Exploring Schizophrenia Classification Through Multimodal MRI and Deep Graph Neural Networks: Unveiling Brain Region-Specific Weight Discrepancies and Their Association With Cell-Type Specific Transcriptomic Features.

BACKGROUND AND HYPOTHESIS: Schizophrenia (SZ) is a prevalent mental disorder that imposes significant health burdens. Diagnostic accuracy remains challenging due to clinical subjectivity. To address this issue, we explore magnetic resonance imaging (MRI) as a tool to enhance SZ diagnosis and provide objective references and biomarkers. Using deep learning with graph convolution, we represent MRI data as graphs, aligning with brain structure, and improving feature extraction, and classification. Integration of multiple modalities is expected to enhance classification. STUDY DESIGN: Our study enrolled 683 SZ patients and 606 healthy controls from 7 hospitals, collecting structural MRI and functional MRI data. Both data types were represented as graphs, processed by 2 graph attention networks, and fused for classification. Grad-CAM with graph convolution ensured interpretability, and partial least squares analyzed gene expression in brain regions. STUDY RESULTS: Our method excelled in the classification task, achieving 83.32% accuracy, 83.41% sensitivity, and 83.20% specificity in 10-fold cross-validation, surpassing traditional methods. And our multimodal approach outperformed unimodal methods. Grad-CAM identified potential brain biomarkers consistent with gene analysis and prior research. CONCLUSIONS: Our study demonstrates the effectiveness of deep learning with graph attention networks, surpassing previous SZ diagnostic methods. Multimodal MRI's superiority over unimodal MRI confirms our initial hypothesis. Identifying potential brain biomarkers alongside gene biomarkers holds promise for advancing objective SZ diagnosis and research in SZ.

Comprehensive exploration of multi-modal and multi-branch imaging markers for autism diagnosis and interpretation: insights from an advanced deep learning model.

Autism spectrum disorder is a complex neurodevelopmental condition with diverse genetic and brain involvement. Despite magnetic resonance imaging advances, autism spectrum disorder diagnosis and understanding its neurogenetic factors remain challenging. We propose a dual-branch graph neural network that effectively extracts and fuses features from bimodalities, achieving 73.9% diagnostic accuracy. To explain the mechanism distinguishing autism spectrum disorder from healthy controls, we establish a perturbation model for brain imaging markers and perform a neuro-transcriptomic joint analysis using partial least squares regression and enrichment to identify potential genetic biomarkers. The perturbation model identifies brain imaging markers related to structural magnetic resonance imaging in the frontal, temporal, parietal, and occipital lobes, while functional magnetic resonance imaging markers primarily reside in the frontal, temporal, occipital lobes, and cerebellum. The neuro-transcriptomic joint analysis highlights genes associated with biological processes, such as "presynapse," "behavior," and "modulation of chemical synaptic transmission" in autism spectrum disorder's brain development. Different magnetic resonance imaging modalities offer complementary information for autism spectrum disorder diagnosis. Our dual-branch graph neural network achieves high accuracy and identifies abnormal brain regions and the neuro-transcriptomic analysis uncovers important genetic biomarkers. Overall, our study presents an effective approach for assisting in autism spectrum disorder diagnosis and identifying genetic biomarkers, showing potential for enhancing the diagnosis and treatment of this condition.

Brain age prediction using the graph neural network based on resting-state functional MRI in Alzheimer's disease.

Introduction: Alzheimer's disease (AD) is a neurodegenerative disease that significantly impacts the quality of life of patients and their families. Neuroimaging-driven brain age prediction has been proposed as a potential biomarker to detect mental disorders, such as AD, aiding in studying its effects on functional brain networks. Previous studies have shown that individuals with AD display impaired resting-state functional connections. However, most studies on brain age prediction have used structural magnetic resonance imaging (MRI), with limited studies based on resting-state functional MRI (rs-fMRI). Methods: In this study, we applied a graph neural network (GNN) model on controls to predict brain ages using rs-fMRI in patients with AD. We compared the performance of the GNN model with traditional machine learning models. Finally, the post hoc model was also used to identify the critical brain regions in AD. Results: The experimental results demonstrate that our GNN model can predict brain ages of normal controls using rs-fMRI data from the ADNI database. Moreover the differences between brain ages and chronological ages were more significant in AD patients than in normal controls. Our results also suggest that AD is associated with accelerated brain aging and that the GNN model based on resting-state functional connectivity is an effective tool for predicting brain age. Discussion: Our study provides evidence that rs-fMRI is a promising modality for brain age prediction in AD research, and the GNN model proves to be effective in predicting brain age. Furthermore, the effects of the hippocampus, parahippocampal gyrus, and amygdala on brain age prediction are verified.

Approach to Seven-Membered Carbocycles via a Lewis Acid Catalyzed Intramolecular Michael Addition of Allenone.

A straightforward strategy for constructing seven-membered carbocycles by employing a Lewis acid catalyzed intramolecular Michael addition of allenones is reported. It offers atom-economic access to synthetically important furan-fused bi- or tricyclic frameworks containing seven-membered carbocycles, which are widely found in natural products possessing various bioactivities. A number of seven-membered carbocycle-containing polycyclic frameworks bearing diverse functional groups were prepared in good to excellent yields. Furthermore, the application potential of this strategy was exemplified by the construction of the key skeletons of Caribenol A and Frondosin B.

Brain functional activity-based classification of autism spectrum disorder using an attention-based graph neural network combined with gene expression.

Autism spectrum disorder (ASD) is a complex brain neurodevelopmental disorder related to brain activity and genetics. Most of the ASD diagnostic models perform feature selection at the group level without considering individualized information. Evidence has shown the unique topology of the individual brain has a fundamental impact on brain diseases. Thus, a data-constructing method fusing individual topological information and a corresponding classification model is crucial in ASD diagnosis and biomarker discovery. In this work, we trained an attention-based graph neural network (GNN) to perform the ASD diagnosis with the fusion of graph data. The results achieved an accuracy of 79.78%. Moreover, we found the model paid high attention to brain regions mainly involved in the social-brain circuit, default-mode network, and sensory perception network. Furthermore, by analyzing the covariation between functional magnetic resonance imaging data and gene expression, current studies detected several ASD-related genes (i.e. MUTYH, AADAT, and MAP2), and further revealed their links to image biomarkers. Our work demonstrated that the ASD diagnostic framework based on graph data and attention-based GNN could be an effective tool for ASD diagnosis. The identified functional features with high attention values may serve as imaging biomarkers for ASD.

Classification of major depressive disorder using an attention-guided unified deep convolutional neural network and individual structural covariance network.

Major depressive disorder (MDD) is the second leading cause of disability worldwide. Currently, the structural magnetic resonance imaging-based MDD diagnosis models mainly utilize local grayscale information or morphological characteristics in a single site with small samples. Emerging evidence has demonstrated that different brain structures in different circuits have distinct developmental timing, but mature coordinately within the same functional circuit. Thus, establishing an attention-guided unified classification framework with deep learning and individual structural covariance networks in a large multisite dataset could facilitate developing an accurate diagnosis strategy. Our results showed that attention-guided classification could improve the classification accuracy from primary 75.1% to ultimate 76.54%. Furthermore, the discriminative features of regional covariance connectivities and local structural characteristics were found to be mainly located in prefrontal cortex, insula, superior temporal cortex, and cingulate cortex, which have been widely reported to be closely associated with depression. Our study demonstrated that our attention-guided unified deep learning framework may be an effective tool for MDD diagnosis. The identified covariance connectivities and structural features may serve as biomarkers for MDD.

Seed rain and soil seed bank in Chinese fir plantations and an adjacent natural forest in southern China: Implications for the regeneration of native species.

The natural regeneration of native broadleaved species underneath forest monoculture plantations is important to recover ecosystem functions and to mitigate adverse environmental effects. To understand how seed rain and soil seed bank facilitate natural regeneration, we surveyed their density and composition in a monoculture Chinese fir plantation, a mixed Chinese fir-broadleaf plantation, and an adjacent natural broadleaved forest for two years in southern China. Twenty-eight species (16 families) were in seed rain, and 45 species (27 families) were in soil seed bank. Seed rain density did not differ significantly across stands; however, the number of taxa in seed rain was highest in the mixed plantation and lowest in the natural forest. Seed bank density was significantly higher in the mixed plantation than in the other stands (p < .05). The Sørensen similarity index of species composition between seed sources and aboveground vegetation were relatively low (<.50). The seeds of various native tree species were common in the seed bank of the plantations, indicating that seed rain and seed bank played an important role in native forest regeneration. We recommend that managers interested in sustainable forestry should take into consideration the presence of existing soil seed bank when developing their management strategies. In addition, with regard to forest regeneration process, we also recommend supplementation of the species composition by direct seeding or planting of desired species.

Autistic Spectrum Disorder Detection and Structural Biomarker Identification Using Self-Attention Model and Individual-Level Morphological Covariance Brain Networks.

Autism spectrum disorder (ASD) is a range of neurodevelopmental disorders, which brings enormous burdens to the families of patients and society. However, due to the lack of representation of variance for diseases and the absence of biomarkers for diagnosis, the early detection and intervention of ASD are remarkably challenging. In this study, we proposed a self-attention deep learning framework based on the transformer model on structural MR images from the ABIDE consortium to classify ASD patients from normal controls and simultaneously identify the structural biomarkers. In our work, the individual structural covariance networks are used to perform ASD/NC classification via a self-attention deep learning framework, instead of the original structural MR data, to take full advantage of the coordination patterns of morphological features between brain regions. The self-attention deep learning framework based on the transformer model can extract both local and global information from the input data, making it more suitable for the brain network data than the CNN- structural model. Meanwhile, the potential diagnosis structural biomarkers are identified by the self-attention coefficients map. The experimental results showed that our proposed method outperforms most of the current methods for classifying ASD patients with the ABIDE data and achieves a classification accuracy of 72.5% across different sites. Furthermore, the potential diagnosis biomarkers were found mainly located in the prefrontal cortex, temporal cortex, and cerebellum, which may be treated as the early biomarkers for the ASD diagnosis. Our study demonstrated that the self-attention deep learning framework is an effective way to diagnose ASD and establish the potential biomarkers for ASD.

Allenone-Mediated Racemization/Epimerization-Free Peptide Bond Formation and Its Application in Peptide Synthesis.

Allenone has been identified as a highly effective peptide coupling reagent for the first time. The peptide bond was formed with an α-carbonyl vinyl ester as the key intermediate, the formation and subsequent aminolysis of which proceed spontaneously in a racemization-/epimerization-free manner. The allenone coupling reagent not only is effective for the synthesis of simple amides and dipeptides but is also amenable to peptide fragment condensation and solid-phase peptide synthesis (SPPS). The robustness of the allenone-mediated peptide bond formation was showcased incisively by the synthesis of carfilzomib, which involved a rare racemization-/epimerization-free N to C peptide elongation strategy. Furthermore, the successful synthesis of the model difficult peptide ACP (65-74) on a solid support suggested that this method was compatible with SPPS. This method combines the advantages of conventional active esters and coupling reagents, while overcoming the disadvantages of both strategies. Thus, this allenone-mediated peptide bond formation strategy represents a disruptive innovation in peptide synthesis.

Responses of leaf morphology, NSCs contents and C:N:P stoichiometry of Cunninghamia lanceolata and Schima superba to shading.

BACKGROUND: The non-structural carbohydrates (NSCs), carbon (C), nitrogen (N), and phosphorus (P) are important energy source or nutrients for all plant growth and metabolism. To persist in shaded understory, saplings have to maintain the dynamic balance of carbon and nutrients, such as leaf NSCs, C, N and P. To improve understanding of the nutrient utilization strategies between shade-tolerant and shade-intolerant species, we therefore compared the leaf NSCs, C, N, P in response to shade between seedlings of shade-tolerant Schima superba and shade-intolerant Cunninghamia lanceolate. Shading treatments were created with five levels (0, 40, 60, 85, 95% shading degree) to determine the effect of shade on leaf NSCs contents and C:N:P stoichiometry characteristics. RESULTS: Mean leaf area was significantly larger under 60% shading degree for C. lanceolata while maximum mean leaf area was observed under 85% shading degree for S. superba seedlings, whereas leaf mass per area decreased consistently with increasing shading degree in both species. In general, both species showed decreasing NSC, soluble sugar and starch contents with increasing shading degree. However shade-tolerant S. superba seedlings exhibited higher NSC, soluble sugar and starch content than shade-intolerant C. lanceolate. The soluble sugar/starch ratio of C. lanceolate decreased with increasing shading degree, whereas that of S. superb remained stable. Leaf C:N ratio decreased while N:P ratio increased with increasing shading degree; leaf C:P ratio was highest in 60% shading degree for C. lanceolata and in 40% shading degree for S. superba. CONCLUSION: S. superba is better adapted to low light condition than C. lanceolata through enlarged leaf area and increased carbohydrate reserves that allow the plant to cope with low light stress. From mixed plantation viewpoint, it would be advisable to plant S. superba later once the canopy of C. lanceolata is well developed but allowing enough sunlight.

[Variation characteristics of soil seed bank during vegetation restoration in red soil erosion area]. / 红壤侵蚀区植被恢复过程中土壤种子库变化特征.

As a natural disturbance agent, soil erosion could affect secondary distribution and species composition of soil seed bank. The composition, storage and distribution pattern of the soil seed banks in five different vegetation recovery areas, including bare ground (1), pine forest land (2-4) and secondary forest (5) in the typical red soil erosion area, were studied to explore the effects of soil erosion on soil seed bank during vegetation restoration. The results showed that a total of 21 species were recorded in the soil seed bank. Species richness was low, and dominated by herbaceous species. The density of soil seed bank varied from 56.7 to 793.3 seeds·m-2 and differed significantly among the sampling plots. Further, the density of soil seed bank decreased obviously with the increasing soil erosion intensity. The seed bank density of 0-2 cm soil layer increased along uphill, middle slope, and downhill. The soil seed banks of severely eroded and strongly eroded plots were mainly distributed in the 5-10 cm soil layer, with almost no seeds in 0-2 cm soil layer on the middle slope and uphill. Soil erosion made the distribution of soil seed bank to deeper soil layer, the accumulation of which will need a long time after vegetation restoration.

Robust Heart Rate Monitoring for Quasi-Periodic Motions by Wrist-Type PPG Signals.

Heart rate (HR) monitoring using photoplethysmography (PPG) is a promising feature in modern wearable devices. PPG is easily contaminated by motion artifacts (MA), hindering estimation of HR. For quasi-periodic motions, previous works generally focused on a few specific motions, such as walking and fast running. However, they may not work well for many different quasi-periodic motions where MA are very complex. In this paper, a robust HR monitoring scheme for different quasi-periodic motions using wrist-type PPG is proposed, which consists of dictionary learning for signal characteristics learning, human motion recognition for the current motion recognition and dictionary selection, sparse representation-based MA elimination for denoising, and spectral peak tracking for HR-related spectral peak tracking. The proposed scheme is robust to MA caused by different motions and has high accuracy. Experiments on six common quasi-periodic motions showed that the average absolute error of heart rate estimation was 2.40 beat per minute, and also showed that the proposed method is more robust than some state-of-the-art approaches for different motions.

Enantioselective Polyene Cyclization Catalyzed by a Chiral Brønsted Acid.

The first enantioselective polyene cyclization initiated by a BINOL-derived chiral N-phosphoramide (NPA) catalyzed protonation of an imine is described. The ion-pair formed between the iminium ion and chiral counter anion of the NPA plays an important role for controlling the stereochemistry of the overall transformation. This strategy offers a highly efficient approach to fused tricyclic frameworks containing three contiguous stereocenters, which are widely found in natural products. In addition, the first catalytic asymmetric total synthesis of (-)-ferruginol was accomplished with an NPA catalyzed enantioselective polyene cyclization, as the key step for the construction of the tricyclic core, with excellent yield and enantioselectivity.

Phylogeny, Seed Trait, and Ecological Correlates of Seed Germination at the Community Level in a Degraded Sandy Grassland.

Seed germination strongly affects plant population growth and persistence, and it can be dramatically influenced by phylogeny, seed traits, and ecological factors. In this study, we examined the relationships among seed mass, seed shape, and germination percentage (GP), and assessed the extent to which phylogeny, seed traits (seed mass, shape, and color) and ecological factors (ecotype, life form, adult longevity, dispersal type, and onset of flowering) influence GP at the community level. All analyses were conducted on the log-transformed values of seed mass and arcsine square root-transformed values of GP. We found that seed mass and GP were significantly negatively correlated, whereas seed shape and GP were significantly positively correlated. The three major factors contributing to differences in GP were phylogeny, dispersal type, and seed shape (explained 5.8, 4.9, and 3.1% of the interspecific variations independently, respectively), but GP also influenced by seed mass and onset of flowering. Thus, GP was constrained not only by phylogeny but also by seed traits and ecological factors. These results indicated that GP is shaped by short-term selective pressures, and long-term phylogenetic constrains. We suggest that correlates of phylogeny, seed traits, and ecology should be taken into account in comparative studies on seed germination strategies.