Messenger RNA (mRNA) is vital for post-transcriptional gene regulation, acting as the direct template for protein synthesis. However, the methods available for predicting mRNA subcellular localization need to be improved and enhanced. Notably, few existing algorithms can annotate mRNA sequences with multiple localizations. In this work, we propose the mRNA-CLA, an innovative multi-label subcellular localization prediction framework for mRNA, leveraging a deep learning approach with a multi-head self-attention mechanism. The framework employs a multi-scale convolutional layer to extract sequence features across different regions and uses a self-attention mechanism explicitly designed for each sequence. Paired with Position Weight Matrices (PWMs) derived from the convolutional neural network layers, our model offers interpretability in the analysis. In particular, we perform a base-level analysis of mRNA sequences from diverse subcellular localizations to determine the nucleotide specificity corresponding to each site. Our evaluations demonstrate that the mRNA-CLA model substantially outperforms existing methods and tools.
Adverse perinatal factors can interfere with the normal development of the brain, potentially resulting in long-term effects on the comprehensive development of children. Presently, the understanding of cognitive and neurodevelopmental processes under conditions of adverse perinatal factors is substantially limited. There is a critical need for an open resource that integrates various perinatal factors with the development of the brain and mental health to facilitate a deeper understanding of these developmental trajectories. In this Data Descriptor, we introduce a multicenter database containing information on perinatal factors that can potentially influence children's brain-mind development, namely, periCBD, that combines neuroimaging and behavioural phenotypes with perinatal factors at county/region/central district hospitals. PeriCBD was designed to establish a platform for the investigation of individual differences in brain-mind development associated with perinatal factors among children aged 3-10 years. Ultimately, our goal is to help understand how different adverse perinatal factors specifically impact cognitive development and neurodevelopment. Herein, we provide a systematic overview of the data acquisition/cleaning/quality control/sharing, processes of periCBD.
Brain , Child Development , Child , Child, Preschool , Humans , Brain/growth & development , Brain/diagnostic imaging , China , Cognition , Databases, Factual , Neuroimaging
The cyclic guanosine monophosphate (GMP)-adenosine monophosphate (AMP) synthase-stimulator of interferon genes (cGAS-STING) signaling pathway, an important component of the innate immune system, is involved in the development of several diseases. Ectopic DNA-induced inflammatory responses are involved in several pathological processes. Repeated damage to tissues and metabolic organelles releases a large number of damage-associated molecular patterns (mitochondrial DNA, nuclear DNA, and exogenous DNA). The DNA fragments released into the cytoplasm are sensed by the sensor cGAS to initiate immune responses through the bridging protein STING. Many recent studies have revealed a regulatory role of the cGAS-STING signaling pathway in cardiovascular diseases (CVDs) such as myocardial infarction, heart failure, atherosclerosis, and aortic dissection/aneurysm. Furthermore, increasing evidence suggests that inhibiting the cGAS-STING signaling pathway can significantly inhibit myocardial hypertrophy and inflammatory cell infiltration. Therefore, this review is intended to identify risk factors for activating the cGAS-STING pathway to reduce risks and to simultaneously further elucidate the biological function of this pathway in the cardiovascular field, as well as its potential as a therapeutic target.
Single-cell epigenomic data has been growing continuously at an unprecedented pace, but their characteristics such as high dimensionality and sparsity pose substantial challenges to downstream analysis. Although deep learning models-especially variational autoencoders-have been widely used to capture low-dimensional feature embeddings, the prevalent Gaussian assumption somewhat disagrees with real data, and these models tend to struggle to incorporate reference information from abundant cell atlases. Here we propose CASTLE, a deep generative model based on the vector-quantized variational autoencoder framework to extract discrete latent embeddings that interpretably characterize single-cell chromatin accessibility sequencing data. We validate the performance and robustness of CASTLE for accurate cell-type identification and reasonable visualization compared with state-of-the-art methods. We demonstrate the advantages of CASTLE for effective incorporation of existing massive reference datasets in a weakly supervised or supervised manner. We further demonstrate CASTLE's capacity for intuitively distilling cell-type-specific feature spectra that unveil cell heterogeneity and biological implications quantitatively.
BACKGROUND: Universal varicella vaccination has been introduced in many countries, but there are a number of important differences in their vaccination strategies. It is essential to establish a vaccination program that can maximize the benefits of varicella vaccine, but there is a lack of comprehensive research on the effectiveness of varicella vaccine in different vaccination status. METHODS: Using data from population-based surveillance platforms we conducted a 1:2 matched case-control study. The cases were clinically diagnosed varicella with onset from 2017 to 2021, 1-14 years old in Chaoyang District, Beijing. The controls were matched according to date of birth (±1 month), sex and residence. The vaccination data of the subjects were obtained from the Childhood Immunization Information Management System in Beijing. Using conditional logistic regression models with or without interaction terms, we evaluated the effectiveness of varicella vaccine in different vaccination status. RESULTS: A total of 2528 cases and 5056 controls were enrolled. This study found that whether the time since last vaccination was adjusted had a substantial effect on the comparing vaccine effectiveness (VE) between subgroups. After adjustment for the time since last vaccination, 1) the incremental VE of 2-dose was 49.6 % (95 % Confidence Interval [CI], 38.8-58.6) compared with 1-dose (93.9 % vs. 88.0 %); 2) Among children who received one dose, the risk of chickenpox in children vaccinated at 18-23 months was 1.382 (95 %CI, 1.084-1.762) times that in children vaccinated at 12-17 months. 3) the VE with less than one, two, and three year intervals is higher than that with six-year-intervals (P < 0.05), respectively. CONCLUSIONS: When comparing VE between subgroups of different vaccination status, the time since last vaccination should be adjusted. The first dose of varicella vaccine should be given as early as the second year of life, and the second dose can improve vaccine effectiveness.
AIMS: This study compared the prevalences of metabolic syndrome and of cardiac or kidney comorbidities among patients with hepatocellular carcinoma (HCC) associated with metabolic dysfunction-related fatty liver disease (MAFLD), chronic infection with hepatitis B or C virus (HBV or HCV), or the combination of MAFLD and chronic HBV infection. METHODS: Medical records were retrospectively analyzed for patients with HCC who underwent hepatectomy between March 2013 and March 2023. Patients with HCC of different etiologies were compared in terms of their clinicodemographic characteristics and laboratory data before surgery. RESULTS: Of the 2422 patients, 1,822 (75.2%) were chronically infected with HBV without MAFLD and HCV, 415 (17.2%) had concurrent MAFLD and chronic HBV infection but no HCV infection, 121 (5.0%) had MAFLD without hepatitis virus infection, and 64 (2.6%) were chronically infected with HCV in the presence or absence of MAFLD and HBV infection. Compared to patients chronically infected with HBV without MAFLD and HCV, those with MAFLD but no hepatitis virus infection showed significantly lower prevalence of cirrhosis, ascites, portal hypertension, alpha-fetoprotein concentration ≥ 400 ng/mL, tumor size > 5 cm, multinodular tumors and microvascular invasion. Conversely, they showed significantly higher prevalence of metabolic syndrome, hypertension, type 2 diabetes, abdominal obesity, history of cardiovascular disease, T-wave alterations, hypertriglyceridemia and hyperuricemia, as well as higher risk of arteriosclerotic cardiovascular disease. Compared to patients with MAFLD but no hepatitis virus infection, those with concurrent MAFLD and chronic infection with HBV showed significantly higher prevalence of cirrhosis, ascites and portal hypertension, but significantly lower prevalence of hypertension and history of cardiovascular disease. Compared to patients with other etiologies, those chronically infected with HCV in the presence or absence of MAFLD and HBV infection, showed significantly higher prevalence of cirrhosis, portal hypertension, ascites, and esophagogastric varices. CONCLUSION: Patients with HCC associated with MAFLD tend to have a background of less severe liver disease than those with HCC of other etiologies, but they may be more likely to suffer metabolic syndrome or comorbidities affecting the heart or kidneys.
Objectives: In this study, we compared the dynamic changes in body composition during XELOX/SOX chemotherapy in patients with gastric cancer. Furthermore, we investigated the potential impact of these changes on the occurrence of toxic side effects. Methods: Patients with gastric cancer who received adjuvant or first-line XELOX/SOX chemotherapy between January 2020 and June 2023 were enrolled. The Brief Conghua Scale was used to assess energy intake, and nutritional management was carried out with reference to the Chinese Guidelines for Nutritional Therapy of Cancer 2020. The NRS 2002 Nutritional Risk Screening Scale, PG-SGA scale, bioelectrical impedance analysis, and dynamic changes in lumbar 3 vertebral skeletal muscle index were compared between baseline and post-chemotherapy in the study. The neutropenia was evaluated using the Common Terminology Criteria for Adverse Events V.5.0, developed by the National Institutes of Health. Results: Dynamic follow-up was completed in 39 cases, with a mean follow-up time of 117.62 ± 43.38 days. The incidence of sarcopenia increased significantly after chemotherapy, escalating from 46.2% to 51.3%. After chemotherapy, the mean L3SMI decreased from 36.00 cm2/m2 to 34.99 cm2/m2. Furthermore, when compared to pre-chemotherapy values, the body composition indexes body mass index (BMI), SL3, fat mass free index (FFMI), lean body mass (LBM), and body surface area (BSA) were significantly reduced after chemotherapy. Regardless of baseline or post-chemotherapy status, the incidence of grade ≥ 3 neutropenia was significantly higher in the sarcopenia group than in the non-sarcopenia group. Furthermore, when the skeletal muscle index decreased during chemotherapy, the incidence of grade ≥ 3 neutropenia was significantly higher in both the sarcopenia and non-sarcopenia groups compared to baseline. When the incidence of grade ≥ 3 neutropenia in the post-chemotherapy sarcopenia group was compared to baseline status, the increase was significantly higher in the sarcopenia group than in the maintenance/increase group. Conclusions: Skeletal muscle mass decreased progressively during XELOX/SOX chemotherapy in gastric cancer patients, followed by a higher incidence of grade ≥ 3 neutropenia.
The design of heterogeneous catalysts generally involves optimizing the reactivity descriptor of adsorption energy, which is inevitably governed by the structure of surface-active sites. A prerequisite for understanding the structure-properties relationship is the precise identification of real surface-active site structures, rather than relying on conceived structures derived from bulk alloy properties. However, it remains a formidable challenge due to the dynamic nature of nanoalloys during catalytic reactions and the lack of accurate and efficient interatomic potentials for simulations. Herein, a generalizable deep-learning potential for the Ag-Pd-F system is developed based on a dataset encompassing the bulk, surface, nanocluster, amorphous, and point defected configurations with diverse compositions to achieve a comprehensive description of interatomic interactions, facilitating precise prediction of adsorption energy, surface energy, formation energy, and diffusion energy barrier and is utilized to investigate the structural evolutions of AgPd nanoalloys during fluorination. The structural evolutions involve the inward diffusion of F, the outward diffusion of Ag in Ag@Pd nanoalloys, the formation of surface AgFx species in mixed and Janus AgPd nanoalloys, and the shape deformation from cuboctahedron to sphere in Ag and Pd@Ag nanoalloys. Moreover, the effects of atomic diffusion and dislocation formation and migration on the reconstructing pathway of nanoalloys are highlighted. It is demonstrated that the stress relaxation upon F adsorption serves as the intrinsic driving factor governing the surface reconstruction of AgPd nanoalloys.
Aqueous Zinc-sulfur (Zn-S) batteries are promising for the field of energy storage due to their low cost, high theoretical capacity, and safety. However, the large volume expansion and the inherently poor conductivity of sulfur would result in electrode cracking and sluggish reaction kinetics, limiting the practical application of Zn-S batteries. Herein, commercial zinc sulfide (ZnS) is employed instead of S as cathode and proposed a doping modification strategy to solve the above problems. The designed ZnS0.93Se0.07 cathode shows good cycle stability and much-improved reaction kinetics, which is due to the smaller bandgap of ZnS0.93Se0.07 (1.40 eV) compared to ZnS (1.86 eV). As a result, the obtained ZnS0.93Se0.07 cathode exhibits a high specific capacity of 552 mAh g-1 (1672.6 mAh g-1 based on S) at 0.1 A g-1 and 330 mAh g-1 (1000 mAh g-1 based on S) at 2 A g-1. Moreover, the ZnS0.93Se0.07 cathode can provide a high areal capacity of 3.8 mAh cm-2 at a high mass loading of 10 mg cm-2 and limited electrolyte (4 µL mg-1). This work provides a simple and effective cathode modification strategy, which is conducive to promoting the practical application of Zn-S batteries.
As the outermost layer of the human body, the skin suffers from various external factors especially light damage, among which ultraviolet B (UVB) irradiation is common and possesses a relatively high biological damage capacity. Pyroptosis is a newly discovered type of programmed cell death, which can induce cell rupture and induce local inflammatory response. However, the molecular mechanisms of pyroptosis in photodamaged skin is poorly understood. Baicalin, a flavonoid extracted from the desiccated root of Scutellaria baicalensis Georgi (Huang Qin). Despite its antioxidant abilities, whether baicalin protects skin by attenuating UVB-induced pyroptosis remains unclear, which was the aim of this study. The UVB-induced acute skin damage model was established by using human immortalized keratinocytes (HaCaT cells) and Kunming (KM) strain mice. The protective dose selection for baicalin is 50 µM in vitro and 100 mg/kg in vivo. In in vitro study, UVB irradiation significantly decreased cell viability, increased cell death and oxidative stress in HaCaT cells, while pretreatment with baicalin improved these phenomena. Furthermore, the baicalin pretreatment notably suppressed nuclear factor kappa B (NF-κB) translocation, the NLRP3 inflammasome activation and gasdermin D (GSDMD) maturation, thus effectively attenuating UVB-induced pyroptosis. In in vivo study, the baicalin pretreatment mitigated epidermal hyperplasia, collagen fiber fragmentation, oxidative stress and pyroptosis in UVB-irradiated mouse skin. In a nutshell, this study suggests that baicalin could be a potential protective agent to attenuate acute skin damage induced by UVB irradiation through decreasing oxidative stress and suppressing NF-κB/NLRP3/GSDMD-involved pyroptosis.
Inverted p-i-n perovskite solar cells (PSCs) are easy to process but need improved interface characteristics with reduced energy loss to prevent efficiency drops when increasing the active photovoltaic area. Here, we report a series of poly ferrocenyl molecules that can modulate the perovskite surface enabling the construction of small- and large-area PSCs. We found that the perovskite-ferrocenyl interaction forms a hybrid complex with enhanced surface coordination strength and activated electronic states, leading to lower interfacial nonradiative recombination and charge transport resistance losses. The resulting PSCs achieve an enhanced efficiency of up to 26.08% for small-area devices and 24.51% for large-area devices (1.0208 cm2). Moreover, the large-area PSCs maintain >92% of the initial efficiency after 2000 h of continuous operation at the maximum power point under 1-sun illumination and 65 °C.
Phosphate derivatives and their interaction with metal cations are involved in many important biological phenomena, so an accurate characterization of the phosphate-metal interaction is necessary to properly understand the role of phosphate-metal contacts in mediating biological function. Herein, we improved the standard 12-6 Lennard-Jones (LJ) potential via the usage of the 12-6-4 LJ model, which incorporates ion-induced dipole interactions. Via parameter scanning, we fine-tuned the 12-6-4 LJ polarizability values to obtain accurate absolute binding free energies for the phosphate anions H2PO4-, HPO42-, PO43- coordinating with Ca2+ and Mg2+. First, we modified the phosphate 12-6-4 LJ parameters to reproduce the solvation free energies of the series of phosphate anions using the thermodynamic integration (TI) method. Then, using the potential mean force (PMF) method, the polarizability of the metal-phosphate interaction was obtained. We show that the free energy profiles of phosphate ions coordinated to Ca2+ and Mg2+ generally show similar trends at longer metal-phosphate distances, while the absolute binding energy values increased with deprotonation. The resulting parameters demonstrate the flexibility of the 12-6-4 LJ-type nonbonded model and its usefulness in accurately describing cation-anion interactions.
OBJECTIVE: The aim of the study was to create two consensus nomograms for predicting Overall Survival (OS) and Cancer-Specific Survival (CSS) in adults with papillary Renal Cell Carcinoma (pRCC). METHODS: Using the Surveillance, Epidemiology, and End Results databases, a retrospective analysis of 1,074 adults with pRCC from 2004 to 2015 was performed. These patients were then randomly divided into two independent cohorts with a ratio of 7:3 (training cohort: 752; validation cohort: 322). In a retrospective analysis of 752 patients from the training cohort, independent prognostic variables affecting OS and CSS were found. R software was used to create prognostic nomograms based on the findings of Cox regression analysis. The performance of the nomograms was assessed using the Concordance Index (C-index), the Area Under Curve (AUC), a calibration curve, and Decision Curve Analysis (DCA). Data from the 107 postoperative pRCC patients at the Affiliated Hospital of Xuzhou Medical University were used for external validation of the nomogram. RESULTS: For OS and CSS, the C-indices and AUCs of the training cohort and the validation cohort indicated that the model had excellent discrimination. The DCA demonstrated that the model was clinically applicable, and the calibration curves in the internal and external validations showed that the model's accuracy was high. CONCLUSION: The authors developed and validated a prognostic nomogram that accurately predicted the 3-, 5-, and 8-year OS and CSS of adults with pRCC. Clinicians can use this knowledge to direct the clinical management and counseling of patients with pRCC.
The aim of the current study is to investigate the diagnostic value of R2* mapping versus reduced field-of-view diffusion-weighted imaging (rDWI) of the primary lesion of rectal cancer for preoperative prediction of nonenlarged lymph node metastasis (NLNM). Eighty-one patients with pathologically confirmed rectal cancer underwent preoperative R2* mapping and rDWI sequences before total mesorectal excisions and accompanying regional lymph node dissections. Two radiologists independently performed whole-tumor measurements of R2* and apparent diffusion coefficient (ADC) parameters on primary lesions of rectal cancer. Patients were divided into positive (NLNM+) and negative (NLNM-) groups based on their pathological analysis. The tumor location, maximum diameter of the tumor, and maximum short diameter of the lymph node were assessed. R2* and ADC, pT stage, tumor grade, status of mesorectal fascia, and extramural vascular invasion were also studied for their potential relationships with NLNM using multivariate logistic regression analysis. The NLNM+ group had significantly higher R2* (43.56 ± 8.43 vs. 33.87 ± 9.57, p < 0.001) and lower ADC (1.00 ± 0.13 vs. 1.06 ± 0.22, p = 0.036) than the NLNM- group. R2* and ADC were correlated to lymph node metastasis (r = 0.510, p < 0.001 for R2*; r = -0.235, p = 0.035 for ADC). R2* and ADC showed good and moderate diagnostic abilities in the assessment of NLNM status with corresponding area-under-the-curve values of 0.795 and 0.636. R2* provided a significantly better diagnostic performance compared with ADC for the prediction of NLNM status (z = 1.962, p = 0.0498). The multivariate logistic regression analysis demonstrated that R2* was a compelling factor of lymph node metastasis (odds ratio = 56.485, 95% confidence interval: 5.759-554.013; p = 0.001). R2* mapping had significantly higher diagnostic performance than rDWI from the primary tumor of rectal cancer in the prediction of NLNM status.
Introduction: Ganoderma lucidum (G. lucidum, Lingzhi) has long been listed as a premium tonic that can be used to improve restlessness, insomnia, and forgetfulness. We previously reported that a rat model of sporadic Alzheimer's disease (sAD) that was induced by an intracerebroventricular injection of streptozotocin (ICV-STZ) showed significant learning and cognitive deficits and sleep disturbances. Treatment with a G. lucidum spore extract with the sporoderm removed (RGLS) prevented learning and memory impairments in sAD model rats. Method: The present study was conducted to further elucidate the preventive action of RGLS on sleep disturbances in sAD rats by EEG analysis, immunofluorescence staining, HPLC-MS/MS and Western blot. Results: Treatment with 720 mg/kg RGLS for 14 days significantly improved the reduction of total sleep time, rapid eye movement (REM) sleep time, and non-REM sleep time in sAD rats. The novelty recognition experiment further confirmed that RGLS prevented cognitive impairments in sAD rats. We also found that RGLS inhibited the nuclear factor-κB (NF-κB)/Nod-like receptor family pyrin domain-containing 3 (NLRP3) inflammatory pathway in the medial prefrontal cortex (mPFC) in sAD rats and ameliorated the lower activity of γ-aminobutyric acid (GABA)-ergic neurons in the parabrachial nucleus (PBN). Discussion: These results suggest that inhibiting the neuroinflammatory response in the mPFC may be a mechanism by which RGLS improves cognitive impairment. Additionally, improvements in PBN-GABAergic activity and the suppression of neuroinflammation in the mPFC in sAD rats might be a critical pathway to explain the preventive effects of RGLS on sleep disturbances in sAD.
Introduction: Ganoderma lucidum: (G. lucidum, Lingzhi) is a medicinal and edible homologous traditional Chinese medicine that is used to treat various diseases, including Alzheimer's disease and mood disorders. We previously reported that the sporoderm-removed G. lucidum spore extract (RGLS) prevented learning and memory impairments in a rat model of sporadic Alzheimer's disease (sAD), but the effect of RGLS on depression-like behaviors in this model and its underlying molecular mechanisms of action remain unclear. Method: The present study investigated protective effects of RGLS against intracerebroventricular streptozotocin (ICV-STZ)-induced depression in a rat model of sAD and its underlying mechanism. Effects of RGLS on depression- and anxiety-like behaviors in ICV-STZ rats were assessed in the forced swim test, sucrose preference test, novelty-suppressed feeding test, and open field test. Results: Behavioral tests demonstrated that RGLS (360 and 720 mg/kg) significantly ameliorated ICV-STZ-induced depression- and anxiety-like behaviors. Immunofluorescence, Western blot and enzyme-linked immunosorbent assay results further demonstrated that ICV-STZ rats exhibited microglia activation and neuroinflammatory response in the medial prefrontal cortex (mPFC), and RGLS treatment reversed these changes, reflected by the normalization of morphological changes in microglia and the expression of NF-κB, NLRP3, ASC, caspase-1 and proinflammatory cytokines. Golgi staining revealed that treatment with RGLS increased the density of mushroom spines in neurons. This increase was associated with elevated expression of brain-derived neurotrophic protein in the mPFC. Discussion: In a rat model of ICV-STZ-induced sAD, RGLS exhibits antidepressant-like effects, the mechanism of which may be related to suppression of the inflammatory response modulated by the NF-κB/NLRP3 pathway and enhancement of synaptic plasticity in the mPFC.
The cardiotoxicity caused by Dox chemotherapy represents a significant limitation to its clinical application and is a major cause of late death in patients undergoing chemotherapy. Currently, there are no effective treatments available. Our analysis of 295 clinical samples from 132 chemotherapy patients and 163 individuals undergoing physical examination revealed a strong positive correlation between intestinal barrier injury and the development of cardiotoxicity in chemotherapy patients. We developed a novel orally available and intestinal targeting protein nanodrug by assembling membrane protein Amuc_1100 (obtained from intestinal bacteria Akkermansia muciniphila), fluorinated polyetherimide, and hyaluronic acid. The protein nanodrug demonstrated favorable stability against hydrolysis compared with free Amuc_1100. The in vivo results demonstrated that the protein nanodrug can alleviate Dox-induced cardiac toxicity by improving gut microbiota, increasing the proportion of short-chain fatty acid-producing bacteria from the Lachnospiraceae family, and further enhancing the levels of butyrate and pentanoic acids, ultimately regulating the homeostasis repair of lymphocytes in the spleen and heart. Therefore, we believe that the integrity of the intestinal barrier plays an important role in the development of chemotherapy-induced cardiotoxicity. Protective interventions targeting the intestinal barrier may hold promise as a general clinical treatment regimen for reducing Dox-induced cardiotoxicity.
Near-infrared-II (NIR-II) fluorescence imaging is pivotal in biomedical research. Organic probes exhibit high potential in clinical translation, due to advantages such as precise structure design, low toxicity, and post-modifications convenience. In related preparation, enhancement of NIR-II tail emission from NIR-I dyes is an efficient method. In particular, the promotion of twisted intramolecular charge transfer (TICT) of relevant NIR-I dyes is a convenient protocol. However, present TICT-type probes still show disadvantages in relatively low emission, large particle sizes, or limited choice of NIR-I dyes, etc. Herein, the synthesis of stable small-sized polymer NIR-II fluoroprobes (e.g., 7.2 nm), integrating TICT and Förster resonance energy transfer process to synergistically enhance the NIR-II emission is reported. Strong enhanced emissions can be obtained from various NIR-I dyes and lanthanide elements (e.g., twelvefold at 1250 nm from Nd-DTPA/IR-808 sample). The fluorophore provides high-resolution angiography, with high-contrast imaging on middle cerebral artery occlusion model mice for distinguishing occlusion. The fluorophore can be rapidly excreted from the kidney (urine ≈65% within 4 h) in normal mice and exhibits long-term renal retention on acute kidney injury mice, showing potential applications in the prognosis of kidney diseases. This development provides an effective strategy to design and synthesize effective NIR-II fluoroprobes.
Long non-coding RNAs (lncRNAs) are important factors involved in biological regulatory networks. Accurately predicting lncRNA-protein interactions (LPIs) is vital for clarifying lncRNA's functions and pathogenic mechanisms. Existing deep learning models have yet to yield satisfactory results in LPI prediction. Recently, graph autoencoders (GAEs) have seen rapid development, excelling in tasks like link prediction and node classification. We employed GAE technology for LPI prediction, devising the FMSRT-LPI model based on path masking and degree regression strategies and thereby achieving satisfactory outcomes. This represents the first known integration of path masking and degree regression strategies into the GAE framework for potential LPI inference. The effectiveness of our FMSRT-LPI model primarily relies on four key aspects. First, within the GAE framework, our model integrates multi-source relationships of lncRNAs and proteins with LPN's topological data. Second, the implemented masking strategy efficiently identifies LPN's key paths, reconstructs the network, and reduces the impact of redundant or incorrect data. Third, the integrated degree decoder balances degree and structural information, enhancing node representation. Fourth, the PolyLoss function we introduced is more appropriate for LPI prediction tasks. The results on multiple public datasets further demonstrate our model's potential in LPI prediction.
