Burnout among Chinese live streamers: Prevalence and correlates.

BACKGROUND: The prevalence of burnout among live streamers remains largely unknown. This study aims to investigate the prevalence and factors associated with burnout among Chinese live streamers. METHODS: A cross-sectional study recruited 343 full-time live streamers from 3 companies in Changsha city. Socio-demographic and occupational characteristics were collected using self-designed items. Job stress was assessed using the Job Content Questionnaire (JCQ-22), while supervisor and coworker support were evaluated using the last 8 items of the JCQ-22. Burnout was assessed using the 17-item Chinese version of the Maslach Burnout Inventory-Human Services Survey (MBI-HSS). RESULTS: Our findings revealed that 30.6% of live streamers experienced burnout. Lower levels of education (OR = 2.65 and 3.37, p = 0,005 and 0.003), higher monthly income (OR = 10.56 and 11.25, both p = 0.003), being an entertainment-oriented streamer (OR = 2.13, p = 0.028), continuous walking during live streams (OR = 2.81, p = 0.006), significant drop in follower count (OR = 2.65, P = 0.006), live streaming during the daytime (OR = 3.75, p = 0.001), and higher support from supervisors and coworkers (OR = 3.66, p = 0.001) were positively associated with burnout. However, the effects of education and drop in followers on burnout were not significant in the multivariate logistic models (p = 0.321 and 0.988). CONCLUSIONS: Burnout among Chinese live streamers is associated with income, being an entertainment streamer, engaging in continuous walking during live streams, conducting live streams during the daytime, and experiencing excessive support from supervisors and coworkers.

PERF: Panoramic Neural Radiance Field from a Single Panorama.

Neural Radiance Field (NeRF) has achieved substantial progress in novel view synthesis given multi-view images. Recently, some works have attempted to train a NeRF from a single image with 3D priors. They mainly focus on a limited field of view with a few occlusions, which greatly limits their scalability to real-world 360-degree panoramic scenarios with large-size occlusions. In this paper, we present PERF, a 360-degree novel view synthesis framework that trains a panoramic neural radiance field from a single panorama. Notably, PERF allows 3D roaming in a complex scene without expensive and tedious image collection. To achieve this goal, we propose a novel collaborative RGBD inpainting method and a progressive inpainting-and-erasing method to lift up a 360-degree 2D scene to a 3D scene. Specifically, we first predict a panoramic depth map as initialization given a single panorama and reconstruct visible 3D regions with volume rendering. Then we introduce a collaborative RGBD inpainting approach into a NeRF for completing RGB images and depth maps from random views, which is derived from an RGB Stable Diffusion model and a monocular depth estimator. Finally, we introduce an inpainting-and-erasing strategy to avoid inconsistent geometry between a newly-sampled view and reference views. The two components are integrated into the learning of NeRFs in a unified optimization framework and achieve promising results. Extensive experiments on Replica and a new dataset PERF-in-the-wild demonstrate the superiority of our PERF over state-of-the-art methods. Our PERF can be widely used for real-world applications, such as panorama-to-3D, text-to-3D, and 3D scene stylization applications. Project page and code are available at https://github.com/perf-project/PeRF.

Can We Differentiate Between Primary Sjögren Syndrome and Idiopathic Multicentric Castleman Disease Based on the Characteristics of Pulmonary Cysts?

PURPOSE: To identify radiological characteristics that could help differentiate cystic lung diseases between primary Sjögren syndrome (pSS) and idiopathic multicentric Castleman disease (iMCD). PATIENTS AND METHODS: Patients with pSS or iMCD who had cysts were enrolled. Cyst characteristics (number, size, morphology, and distribution) and other accompanying manifestations (nodules, ground-glass opacities, calcification, and thickening of the bronchovascular bundles and interlobular septa) were compared between them. RESULTS: Eleven patients with pSS and 25 patients with iMCD were eligible for our study. Eleven patients with pSS (100.0%) and 23 patients with iMCD (92.0%) had round or oval cysts. None of the patients with pSS had irregular cysts, but 21 (84.0%) patients with iMCD had irregular cysts (P = 0.005). Smooth-walled cysts were present in 11 patients with pSS (100.0%) and 18 patients with iMCD (72.0%). Only 1 patient with pSS (9.1%) exhibited non-smooth-walled cysts, whereas 23 patients with iMCD (92.0%) had non-smooth-walled cysts (P = 0.003). The presence of nodules was common in both groups (P = 1.000). However, the nodules were more likely to be larger and more numerous in patients with iMCD (P < 0.001). Cysts with mural nodules (52.2%) and central nodules (47.8%) were only observed in iMCD (P = 0.007). CONCLUSION: Although regular and smooth-walled cysts were common in the 2 diseases, irregular and non-smooth-walled cysts were more often associated with iMCD than pSS. Nodules in iMCD tended to be larger and more numerous, and a close positional relationship between nodules and cysts was only observed in iMCD.

Impact of Long COVID on Health-Related Quality of Life Among Patients After Acute COVID-19 Infection: A Cross-Sectional Study.

Concerns have been raised globally regarding the long-term effects of the novel coronavirus disease 2019 (COVID-19). This study aimed to investigate the impact of long COVID on the health of patients recovering from acute COVID-19 in China. We conducted a cross-sectional questionnaire survey from 1 February to 9 March 2023. Propensity score matching (PSM) was used to understand the differences in health utility values between individuals with and without long COVID. Factors associated with health-related quality of life (HRQoL) were determined using a multiple linear regression model. A chi-square test was used to compare differences between the 2 groups for each dimension of the EuroQoL-5 Dimension-5 Level (EQ-5D-5L) scale. In total, 307 participants were included in the analysis, of which 40.39% exhibited at least 1 persistent symptom. The common symptoms of long COVID were fatigue/weakness, coughing, memory decline, poor concentration, and phlegm in the throat. Most patients with long COVID reported mild effects from their symptoms. After propensity score matching, the long-COVID group had lower health utility scores than the non-long-COVID group (0.94 vs 0.97). In the multivariable linear regression analysis, persistent symptoms and low annual household income were associated with lower health utility values (P < .05). Anxiety/depression and pain/discomfort were the major problems experienced by the participants with long COVID. Long-COVID symptoms following acute COVID-19 infection have a serious impact on health-related quality of life. Therefore, it is necessary to implement interventions to improve patient health after the recovery from acute COVID-19.

Through-polymer, via technology-enabled, flexible, lightweight, and integrated devices for implantable neural probes.

In implantable electrophysiological recording systems, the headstage typically comprises neural probes that interface with brain tissue and integrated circuit chips for signal processing. While advancements in MEMS and CMOS technology have significantly improved these components, their interconnection still relies on conventional printed circuit boards and sophisticated adapters. This conventional approach adds considerable weight and volume to the package, especially for high channel count systems. To address this issue, we developed a through-polymer via (TPV) method inspired by the through-silicon via (TSV) technique in advanced three-dimensional packaging. This innovation enables the vertical integration of flexible probes, amplifier chips, and PCBs, realizing a flexible, lightweight, and integrated device (FLID). The total weight of the FLIDis only 25% that of its conventional counterparts relying on adapters, which significantly increased the activity levels of animals wearing the FLIDs to nearly match the levels of control animals without implants. Furthermore, by incorporating a platinum-iridium alloy as the top layer material for electrical contact, the FLID realizes exceptional electrical performance, enabling in vivo measurements of both local field potentials and individual neuron action potentials. These findings showcase the potential of FLIDs in scaling up implantable neural recording systems and mark a significant advancement in the field of neurotechnology.

Unleashing the potential: integrating nano-delivery systems with traditional Chinese medicine.

This review explores the potential of integrating nano-delivery systems with traditional Chinese herbal medicine, acupuncture, and Chinese medical theory. It highlights the intersections and potential of nano-delivery systems in enhancing the effectiveness of traditional herbal medicine and acupuncture treatments. In addition, it discusses how the integration of nano-delivery systems with Chinese medical theory can modernize herbal medicine and make it more readily accessible on a global scale. Finally, it analyzes the challenges and future directions in this field.

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer.

With the prevalent use of LiDAR sensors in autonomous driving, 3D point cloud object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to the given template during subsampling. 2) We propose a Point Relation Transformer for effective feature aggregation and feature matching between the template and search region. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction through local feature pooling. In addition, motivated by the favorable properties of the Bird's-Eye View (BEV) of point clouds in capturing object motion, we further design a more advanced framework named PTTR++, which incorporates both the point-wise view and BEV representation to exploit their complementary effect in generating high-quality tracking results. PTTR++ substantially boosts the tracking performance on top of PTTR with low computational overhead. Extensive experiments over multiple datasets show that our proposed approaches achieve superior 3D tracking accuracy and efficiency. Code will be available at https://github.com/Jasonkks/PTTR.

A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection.

Accurate detection and segmentation of brain tumors is critical for medical diagnosis. However, current supervised learning methods require extensively annotated images and the state-of-the-art generative models used in unsupervised methods often have limitations in covering the whole data distribution. In this paper, we propose a novel framework Two-Stage Generative Model (TSGM) that combines Cycle Generative Adversarial Network (CycleGAN) and Variance Exploding stochastic differential equation using joint probability (VE-JP) to improve brain tumor detection and segmentation. The CycleGAN is trained on unpaired data to generate abnormal images from healthy images as data prior. Then VE-JP is implemented to reconstruct healthy images using synthetic paired abnormal images as a guide, which alters only pathological regions but not regions of healthy. Notably, our method directly learned the joint probability distribution for conditional generation. The residual between input and reconstructed images suggests the abnormalities and a thresholding method is subsequently applied to obtain segmentation results. Furthermore, the multimodal results are weighted with different weights to improve the segmentation accuracy further. We validated our method on three datasets, and compared with other unsupervised methods for anomaly detection and segmentation. The DSC score of 0.8590 in BraTs2020 dataset, 0.6226 in ITCS dataset and 0.7403 in In-house dataset show that our method achieves better segmentation performance and has better generalization.

Correlation between jingjin injury and wulao and the relevant prevention and treatment strategies. / 经筋损伤与"五劳"çš„ç›¸å ³æ€§åŠé˜²æ²»ç­–ç•¥.

The paper explores the correlation between jingjin (muscle regions of meridians, sinews/fascia) injury and wulao (five types of exhaustion) and the relevant prevention and treatment strategies, and determines the internal mechanism of the disease so as to provide the ideas for prevention and treatment of jingjin injury. Wulao may result in jingjin injury not only through the damages of blood, qi, muscles, bones and tendons indirectly, but also through the damage of soft tissues directly. The great attention should be paid to preventing from jingjin injury, especially wulao, due to which, the appropriate combination of the static and the dynamic skills is emphasized in the way of physical exercise. When the injury occurred, the conditions of the whole body should be analyzed comprehensively and the local affected regions be concentrated simultaneously in treatment. For the indirect injury, the holistic idea should be the basis of regulating five zang organs and restoring the physiological functions of blood, qi, muscles, bones and sinews so as to adjust jingjin. Regarding the direct injury, the staging regimen for the local treatment is considered to harmonize qi and blood and balance sinews and bones. When the injury has been cured, the physical exercise is recommended to strengthen sinews and bones according to individual conditions to prevent from recurrence.

Bioinformatics analysis of the prognostic role of alternative splicing data in lung adenocarcinoma.

Background: As a post-transcriptional regulatory mechanism, alternative splicing (AS) is engaged in a variety of pathophysiological processes, and it has been widely reported in connection with the occurrence, progression, metastasis, and drug resistance of cancer. However, the research on AS in lung adenocarcinoma (LUAD) is very limited. In addition, the prognostic effect of AS event (ASE) on LUAD and its related mechanism are not clear. This study aimed to explore the role and potential prognostic value of ASE in LUAD. Methods: Relevant data and ASE datasets of the sample were acquired from The Cancer Genome Atlas (TCGA) and TCGASpliceSeq databases. We constructed a new prognostic criterion based on ASEs. Then, Cox regression and least absolute shrinkage and selection operator (LASSO) regression analysis were used to construct the model. Based on this model, the risk score of each ASE was calculated, and the reliability of this model was evaluated by Kaplan-Meier survival and receiver operating characteristic (ROC) curve analyses. Finally, these results were verified on different network platforms. Results: We identified seven types of ASEs related to survival. The prognostic risk model for ASEs was established. The Kaplan-Meier curve showed that compared to the low-risk group, the overall survival (OS) rate of LUAD patients in the high-risk group was lower. ROC curve analysis showed that the prognostic risk model of LUAD patients was well predicted, and the area under the curve (AUC) also confirmed this. Conclusions: This study screened the ASE related to the prognosis of LUAD patients, and provided a theoretical basis for further study of the correlation between ASE and the prognosis of LUAD patients. It has provided new ideas for developing new biomarkers and therapeutic targets for LUAD patients.

Effect of enzymatic de-esterification and RG-I degradation of high methoxyl pectin (HMP) on sugar-acid gel properties.

The influence of RG-I domains on high methoxyl pectin (HMP) sugar-acid gel properties has rarely been reported. In our work, HMP was modified by enzymatic de-esterification and degradation of RG-I domains to compare and analyze the relationship between the structure and final sugar-acid gel properties. The results showed that the degree of esterification (DE) of REP (pectin degraded by rhamnosidase) and GEP (pectin debranched by galactosidase) was the same as that of untreated HMP, whereas the DE of PMEP (pectin de-esterified by pectin methyl esterase) decreased from 59.63 % to 54.69 %. The monosaccharide composition suggested no significant changes in the HG and RG-I structural domains of PMEP. In contrast, the percentage of RG-I structural domains of REP and GEP dropped from 37 % to about 28 %, accompanied by a reduction in the proportion of the RG-I backbones and side chains. The rheological characterization of sugar-acid gels demonstrated an enhanced gel grade for PMEP and a weakened one for REP and GEP. Moreover, we constructed a correlation relationship between the fine structure of pectin and the properties of the sugar-acid gels, confirming the critical contribution of the RG-I region (especially the neutral sugar side chains) to the HMP sugar-acid gels.

Narrowband Internet of Things via Low Earth Orbit Satellite Networks: An Efficient Coverage Enhancement Mechanism Based on Stochastic Geometry Approach.

With the development of IoT technology and 5G massive machine-type communication, the 3GPP standardization body considered as viable the integration of Narrowband Internet of Things (NB-IoT) in low Earth orbit (LEO) satellite-based architectures. However, the presence of the LEO satellite channel comes up with new challenges for the NB-IoT random access procedures and coverage enhancement mechanism. In this paper, an Adaptive Coverage Enhancement (ACE) method is proposed to meet the requirement of random access parameter configurations for diverse applications. Based on stochastic geometry theory, an expression of random access channel (RACH) success probability is derived for LEO satellite-based NB-IoT networks. On the basis of a power consumption model of the NB-IoT terminal, a multi-objective optimization problem is formulated to trade-off RACH success probability and power consumption. To solve this multi-objective optimization problem, we employ the Non-dominated Sorting Genetic Algorithms-II (NSGA-II) method to obtain the Pareto-front solution set. According to different application requirements, we also design a random access parameter configuration method to minimize the power consumption under the constraints of RACH success probability requirements. Simulation results show that the maximum number of repetitions and back-off window size have a great influence on the system performance and their value ranges should be set within [4, 18] and [0, 2048]. The power consumption of coverage enhancement with ACE is about 58% lower than that of the 3GPP proposed model. All this research together provides good reference for the scale deployment of NB-IoT in LEO satellite networks.

Multiparametric MRI subregion radiomics for preoperative assessment of high-risk subregions in microsatellite instability of rectal cancer patients: A multicenter study.

BACKGROUND: Microsatellite instability (MSI) is associated with treatment response and prognosis in patients with rectal cancer (RC). However, intratumoral heterogeneity limits MSI testing in patients with RC. We developed a subregion radiomics model based on multiparametric magnetic resonance imaging (MRI) to preoperatively assess high-risk subregions with MSI and predict the MSI status of patients with RC. METHODS: This retrospective study included 475 patients (training cohort, 382; external test cohort, 93) with RC from two participating hospitals between April 2017 and June 2023. In the training cohort, subregion radiomic features were extracted from multiparametric MRI, which included T2-weighted, T1-weighted, diffusion-weighted, and contrast-enhanced T1-weighted imaging. MSI-related subregion radiomic features, classical radiomic features, and clinicoradiological variables were gathered to build five predictive models using logistic regression. Kaplan-Meier survival analysis was conducted to explore the prognostic information. RESULTS: Among the 475 patients (median age, 64 years [interquartile range, IQR: 55-70 years];304 men and 171 women), the prevalence of MSI was 11.16% (53/475). The subregion radiomics model outperformed the classical radiomics and clinicoradiological models in both training (area under the curve [AUC]=0.86, 0.72, and 0.59, respectively) and external test cohorts (AUC=0.83, 0.73, and 0.62, respectively). The subregion-clinicoradiological model combining clinicoradiological variables and subregion radiomic features performed the optimal, with AUCs of 0.87 and 0.85 in the training and external test cohorts, respectively. The 3-year disease-free survival rate of MSI groups predicted based on the model was higher than that of the predicted microsatellite stability (MSS) groups in both patient cohorts (training, P=0.032; external test, P=0.046). CONCLUSIONS: We developed and validated a model based on subregion radiomic features of multiparametric MRI to evaluate high-risk subregions with MSI and predict the MSI status of RC preoperatively, which may assist in individualized treatment decisions and positioning for biopsy.

Sequential embryo transfer combined with intrauterine perfusion improved pregnancy outcomes in patients with recurrent implantation failure.

OBJECTIVE: To compare the application of sequential embryo transfer, cleavage embryo transfer, and blastocyst transfer combined with intrauterine perfusion in frozen-thawed embryo transfer cycles in patients with recurrent implantation failure to provide a reference for reproductive clinicians. METHODS: The 166 patients who underwent frozen-thawed embryo transfer due to recurrent implantation failure in the reproductive center from January 2021 to March 2022 were retrospectively analyzed. According to the different embryos transferred, they were divided into cleavage embryo transfer groups (72 cases in Group A), blastocyst transfer group (29 cases in Group B), and sequential transfer group (65 cases in Group C). All three groups were treated with intrauterine perfusion 5 days before embryo transfer. The general data and clinical pregnancy outcome indicators, such as embryo implantation rate, clinical pregnancy rate, ongoing pregnancy rate, live birth rate, twin rate, were compared among the three groups. RESULTS: The embryo implantation rate (53.1%), clinical pregnancy rate (76.9%), ongoing pregnancy rate (67.7%) and live birth rate(66.15%) in the sequential transfer group were significantly higher than those in the other two groups (P < 0.05), and the ectopic pregnancy rate was lower in the sequential transfer group. CONCLUSION: Sequential transfer combined with intrauterine perfusion partially improves clinical pregnancy outcomes and reduces the risk of ectopic pregnancy in frozen embryo cycle transfers in patients with recurrent implantation failure, which may be a favourable transfer reference strategy for patients with recurrent implantation failure.

Exploring the status and associated factors of the readiness for return-to-work in young and middle-aged stroke patients.

Stroke increasingly affects individuals of working age. An accurate assessment of Readiness for Return-to-Work (RRTW) can help determine the optimal timing for RRTW and facilitate an early reintegration into society. This study investigates the current state of RRTW and the influencing factors among young and middle-aged stroke patients in China. A sample of young and middle-aged stroke patients hospitalized in a tertiary hospital in Henan Province between December 2021 and May 2022 were included in this study. A general information questionnaire and the Readiness for RRTW scale, the Social Support Rate Scale, the Stroke Self-Efficacy Scale, and the Fatigue Severity Scale were administered to the patients. Of the 203 patients successfully surveyed, 60 (29.6%) were in the pre-contemplation stage, 35 (17.2%) in the contemplation stage, 81 (39.9%) in the prepared for action-self-evaluative stage, and 27 (13.3%) in the prepared for action- behavior stage. Logistic regression analysis identified education level, monthly income, time to start rehabilitation therapy, social support, stroke self-efficacy, and fatigue severity as key factors affecting RRTW scale readiness in young and middle-aged stroke patients. The readiness of young and middle-aged stroke patients to Return-to-Work needs to be increased further. Healthcare professionals should consider the influencing factors of RRTW and design targeted intervention programs to facilitate a successful Return-to-Work and normal life.

Physical activity and sleep pattern in relation to incident Parkinson's disease: a cohort study.

BACKGROUND: How physical activity (PA) and different sleep traits and overall sleep pattern interact in the development of Parkinson's disease (PD) remain unknown. OBJECTIVE: To prospectively investigate the joint associations of PA and sleep pattern with risk of PD. METHODS: Included were 339,666 PD-free participants from the UK Biobank. Baseline PA levels were grouped into low (< 600 MET-mins/week), medium (600 to < 3000 MET-mins/week) and high (≥ 3000 MET-mins/week) according to the instructions of the UK Biobank. Healthy sleep traits (chronotype, sleep duration, insomnia, snoring, and daytime sleepiness) were scored from 0 to 5 and were categorized into "ideal sleep pattern" (≥ 3 sleep scores) and "poor sleep pattern" (0-2 sleep scores). Hazard ratios (HRs) and 95% confidence intervals (CIs) of PD were estimated by Cox proportional hazards models. RESULTS: During a median of 11.8 years of follow-up, 1,966 PD events were identified. The PD risk was lower in participants with high PA (HR = 0.73; 95% CI: 0.64, 0.84), compared to those with low PA; and participants with ideal sleep pattern also had a lower risk of PD (HR = 0.78; 95% CI: 0.69, 0.87), compared to those with poor sleep pattern. When jointly investigating the combined effect, participants with both high PA and ideal sleep pattern had the lowest risk of incident PD (HR = 0.55; 95% CI: 0.44, 0.69), compared to those with low PA and poor sleep pattern; notably, participants with high PA but poor sleep pattern also gained benefit on PD risk reduction (HR = 0.74; 95% CI: 0.55, 0.99). CONCLUSIONS: Both high PA and ideal sleep pattern were independently associated with lower risk of developing PD, and those with both high PA level and ideal sleep pattern had the lowest risk. Our results suggest that improving PA levels and sleep quality may be promising intervention targets for the prevention of PD.

Detecting and Grounding Multi-Modal Media Manipulation and Beyond.

Misinformation has become a pressing issue. Fake media, in both visual and textual forms, is widespread on the web. Whilevarious deepfake detection and text fake news detection methods have been proposed, they are only designed for single-modality forgery based on binary classification, let alone analyzing and reasoning subtle forgery traces across different modalities. In this paper, we highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM4). DGM4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content, which requires deeper reasoning of multi-modal media manipulation. To support a large-scale investigation, we construct the first DGM4 dataset. Moreover, we propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities. HAMMER performs 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning, and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning. Dedicated manipulation detection and grounding heads are integrated from shallow to deep levels based on the interacted multi-modal information. To exploit more fine-grained contrastive learning for cross-modal semantic alignment, we further integrate Manipulation-Aware Contrastive Loss with Local View and construct a more advanced model HAMMER++ Finally, we build an extensive benchmark and set up rigorous evaluation metrics for this new research problem. Comprehensive experiments demonstrate the superiority of HAMMER and HAMMER++; several valuable observations are also revealed to facilitate future research in multi-modal media manipulation..

FNICM: A New Methodology To Identify Core Metabolites Based on Significantly Perturbed Metabolic Subnetworks.

Metabolomics has emerged as a powerful tool in biomedical research to understand the pathophysiological processes and metabolic biomarkers of diseases. Nevertheless, it is a significant challenge in metabolomics to identify the reliable core metabolites that are closely associated with the occurrence or progression of diseases. Here, we proposed a new research framework by integrating detection-based metabolomics with computational network biology for function-guided and network-based identification of core metabolites, namely, FNICM. The proposed FNICM methodology is successfully utilized to uncover ulcerative colitis (UC)-related core metabolites based on the significantly perturbed metabolic subnetwork. First, seed metabolites were screened out using prior biological knowledge and targeted metabolomics. Second, by leveraging network topology, the perturbations of the detected seed metabolites were propagated to other undetected ones. Ultimately, 35 core metabolites were identified by controllability analysis and were further hierarchized into six levels based on confidence level and their potential significance. The specificity and generalizability of the discovered core metabolites, used as UC's diagnostic markers, were further validated using published data sets of UC patients. More importantly, we demonstrated the broad applicability and practicality of the FNICM framework in different contexts by applying it to multiple clinical data sets, including inflammatory bowel disease, colorectal cancer, and acute coronary syndrome. In addition, FNICM was also demonstrated as a practicality methodology to identify core metabolites correlated with the therapeutic effects of Clematis saponins. Overall, the FNICM methodology is a new framework for identifying reliable core metabolites for disease diagnosis and drug treatment from a systemic and a holistic perspective.

Exploiting Hierarchical Interactions for Protein Surface Learning.

Predicting interactions between proteins is one of the most important yet challenging problems in structural bioinformatics. Intrinsically, potential function sites in protein surfaces are determined by both geometric and chemical features. However, existing works only consider handcrafted or individually learned chemical features from the atom type and extract geometric features independently. Here, we identify two key properties of effective protein surface learning: 1) relationship among atoms: atoms are linked with each other by covalent bonds to form biomolecules instead of appearing alone, leading to the significance of modeling the relationship among atoms in chemical feature learning. 2) hierarchical feature interaction: the neighboring residue effect validates the significance of hierarchical feature interaction among atoms and between surface points and atoms (or residues). In this paper, we present a principled framework based on deep learning techniques, namely Hierarchical Chemical and Geometric Feature Interaction Network (HCGNet), for protein surface analysis by bridging chemical and geometric features with hierarchical interactions. Extensive experiments demonstrate that our method outperforms the prior state-of-the-art method by 2.3% in site prediction task and 3.2 available at https://github.com/lyqun/HCGNet.

Estimating the methane flux of the Dajiuhu subalpine peatland using machine learning algorithms and the maximal information coefficient technique.

The eddy covariance (EC) technique has emerged as the most widely used method for long-term continuous methane flux (FCH4) observations. However, the completeness of the FCH4 time series is limited by instrumental failures and data quality issues, resulting in missing data gaps ranging from 20 % to 90 %. In this situation, the excellent performance of machine learning (ML) algorithms in filling missing FCH4 data has provided a foundation for developing regional-scale FCH4 models. In this study, we established estimation models for FCH4 utilizing random forest (RF), support vector machine (SVM), back propagation (BP) and nonlinear multiple regression (MLR) algorithms. The maximal information coefficient (MIC) technique was employed to identify and rank the environmental factors that were correlated with FCH4. Our findings revealed that soil temperature (Ts), soil water content (SWC) and air temperature (Ta) were the primary environmental factors influencing FCH4. Among the four algorithms, from perspectives of model accuracy and relatively small number of driving factors, the RF models exhibited the best performance, followed by BP and SVM, whereas MLR demonstrated the lowest performance. Among the 144 RF models established using nine datasets, RF model with 8 driving factors in all-year (RFall-year8) could capture seasonal variations. Ultimately, we recommend (RFall-year8 as the optimal model for estimating FCH4 in the Dajiuhu subalpine peatland.