Search

The unique flavor properties and rich nutrients of traditional fermented food are closely related to its complex and variable microbial structure, which also makes it difficult to control the quality of final fermented product. In order to explore the changes of microbial structure and sensory property and nutritional property in the process of food fermentation and the internal relationship between them, the data analysis process is a key step. Therefore, it is necessary to establish a fast and accurate data analysis method for quality control of fermented food. Machine learning has the advantages of high-dimensional simplification rate, large data throughput and high prediction accuracy, showing great application potential in the field of quality control of fermented food. Hence, machine learning has become one of the research hotspots. This paper reviews the application of machine learning in the quality control of fermented food. On the basis of an overview of common models of machine learning, this paper systematically summarizes the application of machine learning in the prediction of microbial structure evolution, flavor compound composition analysis and customization of personalized consumption in the process of food fermentation. The problems and developmental trends in the application of machine learning to quality control of traditional fermented food are summarized and prospected. Although the application of machine learning in fermented food is still confined by the problems such as insufficient general applicability of the model, limited quality indicators, and limited personalized consumption scenario, etc., with the iterative update of the technical model, the adaptation for multi-factors and whole process, and the application expansion in the background of personalized consumption, machine learning will show a greater value for practical application in the field of fermented food. The purpose of this study is to provide guidance for the further application of machine learning in the standardized and controllable production of traditional fermented food.

Background Lenvatinib plus PD-1 inhibitors and interventional (LPI) therapy have demonstrated promising treatment effects in unresectable hepatocellular carcinoma (HCC). However, biomarkers for predicting the response to LPI therapy remain to be further explored. We aimed to develop a radiomics model to noninvasively predict the efficacy of LPI therapy.Methods Clinical data of patients with HCC receiving LPI therapy were collected in our institution. The clinical model was built with clinical information. Nine machine learning classifiers were tested and the multilayer perceptron classifier with optimal performance was used as the radiomics model. The clinical-radiomics model was constructed by integrating clinical and radiomics scores through logistic regression analysis.Results 151 patients were enrolled in this study (2:1 randomization, 101 and 50 in the training and validation cohorts), of which three achieved complete response, 69 showed partial response, 46 showed stable disease, and 33 showed progressive disease. The objective response rate, disease control rate, and conversion resection rates were 47.7, 78.1 and 23.2%. 14 features were selected from the initially extracted 1223 for radiomics model construction. The area under the curves of the radiomics model (0.900 for training and 0.893 for validation) were comparable to that of the clinical-radiomics model (0.912 for training and 0.892 for validation), and both were superior to the clinical model (0.669 for training and 0.585 for validation). Meanwhile, the radiomics model can categorize participants into high-risk and low-risk groups for progression-free survival (PFS) and overall survival (OS) in the training (HR 1.913, 95% CI 1.121 to 3.265, p=0.016 for PFS; HR 4.252, 95% CI 2.051 to 8.816, p=0.001 for OS) and validation sets (HR 2.347, 95% CI 1.095 to 5.031, p=0.012 for PFS; HR 2.592, 95% CI 1.050 to 6.394, p=0.019 for OS).Conclusion The promising machine learning radiomics model was developed and validated to predict the efficacy of LPI therapy for patients with HCC and perform risk stratification, with comparable performance to clinical-radiomics model.

Abstract Circular RNAs (circRNAs) have been implicated in tumorigenesis and progression of various cancers. However, the underlying mechanisms of circRNAs in hepatocellular carcinoma (HCC) have not been fully elucidated. Herein, a new oncogenic circRNA, hsa_circ_0070039 (circNUP54), was identified to be significantly upregulated in HCC through circRNA sequencing. As verified in 68 HCC samples, circNUP54 overexpression was correlated with aggressive cancerous behaviors and poor outcomes. Moreover, the function experiments showed that knockdown of circNUP54 inhibited the malignant progression of HCC in vitro and in vivo, whereas overexpression of circNUP54 had the opposite role. Mechanistic investigations carried out by RNA pull-down, RNA immunoprecipitation, and immunofluorescence revealed that circNUP54 interacted with the RNA-binding protein Hu-antigen R (HuR) and promoted its cytoplasmic export. The cytoplasmic accumulation of HuR stabilized the downstream BIRC3 mRNA through its binding to the 3′ UTR region. Consequently, the encoded protein of BIRC3, cellular inhibitor of apoptosis 2 (cIAP2), proceeded to activate the NF-κB signal pathway and ultimately contributed to HCC progression. In addition, depletion of BIRC3 rescued the pro-tumorigenic effect of circNUP54 on HCC cells. Overall, this study demonstrated that circNUP54 facilitates HCC progression via regulating the HuR/BIRC3/NF-κB axis, which may serve as a promising therapeutic target for HCC treatment.

Abstract Background Forkhead-box protein P1 (FOXP1) has been proposed to have both oncogenic and tumor-suppressive properties, depending on tumor heterogeneity. However, the role of FOXP1 in intrahepatic cholangiocarcinoma (ICC) has not been previously reported. Methods Immunohistochemistry was performed to detect FOXP1 expression in ICC and normal liver tissues. The relationship between FOXP1 levels and the clinicopathological characteristics of patients with ICC was evaluated. Finally, in vitro and in vivo experiments were conducted to examine the regulatory role of FOXP1 in ICC cells. Results FOXP1 was significantly downregulated in the ICC compared to their peritumoral tissues (p

Lemon, as an important cash crop with rich nutritional value, holds significant cultivation importance and market demand worldwide. However, lemon diseases seriously impact the quality and yield of lemons, necessitating their early detection for effective control. This paper addresses this need by collecting a dataset of lemon diseases, consisting of 726 images captured under varying light levels, growth stages, shooting distances and disease conditions. Through cropping high-resolution images, the dataset is expanded to 2022 images, comprising 4441 healthy lemons and 718 diseased lemons, with approximately 1–6 targets per image. Then, we propose a novel model lemon surface disease YOLO (LSD-YOLO), which integrates Switchable Atrous Convolution (SAConv) and Convolutional Block Attention Module (CBAM), along with the design of C2f-SAC and the addition of a small-target detection layer to enhance the extraction of key features and the fusion of features at different scales. The experimental results demonstrate that the proposed LSD-YOLO achieves an accuracy of 90.62% on the collected datasets, with mAP@50–95 reaching 80.84%. Compared with the original YOLOv8n model, both mAP@50 and mAP@50–95 metrics are enhanced. Therefore, the LSD-YOLO model proposed in this study provides a more accurate recognition of healthy and diseased lemons, contributing effectively to solving the lemon disease detection problem.

Abstract Genome-wide association studies (GWAS) have linked hundreds of loci to cardiac diseases. However, in most loci the causal variants and their target genes remain unknown. We developed a combined experimental and analytical approach that integrates single cell epigenomics with GWAS to prioritize risk variants and genes. We profiled accessible chromatin in single cells obtained from human hearts and leveraged the data to study genetics of Atrial Fibrillation (AF), the most common cardiac arrhythmia. Enrichment analysis of AF risk variants using cell-type-resolved open chromatin regions (OCRs) implicated cardiomyocytes as the main mediator of AF risk. We then performed statistical fine-mapping, leveraging the information in OCRs, and identified putative causal variants in 122 AF-associated loci. Taking advantage of the fine-mapping results, our novel statistical procedure for gene discovery prioritized 46 high-confidence risk genes, highlighting transcription factors and signal transduction pathways important for heart development. In summary, our analysis provides a comprehensive map of AF risk variants and genes, and a general framework to integrate single-cell genomics with genetic studies of complex traits.

Abstract Hepatocellular carcinoma (HCC) has a desmoplastic and hypoxic tumor microenvironment (TME), resulting in poor prognosis and treatment resistance. This study aimed to construct a novel prognostic classifier to investigate the degree of hypoxia and immune profiles in HCC. Patients with HCC from public databases were classified into three HIF-1α clusters according to 16 reported HIF-1α-related genes. Then, an HIF-1α score system was constructed based on nine overlapping differentially expressed genes (ODEGs) among various HIF-1α clusters. Then, an HIF-1α score system was constructed based on nine overlapping differentially expressed genes (ODEGs) among various HIF-1α cluster. Besides, oncologic pathways and immune infiltration profiles were also investigated among HCCs with different HIF-1α scores. The reliable predictive abilities of the HIF-1α score system for patients’ survival were impressively suggested by the significant C-indexes and ROC analysis. All enrolled tumors were divided into high-, medium-, and low-HIF-1α score groups. Compared with the other two groups, the high HIF-1α score group exhibited highest enrichment of multiple oncogenic pathways, such as TNF-α signaling via NF-кB, IL6-JAK-STAT3 signaling, mTORC1 signaling, MYC signaling, Hedgehog signaling. Notably, higher HIF-1α scores correlated with advanced immunosuppressive TME. Besides, tumors with high HIF-1α scores represented high non-response rate to transcatheter arterial chemoembolization (TACE) and immune checkpoint blockade (ICB). In conclusion, we developed a novel HIF-1α score system to distinguish HCC with different degree of hypoxia and immune infiltration profiles.

Abstract The carcinogenic role of FASN by regulating lipid metabolism reprogramming has been well-established in multiple tumors. However, whether mechanisms during intrahepatic cholangiocarcinoma (ICC) progression, such as circRNAs, regulate FASN expression remains unknown. Here we demonstrate a lipid metabolism-related circRNA, circMBOAT2 (hsa_circ_0007334 in circBase), frequently upregulated in ICC tissues, and positively correlated with ICC malignant features. CircMBOAT2 knockdown inhibits the growth and metastasis of ICC cells. Mechanistically, circMBOAT2 combines with PTBP1 and protects PTBP1 from ubiquitin/proteasome-dependent degradation, impairing the function of PTBP1 to transfer FASN mRNA from the nucleus to the cytoplasm. Moreover, circMBOAT2 and FASN have the same effect on fatty acid profile, unsaturated fatty acids instead of saturated fatty acids are primarily regulated and associated with malignant behaviors of ICC cells. The levels of lipid peroxidation and ROS were significantly higher when FASN was knocked down and recovered when circMBOAT2 was overexpressed. Our results identified that circMBOAT2 was upregulated in ICC and promoted progression by stabilizing PTBP1 to facilitate FASN mRNA cytoplasmic export, which altered lipid metabolic profile and regulated redox homeostasis in ICC, suggesting that circMBOAT2 may serve as an available therapeutic target for ICC with active lipid metabolism.

As a high-tech strategic emerging comprehensive industry, the nuclear industry is committed to the research, production, and processing of nuclear fuel, as well as the development and utilization of nuclear energy. Nowadays, the nuclear industry has made remarkable progress in the application fields of nuclear weapons, nuclear power, nuclear medical treatment, radiation processing, and so on. With the development of artificial intelligence and the proposal of "Industry 4.0", more and more artificial intelligence technologies are introduced into the nuclear industry chain to improve production efficiency, reduce operation cost, improve operation safety, and realize risk avoidance. Meanwhile, deep learning, as an important technology of artificial intelligence, has made amazing progress in theoretical and applied research in the nuclear industry, which vigorously promotes the development of informatization, digitization, and intelligence of the nuclear industry. In this paper, we first simply comb and analyze the intelligent demand scenarios in the whole industrial chain of the nuclear industry. Then, we discuss the data types involved in the nuclear industry chain. After that, we investigate the research status of deep learning in the application fields corresponding to different data types in the nuclear industry. Finally, we discuss the limitation and unique challenges of deep learning in the nuclear industry and the future direction of the intelligent nuclear industry.

Abstract With the proposal and development of Generative Adversarial Networks, the great achievements in the field of image generation are made. Meanwhile, many works related to the generation of painting art have also been derived. However, due to the difficulty of data collection and the fundamental challenge from freehand expressions, the generation of traditional Chinese painting is still far from being perfect. This paper specialises in Chinese art painting generation of flowers, which is important and classic, by deep learning method. First, an unpaired flowers paintings data set containing three classic Chinese painting style: line drawing, meticulous, and ink is constructed. Then, based on the collected dataset, a Flower‐Generative Adversarial Network framework to generate multi‐style Chinese art painting of flowers is proposed. The Flower‐Generative Adversarial Network, consisting of attention‐guided generators and discriminators, transfers the style among line drawing, meticulous, and ink by an adversarial training way. Moreover, in order to solve the problem of artefact and blur in image generation by existing methods, a new loss function called Multi‐Scale Structural Similarity to force the structure preservation is introduced. Extensive experiments show that the proposed Flower‐Generative Adversarial Network framework can produce better and multi‐style Chinese art painting of flowers than existing methods.

BackgroundSmith-like (LSM) family members play critical roles in multiple oncologic processes in several types of malignancies. The study on LSM family members of HCC might provide new insights into the tumorigenesis and therapeutic strategies of HCC.MethodsThe clinical significance and oncologic biological functions of LSM family members were assessed through multiple bioinformatics methods and in vitro studies. The potential correlation between LSM family members and tumor immunity was also investigated using single sample gene set enrichment analysis (ssGSEA) and the ESTIMATE algorithm.ResultsLSM family member overexpression in HCC was significantly correlated with poor clinical outcomes such as higher TNM stage, advanced histologic grade, and worse prognosis. A risk score system based on LSM5, LSM10, LSM12, and LSM14B showed a reliable predictive ability for OS of HCC patients. Functional enrichment analysis demonstrated that LSM family members overexpressed were all involved in cell cycle related biological processes. Besides, LSM12, LSM14A, and LSM14B were found to be significantly associated with PI3K-Akt-mTOR and T cell receptor signaling pathways. Tumors with LSM12, LSM14A, and LSM14B overexpression exhibited lower infiltration of activated CD8+ T cells with declined cytolytic activity and immune score, but increased infiltration of Th2 cells and Th2/Th1. LSM12, LSM14A, and LSM14B overexpression is also associated with higher tumor-related immune checkpoints (e.g., PD-L1, B7-H3, and PVR) expression and increased therapeutic insensitivity to immune checkpoint blockade (ICB). Moreover, the knockdown of LSM12, LSM14A, and LSM14B significantly inhibited the proliferation and invasion of HCC cells.ConclusionThis study systematically investigated the expression pattern and biological values of LSM family members in HCC and identified LSM family members as novel therapeutic targets in HCC.

Our study investigated the differences in speech performance and neurophysiological response in groups of school-age children with unilateral hearing loss (UHL) who were otherwise typically developing (TD). We recruited a total of 16 primary school-age children for our study (UHL = 9/TD = 7), who were screened by doctors at Shin Kong Wu-Ho-Su Memorial Hospital. We used the Peabody Picture Vocabulary Test--Revised (PPVT-R) to test word comprehension, and the PPVT-R percentile rank (PR) value was proportional to the auditory memory score (by The Children's Oral Comprehension Test) in both groups. Later, we assessed the latency and amplitude of auditory ERP P300 and found that the latency of auditory ERP P300 in the UHL group was prolonged compared with that in the TD group. Although students with UHL have typical hearing in one ear, based on our results, long-term UHL might be the cause of atypical organization of brain areas responsible for auditory processing or even visual perceptions attributed to speech delay and learning difficulties.