HerbMet: Enhancing metabolomics data analysis for accurate identification of Chinese herbal medicines using deep learning.

INTRODUCTION: Chinese herbal medicines have been utilized for thousands of years to prevent and treat diseases. Accurate identification is crucial since their medicinal effects vary between species and varieties. Metabolomics is a promising approach to distinguish herbs. However, current metabolomics data analysis and modeling in Chinese herbal medicines are limited by small sample sizes, high dimensionality, and overfitting. OBJECTIVES: This study aims to use metabolomics data to develop HerbMet, a high-performance artificial intelligence system for accurately identifying Chinese herbal medicines, particularly those from different species of the same genus. METHODS: We propose HerbMet, an AI-based system for accurately identifying Chinese herbal medicines. HerbMet employs a 1D-ResNet architecture to extract discriminative features from input samples and uses a multilayer perceptron for classification. Additionally, we design the double dropout regularization module to alleviate overfitting and improve model's performance. RESULTS: Compared to 10 commonly used machine learning and deep learning methods, HerbMet achieves superior accuracy and robustness, with an accuracy of 0.9571 and an F1-score of 0.9542 for distinguishing seven similar Panax ginseng species. After feature selection by 25 different feature ranking techniques in combination with prior knowledge, we obtained 100% accuracy and an F1-score for discriminating P. ginseng species. Furthermore, HerbMet exhibits acceptable inference speed and computational costs compared to existing approaches on both CPU and GPU. CONCLUSIONS: HerbMet surpasses existing solutions for identifying Chinese herbal medicines species. It is simple to use in real-world scenarios, eliminating the need for feature ranking and selection in classical machine learning-based methods.

CD151, a novel host factor of nuclear export signaling in influenza virus infection.

BACKGROUND: Despite advances in our understanding of the mechanisms of influenza A virus (IAV) infection, the crucial virus-host interactions during the viral replication cycle still remain incomplete. Tetraspanin CD151 is highly expressed in the human respiratory tract, but its pathological role in IAV infection is unknown. OBJECTIVES: We sought to characterize the functional role and mechanisms of action of CD151 in IAV infection of the upper and lower respiratory tracts with H1N1 and H3N2 strains. METHODS: We used CD151-null mice in an in vivo model of IAV infection and clinical donor samples of in vitro-differentiated human nasal epithelial cells cultured at air-liquid interface. RESULTS: As compared with wild-type infected mice, CD151-null infected mice exhibited a significant reduction in virus titer and improvement in survival that is associated with pronounced host antiviral response and inflammasome activation together with accelerated lung repair. Interestingly, we show that CD151 complexes newly synthesized viral proteins with host nuclear export proteins and stabilizes microtubule complexes, which are key processes necessary for the polarized trafficking of viral progeny to the host plasma membrane for assembly. CONCLUSIONS: Our results provide new mechanistic insights into our understanding of IAV infection. We show that CD151 is a critical novel host factor of nuclear export signaling whereby the IAV nuclear export uses it to complement its own nuclear export proteins (a site not targeted by current therapy), making this regulation unique, and holds promise for the development of novel alternative/complementary strategies to reduce IAV severity.

CD151, a laminin receptor showing increased expression in asthmatic patients, contributes to airway hyperresponsiveness through calcium signaling.

BACKGROUND: Airway smooth muscle (ASM) contraction underpins airway constriction; however, underlying mechanisms for airway hyperresponsiveness (AHR) remain incompletely defined. CD151, a 4-transmembrane glycoprotein that associates with laminin-binding integrins, is highly expressed in the human lung. The role of CD151 in ASM function and its relationship to asthma have yet to be elucidated. OBJECTIVE: We sought to ascertain whether CD151 expression is clinically relevant to asthma and whether CD151 expression affects AHR. METHODS: Using immunohistochemical analysis, we determined the expression of CD151 in human bronchial biopsy specimens from patients with varying asthma severities and studied the mechanism of action of CD151 in the regulation of ASM contraction and bronchial caliber in vitro, ex vivo, and in vivo. RESULTS: The number of CD151+ ASM cells is significantly greater in patients with moderate asthma compared with those in healthy nonasthmatic subjects. From loss- and gain-of-function studies, we reveal that CD151 is required for and enhances G protein-coupled receptor (GPCR)-induced peak intracellular calcium release, the primary determinant of excitation-contraction coupling. We show that the localization of CD151 can also be perinuclear/cytoplasmic and offer an explanation for a novel functional role for CD151 in supporting protein kinase C (PKC) translocation to the cell membrane in GPCR-mediated ASM contraction at this site. Importantly, CD151-/- mice are refractory to airway hyperreactivity in response to allergen challenge. CONCLUSIONS: We identify a role for CD151 in human ASM contraction. We implicate CD151 as a determinant of AHR in vivo, likely through regulation of GPCR-induced calcium and PKC signaling. These observations have significant implications in understanding the mechanism for AHR and the efficacy of new and emerging therapeutics.

GSK-3ß activation index is a potential indicator for recurrent inflammation of chronic rhinosinusitis without nasal polyps.

Chronic rhinosinusitis without nasal polyps (CRSsNP) is one of the most common otorhinolaryngologic diseases worldwide. However, the underlying mechanism remains unclear. In this study, the expression of glycogen synthase kinase 3 (GSK-3) was quantitatively evaluated in patients with CRSsNP (n = 20) and healthy controls (n = 20). The mRNA levels of GSK-3α and GSK-3ß were examined by qPCR, the immunoreactivities of GSK-3ß and nuclear factor-κB (NF-κB) were examined by immunohistochemistry (IHC) staining, and the protein levels of GSK-3ß, phospho-GSK-3ß (p-GSK-3ß, s9) and NF-κB were examined using Western blot analysis. We found that GSK-3 was highly expressed in both CRSsNP and control groups without significant difference in both GSK-3ß mRNA and protein levels. However, when compared with healthy control group, the GSK-3ß activation index, defined as the ratio of GSK-3ß over p-GSK-3ß, was significantly decreased, whereas the NF-κB protein abundance was significantly increased in CRSsNP group (P < 0.05). Strikingly, the GSK-3ß activation index, was highly correlated with NF-κB protein level, as well as CT scores in CRSsNP group (P < 0.05). It was also highly correlated with the mRNA expressions of inflammation-related genes, including T-bet, IFN-γ and IL-4 in CRSsNP group (P < 0.05). Our findings suggest that GSK-3ß activation index, reflecting the inhibitory levels of GSK-3ß through phosphorylation, may be a potential indicator for recurrent inflammation of CRSsNP, and that the insufficient inhibitory phosphorylation of GSK-3ß may play a pivotal role in the pathogenesis of CRSsNP.

Laminin drives survival signals to promote a contractile smooth muscle phenotype and airway hyperreactivity.

Increased airway smooth muscle (ASM) mass is believed to underlie the relatively fixed airway hyperresponsiveness (AHR) in asthma. Developments of therapeutic approaches to reverse airway remodeling are impeded by our lack of insight on the mechanisms behind the increase in mass of contractile ASM cells. Increased expression of laminin, an extracellular matrix protein, is associated with asthma. Our studies investigate the role of laminin-induced ASM survival signals in the development of increased ASM and AHR. Antagonizing laminin integrin binding using the laminin-selective competing peptide, YIGSR, and mimicking laminin with exogenous α2-chain laminin, we show that laminin is both necessary and sufficient to induce ASM cell survival, concomitant with the induction of ASM contractile phenotype. Using siRNA, we show that the laminin-binding integrin α7ß1 mediates this process. Moreover, in laminin-211-deficient mice, allergen-induced AHR was not observed. Notably, ASM cells from asthmatic airways express a higher abundance of intracellular cell survival proteins, consistent with a role for reduced rates of cell apoptosis in development of ASM hyperplasia. Targeting the laminin-integrin α7ß1 signaling pathway may offer new avenues for the development of therapies to reduce the increase in mass of contractile phenotype ASM cells that underlie AHR in asthma.

A LSTM-RNN based intelligent control approach for temperature and humidity environment of urban utility tunnels.

Temperature and relative humidity are important indicators of utility tunnel indoor atmosphere hazards and operational risks, which can be effectively mitigated by accurate forecasting and corrective control measures. To this end, this paper proposed a multi-layer long short-term memory (LSTM) recurrent neural network (RNN) architecture to forecast the changing trend of temperature and relative humidity inside utility tunnels with distant past monitoring data. Based on the forecasting architecture, an intelligent control approach was designed, including early warning and ventilation control measures. Case study results showed that the proposed architecture fit the training dataset well and the prediction accuracy on testing datasets of temperature and relative humidity exceeded 98% and 99%, respectively. Meanwhile, the proposed LSTM-RNN architecture can also be used to simulate and evaluate the ventilation effects on the temperature and relative humidity environment of urban utility tunnels. Findings of this paper provide a reference for the safe, efficient and energy-saving indoor environment control of urban utility tunnels.

A method for Kashin-Beck disease auxiliary diagnosis based on the features in regions of the potential lesion.

BACKGROUND: Kashin-Beck disease (KBD) is a severe arthropathy that causes deformity. Patients with advanced stages of KBD often show symptoms, such as short stature. Early-stage diagnosis and treatment can effectively prevent the disease from worsening. Diagnosis of early-stage patients is usually made by X-ray examination. However, the time-consuming image recognition and the lack of professional doctors may delay the patient's condition. Therefore, a method that can efficiently complete the auxiliary diagnosis is necessary. PURPOSE: This study presents a KBD auxiliary diagnosis method based on radiographs, which uses deep learning to locate potential lesion regions and extract features for accurate diagnosis. METHODS: This work presents a method that relies on hand radiographs to locate eight regions of the potential lesion (RoPL) and finally make the KBD auxiliary diagnosis. The localization of RoPL is achieved through a two-step model, with the first step predicting a rough location and a deep convolutional neural network (DCNN) with attention mechanism used to generate precise center coordinates based on the previous step's results. Based on the localization result, regional features are extracted, which provides information about the joints and textures of RoPL from a finer granularity. Another DCNN is utilized to obtain general features from hand radiographs, which provide morphological and structural information about the entire hand bone These features offer a concatenated feature for categorization to raise accuracy. A doctor-like approach is adopted to diagnose based on regional features to enhance performance, and a final decision is made using a vote that considers diagnostic outcomes from all aspects. The dataset used in our study was collected by our research team in KBD-endemic areas of Tibet since 2017, containing 373 diseased and 764 normal images. RESULT: Our model guarantees that over 95% of the predicted coordinates are within five pixels of the real coordinates according to Euclidean distance. The accuracy of the diagnostic network achieved 91.3%, with precision and recall achieving 83% and 87%, respectively. Compared to the approach without exact localization of the illness region on the same test set, our method achieved a roughly 6% increase in accuracy and nearly 30% increase in recall rate. CONCLUSIONS: Based on hand radiographs, this study suggests a novel method for KBD diagnosis. The high-precision localization network guarantees precise extraction of lesion-prone regional features, and the multi-scale features and innovative classification method further enhance model performance compared to related approaches.

FGF2 is overexpressed in asthma and promotes airway inflammation through the FGFR/MAPK/NF-κB pathway in airway epithelial cells.

BACKGROUND: Airway inflammation is the core pathological process of asthma, with the key inflammatory regulators incompletely defined. Recently, fibroblast growth factor 2 (FGF2) has been reported to be an inflammatory regulator; however, its role in asthma remains elusive. This study aimed to investigate the immunomodulatory role of FGF2 in asthma. METHODS: First, FGF2 expression was characterised in clinical asthma samples and the house dust mite (HDM)-induced mouse chronic asthma model. Second, recombinant mouse FGF2 (rm-FGF2) protein was intranasally delivered to determine the effect of FGF2 on airway inflammatory cell infiltration. Third, human airway epithelium-derived A549 cells were stimulated with either HDM or recombinant human interleukin-1ß (IL-1ß) protein combined with or without recombinant human FGF2. IL-1ß-induced IL-6 or IL-8 release levels were determined using enzyme-linked immunosorbent assay, and the involved signalling transduction was explored via Western blotting. RESULTS: Compared with the control groups, the FGF2 protein levels were significantly upregulated in the bronchial epithelium and alveolar areas of clinical asthma samples (6.70 ± 1.79 vs. 16.32 ± 2.40, P = 0.0184; 11.20 ± 2.11 vs. 21.00 ± 3.00, P = 0.033, respectively) and HDM-induced asthmatic mouse lung lysates (1.00 ± 0.15 vs. 5.14 ± 0.42, P < 0.001). Moreover, FGF2 protein abundance was positively correlated with serum total and anti-HDM IgE levels in the HDM-induced chronic asthma model (R2 = 0.857 and 0.783, P = 0.0008 and 0.0043, respectively). Elevated FGF2 protein was mainly expressed in asthmatic bronchial epithelium and alveolar areas and partly co-localised with infiltrated inflammatory cell populations in HDM-induced asthmatic mice. More importantly, intranasal instillation of rm-FGF2 aggravated airway inflammatory cell infiltration (2.45 ± 0.09 vs. 2.88 ± 0.14, P = 0.0288) and recruited more subepithelial neutrophils after HDM challenge [(110.20 ± 29.43) cells/mm2 vs. (238.10 ± 42.77) cells/mm2, P = 0.0392] without affecting serum IgE levels and Th2 cytokine transcription. In A549 cells, FGF2 was upregulated through HDM stimulation and promoted IL-1ß-induced IL-6 or IL-8 release levels (up to 1.41 ± 0.12- or 1.44 ± 0.14-fold change vs. IL-1ß alone groups, P = 0.001 or 0.0344, respectively). The pro-inflammatory effect of FGF2 is likely mediated through the fibroblast growth factor receptor (FGFR)/mitogen-activated protein kinase (MAPK)/nuclear factor kappa B (NF-κB) pathway. CONCLUSION: Our findings suggest that FGF2 is a potential inflammatory modulator in asthma, which can be induced by HDM and acts through the FGFR/MAPK/NF-κB pathway in the airway epithelial cells.

FGF2, an Immunomodulatory Factor in Asthma and Chronic Obstructive Pulmonary Disease (COPD).

The fibroblast growth factor 2 (FGF2) is a potent mitogenic factor belonging to the FGF family. It plays a role in airway remodeling associated with chronic inflammatory airway diseases, including asthma and chronic obstructive pulmonary disease (COPD). Recently, research interest has been raised in the immunomodulatory function of FGF2 in asthma and COPD, through its involvement in not only the regulation of inflammatory cells but also its participation as a mediator between immune cells and airway structural cells. Herein, this review provides the current knowledge on the biology of FGF2, its expression pattern in asthma and COPD patients, and its role as an immunomodulatory factor. The potential that FGF2 is involved in regulating inflammation indicates that FGF2 could be a therapeutic target for chronic inflammatory diseases.

TLR4 antagonist suppresses airway remodeling in asthma by inhibiting the T-helper 2 response.

Airway remodeling is a hallmark of bronchial asthma. Our group has previously reported that the thymic stromal lymphopoietin (TSLP), an airway epithelial-derived cytokine, has a central role in the pathogenesis of airway remodeling, and that toll-like receptor (TLR) 4 signaling in epithelial cells may trigger T-helper 2 (Th2) immune responses by overexpression of TSLP. However, it is currently unclear whether TLR4 is a target in the treatment of airway remodeling in asthma. The present study established a house dust mite (HDM)-induced chronic asthmatic model in female BALB/c mice and treated the HDM-exposed mice with 3 mg/kg TAK242, as a TLR4 antagonist, 30 min prior to HDM challenge for up to 2 weeks. General structural changes in the airways were subsequently evaluated and the levels of TSLP in the bronchoalveolar lavage fluid (BALF) and interleukin (IL)-4, IL-13 and interferon (IFN)-γ in the blood serum were determined. Results indicated that TAK242 treatment markedly reduced pathological changes in the airways of HDM-induced asthmatic mice, as demonstrated by reductions in airway wall thickening, peribronchial collagen deposition and subepithelial fibrosis. Furthermore, airway hyperresponsiveness to inhaled methacholine and the levels of TSLP in the BALF and IL-4, IL-13 and IFN-γ in the peripheral blood were significantly reduced by TAK242 treatment (P<0.05). Furthermore, the shift in the IFN-γ/IL-4 ratio induced by HDM treatment was significantly reversed following TAK242 pretreatment, which indicated that TAK242 modulated Th1/Th2 immune homeostasis in the chronic asthma mouse model. The present findings in a chronic asthma mouse model suggest that TAK242 may be an efficient treatment for airway remodeling, possibly through the inhibition of TSLP overexpression and Th2 airway inflammation.

p53 gene targeting by homologous recombination in fish ES cells.

BACKGROUND: Gene targeting (GT) provides a powerful tool for the generation of precise genetic alterations in embryonic stem (ES) cells to elucidate gene function and create animal models for human diseases. This technology has, however, been limited to mouse and rat. We have previously established ES cell lines and procedures for gene transfer and selection for homologous recombination (HR) events in the fish medaka (Oryzias latipes). METHODOLOGY AND PRINCIPAL FINDINGS: Here we report HR-mediated GT in this organism. We designed a GT vector to disrupt the tumor suppressor gene p53 (also known as tp53). We show that all the three medaka ES cell lines, MES1∼MES3, are highly proficient for HR, as they produced detectable HR without drug selection. Furthermore, the positive-negative selection (PNS) procedure enhanced HR by ∼12 folds. Out of 39 PNS-resistant colonies analyzed, 19 (48.7%) were positive for GT by PCR genotyping. When 11 of the PCR-positive colonies were further analyzed, 6 (54.5%) were found to be bona fide homologous recombinants by Southern blot analysis, sequencing and fluorescent in situ hybridization. This produces a high efficiency of up to 26.6% for p53 GT under PNS conditions. We show that p53 disruption and long-term propagation under drug selection conditions do not compromise the pluripotency, as p53-targeted ES cells retained stable growth, undifferentiated phenotype, pluripotency gene expression profile and differentiation potential in vitro and in vivo. CONCLUSIONS: Our results demonstrate that medaka ES cells are proficient for HR-mediated GT, offering a first model organism of lower vertebrates towards the development of full ES cell-based GT technology.

[Dynamics of biomass and stem volume of Picea asperata stands in artificial restoration process of subalpine coniferous forest].

The dynamics of aboveground biomass and stem volume in subalpine coniferous Picea asperata plantations with different stand ages in 70 years of artificial restoration process were studied by adopting the concept of space as a substitute for time. The results indicated that before 20 years of stand age, the biomass of spruce single tree grew quite slow, with that of the twigs and needles accounting for about 50%; after 20 years, it increased obviously, with 60% of biomass accumulated in stem; from 30 to 40 years, the increasing rate of biomass relatively slowed down, and maintained a rapid growth after 40 years. The biomass of spruce population showed a similar trend, though the period of relative slow-down of growth continued from 30 to 50 years. For the biomass of community as a whole, it presented a general continuous increase, but varied greatly for different layers. In shrub layer, the biomass rose rapidly at the early stage of plantation establishment and gradually decreased after 20 years, while that of the herbaceous plants reduced continuously and accounted less than 0.2% of the total biomass of community when the stand reached 70 years. Both the mean annual increment and the current annual increment of stem volume of spruce single tree went up with the increasing stand age, and more rapidly at the later stages. Similar changes were observed for the stock volume of the plantations, with the only difference that the current annual increment from 30 to 50 years was relatively reduced. Based on the data from stem analysis and growth ring measurement, regression models of stem volume with DBH and tree height of 70 years Picea asperata plantation were established.

[Dynamics of litters in artificial restoration process of subalpine coniferous forest].

By adopting the concept of space as a substitute for time and taking the primitive subalpine coniferous forests as a reference, this paper investigated the forest litters in 10, 30, 40, 50 and 60-years subalpine Picea asperata stands to study the development process of litters in subalpine coniferous plantations with different restoration stages. The difference in litter development in artificial and natural stands was also discussed. The results indicated that in Picea asperata plantations with different ages, the litter pool on forest floor and the nutrient storage and maximum moisture holding capacity of litters showed a general trend of decrease at their earlier restoration stages, and of increase at the later stages. The trend of increase reached the maximum around 50 years of restoration, and then gradually leveled off or even slightly decreased. The observed litter pool (70.21 x 10(3) kg x hm(-2)), nutrient storage (4.73 x 10(3) kg x hm(-2)) and maximum moisture holding capacity (89.98 x 10(3) kg x hm(-2)) of 60-years plantations were considerably small, only accounted for 48.40%, 46.79% and 46.99% of the primitive forests, respectively. After 40 years of restoration, both artificial stands and naturally regenerated secondary forests showed similarity in litter dynamics, annual litterfall, and amount of annual nutrient returning to the soils, while a big difference in litter components, litter pool and structure on the forest floor, nutrient storage, and maximum moisture holding capacity. The difference which accounts for the difference in ecological functioning of the subalpine coniferous plantations lagging behind that of the secondary forests might be mainly caused by the less species diversity of the former.