Changes in genome architecture and transcriptional dynamics progress independently of sensory experience during post-natal brain development.

Both transcription and three-dimensional (3D) architecture of the mammalian genome play critical roles in neurodevelopment and its disorders. However, 3D genome structures of single brain cells have not been solved; little is known about the dynamics of single-cell transcriptome and 3D genome after birth. Here, we generated a transcriptome (3,517 cells) and 3D genome (3,646 cells) atlas of the developing mouse cortex and hippocampus by using our high-resolution multiple annealing and looping-based amplification cycles for digital transcriptomics (MALBAC-DT) and diploid chromatin conformation capture (Dip-C) methods and developing multi-omic analysis pipelines. In adults, 3D genome "structure types" delineate all major cell types, with high correlation between chromatin A/B compartments and gene expression. During development, both transcriptome and 3D genome are extensively transformed in the first post-natal month. In neurons, 3D genome is rewired across scales, correlated with gene expression modules, and independent of sensory experience. Finally, we examine allele-specific structure of imprinted genes, revealing local and chromosome (chr)-wide differences. These findings uncover an unknown dimension of neurodevelopment.

Correlated gene modules uncovered by high-precision single-cell transcriptomics.

Correlations in gene expression are used to infer functional and regulatory relationships between genes. However, correlations are often calculated across different cell types or perturbations, causing genes with unrelated functions to be correlated. Here, we demonstrate that correlated modules can be better captured by measuring correlations of steady-state gene expression fluctuations in single cells. We report a high-precision single-cell RNA-seq method called MALBAC-DT to measure the correlation between any pair of genes in a homogenous cell population. Using this method, we were able to identify numerous cell-type specific and functionally enriched correlated gene modules. We confirmed through knockdown that a module enriched for p53 signaling predicted p53 regulatory targets more accurately than a consensus of ChIP-seq studies and that steady-state correlations were predictive of transcriptome-wide response patterns to perturbations. This approach provides a powerful way to advance our functional understanding of the genome.

Beijing Children's Hospital guidelines on the design and conduction of the first standardized database for medulloblastoma.

Medulloblastoma (MB) is one of the most common malignant childhood brain tumors (WHO grade IV). Its high degree of malignancy leads to an unsatisfactory prognosis, requiring more precise and personalized treatment in the near future. Multi-omics and artificial intelligence have been playing a significant role in precise medical research, but their implementation needs a large amount of clinical information and biomaterials. For these reasons, it is urgent for current MB researchers to establish a large sample-size database of MB that contains complete clinical data and sufficient biomaterials such as blood, cerebrospinal fluid (CSF), cancer tissue, and urine. Unfortunately, there are few biobanks of pediatric central nervous system (CNS) tumors throughout the world for limited specimens, scarce funds, different standards collecting methods and et cl. Even though, China falls behind western countries in this area. The present research set up a standard workflow to construct the Beijing Children's Hospital Medulloblastoma (BCH-MB) biobank. Clinical data from children with MB and for collecting and storing biomaterials, along with regular follow-up has been collected and recorded in this database. In the future, the BCH-MB biobank could make it possible to validate the promising biomarkers already identified, discover unrevealed MB biomarkers, develop novel therapies, and establish personalized prognostic models for children with MB upon the support of its sufficient data and biomaterials, laying the foundation for individualized therapies of children with MB.

Novel mutation of SIK1 gene causing a mild form of pediatric epilepsy in a Chinese patient.

Developmental and Epileptic Encephalopathy (DEE) is a group of disorders affecting children at early stages of infancy, which is characterized by frequent seizures, epileptiform activity on EEG, and developmental delayor regression. Developmental and epileptic encephalopathy-30 (DEE30) is a severe neurologic disorder characterized by onset of refractory seizures soon after birth or in the first months of life. Which was recently found to be caused by heterozygous mutations in the salt-inducible kinase SIK1. In this study, we investigated a patient with early onset epilepsy. DNA sequencing of the whole coding region revealed a de novel heterozygous nucleotide substitution (c.880G > A) causing a missense mutation (p.A294T). This mutation was classified as variant of unknown significance (VUS) by American College of Medical Genetics and Genomics (ACMG). To further investigate the pathogenicity and pathogenesis of this mutation, we established a human neuroblastoma cell line (SH-SY5Y) stably-expressing wild type SIK1 and A294T mutant, and compared the transcriptome and metabolomics profiles. We presented a pediatric patient suffering from infantile onset epilepsy. Early EEG showed a boundary dysfunction of activity and MRI scan of the brain was normal. The patient responded well to single anti-epileptic drug treatment. Whole-exome sequencing found a missense mutation of SIK1 gene (c.880G > A chr21: 43,420,326 p. A294T). Dysregulated transcriptome and metabolome in cell models expressing WT and MUT SIK1 confirmed the pathogenicity of the mutation. Specifically, we found MEF2C target genes, certain epilepsy causing genes and metabolites are dysregulated by SIK1 mutation. We found MEF2C target genes, certain epilepsy causing genes and metabolites are dysregulated by SIK1 mutation. Our finding further expanded the disease spectrum and provided novel mechanistic insights of DEE30.

Comparison of lipid deposition of intramuscular preadipocytes in Tan sheep co-cultured with satellite cells or alone.

The purpose of this study was to investigate the effect of the skeletal muscle satellite cells (SMSCs) on the lipid deposition of the intramuscular preadipocytes (IMPs) in a co-culture system of the Tan sheep cells. The SMSCs and IMPs from Tan sheep were separated and cultured. After the two kinds of cells were separated and cultured, they were inoculated onto a transwell cell chamber co-culture plate for co-cultivation. When the cell density reached more than 90%, the cells were induced to differentiate. After the induction of the SMSCs differentiation for 8 days, the level of the IMPs differentiation and the expression levels of the differentiation marker genes and the key enzymes of the lipid metabolism were assessed. The results showed that the number and area of the lipid droplets in the IMPs in the co-culture system were significantly reduced compared to those in the IMPs culture alone (p < 0.05). Meanwhile, the expression levels of the PPARγ, c/EBPα, ACC, FAS mRNA in the IMPs were significantly decreased (p < 0.05); the expression level of aP2 mRNA was decreased, but the difference was not significant (p > 0.05).These findings indicate that the SMSCs of the Tan sheep in the co-culture system inhibited the lipid deposition by the IMPs.

Metabolic expression profiling stratifies diffuse lower-grade glioma into three distinct tumour subtypes.

BACKGROUND: Lower-grade gliomas (LGGs) show highly metabolic heterogeneity and adaptability. To develop effective therapeutic strategies targeting metabolic processes, it is necessary to identify metabolic differences and define metabolic subtypes. Here, we aimed to develop a classification system based on metabolic gene expression profile in LGGs. METHODS: The metabolic gene profile of 402 diffuse LGGs from the Cancer Genome Atlas (TCGA) was used for consensus clustering to determine robust clusters of patients, and the reproducibility of the classification system was evaluated in three Chinese Glioma Genome Atlas (CGGA) cohorts. Then, the metadata set for clinical characteristics, immune infiltration, metabolic signatures and somatic alterations was integrated to characterise the features of each subtype. RESULTS: We successfully identified and validated three highly distinct metabolic subtypes in LGGs. M2 subtype with upregulated carbohydrate, nucleotide and vitamin metabolism correlated with worse prognosis, whereas M1 subtype with upregulated lipid metabolism and immune infiltration showed better outcome. M3 subtype was associated with low metabolic activities and displayed good prognosis. Three metabolic subtypes correlated with diverse somatic alterations. Finally, we developed and validated a metabolic signature with better performance of prognosis prediction. CONCLUSIONS: Our study provides a new classification based on metabolic gene profile and highlights the metabolic heterogeneity within LGGs.

GXYLT2 accelerates cell growth and migration by regulating the Notch pathway in human cancer cells.

Glucoside xylosyltransferase2 (GXYLT2), a member of the human α-1,3-D-xylosyltransferases, functions to modify the first xylose to the O-Glucose residue on epidermal growth factor (EGF) repeats of Notch receptors. It is well-established that the Notch signaling pathway plays a critical role in proper development and homeostasis. However, the regulatory role of EGF xylosylation in Notch signaling and different cell activities in human cells remains unknown. In this study, we showed that knockdown of GXYLT2 suppressed human cell proliferation and induced G1/S phase cell cycle arrest. GXYLT2 downregulation also inhibited cell migration and invasion, whereas the overexpression of GXYLT2 had the opposite effects. Additionally, GXYLT2 activated Notch signaling and promoted the phosphorylation of MAPKs but not PI3K and Akt. Taken together, our findings indicated that GXYLT2 plays an important role in cell activities via regulation of the Notch signaling.

NPMA: A Novel Privacy-Preserving Mutual Authentication in TMIS for Mobile Edge-Cloud Architecture.

Mobile Edge-Cloud Network is a new network structure after fog-cloud computing, where service and data computing are scattered in the most logical, nearby and efficient place. It provides better services than fog-cloud computing with better performance in reasonably low cost way and allows users to eliminate numerous limitations inherent in fog-cloud computing, although it inherits those security-privacy issues from fog-cloud computing. A novel privacy-preserving mutual authentication in TMIS for mobile Edge-Cloud architecture (abbreviated to NPMA) is constructed in this paper. NPMA scheme not only mitigates some weaknesses of fog-cloud computing, but has other advantages. First, NPMA scheme supports patients(edge-servers) anonymity and forward-backward untraceability (traceability, when needed), since their identities are hidden in two distinct dynamic anonyms and a static one and only the trusted center can recover their real identities, when needed. Second, each edge-server shares a secret value, which realizes authentication with extremely low computional cost in authentication phase. Finally, NPMA scheme is proven safely against passive and active attacks under elliptic curve computable Diffie-Hellman problem (ECDHP) assumption in random oracle model. Hence, it achieves the required security properties and outperforms prior approaches in terms of energy and computational costs.

Nop-7-associated 2 (NSA2) is required for ribosome biogenesis and protein synthesis.

Ribosome biogenesis is a fundamental cellular process and occurs mainly in the nucleolus in eukaryotes. The process is exceptionally complex and highly regulated by numerous ribosomal and non-ribosomal factors. A recent discovery strengthened the link between ribosome biogenesis and malignant transformation. Here, we determined that Nop-7-associated 2 (NSA2) is a nucleolar protein required for ribosome biogenesis. NSA2 knockdown reduced the rate of rRNA synthesis, diminishing the 60S ribosomal subunit. Moreover, we demonstrated that depletion of NSA2 suppressed protein synthesis. To investigate the signaling pathway affected by NSA2, NSA2 was depleted, which triggered the inactivation of the mTOR signaling pathway. Taken together, our findings reveal a novel function of NSA2 and provide insight into the regulation of ribosome biogenesis by NSA2.

CDAKA: A Provably-Secure Heterogeneous Cross-Domain Authenticated Key Agreement Protocol with Symptoms-Matching in TMIS.

Telecare Medical Information System (TMIS) provides the flexible and convenient e-health care. It helps the patients to gain health monitoring information and provides patients to share their experience wirelessly. Traditional authentication and key agreement (AKA) protocols in TMIS are mostly considered in same-domain environment. However, future generation network may integrate various of wireless mesh networks under various domain. What's more, patients heterogeneous cross-domain service has become an inevitable trend. However, there is still no heterogeneous cross-domain authenticated protocol between PKI-domain and IBC-domain in TMIS. In this paper, we propose a heterogeneous cross-domain AKA protocol with symptoms-matching in TMIS (short for CDAKA). It not only keeps good security features, but also truly provides patients' anonymity to protect sensitive information from illegal interception. It still provides patients in two different domains to share their experience, broaden their understanding of illness by using their mobile device freely. Besides, it can realize AKA with extremely low computing cost and communication cost. What's more, it is proved to be secure against known possible attacks under the Elliptic Curve Computable Diffie-Hellman problem (ECDHP) assumption in the random oracle model. Hence, these features make CDAKA protocol very suitable for mobile application scenarios, where resource is severely constrained and security is particularly concerned.

LncRNA H19 promotes the differentiation of bovine skeletal muscle satellite cells by suppressing Sirt1/FoxO1.

BACKGROUND: H19 is a well-characterized Long noncoding RNA (lncRNA) that has been proven to promote myoblast differentiation in humans and mice. However, its mechanism of action is still not fully interpreted. METHODS: Using RT-qPCR, we examined H19 RNA levels in various tissues from 1-week, 1-month, 6-month and 36-month old male cattle (i.e., newborn, infant, young and adult). The protein and mRNA levels of MyoG, MyHC, Sirt1 and FoxO1 in the satellite and C2C12 cells with an H19 silencing or overexpression vector were respectively detected using western blot and real-time qPCR. RESULTS: H19 was highly expressed in skeletal muscle at all the studied ages. High expression of H19 was required for the differentiation of bovine satellite cells. Knockdown of H19 caused a remarkable increase in the myoblast-inhibitory genes Sirt1/FoxO1, suggesting that H19 suppresses Sirt1/FoxO1 expression during myogenesis. Western blotting analysis of co-transfection of Sirt1 or FoxO1 expression vectors with pcDNA-H19 indicated that Sirt1/FoxO1 overexpression neutralized the promotion of myoblast differentiation through transfection of pcDNA-H19. CONCLUSION: H19 promoted the differentiation of bovine skeletal muscle satellite cells by suppressing Sirt1/FoxO1.

A multipopulation coevolutionary strategy for multiobjective immune algorithm.

How to maintain the population diversity is an important issue in designing a multiobjective evolutionary algorithm. This paper presents an enhanced nondominated neighbor-based immune algorithm in which a multipopulation coevolutionary strategy is introduced for improving the population diversity. In the proposed algorithm, subpopulations evolve independently; thus the unique characteristics of each subpopulation can be effectively maintained, and the diversity of the entire population is effectively increased. Besides, the dynamic information of multiple subpopulations is obtained with the help of the designed cooperation operator which reflects a mutually beneficial relationship among subpopulations. Subpopulations gain the opportunity to exchange information, thereby expanding the search range of the entire population. Subpopulations make use of the reference experience from each other, thereby improving the efficiency of evolutionary search. Compared with several state-of-the-art multiobjective evolutionary algorithms on well-known and frequently used multiobjective and many-objective problems, the proposed algorithm achieves comparable results in terms of convergence, diversity metrics, and running time on most test problems.

Decomposition-based multiobjective evolutionary algorithm for community detection in dynamic social networks.

Community structure is one of the most important properties in social networks. In dynamic networks, there are two conflicting criteria that need to be considered. One is the snapshot quality, which evaluates the quality of the community partitions at the current time step. The other is the temporal cost, which evaluates the difference between communities at different time steps. In this paper, we propose a decomposition-based multiobjective community detection algorithm to simultaneously optimize these two objectives to reveal community structure and its evolution in dynamic networks. It employs the framework of multiobjective evolutionary algorithm based on decomposition to simultaneously optimize the modularity and normalized mutual information, which quantitatively measure the quality of the community partitions and temporal cost, respectively. A local search strategy dealing with the problem-specific knowledge is incorporated to improve the effectiveness of the new algorithm. Experiments on computer-generated and real-world networks demonstrate that the proposed algorithm can not only find community structure and capture community evolution more accurately, but also be steadier than the two compared algorithms.

A bioactive calcium silicate nanowire-containing hydrogel for organoid formation and functionalization.

Organoids, which are 3D multicellular constructs, have garnered significant attention in recent years. Existing organoid culture methods predominantly utilize natural and synthetic polymeric hydrogels. This study explored the potential of a composite hydrogel mainly consisting of calcium silicate (CS) nanowires and methacrylated gelatin (GelMA) as a substrate for organoid formation and functionalization, specifically for intestinal and liver organoids. Furthermore, the research delved into the mechanisms by which CS nanowires promote the structure formation and development of organoids. It was discovered that CS nanowires can influence the stiffness of the hydrogel, thereby regulating the expression of the mechanosensory factor yes-associated protein (YAP). Additionally, the bioactive ions released by CS nanowires in the culture medium could accelerate Wnt/ß-catenin signaling, further stimulating organoid development. Moreover, bioactive ions were found to enhance the nutrient absorption and ATP metabolic activity of intestinal organoids. Overall, the CS/GelMA composite hydrogel proves to be a promising substrate for organoid formation and development. This research suggested that inorganic biomaterials hold significant potential in organoid research, offering bioactivities, biosafety, and cost-effectiveness.

Lycium barbarum polysaccharide reverses drug resistance in oxaliplatin-resistant colon cancer cells by inhibiting PI3K/AKT-dependent phosphomannose isomerase.

Objective: Here, we aimed to explore the effect of LBP in combination with Oxaliplatin (OXA) on reversing drug resistance in colon cancer cells through in vitro and in vivo experiments. We also aimed to explore the possible mechanism underlying this effect. Finally, we aimed to determine potential targets of Lycium barbarum polysaccharide (LBP) in colon cancer (CC) through network pharmacology and molecular docking. Methods: The invasion ability of colon cancer cells was assessed using the invasion assay. The migration ability of these cells was assessed using the migration assay and wound healing assay. Cell cycle analysis was carried out using flow cytometry. The expression levels of phosphomannose isomerase (PMI) and ATP-binding cassette transport protein of G2 (ABCG2) proteins were determined using immunofluorescence and western blotting. The expression levels of phosphatidylinositol3-kinase (PI3K), protein kinase B (AKT), B-cell lymphoma 2 (Bcl-2), and BCL2-Associated X (Bax) were determined using western blotting. Forty BALB/c nude mice purchased from Weitong Lihua, Beijing, for the in vivo analyses. The mice were randomly divided into eight groups. They were administered HCT116 and HCT116-OXR cells to prepare colon cancer xenograft models and then treated with PBS, LBP (50 mg/kg), OXA (10 mg/kg), or LBP + OXA (50 mg/kg + 10 mg/kg). The tumor weight and volume of treated model mice were measured, and organ toxicity was evaluated using hematoxylin and eosin staining. The expression levels of PMI, ABCG2, PI3K, and AKT proteins were then assessed using immunohistochemistry. Moreover, PMI and ABCG2 expression levels were analyzed using immunofluorescence and western blotting. The active components and possible targets of LBP in colon cancer were explored using in silico analysis. GeneCards was used to identify CC targets, and an online Venn analysis tool was used to determine intersection targets between these and LBP active components. The PPI network for intersection target protein interactions and the PPI network for interactions between the intersection target proteins and PMI was built using STRING and Cytoscape. To obtain putative targets of LBP in CC, we performed GO function enrichment and KEGG pathway enrichment analyses. Results: Compared with the HCT116-OXR blank treatment group, both invasion and migration abilities of HCT116-OXR cells were inhibited in the LBP + OXA (2.5 mg/mL LBP, 10 µΜ OXA) group (p < 0.05). Cells in the LBP + OXA (2.5 mg/mL LBP, 10 µΜ OXA) group were found to arrest in the G1 phase of the cell cycle. Knockdown of PMI was found to downregulate PI3K, AKT, and Bcl-2 (p < 0.05), while it was found to upregulate Bax (p < 0.05). After treatment with L. barbarum polysaccharide, 40 colon cancer subcutaneous tumor models showed a decrease in tumor size. There was no difference in the liver index after LBP treatment (p > 0.05). However, the spleen index decreased in the OXA and LBP + OXA groups (p < 0.05), possibly as a side effect of oxaliplatin. Immunohistochemistry, immunofluorescence, and western blotting showed that LBP + OXA treatment decreased PMI and ABCG2 expression levels (p < 0.05). Moreover, immunohistochemistry showed that LBP + OXA treatment decreased the expression levels of PI3K and AKT (p < 0.05). Network pharmacology analysis revealed 45 active LBP components, including carotenoids, phenylpropanoids, quercetin, xanthophylls, and other polyphenols. It also revealed 146 therapeutic targets of LBP, including AKT, SRC, EGFR, HRAS, STAT3, and MAPK3. KEGG pathway enrichment analysis showed that the LBP target proteins were enriched in pathways, including cancer-related signaling pathways, PI3K/AKT signaling pathway, and IL-17 signaling pathways. Finally, molecular docking experiments revealed that the active LBP components bind well with ABCG2 and PMI. conclusion: Our in vitro experiments showed that PMI knockdown downregulated PI3K, AKT, and Bcl-2 and upregulated Bax. This finding confirms that PMI plays a role in drug resistance by regulating the PI3K/AKT pathway and lays a foundation to study the mechanism underlying the reversal of colon cancer cell drug resistance by the combination of LBP and OXA. Our in vivo experiments showed that LBP combined with oxaliplatin could inhibit tumor growth. LBP showed no hepatic or splenic toxicity. LBP combined with oxaliplatin could downregulate the expression levels of PMI, ABCG2, PI3K, and AKT; it may thus have positive significance for the treatment of advanced metastatic colon cancer. Our network pharmacology analysis revealed the core targets of LBP in the treatment of CC as well as the pathways they are enriched in. It further verified the results of our in vitro and in vivo experiments, showing the involvement of multi-component, multi-target, and multi-pathway synergism in the drug-reversing effect of LBP in CC. Overall, the findings of the present study provide new avenues for the future clinical treatment of CC.

Carbon Dot-Mediated Photodynamic Treatment Improves the Quality Attributes of Post-Harvest Goji Berries (Lycium barbarum L.) via Regulating the Antioxidant System.

Carbon dots (CDs) have been proposed as photosensitizers in photodynamic treatment (PDT), owing to their excellent biological attributes and budding fruit preservation applications. In the present study, CDs (4.66 nm) were synthesized for photodynamic treatment to improve the quality attributes in post-harvest goji berries. The prepared CDs extended the storage time of the post-harvest goji berries by 9 d. The CD-mediated PDT postponed the hardness and decay index loss, reduced the formation of malondialdehyde (MDA), hydrogen peroxide (H2O2), and superoxide anion (O2•-) significantly, and delayed the loss of vital nutrients like the total protein, phenols, and flavonoids. The CD-mediated PDT improved the catalase (CAT), ascorbate peroxidase (APX), peroxidase (POD), phenylalanine ammonia-lyase (PAL), glutathione reductase (GR), and superoxide dismutase (SOD) activities, but did not improve polyphenol oxidase (PPO) activity. In addition, The CD-mediated PDT induced the accumulation of ascorbic acid (ASA) and glutathione (GSH). Overall, a CD-mediated PDT could extend the storage time and augment the quality attributes in post-harvest fresh goji berries by regulating the antioxidant system.

Brain-Inspired Learning, Perception, and Cognition: A Comprehensive Review.

The progress of brain cognition and learning mechanisms has provided new inspiration for the next generation of artificial intelligence (AI) and provided the biological basis for the establishment of new models and methods. Brain science can effectively improve the intelligence of existing models and systems. Compared with other reviews, this article provides a comprehensive review of brain-inspired deep learning algorithms for learning, perception, and cognition from microscopic, mesoscopic, macroscopic, and super-macroscopic perspectives. First, this article introduces the brain cognition mechanism. Then, it summarizes the existing studies on brain-inspired learning and modeling from the perspectives of neural structure, cognitive module, learning mechanism, and behavioral characteristics. Next, this article introduces the potential learning directions of brain-inspired learning from four aspects: perception, cognition, understanding, and decision-making. Finally, the top-ten open problems that brain-inspired learning, perception, and cognition currently face are summarized, and the next generation of AI technology has been prospected. This work intends to provide a quick overview of the research on brain-inspired AI algorithms and to motivate future research by illuminating the latest developments in brain science.

Improving the classification of multiple sclerosis and cerebral small vessel disease with interpretable transfer attention neural network.

As an autoimmune-mediated inflammatory demyelinating disease of the central nervous system, multiple sclerosis (MS) is often confused with cerebral small vessel disease (cSVD), which is a regional pathological change in brain tissue with unknown pathogenesis. This is due to their similar clinical presentations and imaging manifestations. That misdiagnosis can significantly increase the occurrence of adverse events. Delayed or incorrect treatment is one of the most important causes of MS progression. Therefore, the development of a practical diagnostic imaging aid could significantly reduce the risk of misdiagnosis and improve patient prognosis. We propose an interpretable deep learning (DL) model that differentiates MS and cSVD using T2-weighted fluid-attenuated inversion recovery (FLAIR) images. Transfer learning (TL) was utilized to extract features from the ImageNet dataset. This pioneering model marks the first of its kind in neuroimaging, showing great potential in enhancing differential diagnostic capabilities within the field of neurological disorders. Our model extracts the texture features of the images and achieves more robust feature learning through two attention modules. The attention maps provided by the attention modules provide model interpretation to validate model learning and reveal more information to physicians. Finally, the proposed model is trained end-to-end using focal loss to reduce the influence of class imbalance. The model was validated using clinically diagnosed MS (n=112) and cSVD (n=321) patients from the Beijing Tiantan Hospital. The performance of the proposed model was better than that of two commonly used DL approaches, with a mean balanced accuracy of 86.06 % and a mean area under the receiver operating characteristic curve of 98.78 %. Moreover, the generated attention heat maps showed that the proposed model could focus on the lesion signatures in the image. The proposed model provides a practical diagnostic imaging aid for the use of routinely available imaging techniques such as magnetic resonance imaging to classify MS and cSVD by linking DL to human brain disease. We anticipate a substantial improvement in accurately distinguishing between various neurological conditions through this novel model.

A multipopulation PSO based memetic algorithm for permutation flow shop scheduling.

The permutation flow shop scheduling problem (PFSSP) is part of production scheduling, which belongs to the hardest combinatorial optimization problem. In this paper, a multipopulation particle swarm optimization (PSO) based memetic algorithm (MPSOMA) is proposed in this paper. In the proposed algorithm, the whole particle swarm population is divided into three subpopulations in which each particle evolves itself by the standard PSO and then updates each subpopulation by using different local search schemes such as variable neighborhood search (VNS) and individual improvement scheme (IIS). Then, the best particle of each subpopulation is selected to construct a probabilistic model by using estimation of distribution algorithm (EDA) and three particles are sampled from the probabilistic model to update the worst individual in each subpopulation. The best particle in the entire particle swarm is used to update the global optimal solution. The proposed MPSOMA is compared with two recently proposed algorithms, namely, PSO based memetic algorithm (PSOMA) and hybrid particle swarm optimization with estimation of distribution algorithm (PSOEDA), on 29 well-known PFFSPs taken from OR-library, and the experimental results show that it is an effective approach for the PFFSP.

EGST: Enhanced Geometric Structure Transformer for Point Cloud Registration.

We explore the effect of geometric structure descriptors on extracting reliable correspondences and obtaining accurate registration for point cloud registration. The point cloud registration task involves the estimation of rigid transformation motion in unorganized point cloud, hence it is crucial to capture the contextual features of the geometric structure in point cloud. Recent coordinates-only methods ignore numerous geometric information in the point cloud which weaken ability to express the global context. We propose Enhanced Geometric Structure Transformer to learn enhanced contextual features of the geometric structure in point cloud and model the structure consistency between point clouds for extracting reliable correspondences, which encodes three explicit enhanced geometric structures and provides significant cues for point cloud registration. More importantly, we report empirical results that Enhanced Geometric Structure Transformer can learn meaningful geometric structure features using none of the following: (i) explicit positional embeddings, (ii) additional feature exchange module such as cross-attention, which can simplify network structure compared with plain Transformer. Extensive experiments on the synthetic dataset and real-world datasets illustrate that our method can achieve competitive results.