Contrastive voxel clustering for multiscale modeling of brain network.

Resting-state functional magnetic resonance imaging (fMRI) provides an efficient way to analyze the functional connectivity between brain regions. A comprehensive understanding of brain functionality requires a unified description of multi-scale layers of neural structure. However, existing brain network modeling methods often simplify this property by averaging Blood oxygen level dependent (BOLD) signals at the brain region level for fMRI-based analysis with the assumption that BOLD signals are homogeneous within each brain region, which ignores the heterogeneity of voxels within each Region of Interest (ROI). This study introduces a novel multi-stage self-supervised learning framework for multiscale brain network analysis, which effectively delineates brain functionality from voxel to ROIs and up to sample level. A Contrastive Voxel Clustering (CVC) module is proposed to simultaneously learn the voxel-level features and clustering assignments, which ensures the retention of informative clustering features at the finest voxel-level and concurrently preserves functional connectivity characteristics. Additionally, based on the extracted features and clustering assignments at the voxel level by CVC, a Brain ROI-based Graph Neural Network (BR-GNN) is built to extract functional connectivity features at the brain ROI-level and used for sample-level prediction, which integrates the functional clustering maps with the pre-established structural ROI maps and creates a more comprehensive and effective analytical tool. Experiments are performed on two datasets, which illustrate the effectiveness and generalization ability of the proposed method by analyzing voxel-level clustering results and brain ROIs-level functional characteristics. The proposed method provides a multiscale modeling framework for brain functional connectivity analysis, which will be further used for other brain disease identification. Code is available at https://github.com/yanliugroup/fmri-cvc.

Exosome-transmitted S100A4 induces immunosuppression and non-small cell lung cancer development by activating STAT3.

Non-small cell lung cancer (NSCLC) is the primary reason of tumor morbidity and mortality worldwide. We aimed to study the transfer process of S100A4 between cells and whether it affected NSCLC development by affecting STAT3 expression. First, S100A4 expression in NSCLC cells was measured. The exosomes in MRC-5, A549, and H1299 cells were isolated and identified. We constructed si-S100A4 and si-PD-L1 to transfect A549 cells and oe-S100A4 to transfect H1299 cells, and tested the transfection efficiency. Cell function experiments were performed to assess cell proliferation, clone number, apoptosis, cell cycle, migration, and invasion abilities. In addition, ChIP was applied to determine the targeting relationship between S100A4 and STAT3. Next, we explored NSCLC cell-derived exosomes role in NSCLC progress by transmitting S100A4. Finally, we verified the function of exosome-transmitted S100A4 in NSCLC in vivo. High expression of S100A4 was secreted by exosomes. After knocking down S100A4, cell proliferation ability was decreased, clones number was decreased, apoptosis was increased, G1 phase was increased, S phase was repressed, and migration and invasion abilities were also decreased. ChIP validated STAT3 and PD-L1 interaction. After knocking down S100A4, PD-L1 expression was decreased, while ov-STAT3 reversed the effect of S100A4 on PD-L1 expression. Meanwhile, S100A4 inhibited T-cell immune activity by activating STAT3. In addition, knockdown of PD-L1 inhibited cell proliferation, migration, and invasion. NSCLC cell-derived exosomes promoted cancer progression by transmitting S100A4 to activate STAT3 pathway. Finally, in vivo experiments further verified that exosome-transmitted S100A4 promoted NSCLC progression. Exosome-transmitted S100A4 induces immunosuppression and the development of NSCLC by activating STAT3.

Distillation-based Chinese Food Ingredient Recognition and Nutrition Estimation System.

The foods' ingredients and nutrition are of great significance for human health so that people can meet their fitness needs or avoid consuming allergenic and post-operative contraindicated foods. However, the diversity of recipes and the randomness of combinations in Chinese cuisine make great challenges for Chinese food identification. To address the above issues, we built a new lightweight end-to-end food query and nutrition recognition system, which is based on knowledge distillation and deep learning methods. Firstly, well-performed DenseNet-121 is used to recognize the categories of food. At the same time, ResNet-50 is used as the Net-T, and pre-trained VGG-16 is used as the Net-S in the knowledge distillation framework, which is used to recognize the ingredients of the food. Finally, ingredient nutrition is obtained by querying the ingredient table. Experiments illustrate the good performance of the proposed method, with 91.65% Accuracy of food classification and 92.01% Accuracy of ingredients recognition.

Epigallocatechin gallate enhances the motor neuron survival and functional recovery after brachial plexus root avulsion by regulating FIG4.

The survival of motor neurons (MNs) is the key to recovery of the motor function after brachial plexus root avulsion (BPRA). (-)-epigallocatechin-3-gallate (EGCG) exerts neuroprotective roles in neurons under different pathological conditions. However, the role of EGCG in regulating motor neurons under BPRA remains to be unclear. In the present study, we investigated the functional role of EGCG both in vitro and in vivo. In an in vitro study, we observed that EGCG obviously increased the cell survival rate of MNs and FIG4 protein levels compared with the vehicle control, with a peak level observed at 50 µM; EGCG can also upregulate FIG4 to reduce the cell death of MNs and increase the neurite outgrowth under oxidative stress; moreover, EGCG can upregulate FIG4 to promote the functional recovery and the survival of MNs in the ventral horn in mice after BPRA. These combined results may lay the foundation for EGCG to be a novel strategy for the treatment of BPRA.