order to create biosynthetic materials that mimic the native cornea structure. Addition of ßCD to collagen vitrigels produces materials with aligned fibers and lamellae similar to native cornea, resulting in mechanically robust and transparent materials. Biochemistry analysis revealed that CD interacts with hydrophobic amino acids in collagen to influence assembly and fibril organization. To translate the self-assembled collagen materials for cornea reconstruction, custom molds for gelation and vitrification are engineered to create ßCD/Col implants with curvature matching that of the cornea. Acellular ßCD/Col materials are implanted in a rabbit partial keratoplasty model with interrupted sutures. The implants demonstrate tissue integration and support re-epithelialization. Therefore, the addition of CD molecules regulates collagen self-assembly and provides a simple process to engineer corneal mimetic substitutes with advanced structural and functional properties.

MicroRNA-19b-3p Modulates Japanese Encephalitis Virus-Mediated Inflammation via Targeting RNF11.

UNLABELLED: Japanese encephalitis virus (JEV) can invade the central nervous system and consequently induce neuroinflammation, which is characterized by profound neuronal cell damage accompanied by astrogliosis and microgliosis. Albeit microRNAs (miRNAs) have emerged as major regulatory noncoding RNAs with profound effects on inflammatory response, it is unknown how astrocytic miRNAs regulate JEV-induced inflammation. Here, we found the involvement of miR-19b-3p in regulating the JEV-induced inflammatory responsein vitroandin vivo The data demonstrated that miR-19b-3p is upregulated in cultured cells and mouse brain tissues during JEV infection. Overexpression of miR-19b-3p led to increased production of inflammatory cytokines, including tumor necrosis factor alpha, interleukin-6, interleukin-1ß, and chemokine (C-C motif) ligand 5, after JEV infection, whereas knockdown of miR-19b-3p had completely opposite effects. Mechanistically, miR-19b-3p modulated the JEV-induced inflammatory response via targeting ring finger protein 11, a negative regulator of nuclear factor kappa B signaling. We also found that inhibition of ring finger protein 11 by miR-19b-3p resulted in accumulation of nuclear factor kappa B in the nucleus, which in turn led to higher production of inflammatory cytokines.In vivosilencing of miR-19b-3p by a specific antagomir reinvigorates the expression level of RNF11, which in turn reduces the production of inflammatory cytokines, abrogates gliosis and neuronal cell death, and eventually improves the survival rate in the mouse model. Collectively, our results demonstrate that miR-19b-3p positively regulates the JEV-induced inflammatory response. Thus, miR-19b-3p targeting may constitute a thought-provoking approach to rein in JEV-induced inflammation. IMPORTANCE: Japanese encephalitis virus (JEV) is one of the major causes of acute encephalitis in humans worldwide. The pathological features of JEV-induced encephalitis are inflammatory reactions and neurological diseases resulting from glia activation. MicroRNAs (miRNAs) are small noncoding RNAs that regulate gene expression posttranscriptionally. Accumulating data indicate that miRNAs regulate a variety of cellular processes, including the host inflammatory response under pathological conditions. Recently, a few studies demonstrated the role of miRNAs in a JEV-induced inflammatory response in microglia; however, their role in an astrocyte-derived inflammatory response is largely unknown. The present study reveals that miR-19b-3p targets ring finger protein 11 in glia and promotes inflammatory cytokine production by enhancing nuclear factor kappa B activity in these cells. Moreover, administration of an miR-19b-3p-specific antagomir in JEV-infected mice reduces neuroinflammation and lethality. These findings suggest a new insight into the molecular mechanism of the JEV-induced inflammatory response and provide a possible therapeutic entry point for treating viral encephalitis.

MicroRNA-15b Modulates Japanese Encephalitis Virus-Mediated Inflammation via Targeting RNF125.

Japanese encephalitis virus (JEV) can target CNS and cause neuroinflammation that is characterized by profound neuronal damage and concomitant microgliosis/astrogliosis. Although microRNAs (miRNAs) have emerged as a major regulatory network with profound effects on inflammatory response, it is less clear how they regulate JEV-induced inflammation. In this study, we found that miR-15b is involved in modulating the JEV-induced inflammatory response. The data demonstrate that miR-15b is upregulated during JEV infection of glial cells and mouse brains. In vitro overexpression of miR-15b enhances the JEV-induced inflammatory response, whereas inhibition of miR-15b decreases it. Mechanistically, ring finger protein 125 (RNF125), a negative regulator of RIG-I signaling, is identified as a direct target of miR-15b in the context of JEV infection. Furthermore, inhibition of RNF125 by miR-15b results in an elevation in RIG-I levels, which, in turn, leads to a higher production of proinflammatory cytokines and type I IFN. In vivo knockdown of virus-induced miR-15b by antagomir-15b restores the expression of RNF125, reduces the production of inflammatory cytokines, attenuates glial activation and neuronal damage, decreases viral burden in the brain, and improves survival in the mouse model. Taken together, our results indicate that miR-15b modulates the inflammatory response during JEV infection by negative regulation of RNF125 expression. Therefore, miR-15b targeting may constitute an interesting and promising approach to control viral-induced neuroinflammation.

The Role of Ubiquitination in Regulation of Innate Immune Signaling.

Ubiquitination, also denoted ubiquitylation, is a posttranslational modification that has been implicated in the regulation of both innate and adaptive immune responses. Ubiquitination plays crucial roles in innate immune signaling by ensuring the proper orchestration of several signaling mediators that constitute a functional immune response. Herein, we briefly summarize the latest discoveries concerning the molecular ubiquitination-related machinery that senses, assembles, and disassembles innate immune signaling mediators.

Ground-based airglow imaging interferometer. Part 2: forward model and inverse method.

The ground-based airglow imaging interferometer (GBAII) observes the nighttime airglow of the O2(0-1) 867.7 nm line, peaked at 94 km altitude, to measure the upper atmospheric wind and temperature field. Its forward model, a code package in interactive data language (IDL), is developed to simulate the expected imaging interference fringes. It includes eight modules to simulate the light source, the atmospheric radiation transmission, the wide-angle Michelson interferometer, the interference filter, the optical system decay function, the responsivity, the imaging CCD, and the noises. The inverse method is also developed for obtaining the rest phase calibration, temperature, and wind. By means of both theoretical tools, we carry out a comparison of theoretical results with a field observation case. The apparent quantities J(1-p) from the forward model has the deviation of 1.5%-2.5% compared with that from the observation image. The temperature falls mainly in the range of 167-196 K with the precision of 2 K. The zonal and meridional winds are mainly in the region of 5.1 to 46.5 m/s and 12.5 to 48.3 m/s respectively, with errors of 13.2 to 21.5 m/s. The consistent trends between the observation results and standard models (MSISE90 and HWM93) suggest that the forward model and inverse method are suitable for GBAII.

Hierarchical Negative Sampling Based Graph Contrastive Learning Approach for Drug-Disease Association Prediction.

Predicting potential drug-disease associations (RDAs) plays a pivotal role in elucidating therapeutic strategies for diseases and facilitating drug repositioning, making it of paramount importance. However, existing methods are constrained and rely heavily on limited domain-specific knowledge, impeding their ability to effectively predict candidate associations between drugs and diseases. Moreover, the simplistic definition of unknown information pertaining to drug-disease relationships as negative samples presents inherent limitations. To overcome these challenges, we introduce a novel hierarchical negative sampling-based graph contrastive model, termed HSGCLRDA, which aims to forecast latent associations between drugs and diseases. In this study, HSGCLRDA integrates the association information as well as similarity between drugs, diseases and proteins. Meanwhile, the model constructs a drug-disease-protein heterogeneous network. Subsequently, employing a hierarchical structural sampling technique, we establish reliable negative drug-disease samples utilizing PageRank algorithms. Utilizing meta-path aggregation within the heterogeneous network, we derive low-dimensional representations for drugs and diseases, thereby constructing global and local feature graphs that capture their interactions comprehensively. To obtain representation information, we adopt a self-supervised graph contrastive approach that leverages graph convolutional networks (GCNs) and second-order GCNs to extract feature graph information. Furthermore, we integrate a contrastive cost function derived from the cross-entropy cost function, facilitating holistic model optimization. Experimental results obtained from benchmark datasets not only showcase the superior performance of HSGCLRDA compared to various baseline methods in predicting RDAs but also emphasize its practical utility in identifying novel potential diseases associated with existing drugs through meticulous case studies.

Bridging the Gap between Field Experiments and Machine Learning: The EC H2020 B-GOOD Project as a Case Study towards Automated Predictive Health Monitoring of Honey Bee Colonies.

Honey bee colonies have great societal and economic importance. The main challenge that beekeepers face is keeping bee colonies healthy under ever-changing environmental conditions. In the past two decades, beekeepers that manage colonies of Western honey bees (Apis mellifera) have become increasingly concerned by the presence of parasites and pathogens affecting the bees, the reduction in pollen and nectar availability, and the colonies' exposure to pesticides, among others. Hence, beekeepers need to know the health condition of their colonies and how to keep them alive and thriving, which creates a need for a new holistic data collection method to harmonize the flow of information from various sources that can be linked at the colony level for different health determinants, such as bee colony, environmental, socioeconomic, and genetic statuses. For this purpose, we have developed and implemented the B-GOOD (Giving Beekeeping Guidance by computational-assisted Decision Making) project as a case study to categorize the colony's health condition and find a Health Status Index (HSI). Using a 3-tier setup guided by work plans and standardized protocols, we have collected data from inside the colonies (amount of brood, disease load, honey harvest, etc.) and from their environment (floral resource availability). Most of the project's data was automatically collected by the BEEP Base Sensor System. This continuous stream of data served as the basis to determine and validate an algorithm to calculate the HSI using machine learning. In this article, we share our insights on this holistic methodology and also highlight the importance of using a standardized data language to increase the compatibility between different current and future studies. We argue that the combined management of big data will be an essential building block in the development of targeted guidance for beekeepers and for the future of sustainable beekeeping.

Ground-based airglow imaging interferometer. Part 1: instrument and observation.

A ground-based airglow imaging interferometer (GBAII) is proposed to measure simultaneously the temperature and wind in the mesopause region by using airglow emissions of the O2(0-1) band. Since it employs a wide angle Michelson interferometer with a large air gap, combined with the rotational temperature measurement, both the phase and spectral information can be obtained from the imaging results. Based on the optimization and calibrations for the optical system in the laboratory, we developed and assembled a prototype of a GBAII, and carried out one observation at the observatory of Xi'an University of Technology on 12 June 2012. The observed temperatures fall mainly on the range of 167-196 K, while both the zonal and meridional winds faintly show the feature of half-day oscillation. The consistent trends between the observation results and the standard atmospheric models suggest that the GBAII has achieved our basic design goals.

[Regulation effects of liuwei dihuang pill, jingui shenqi pill, jiangu erxian pill containing serums on adipogenic and osteogenic differentiation-related genes expressions in the differentiation process of preadipocytes to osteoblasts].

OBJECTIVE: To study the effects of Chinese medical recipes for invigorating Shen on rat bone marrow mesenchymal stem cells (BMSCs)-derived preadipocytes' differentiation to osteoblasts. METHODS: The BMSCs were cultured using whole bone marrow adherence wall method. The BMSCs were induced to preadipocytes by classic chemical method. The osteogenic differentiation process of preadipocytes was intervened by Liuwei Dihuang Pill (LDP), Jingui Shenqi Pill (JSP), or Jiangu Erxian Pill (JEP)-containing serums (with the concentRation of 10%, on behalf of tonifying Shen yin, tonifying Shen yang, and tonifying Shen essence). Reverse transcription-real time fluorescent quantitative-PCR (RT real time qPCR) was used to detect RUNX2, ALP, BGP, BMP2, BMP4, SPP1, and IGF1 mRNA expressions of osteogenic differentiation-related genes, mRNA expressions of LPL, FABP4, and PPARgamma of adipogenic differentiation-related genes on the 6th, the 12th, and the 18th day. RESULTS: As for the osteogenic differentiation-related gene, when compared with the control group, there was no statistical difference in the gene expression level in the experimental groups on the 6th day (2.0 > Ratio > 0.5). On the 12th day, the mRNA expressions of IGF1 and Runx2 increased more significantly in the JSP group, with their relative quantification (Ratio) being 2.97 and 1.81 respectively. On the 18th day the IGF1 mRNA expression significantly increased, being the Ratio value of 3.74, 12.60, and 8.35, respectively, in the LDP group, the JSP group, and the JEP group. The SPP1 mRNA expression also significantly increased, with the Ratio value of 2.94, 3.18, and 2.62, respectively, in the LDP group, the JSP group, and the JEP group. As for adipogenic differentiation-related genes, on the 6th day, when compared with the control group, FABP4 mRNA expression significantly decreased in the LDP group and the JSP group (with the Ratio value of 0.47 and 0.40 respectively). The expression levels of other genes were all down-regulated, but not significantly. On the 12th day and 18th day, there was no statistical change in the adipogenic differentiation-related genes expressions (2.0 > Ratio > 0.5). CONCLUSIONS: Up-regulation of osteogenic differentiation-related genes expression occurred in later time, while down-regulation of adipogenic differentiation-related genes expression occurred in earlier time after treatment by Chinese medical recipes for invigorating Shen. In general, above data indicated that tonifying Shen yang was more effective in promoting osteogenic differentiation and inhibiting adipogenic differentiation of BMSCs.

Predicting Potential Drug-Disease Associations Based on Hypergraph Learning with Subgraph Matching.

The search for potential drug-disease associations (DDA) can speed up drug development cycles, reduce costly wasted resources, and accelerate disease treatment by repurposing existing drugs that can control further disease progression. As technologies such as deep learning continue to mature, many researchers tend to use emerging technologies to predict potential DDA. The performance of DDA prediction is still challenging and there is some space for improvement due to issues such as the small number of existing associations and possible noise in the data. To better predict DDA, we propose a computational approach based on hypergraph learning with subgraph matching (HGDDA). In particular, HGDDA first extracts feature subgraph information in the validated drug-disease association network and proposes a negative sampling strategy based on similarity network to reduce the data imbalance. Second, the hypergraph Unet module is used by extracting Finally, the potential DDA is predicted by designing a hypergraph combination module to convolution and pooling the two constructed hypergraphs separately, and calculating the difference information between the subgraphs using cosine similarity for node matching. The performance of HGDDA is verified under two standard datasets by 10-fold cross-validation (10-CV), and the results outperform existing drug-disease prediction methods. In addition, to validate the overall utility of the model, the top 10 drugs for the specific disease are predicted through the case study and validated using the CTD database.

A study on table tennis landing point detection algorithm based on spatial domain information.

To address the limitations of computer vision-assisted table tennis ball detection, which heavily relies on vision acquisition equipment and exhibits slow processing speed, we propose a real-time calculation method for determining the landing point of table tennis balls. This novel approach is based on spatial domain information and reduces the dependency on vision acquisition equipment. This method incorporates several steps: employing dynamic color thresholding to determine the centroid coordinates of all objects in the video frames, utilizing target area thresholding and spatial Euclidean distance to eliminate interference balls and noise, optimizing the total number of video frames through keyframe extraction to reduce the number of operations for object recognition and landing point detection, and employing the four-frame difference slope method and polygonal area determination to detect the landing point and area of the target object, thereby obtaining precise coordinates and their corresponding areas. Experimental results on the above method on the Jetson Nano development board show that the dynamic color thresholding method achieves a detection speed of 45.3 fps. The keyframe extraction method correctly identifies the landing point frames with an accuracy rate exceeding 93.3%. In terms of drop point detection, the proposed method achieves 78.5% overall accuracy in detecting table tennis ball drop points while ensuring real-time detection. These experiments validate that the proposed method has the ability to detect table tennis ball drop points in real time and accurately in low frame rate vision acquisition devices and real environments.

Construction of diagnostic and prognostic models based on gene signatures of nasopharyngeal carcinoma by machine learning methods.

Background: Diagnostic models based on gene signatures of nasopharyngeal carcinoma (NPC) were constructed by random forest (RF) and artificial neural network (ANN) algorithms. Least absolute shrinkage and selection operator (Lasso)-Cox regression was used to select and build prognostic models based on gene signatures. This study contributes to the early diagnosis and treatment, prognosis, and molecular mechanisms associated with NPC. Methods: Two gene expression datasets were downloaded from the Gene Expression Omnibus (GEO) database, and differentially expressed genes (DEGs) associated with NPC were identified by gene expression differential analysis. Subsequently, significant DEGs were identified by a RF algorithm. ANN were used to construct a diagnostic model for NPC. The performance of the diagnostic model was evaluated by area under the curve (AUC) values using a validation set. Lasso-Cox regression examined gene signatures associated with prognosis. Overall survival (OS) and disease-free survival (DFS) prediction models were constructed and validated from The Cancer Genome Atlas (TCGA) database and the International Cancer Genome Consortium (ICGC) database. Results: A total of 582 DEGs associated with NPC were identified, and 14 significant genes were identified by the RF algorithm. A diagnostic model for NPC was successfully constructed using ANN, and the validity of the model was confirmed on the training set AUC =0.947 [95% confidence interval (CI): 0.911-0.969] and the validation set AUC =0.864 (95% CI: 0.828-0.901). The 24-gene signatures associated with prognosis were identified by Lasso-Cox regression, and prediction models for OS and DFS of NPC were constructed on the training set. Finally, the ability of the model was validated on the validation set. Conclusions: Several potential gene signatures associated with NPC were identified, and a high-performance predictive model for early diagnosis of NPC and a prognostic prediction model with robust performance were successfully developed. The results of this study provide valuable references for early diagnosis, screening, treatment and molecular mechanism research of NPC in the future.

Predicting circRNA-drug resistance associations based on a multimodal graph representation learning framework.

Circular RNA (circRNA) is a class of noncoding RNA that is highly conserved and exhibit exceptional stability. Due to its function as a microRNA sponge, circRNA has gained significant attention as an essential biomarker and potential drug target in the pathogenesis of several cancers. Although many circRNAs have been identified to play a role in cancer resistance, traditional methods are time-consuming and expensive. In this context, computational methods offer a promising way to facilitate the discovery process. However, most existing prediction models focus on the association between circRNAs and drug resistance, without considering the corresponding disease-related information in the circRNA-drug resistance association. Incorporating disease-related information into the prediction of circRNA-drug resistance associations could potentially improve the efficiency and speed of discovering and developing circRNA-targeting drugs. We propose a computational framework, named GraphCDD, for predicting the association between circRNA and drug resistance. Our model utilizes data from three sources, namely circRNA, disease, and drug, to construct three similarity networks that represent the features of circRNA, disease, and drug, respectively. We utilize a multimodal graph neural network to acquire efficient representations of circRNAs, diseases, and drugs by integrating various types of information, and establish a predictive model. The experimental results have validated the effectiveness of our model and provided a promising method in predicting potential associations between circRNA and drug resistance. The source code and dataset of GraphCDD can be found at https://github.com/Ziqiang-Liu/GraphCDD.