Functional Network Structure Research Articles

Implementation of data transmission mechanism in a Bi-directional optical fiber network

Abstract Passive optical network (PON) has become the leader in delivering broadband high-speed connectivity. The paper introduces a detailed description of PON, its working principle, key features, and their potential applications. In addition, we discuss the types of PON architectures including GPON, EPON, and XG-PON with merits and demerits. Finally, we discuss the technical considerations of PONs in data transmission mechanisms, network design, and component selection. This paper further demonstrates the use of PON technology via a case study on the design and implementation of a bidirectional optical fiber network. Within this project, we went ahead to demonstrate the use of PON components including optical splitters, transmitters, receivers, and power controllers towards the development of an efficient and functional network structure. It mainly covered the results of the project since the PONs appeared to be a promising solution for obtaining high-performing and reliable broadband services.

Static and dynamic connectivity structure of white-matter functional networks across the adult lifespan.

Aging of the human brain involves intricate biological processes, resulting in complex changes in structure and function. While the effects of aging on gray matter (GM) connectivity are extensively studied, white matter (WM) functional changes have received comparatively less attention. This study examines age-related WM functional dynamics using resting-state fMRI across the adult lifespan. We identified GM and WM functional networks (FNs) using k-means clustering. Static and dynamic analyses of WM functional network connectivity (FNC) were performed to explore age effects on WM-FNs and recurrent patterns of dynamic FNC. We identified 9 WM and 12 GM FNs. Age-related effects on WM FNC strength and WM-GM FNC dynamics included linear positive and U-shaped age trajectories in static FNC strength, and linear negative and inverted U-shaped trajectories in FNC temporal variability. Three distinct brain states with significant age-related differences were identified and validated. These findings were largely replicated in the validation analysis. High integration and low temporal variability in WM-GM FNC may indicate reduced adaptability of the network system in older adults, offering insights into brain aging processes.

Alterations of upper-extremity functional muscle networks in chronic stroke survivors

Current clinical assessment tools don’t fully capture the genuine neural deficits experienced by chronic stroke survivors and, consequently, they don’t fully explain motor function throughout everyday life. Towards addressing this problem, here we aimed to characterise post-stroke alterations in upper-limb control from a novel perspective to the muscle synergy by applying, for the first time, a computational approach that quantifies diverse types of functional muscle interactions (i.e. functionally-similar (redundant), -complementary (synergistic) and -independent (unique)). From single-trials of a simple forward pointing movement, we extracted networks of functionally diverse muscle interactions from chronic stroke survivors and unimpaired controls, identifying shared and group-specific modules across each interaction type (i.e. redundant, synergistic and unique). Reconciling previous studies, we found evidence for both the concurrent preservation of healthy functional modules post-stroke and muscle network structure alterations underpinned by systemic muscle interaction re-weighting and functional reorganisation across all interaction types. Cluster analysis of stroke survivors revealed two distinct patient subgroups from each interaction type that all distinguished less impaired individuals who were able to adopt novel motor patterns different to unimpaired controls from more severely impaired individuals who did not. Our work here provides a nuanced account of post-stroke functional impairment and, in doing so, paves new avenues towards progressing the clinical use case of muscle synergy analysis.

Deep reinforcement learning for collision avoidance of autonomous ships in inland rivers

Due to the characteristics of large inertia, large time delay and non-linearity in ship motion, the manoeuvrability of ships is an important issue related to the safety of ship navigation. The manipulation of ships significantly affects the safety of ship navigation, and its importance will gradually increase with the development of autonomous ships (ASs). Due to the complexity of inland waterways and the density of ships, collisions are common. In this work, an autonomous learning framework with deep reinforcement learning (DRL) was constructed for ASs. The state space, action space, reward function and neural network structure of DRL were designed based on the AS's manoeuvring characteristics and control requirements. A deep deterministic policy gradient (DDPG) algorithm was then used to implement the controller. Finally, some representative route segments of an inland waterway were selected for simulation research based on a virtual simulation environment. The designed DRL controller was able to quickly converge from the training and learning process to meet the control requirements. The effectiveness of the DDPG algorithm was verified by comparisons with the experimental results. This study provides a reference for future research on collision-avoidance technology for ASs in inland rivers.

Abnormal intrinsic brain functional network dynamics in patients with retinal detachment based on graph theory and machine learning

Backgroundand purpose: The investigation of functional plasticity and remodeling of the brain in patients with retinal detachment (RD) has gained increasing attention and validation. However, the precise alterations in the topological configuration of dynamic functional networks are still not fully understood. This study aimed to investigate the topological structure of dynamic brain functional networks in RD patients. MethodsWe recruited 32 patients with RD and 33 healthy controls (HCs) to participate in resting-state fMRI. Employing the sliding time window analysis and K-means clustering method, we sought to identify dynamic functional connectivity (dFC) variability patterns in both groups. The investigation into the topological structure of whole-brain functional networks utilized a graph theoretical approach. Furthermore, we employed machine learning analysis, selecting altered topological properties as classification features to distinguish RD patients from HCs. ResultsAll participants exhibited four distinct states of dynamic functional connectivity. Compared to the healthy control (HC) group, patients with RD experienced a significant reduction in the number of transitions among these four states. Additionally, the dynamic topological properties of RD patients demonstrated notable changes in both global and node-specific characteristics, with these changes correlating with clinical parameters. The support vector machine (SVM) model used for classification achieved an accuracy of 0.938, an area under the curve (AUC) of 0.988, and both sensitivity and specificity of 0.937. ConclusionThe alterations in the topological properties of the brain in RD patients may indicate the integration function and information exchange efficiency of the whole brain network were reduced. In addition, the topological properties hold considerable promise for distinguishing between RD and HCs.

Research on trajectory planning based on deep reinforcement learning

Abstract For trajectory planning in a three-dimensional continuous space with multiple complex constraints, traditional optimal control methods face significant challenges, such as long computation times and poor dynamic performance. Using deep reinforcement learning algorithms for training agents in flight trajectory planning can effectively improve the dynamic performance of the planning algorithms. This paper focuses on training agents for UAV emergency landing and obstacle avoidance trajectory planning based on deep reinforcement learning algorithms. Within the reinforcement learning framework, we design the training environment, state space, action space, reward function, and neural network structure. To address common issues in reinforcement learning, such as poor generalization and slow training speed, we improve the training process using the concept of curriculum learning. Comparisons with pseudospectral methods demonstrate that deep reinforcement learning can effectively handle trajectory planning tasks in real flight environments, achieving trajectory quality close to that of pseudospectral methods while offering superior real-time performance.

Mapless navigation via Hierarchical Reinforcement Learning with memory-decaying novelty

Hierarchical Reinforcement Learning (HRL) has shown superior performance for mapless navigation tasks. However, it remains limited in unstructured environments that might contain terrains like long corridors and dead corners, which can lead to local minima. This is because most HRL-based mapless navigation methods employ a simplified reward setting and exploration strategy. In this work, we propose a novel reward function for training the high-level (HL) policy, which contains two components: extrinsic reward and intrinsic reward. The extrinsic reward encourages the robot to move towards the target location, while the intrinsic reward is computed based on novelty, episode memory and memory decaying, making the agent capable of accomplishing spontaneous exploration. We also design a novel neural network structure that incorporates an LSTM network to augment the agent with memory and reasoning capabilities. We test our method in unknown environments and specific scenarios prone to the local minimum problem to evaluate the navigation performance and local minimum resolution ability. The results show that our method significantly increases the success rate when compared to advanced RL-based methods, achieving a maximum improvement of nearly 28%. Our method demonstrates effective improvement in addressing the local minimum issue, especially in cases where the baselines fail completely. Additionally, numerous ablation studies consistently confirm the effectiveness of our proposed reward function and neural network structure.

A Semi-Supervised Active Learning Method for Structured Data Enhancement with Small Samples

In order to solve the problems of the small capacity of structured data and uneven distribution among classes in machine learning tasks, a supervised generation method for structured data called WAGAN and a cyclic sampling method named SACS (Semi-supervised and Active-learning Cyclic Sampling), based on semi-supervised active learning, are proposed. The loss function and neural network structure are optimized, and the quantity and quality of the small sample set are enhanced. To enhance the reliability of generating pseudo-labels, a Semi-supervised Active learning Framework (SAF) is designed. This framework redistributes class labels to samples, which not only enhances the reliability of generated samples but also reduces the influence of noise and uncertainty on the generation of false labels. To mine the diversity information of generated samples, an uncertain sampling strategy based on spatial overlap is designed. This strategy incorporates the idea of spatial overlap and uses global and local sampling methods to calculate the information content of generated samples. Experimental results show that the proposed method performs better than other data enhancement methods on three different datasets. Compared to the original data, the average F1macro value of the classification model is improved by 11.5%, 16.1%, and 19.6% relative to compared methods.

Network resilience of plant-bee interactions in the Eastern Afromontane Biodiversity Hotspot

Interaction network resilience can be defined as the ability of interacting organisms to maintain their functions, processes or populations after experiencing a disturbance. Studies on mutualistic interactions between plants and pollinators along environmental gradients are essential to understand the provision of ecosystem services and the mechanisms challenging their network resilience. However, it remains unknown to what level ecological changes along climatic gradients constrain the network resilience of mutualistic organisms, especially along elevation gradients. We surveyed bee species and recorded their interactions with plants throughout the four major seasons (i.e. long and short rainy, and long and short dry) on 50 study sites positioned along an elevation gradient (525 m to 2,530 m asl) in the Eastern Afromontane Biodiversity Hotspots in Kenya, East Africa. We calculated bee and plant network resilience using the network resilience parameter (βeff) and assessed changes in bee and plant network resilience along the elevation gradient using generalised additive models (gams). We quantified the effects of climate, bee and plant diversity, bee functional traits, network structure, and landscape configuration on bee and plant network resilience using a set of multi-model inference frameworks followed by structural equation models (SEM). We found that bee and plant species exhibited higher levels of network resilience at higher elevations. While bee network resilience increased linearly across the elevation gradient, plant network resilience increased exponentially from ∼1500 m and higher. Bee and plant network resilience increased in areas with reduced mean annual temperature (MAT) and decreased in areas with lower mean annual precipitation (MAP). Our SEM model showed that increasing temperatures indirectly influenced plant network resilience via network modularity and community assemblage of bees. We also found that MAP had a direct positive effect on plant diversity and network resilience, while the fragmentation of habitats reduced richness of plant communities and enhanced network modularity. In conclusion, we revealed that mutualistic networks showed higher network resilience at higher elevations. We also unveiled that climate and habitat fragmentation directly or indirectly influences the network resilience of plants and bees via the modulation of community assemblages and interaction networks. These influences are lower at higher elevations such that these systems seem better able to buffer against extinction cascades. We thus suggest that, management efforts should be geared at consolidating natural habitats. In contrast, restoration efforts should aim at mitigating climate change effects and harnessing the ability of mutualists to reconnect broken links to improve the network resilience and functioning of East-African montane ecosystems.

Abnormal Dynamic Reconstruction of Overlapping Communities in Schizophrenia Patients.

This study aims to explore the changes in dynamic overlapping communities in the brains of schizophrenia (SZ) patients and further investigate the dynamic restructuring patterns of overlapping communities in SZ patients. A total of 43 SZ patients and 49 normal controls (NC) were selected for resting-state functional MRI (rs-fMRI) scans. Dynamic functional connectivity analysis was conducted separately on SZ patients and NC using rs-fMRI and Jackknife Correlation techniques to construct dynamic brain network models. Based on these models, a dynamic overlapping community detection method was utilized to explore the abnormal overlapping community structure in SZ patients using evaluation metrics such as the structural stability of overlapping communities, nodes' functional diversity, and activity level of overlapping communities. The stability of communities in SZ patients showed a decreasing trend. The changes in the overlapping community structure of SZ patients may be related to a decrease in the diversity of overlapping node functions. Additionally, compared to the NC group, the activity level of overlapping communities of SZ patients was significantly reduced. The structure or organization of the brain functional network in SZ patients is abnormal or disrupted, and the activity of the brain network in information processing and transmission is weakened in SZ patients.

Analyzing the topological properties of resting-state brain function network connectivity based on graph theoretical methods in patients with high myopia

AimRecent imaging studies have found significant abnormalities in the brain’s functional or structural connectivity among patients with high myopia (HM), indicating a heightened risk of cognitive impairment and other behavioral changes. However, there is a lack of research on the topological characteristics and connectivity changes of the functional networks in HM patients. In this study, we employed graph theoretical analysis to investigate the topological structure and regional connectivity of the brain function network in HM patients.MethodsWe conducted rs-fMRI scans on 82 individuals with HM and 59 healthy controls (HC), ensuring that the two groups were matched for age and education level. Through graph theoretical analysis, we studied the topological structure of whole-brain functional networks among participants, exploring the topological properties and differences between the two groups.ResultsIn the range of 0.05 to 0.50 of sparsity, both groups demonstrated a small-world architecture of the brain network. Compared to the control group, HM patients showed significantly lower values of normalized clustering coefficient (γ) (P = 0.0101) and small-worldness (σ) (P = 0.0168). Additionally, the HM group showed lower nodal centrality in the right Amygdala (P < 0.001, Bonferroni-corrected). Notably, there is an increase in functional connectivity (FC) between the saliency network (SN) and Sensorimotor Network (SMN) in the HM group, while the strength of FC between the basal ganglia is relatively weaker (P < 0.01).ConclusionHM Patients exhibit reduced small-world characteristics in their brain networks, with significant drops in γ and σ values indicating weakened global interregional information transfer ability. Not only that, the topological properties of the amygdala nodes in HM patients significantly decline, indicating dysfunction within the brain network. In addition, there are abnormalities in the FC between the SN, SMN, and basal ganglia networks in HM patients, which is related to attention regulation, motor impairment, emotions, and cognitive performance. These findings may provide a new mechanism for central pathology in HM patients.

Greater Neighborhood Disadvantage Is Associated with Alterations in Fetal Functional Brain Network Structure

To determine the association between neighborhood disadvantage (ND) and functional brain development of in utero fetuses. We conducted an observational study using Social Vulnerability Index (SVI) scores to assess the impact of ND on a prospectively recruited sample of healthy pregnant women from Washington, DC. Using 79 functional magnetic resonance imaging scans from 68 healthy pregnancies at a mean gestational age of 33.12weeks, we characterized the overall functional brain network structure using a graph metric approach. We used linear mixed effects models to assess the relationship between SVI and gestational age on 5 graph metrics, adjusting for multiple scans. Exposure to greater ND was associated with less well integrated functional brain networks, as observed by longer characteristic path lengths and diminished global efficiency (GE), as well as diminished small world propensity (SWP). Across gestational ages, however, the association between SVI and network integration diminished to a negligible relationship in the third trimester. Conversely, SWP was significant across pregnancy, but the relationship changed such that there was a negative association with SWP earlier in the second trimester that inverted around the transition to the third trimester to a positive association. These data directly connect ND and altered functional brain maturation in fetuses. Our results suggest that, even before birth, proximity to environmental stressors in the wider neighborhood environment are associated with altered brain development.

An anesthetic protocol for preserving functional network structure in the marmoset monkey brain

Abstract Initiatives towards acquiring large-scale neuroimaging data in non-human primates promise improving translational neuroscience and cross-species comparisons. Crucial among these efforts is the need to expand sample sizes while reducing the impact of anesthesia on the functional properties of brain networks. Yet, the effects of anesthesia on non-human primate brain networks remain unclear. Here, we demonstrate using functional magnetic resonance imaging (fMRI) at 9.4 tesla that isoflurane anesthesia induces a variety of brain states in the marmoset brain with dramatically altered functional connectivity profiles. As an alternative, we recommend using a continuous infusion of the sedative medetomidine, supplemented with a low concentration of isoflurane. Using this protocol in eight marmosets, we observed robust visual activation during flickering light stimulation and identified resting-state networks similar to the awake state. In contrast, isoflurane alone led to a suppressed visual activation and the absence of awake-like network patterns. Comparing states using a graph-theoretical approach, we confirmed that the structure of functional networks is preserved under our proposed anesthesia protocol but is lost using isoflurane alone at concentration levels greater than 1%. We believe that the widespread adoption of this protocol will be a step towards advancing translational neuroscience initiatives in non-human primate neuroimaging. To promote the collaborative use of neuroimaging resources, we openly share our datasets (https://zenodo.org/records/11118775).

Persistence, changes and robustness of nest webs along a latitudinal gradient in the Canadian boreal forest

IntroductionIn eastern Canada, the boreal forest is associated with an important latitudinal shift in forest composition and structure, which occurs in the transition between the mixed southern boreal forest and the coniferous northern boreal forest. Along this transition, upland mixedwood stands with large deciduous trees (important for cavity-dependent vertebrate species) are gradually replaced by forests with smaller conifer trees, primarily black spruce (Picea mariana). Concomitantly, the availability of lowland forests flooded by the American beaver (Castor canadensis), which can provide adequate conditions for tree-cavity users, is also decreasing.MethodsWe hypothesized that this latitudinal gradient would bring important changes in the functional diversity and network structure of vertebrate cavity-using communities. Along this latitudinal gradient we used a nest web approach to analyze the structure and robustness of networks of cavity users in upland forests and in lowland forests flooded by beavers.ResultsDespite their low availability in the northern forest region, we found that mixedwood stands persisted throughout the boreal forest in being the main drivers of nest webs network structure of upland forests whereas old black spruce stands contribution was low. In lowland forests, beaver ponds harbored nest webs with a rich and complex structure in both forest regions. Species removal simulations revealed that across our latitudinal gradient upland and lowland forest nest webs responded differently. In upland forests, the removal of trembling aspen and the Pileated Woodpecker (Dryocopus pileatus) caused the highest proportions of secondary extinctions, showing low robustness of nest webs given that these two species were highly connected to the other species. Contrastingly, nest webs in beaver ponds were more robust mainly because excavator species used a higher diversity of tree species despite the removal of the Northern Flicker (Colaptes auratus) which induced numerous secondary extinctions. The Pileated Woodpecker remained the pivotal species across the two forest regions in upland forests whereas the Northern Flicker became the main large cavity provider in beaver ponds across the latitudinal gradient.DiscussionWe discuss how mixedwood forests and beaver ponds, which are key habitat types for the cavity-using vertebrate community across our latitudinal gradient, should be maintained and protected in landscapes under industrial timber harvesting.

Differential impacts of polyethylene microplastic and additives on soil nitrogen cycling: A deeper dive into microbial interactions and transformation mechanisms

The impact of microplastics and their additives on soil nutrient cycling, particularly through microbial mechanisms, remains underexplored. This study investigated the effects of polyethylene microplastics, polyethylene resin, and plastic additives on soil nitrogen content, physicochemical properties, nitrogen cycling functional genes, microbial composition, and nitrogen transformation rates. Results showed that all amendments increased total nitrogen but decreased dissolved total nitrogen. Polyethylene microplastics and additives increased dissolved organic nitrogen, while polyethylene resin reduced it and exhibited higher microbial biomass. Amendments reduced or did not change inorganic nitrogen levels, with additives showing the lowest values. Polyethylene resin favored microbial nitrogen immobilization, while additives were more inhibitory. Amendment type and content significantly interacted with nitrogen cycling genes and microbial composition. Distinct functional microbial biomarkers and network structures were identified for different amendments. Polyethylene microplastics had higher gross ammonification, nitrification, and immobilization rates, followed by polyethylene resin and additives. Nitrogen transformation was driven by multiple functional genes, with Proteobacteria playing a significant role. Soil physicochemical properties affected nitrogen content through transformation rates, with C/N ratio having an indirect effect and water holding capacity directly impacting it. In summary, plastic additives, compared to polyethylene microplastics and resin, are less conducive to nitrogen degradation and microbial immobilization, exert significant effects on microbial community structure, inhibit transformation rates, and ultimately impact nitrogen cycling.

Adoption of deep learning-based magnetic resonance image information diagnosis in brain function network analysis of Parkinson’s disease patients with end-of-dose wearing-off

Objectivethis study was to analyze the brain functional network of end-of-dose wearing-off (EODWO) in patients with Parkinson’s disease (PD) using a convolutional neural network (CNN)-based functional magnetic resonance imaging (fMRI) data classification model. Methodsone hundred PD patients were recruited and assigned to control (Ctrl) group (39 cases without EODWO) and experimental (Exp) group (61 cases with EODWO). The data classification model based on a CNN was employed to assist the analysis of the changes in brain functional network structure in the two groups. The CNN-based fMRI data classification model was primarily based on a CNN architecture, with improvements made to the initialization of convolutional kernel parameters. Firstly, a structure based on restricted Boltzmann machine (RBM) was constructed, followed by the initialization of convolutional kernel parameters. Subsequently, the model underwent training. Utilizing the data analysis module within the GRETNA toolbox, extracted feature sets were analyzed, including local measures such as betweenness centrality (BC) and degree centrality (DC), as well as global measures such as global efficiency (Eg) and local efficiency (Eloc). Resultsas sparsity increased, there was a gradual upward trend observed in Eg; however, the values of Eg in both brain functional networks remained relatively stable within the range of 0.2–0.5. The Eg value of the Ctrl group’s whole-brain functional network was 0.17 ± 0.02, while that of the Exp group’s whole-brain functional network was 0.17 ± 0.03, with no significant difference between them (P>0.05). The functional DC value of the superior frontal gyrus in the Exp group (8.71 ± 2.56) was significantly lower than that of the Ctrl group (13.32 ± 3.22), whereas the functional DC value of the anterior cingulate gyrus in the Exp group (19.33 ± 4.78) was significantly higher than that of the Ctrl group (15.21 ± 4.02) (P<0.05). There was no significant correlation observed between the functional DC value and levodopa or dopamine agonist therapy (DDT) in the Exp group, whereas the Ctrl group exhibited a significant positive correlation. Conclusionanalysis conducted via a CNN-based fMRI data classification model revealed a correlation between the occurrence of EODWO in PD patients and functional impairments in the left precuneus. Additionally, the occurrence of EODWO may potentially diminish the plasticity of the central prefrontal dopamine.

Design and preparation of reticular superabsorbent hydrogel material with nutrient slow-release and high shear strength for ecological remediation of abandoned mines with steep slopes

In order to solve ecological remediation issues for abandoned mines with steep slopes, a kind of hydrogels with high cohesion and water-retaining were designed by inorganic mineral skeleton combining with polymeric organic network cavities. This eco-friendly hydrogel (MFA/HA-g-p(AA-co-AM)) was prepared with acrylic acid (AA)-acrylamide (AM) as network, which was grafted with humic acids (HA) as network binding point reinforcement skeleton and polar functional group donors, KOH-modified fly ash (MFA) as internal supporter. The maximum water absorption capacities were 1960 g/g for distilled water, which followed the pseudo-second-order model. This super water absorption was attributed to the first stage of 62 % fast absorption due to the high specific surface area, pore volume and low osmotic pressure, moreover, the multiple hydrophilic functional groups and network structure swell contributed to 36 % of the second stage slow adsorption. In addition, the pore filling of water in mesoporous channels contributed the additional 2 % water retention on the third stage. The high saline-alkali resistance correlated with the electrostatic attraction with MFA and multiple interactions with oxygen-containing functional groups in organic components. MFA and HA also enhanced the shear strength and fertility retention properties. After 5 cycles of natural dehydration and reabsorption process, these excellent characteristics of reusability and water absorption capacity kept above 97 %. The application of 0.6 wt% MFA/HA-g-p(AA-co-AM) at 15° slope could improve the growth of ryegrass by approximately 45 %. This study provides an efficient and economic superabsorbent material for ecological restoration of abandoned mines with steep slopes.

Alterations in the hub structure of whole-brain functional networks in patients with drug-naïve schizophrenia: Insights from electroencephalography-based research.

This study aimed to identify atypical hubs in the whole-brain networks of patients with schizophrenia (SZ) and examine the effects of antipsychotic medications, using electroencephalography (EEG) data. We estimated the functional connectivity across all electrodes by applying the phase lag index to the EEG signals of 21 drug-naïve patients with SZ and 31 age-matched healthy controls. Betweenness centrality (BC), a measure of hub status, was calculated for each electrode and frequency band. Data from 14 patients were re-evaluated after initiating treatment with antipsychotic medications. BC values decreased significantly at the Fz site in the beta band, decreased significantly at Pz in the gamma band, and increased significantly at O1 in the gamma band among patients with SZ. These changes persisted after antipsychotic treatment and were unrelated to clinical symptoms. The abnormal hub topology we observed, especially in the high-frequency band, may reflect the pathophysiology of SZ, and this study highlights the utility of BC analysis of EEG data for detecting alterations in the whole-brain networks of patients with SZ.

U-shaped convolutional transformer GAN with multi-resolution consistency loss for restoring brain functional time-series and dementia diagnosis.

The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data. In this paper, a novel U-shaped convolutional transformer GAN (UCT-GAN) model is proposed to restore the missing brain functional time-series data. The proposed model leverages the power of generative adversarial networks (GANs) while incorporating a U-shaped architecture to effectively capture hierarchical features in the restoration process. Besides, the multi-level temporal-correlated attention and the convolutional sampling in the transformer-based generator are devised to capture the global and local temporal features for the missing time series and associate their long-range relationship with the other brain regions. Furthermore, by introducing multi-resolution consistency loss, the proposed model can promote the learning of diverse temporal patterns and maintain consistency across different temporal resolutions, thus effectively restoring complex brain functional dynamics. We theoretically tested our model on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and our experiments demonstrate that the proposed model outperforms existing methods in terms of both quantitative metrics and qualitative assessments. The model's ability to preserve the underlying topological structure of the brain functional networks during restoration is a particularly notable achievement. Overall, the proposed model offers a promising solution for restoring brain functional time-series and contributes to the advancement of neuroscience research by providing enhanced tools for disease analysis and interpretation.

Genome-wide identification of rice CXE gene family and mining of alleles for potential application in rice improvement.

Carboxylesterases (CXE, EC 3.1.1.1), a class of hydrolases with an α/β folding domain, play important roles in plant growth and development and stress response. Here, we identified 32, 63, 41, and 45 CXE genes in Oryza sativa Japonica (Nipponbare), Oryza sativa Indica (93-11), Oryza sativa Indica (Xian-1B1 var.IR64), and Oryza sativa Japonica (Geng-sbtrp var.ChaoMeo), respectively. Then, we analyzed the chromosomal location, physical and chemical properties, subcellular localization, collinearity, and selection pressure of CXE genes in four rice varieties. We also analyzed the functional interaction network, cis-regulatory elements, evolutionary relationship, and protein tertiary structure, and performed gene expression profiling and qPCR verification under abiotic stress, as well as diversity analysis of 3010 gene-CDS-haplotype (gcHap) rice samples, aiming to understand the potential function of the 32 OsCXE genes. Our results indicated that fragment replication is the main reason for amplification of the CXE gene family in rice, and the gene family has undergone strong purification selection. OsCXE3.1, OsCXE3.2, OsCXE3.3, OsCXE5.1, and OsCXE7.3 may be used to improve the tolerance of rice to abiotic stress. OsCXE play important roles in rice population differentiation and improvement, and the major gcHaps at most OsCXE locus are significantly associated with yield traits. Therefore, natural variations of most OsCXE locus have great potential value for improvement of rice productivity.