Simultaneous determination of pigments of spinach (Spinacia oleracea L.) leaf for quality inspection using hyperspectral imaging and multi-task deep learning regression approaches.

Rapid and accurate determination of pigment content is important for quality inspection of spinach leaves during storage. This study aimed to use hyperspectral imaging at two spectral ranges (visible/near-infrared, VNIR: 400-1000 nm; NIR: 900-1700 nm) to simultaneously determine the pigment (chlorophyll a, chlorophyll b, total chlorophyll, and carotenoids) content in spinach stored at different durations and conditions (unpackaged and packaged). Partial least squares (PLS), back propagation neural network (BPNN) and convolutional neural network (CNN) were used to establish single-task and multi-task regression models. Single-task CNN (STCNN) models and multi-task CNN (MTCNN) models obtained better performances than the other models. The models using VNIR spectra were superior to those using NIR spectra. The overall results indicated that hyperspectral imaging with multi-task learning could predict the quality attributes of spinach simultaneously for spinach quality inspection under various storage conditions. This research will guide food quality inspection by simultaneously inspecting multiple quality attributes.

Tumor-repopulating cells evade ferroptosis via PCK2-dependent phospholipid remodeling.

Whether stem-cell-like cancer cells avert ferroptosis to mediate therapy resistance remains unclear. In this study, using a soft fibrin gel culture system, we found that tumor-repopulating cells (TRCs) with stem-cell-like cancer cell characteristics resist chemotherapy and radiotherapy by decreasing ferroptosis sensitivity. Mechanistically, through quantitative mass spectrometry and lipidomic analysis, we determined that mitochondria metabolic kinase PCK2 phosphorylates and activates ACSL4 to drive ferroptosis-associated phospholipid remodeling. TRCs downregulate the PCK2 expression to confer themselves on a structural ferroptosis-resistant state. Notably, in addition to confirming the role of PCK2-pACSL4(T679) in multiple preclinical models, we discovered that higher PCK2 and pACSL4(T679) levels are correlated with better response to chemotherapy and radiotherapy as well as lower distant metastasis in nasopharyngeal carcinoma cohorts.

A nomogram for predicting cerebral white matter lesions in elderly men.

Objective: This study aimed to develop a nomogram tool to predict cerebral white matter lesions (WMLs) in elderly men. Methods: Based on a retrospective cohort from January 2017 to December 2019, a multivariate logistic analysis was performed to construct a nomogram for predicting WMLs. The nomogram was further validated using a follow-up cohort between January 2020 and December 2022. The calibration curve, receiver operating characteristics (ROC) curves, and the decision curves analysis (DCA) were used to evaluate discrimination and calibration of this nomogram. Result: A total of 436 male patients were enrolled in this study, and all 436 patients were used as the training cohort and 163 follow-up patients as the validation cohort. A multivariate logistic analysis showed that age, cystatin C, uric acid, total cholesterol, platelet, and the use of antiplatelet drugs were independently associated with WMLs. Based on these variables, a nomogram was developed. The nomogram displayed excellent predictive power with the area under the ROC curve of 0.951 [95% confidence interval (CI), 0.929-0.972] in the training cohort and 0.915 (95% CI, 0.864-0.966) in the validation cohort. The calibration of the nomogram was also good, as indicated by the Hosmer-Lemeshow test with p-value of 0.594 in the training cohort and 0.178 in the validation cohort. The DCA showed that the nomogram holds good clinical application value. Conclusion: We have developed and validated a novel nomogram tool for identifying elderly men at high risk of WMLs, which exhibits excellent predictive power, discrimination, and calibration.

IGF2BP2 inhibits invasion and migration of clear cell renal cell carcinoma via targeting Netrin-4 in an m6A-dependent manner.

Clear cell renal cell carcinoma (ccRCC), the most common subtype of renal cell carcinoma, often leads to a poor prognosis due to metastasis. The investigation of N6-methyladenosine (m6A) methylation, a crucial RNA modification, and its role in ccRCC, particularly through the m6A reader insulin-like growth factor 2 mRNA-binding protein 2 (IGF2BP2), revealed significant insights. We found that IGF2BP2 was notably downregulated in ccRCC, which correlated with tumor aggressiveness and poor prognosis. Thus, IGFBP2 has emerged as an independent prognostic factor of ccRCC. Moreover, a strong positive correlation was observed between the expression of IGF2BP2 and Netrin-4. Netrin-4 was also downregulated in ccRCC, and its lower levels were associated with increased malignancy and poor prognosis. Overexpression of IGF2BP2 and Netrin-4 suppressed the invasion and migration of ccRCC cells, while Netrin-4 knockdown reversed these effects in ccRCC cell lines. RNA immunoprecipitation (RIP)-quantitative polymerase chain reaction validated the robust enrichment of Netrin-4 mRNA in anti-IGF2BP2 antibody immunoprecipitates. MeRlP showed significantly increased Netrin4 m6A levels after lGF2BP2 overexpression. Moreover, we found that IGF2BP2 recognized and bound to the m6A site within the coding sequence of Netrin-4, enhancing its mRNA stability. Collectively, these results showed that IGF2BP2 plays a suppressive role in the invasion and migration of ccRCC cells by targeting Netrin-4 in an m6A-dependent manner. These findings underscore the potential of IGF2BP2/Netrin-4 as a promising prognostic biomarker and therapeutic target in patients with ccRCC metastasis.

Risk prediction models of depression in older adults with chronic diseases.

BACKGROUND: Detecting potential depression and identifying the critical predictors of depression among older adults with chronic diseases are essential for timely intervention and management of depression. Therefore, risk prediction models (RPMs) of depression in elderly people should be further explored. METHODS: A total of 3959 respondents aged 60 years or over from the wave four survey of the China Health and Retired Longitudinal Study (CHARLS) were included in this study. We used five machine learning (ML) algorithms and three data balancing techniques to construct RPMs of depression and calculated feature importance scores to determine which features are essential to depression. RESULTS: The prevalence of depression was 19.2 % among older Chinese adults with chronic diseases in the wave four survey. The random forest (RF) model was more accurate than the other models after balancing the data using the Synthetic Minority Oversampling Technique (SMOTE) algorithm, with an area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) of 0.957 and 0.920, respectively, a balanced accuracy of 0.891 and a sensitivity of 0.875. Furthermore, we further identified several important predictors between male and female patients via constructed sex-stratified models. LIMITATIONS: Further research on the clinical impact studies of our models and external validation are needed. CONCLUSIONS: After several techniques were used to address class imbalance issues, most RPMs achieved satisfactory accuracy in predicting depression among elderly people with chronic diseases. RPMs may thus become valuable screening tools for both older individuals and healthcare practitioners to assess the risk of depression.

Genomic landscape and functional characterization of structural variations in schizophrenia and bipolar disorder.

Multiple types of variations have been postulated to confer risk of schizophrenia and bipolar disorder, but majority of present GWAS solely focused on SNPs or small indels, and the impacts of structural variations (SVs) remain less understood. Nevertheless, accumulating evidence suggest that SVs may explain the association signals in certain GWAS hits. Here, we conducted pairwise linkage disequilibrium (LD) analyses of SNPs and SVs in populations from 1000 Genomes Project. Among the 299 psychiatric GWAS loci, 1213 SVs showed an LD of r2 > 0.1 with GWAS risk SNPs, and 66 of them were in moderate to strong LD (r2 > 0.6) with at least one GWAS risk SNP. Nine SVs were subject to further explorative analyses, including eQTL analysis in DLPFC, luciferase reporter gene assays, CRISPR/Cas9-mediated genome deletion and RT-qPCR. These assays highlighted several functional SVs showing regulatory effects on transcriptional activities, and some risk genes (e.g., BORCS7, GNL3) affected by the SVs were also annotated. Finally, mice overexpressing Borcs7 in the mPFC exhibited schizophrenia-like behaviors, such as abnormal prepulse inhibition and social dysfunction. These data suggest that SNPs association signals at GWAS loci might be driven by SVs, highlighting the necessities of considering such variants in future.

Quercetin exerts anti-tumor immune mechanism by regulating IL-6/JAK2/STAT3 signaling pathway to deplete Treg cells.

Breast cancer is still the leading cause of death among women worldwide. Due to the lack of effective drug targets, triple-negative breast cancer has a worse prognosis and higher mortality compared with other types of breast cancer, and chemotherapy is still the main treatment for triple-negative breast cancer at present. Quercetin (QUE) is a flavonoid compound found in a variety of fruits and vegetables. The mechanism of QUE has been extensively studied, such as prostate cancer, colon cancer, ovarian cancer, etc. However, the anti-tumor immune mechanism of QUE in triple-negative breast cancer remains unclear. Therefore, we assessed the anti-tumor immune effects of QUE on triple-negative breast cancer using both 4T1 cells and a xenograft mouse model of 4T1 cells. In vitro, we examined the inhibitory effects of QUE on 4T1 cells and its molecular mechanisms through MTT, Transwell, ELISA, and Western blotting. In vivo, by establishing a xenograft mouse model, we utilized flow cytometry, immunohistochemistry, ELISA, and Western blotting to evaluate the anti-tumor immune effects of QUE on triple-negative breast cancer. The results indicate that QUE inhibits the proliferation, migration, and invasion of 4T1 cells, concurrently significantly suppressing the IL-6/JAK2/STAT3 signaling pathway. Furthermore, it depletes Treg cell content in 4T1 xenograft mice, thereby improving the tumor immune microenvironment and promoting the cytotoxicity of relevant tumor immune cells. These findings suggest that QUE may serve as a potential adjuvant for immune therapy in triple-negative breast cancer.

Sinomenine attenuates pulmonary fibrosis by downregulating TGF-ß1/Smad3, PI3K/Akt and NF-κB signaling pathways.

BACKGROUND: Since COVID-19 became a global epidemic disease in 2019, pulmonary fibrosis (PF) has become more prevalent among persons with severe infections, with IPF being the most prevalent form. In traditional Chinese medicine, various disorders are treated using Sinomenine (SIN). The SIN's strategy for PF defense is unclear. METHODS: Bleomycin (BLM) was used to induce PF, after which inflammatory factors, lung histological alterations, and the TGF-/Smad signaling pathway were assessed. By administering various dosages of SIN and the TGF- receptor inhibitor SB-431,542 to human embryonic lung fibroblasts (HFL-1) and A549 cells, we were able to examine proliferation and migration as well as the signaling molecules implicated in Epithelial-Mesenchymal Transition (EMT) and Extra-Cellular Matrix (ECM). RESULTS: In vivo, SIN reduced the pathological changes in the lung tissue induced by BLM, reduced the abnormal expression of inflammatory cytokines, and improved the weight and survival rate of mice. In vitro, SIN inhibited the migration and proliferation by inhibiting TGF-ß1/Smad3, PI3K/Akt, and NF-κB pathways, prevented the myofibroblasts (FMT) of HFL-1, reversed the EMT of A549 cells, restored the balance of matrix metalloenzymes, and reduced the expression of ECM proteins. CONCLUSION: SIN attenuated PF by down-regulating TGF-ß/Smad3, PI3K/Akt, and NF-κB signaling pathways, being a potential effective drug in the treatment of PF.

Numerical study on the uniform distribution of flow field of airflow dryer.

The uniformity of hot air flow inside the airflow dryer not only affects the moisture distribution at the outlet, but also affects the quality of the product. Based on the guide plate structure of the SH23A airflow tobacco dryer, a gradient curved guide plate dryer is designed, and the flow field distribution of the dryer is numerically investigated under different flow distribution conditions at the hot air inlet and flue gas inlet. The results show that the airflow uniformity is affected by the flow distribution at the inlet of the heated air and the inlet of the cigarette smoke, the structure of the guide plate, etc., the non-uniformity coefficient decreases with the increase of hot air inlet flow rate. The non-uniformity coefficient of tapered arc deflector decreases by 9-12 %.

Changes in physiology, antioxidant system, and gene expression in Microcystis aeruginosa under fenoxaprop-p-ethyl stress.

Fenoxaprop-p-ethyl (FE) is one of the typical aryloxyphenoxypropionate herbicides. FE has been widely applied in agriculture in recent years. Human health and aquatic ecosystems are threatened by the cyanobacteria blooms caused by Microcystis aeruginosa, which is one of the most common cyanobacteria responsible for freshwater blooming. Few studies have been reported on the physiological effects of FE on M. aeruginosa. This study analyzed the growth curves, the contents of chlorophyll a and protein, the oxidative stress, and the microcystin-LR (MC-LR) levels of M. aeruginosa exposed to various FE concentrations (i.e., 0, 0.5, 1, 2, and 5 mg/L). FE was observed to stimulate the cell density, chlorophyll a content, and protein content of M. aeruginosa at 0.5- and 1-mg/L FE concentrations but inhibit them at 2 and 5 mg/L FE concentrations. The superoxide dismutase and catalase activities were enhanced and the malondialdehyde concentration was increased by FE. The intracellular (intra-) and extracellular (extra-) MC-LR contents were also affected by FE. The expression levels of photosynthesis-related genes psbD1, psaB, and rbcL varied in response to FE exposure. Moreover, the expressions of microcystin synthase-related genes mcyA and mcyD and microcystin transportation-related gene mcyH were significantly inhibited by the treatment with 2 and 5 mg/L FE concentrations. These results might be helpful in evaluating the ecotoxicity of FE and guiding the rational application of herbicides in modern agriculture.

Bu zhong Yiqi Decoction ameliorates mild cognitive impairment by improving mitochondrial oxidative stress damage via the SIRT3/MnSOD/OGG1 pathway.

ETHNOPHARMACOLOGICAL RELEVANCE: Bu-Zhong-Yi-Qi Decoction(BZYQD) is a traditional formula commonly used in China, known for its effects in tonifying Qi and raising Yang. It can relieve symptoms of cognitive impairment such as forgetfulness and lack of concentration caused by qi deficiency, which is common in aging and debilitating. However, much of the current research on BZYQD has been focused on its impact on the digestive system, leaving its molecular mechanisms in improving cognitive function largely unexplored. AIM OF THE STUDY: Cognitive decline in the aging central nervous system is intrinsically linked to oxidative damage. This study aims to investigate the therapeutic mechanism of BZYQD in treating mild cognitive impairment caused by qi deficiency, particularly through repair of mitochondrial oxidative damage. MATERIALS AND METHODS: A rat model of mild cognitive impairment (MCI) was established by administering reserpine subcutaneously for two weeks, followed by a two-week treatment with BZYQD/GBE. In vitro experiments were conducted to assess the effects of BZYQD on neuronal cells using a H2O2-induced oxidative damage model in PC12 cells. The open field test and the Morris water maze test evaluated the cognitive and learning memory abilities of the rats. HE staining and TEM were employed to observe morphological changes in the hippocampus and its mitochondria. Mitochondrial activity, ATP levels, and cellular viability were measured using assay kits. Protein expression in the SIRT3/MnSOD/OGG1 pathway was analyzed in tissues and cells through western blotting. Levels of 8-OH-dG in mitochondria extracted from tissues and cells were quantified using ELISA. Mitochondrial morphology in PC12 cells was visualized using Mito Red, and mitochondrial membrane potential was assessed using the JC-1 kit. RESULTS: BZYQD treatment significantly improved cognitive decline caused by reserpine in rats, as well as enhanced mitochondrial morphology and function in the hippocampus. Our findings indicate that BZYQD mitigates mtDNA oxidative damage in rats by modulating the SIRT3/MnSOD/OGG1 pathway. In PC12 cells, BZYQD reduced oxidative damage to mitochondria and mtDNA in H2O2-induced conditions and was associated with changes in the SIRT3/MnSOD/OGG1 pathway. CONCLUSION: BZYQD effectively counteracts reserpine-induced mild cognitive impairment and ameliorates mitochondrial oxidative stress damage through the SIRT3/MnSOD/OGG1 pathway.

Association between peripheral plasma cytokine levels and suicidal ideation in first-episode, drug-naïve major depressive disorder.

BACKGROUND: Inflammatory processes could potentially impact both mood and suicide risk, however, the relationship between cytokines and suicidal ideation remains unclear. This study aimed to investigate the association between plasma levels of cytokines and suicidal ideation in population with major depressive disorders (MDD). METHODS: A cross-sectional study was performed to assess the peripheral plasma levels of interleukin-1ß (IL-1ß), IL-2, IL-6, IL-8, IL-10 and tumor necrosis factor-α (TNF-α) in 88 Chinese Han first-episode drug-naïve MDD patients. Suicidal ideation in the past week were identified using the Beck Scale for Suicide Ideation-Chinese Version (BSI-CV). The Hamilton Depression Rating Scale-17 (HAMD-17), the Hamilton Anxiety Rating Scale-14 (HAMA-14) and the Childhood Trauma Questionnaire (CTQ) was used to assess depression, anxiety and childhood trauma. Multivariable logistic regression models were used to estimate the association between cytokines and suicidal ideation. Interaction and stratified analyses were conducted according to age, sex, marital status, education, smoking status, BMI and physical activity. RESULTS: Among the 88 participants, 42 individuals (47.7%) reported suicidal ideation within the past week. In the fully adjusted model, a statistically significant trend was observed in the association between IL-2 level and suicidal ideation (OR: 1.40, 95% CI: 1.00-1.97). The stratified analysis showed a statistically significant association between IL-6 level and suicidal ideation among younger people (OR: 1.17, 95% CI: 1.01-1.36) and a significant positive association between IL-8 (OR: 1.59, 95% CI: 1.03-2.44) and IL-10 (OR: 2.51, 95% CI: 1.27-4.96) levels and suicide ideation among higher educated populations. LIMITATIONS: The cross-sectional design, residual confounding effects and small sample size CONCLUSION: Our findings indicate a significant positive association between plasma IL-2 level and suicidal ideation in MDD patients. IL-2 has the potential to be a biomarker of suicidal ideation in patients with depression.

Cartilage protective and anti-edema effects of JTF in osteoarthritis via inhibiting NCOA4-HMGB1-driven ferroptosis and aquaporin dysregulation.

BACKGROUND: Preventing joint edema is crucial in halting osteoarthritis (OA) progression. Growing clinical evidence indicate that Jianpi-Tongluo Formula (JTF) may have a promising anti-edema effect. However, the therapeutic properties of JTF and the underlying mechanisms remains unclear. MATERIALS AND METHODS: An OA rat model was established and employed to evaluate pharmacological effects of JTF in vivo based on dynamic histopathologic assessments and micro-CT observations. Then, OA-related genes and potential targets of JTF were identified through clinical transcriptomic data analysis and "disease gene-drug target" network analysis, which were verified by a series of in vivo experiments. RESULTS: JTF administration effectively reduced pain and joint edema, inhibited matrix degradation, chondrocyte apoptosis, and aquaporin expression in OA rats. Notably, JTF dose-dependently reversed damage-associated molecular patterns and inflammatory factor upregulation. Mechanically, our "disease gene-drug target" network analysis indicated that the NCOA4-HMGB1-GSK3B-AQPs axis, implicated in ferroptosis and aquaporin dysregulation, may be potentially served as a target of JTF against OA. Accordingly, JTF mitigated NCOA4, HMGB1, and GSK3B expression, oxidative stress, and iron metabolism aberrations in OA rats. Furthermore, JTF treatment significantly attenuated the aberrant upregulation of AQP1, AQP3, and AQP4 proteins observed in cartilage tissues of OA rats. CONCLUSION: Our data reveal for the first time that JTF may exert cartilage protective and anti-edema effects in osteoarthritis therapy by inhibiting NCOA4-HMGB1-driven ferroptosis and aquaporin dysregulation.

Clinical significance and potential pathogenesis of VCAN in adult non-cystic fibrosis bronchiectasis: a retrospective study.

BACKGROUND: The pathogenesis of adult non-cystic fibrosis (CF) bronchiectasis is complex, and the relevant molecular mechanism remains ambiguous. Versican (VCAN) is a key factor in inflammation through interactions with adhesion molecules. This study constructs a stable panoramic map of mRNA, reveals the possible pathogenesis of bronchiectasis, and provides new ideas and methods for bronchiectasis. METHODS: Peripheral blood and tissue gene expression data from patients with bronchiectasis and normal control were selected by bioinformatics analysis. The expression of VCAN in peripheral blood and bronchial tissues of bronchiectasis were obtained by transcriptome sequencing. The protein expression levels of VCAN in serums were verified by the enzyme-linked immunosorbent assay (ELISA). The mRNA expression levels of VCAN in co-culture of Pseudomonas aeruginosa and bronchial epithelial cells were verified by real-time quantitative polymerase chain reaction (RT-qPCR). In addition, the biological function of VCAN was detected by the transwell assay. RESULTS: The expression of VCAN was upregulated in the bronchiectasis group by sequencing analysis (P < 0.001). The expression of VCAN in the bronchial epithelial cell line BEAS-2B was increased in P. aeruginosa (P.a), which was co-cultured with BEAS-2B cells (P < 0.05). The concentration of VCAN protein in the serum of patients with bronchiectasis was higher than that in the normal control group (P < 0.05). Transwell experiments showed that exogenous VCAN protein induced the migration of neutrophils (P < 0.0001). CONCLUSIONS: Our findings indicate that VCAN may be involved in the development of bronchiectasis by increasing the migration of neutrophils and play an important role in bronchial pathogenesis.

Therapeutic Potential of Danyankang Capsule in High-Fat Diet-Induced Cholelithiasis and Its Impact on Liver FXR Signaling and Gut Microbiota.

Cholelithiasis, commonly known as gallstones, represents a prevalent hepatobiliary disorder. This study aimed to elucidate the therapeutic role and mechanism of Danyankang capsulein treating cholelithiasis induced by a high-fat diet in C57BL/6 mice. The therapeutical potential of Danyankang was assessed through biochemical analyses, histopathological examinations, protein detection, and 16S rDNA sequencing. A high-fat diet resulted in cholelithiasis manifestation in mice, with discernable abnormal serum biochemical indices and disrupted biliary cholesterol homeostasis. Danyankang treatment notably ameliorated liver inflammation symptoms and rectified serum and liver biochemical abnormalities. Concurrently, it addressed biliary imbalances. Elevated expressions of toll-like receptor 4 (TLR4), nuclear factor-kappaB (NF-κB)/pNF-κB, HMGCR, CYP7A1, and CYP8B1 observed at the inception of cholelithiasis, were notably reduced upon Danyankang administration. Furthermore, 16S rDNA analysis revealed a decline in species number and diversity of the intestinal flora in cholelithiasis-treated mice, while the decline was reversed with Danyankang treatment. Danyankang capsules reduced the abundance of Verrucomicrobiota and increased the abundance of Actinobacteriota and Proteobacteria. In conclusion, the present study demonstrates that Danyankang exerts potent therapeutic efficacy against high-fat diet-induced cholelithiasis. This beneficial outcome is potentially linked to the inhibition of the TLR4/pNF-κB and SHP/CYP7A1/CYP8B1 signaling pathways, as well as the enhancement of intestinal flora species abundance.

A Predictive Network-Based Immune Checkpoint Blockade Immunotherapeutic Signature Optimizing Patient Selection and Treatment Strategies.

Immune checkpoint blockade (ICB) therapy has brought significant advancements to the field of oncology. However, the diverse responses among patients highlight the need for more accurate predictive tools. In this study, insights are drawn from tumor-immunology pathways, and a novel network-based ICB immunotherapeutic signature, termed ICBnetIS, is constructed. The signature is derived from advanced biological network-based computational strategies involving co-expression networks and molecular interactions networks. The efficacy of ICBnetIS is established through its association with enhanced patient survival and a robust immune response characterized by diverse immune cell infiltration and active anti-tumor immune pathways. The validation process positions ICBnetIS as an effective tool in predicting responses to ICB therapy, analyzing ICB data from a broad collection of over 700 samples from multiple cancer types of more than 15 datasets. It achieves an aggregated prediction AUC of 0.784, which outperforms the other nine renowned immunotherapeutic signatures, indicating the superior predictive capability of ICBnetIS. To sum up, the findings suggest ICBnetIS as a potent tool in predicting ICB therapy responses, offering significant implications for patient selection and treatment optimization in oncology. The study highlights the role of ICBnetIS in advancing personalized treatment strategies, potentially transforming the clinical landscape of ICB therapy.

Transcriptomic insights into the lipotoxicity of high-fat high-fructose diet in rat and mouse.

Along with the increasing prevalence of obesity worldwide, the deleterious effects of high-calorie diet are gradually recognized through more and more epidemiological studies. However, the concealed and chronic causality whitewashes its unhealthy character. Given an ingenious mechanism orchestrates the metabolic adaptation to high-fat high-fructose (HFF) diet and connive its lipotoxicity, in this study, an experimental rat/mouse model of obesity was induced and a comparative transcriptomic analysis was performed to probe the mystery. Our results demonstrated that HFF diet consumption altered the transcriptomic pattern as well as different high-calorie diet fed rat/mouse manifested distinct hepatic transcriptome. Validation with RT-qPCR and Western blotting confirmed that SREBP1-FASN involved in de novo lipogenesis partly mediated metabolic self-adaption. Moreover, hepatic ACSL1-CPT1A-CPT2 pathway involved in fatty acids ß-oxidation, played a key role in the metabolic adaption to HFF. Collectively, our findings enrich the knowledge of the chronic adaptation mechanisms and also shed light on future investigations. Meanwhile, our results also suggest that efforts to restore the fatty acids metabolic fate could be a promising avenue to fight against obesity and associated steatosis and insulin resistance challenged by HFF diet.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

BACKGROUND AND AIMS: Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. METHODS: Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). RESULTS: The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). CONCLUSIONS: Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

Swarm intelligence based deep learning model via improved whale optimization algorithm and Bi-directional long short-term memory for fault diagnosis of chemical processes.

The chemical production process typically possesses complexity and high risks. Effective fault diagnosis is a key technology for ensuring the reliability and safety of chemical production processes. In this study, a comprehensive fault diagnosis method based on time-varying filtering empirical mode decomposition (TVF-EMD), kernel principal component analysis (KPCA), and an improved whale optimization algorithm (WOA) to optimize bi-directional long short-term memory (BiLSTM) is proposed. This research utilizes TVF-EMD and KPCA to analyze and preprocess the raw data, eliminating noise and and reducing the dimensions of the fault data. Subsequently, BiLSTM is employed for fault data classification. To address the hyperparameters within BiLSTM, the enhanced WOA is used for optimization. Finally, the efficacy and superiority of this approach are validated through two fault diagnosis examples.