Knowledge-reinforced explainable next basket recommendation.

The next basket recommendation task aims to predict the items in the user's next basket by modeling the user's basket sequence. Existing next basket recommendations focus on improving recommendation performance, and most of these methods are black-box models, ignoring the importance of providing explanations to improve user satisfaction. Furthermore, most next basket recommendation methods are designed for consumer users, and few methods are proposed for business user characteristics. To address the above problems, we propose a Knowledge Reinforced Explainable Next Basket Recommendation (KRE-NBR). Specifically, we construct a basket-based knowledge graph and obtain pretrained embeddings of entities that contain rich information of the knowledge graph. To obtain high-quality user predictive vectors, we fuse user pretrained embeddings, user basket sequence level embeddings, and user repurchase embeddings. One highlight of the user repurchase embeddings is that they are able to model business user repurchase behavior. To make the results of next basket recommendations explainable, we use reinforcement learning for path reasoning to find the items recommended in the next basket and generate recommendation explanations at the same time. To the best of our knowledge, this is the first work to provide recommendation explanations for next basket recommendations. Extensive experiments on real datasets show that the recommendation performance of our proposed approach outperforms several state-of-the-art baselines.

Deep learning-based image analysis predicts PD-L1 status from 18F-FDG PET/CT images in non-small-cell lung cancer.

Background: There is still a lack of clinically validated biomarkers to screen lung cancer patients suitable for programmed dead cell-1 (PD-1)/programmed dead cell receptor-1 (PD-L1) immunotherapy. Detection of PD-L1 expression is invasively operated, and some PD-L1-negative patients can also benefit from immunotherapy; thus, the joint modeling of both deep learning images and clinical features was used to improve the prediction performance of PD-L1 expression in non-small cell lung cancer (NSCLC). Methods: Retrospective collection of 101 patients diagnosed with pathology in our hospital who underwent 18F FDG PET/CT scans, with lung cancer tissue Tumor Propulsion Score (TPS) ≥1% as a positive expression. Lesions were extracted after preprocessing PET/CT images, and using deep learning 3D DenseNet121 to learn lesions in PET, CT, and PET/CT images, 1,024 fully connected features were extracted; clinical features (age, gender, smoking/no smoking history, lesion diameter, lesion volume, maximum standard uptake value of lesions [SUVmax], mean standard uptake value of lesions [SUVmean], total lesion glycolysis [TLG]) were combined for joint modeling based on the structured data Category Embedding Model. Results: Area under a receiver operating characteristic (ROC) curve (AUC) and accuracy of predicting PD-L1 positive for PET, CT, and PET/CT test groups were 0.814 ± 0.0152, 0.7212 ± 0.0861, and 0.90 ± 0.0605, 0.806 ± 0.023, 0.70 ± 0.074, and 0.950 ± 0.0250, respectively. After joint clinical feature modeling, the AUC and accuracy of predicting PD-L1 positive for PET/CT were 0.96 ± 0.00905 and 0.950 ± 0.0250, respectively. Conclusion: This study combines the features of 18F-FDG PET/CT images with clinical features using deep learning to predict the expression of PD-L1 in NSCLC, suggesting that 18F-FDG PET/CT images can be conducted as biomarkers for PD-L1 expression.

Clinical usefulness of the baby vision test in young children and its correlation with the Snellen chart.

AIM: To investigate the efficacy of a new visual acuity (VA) screening method, the baby vision test for young children. METHODS: A total 105 eyes of 65 children aged 2-8y were included in the study. Acuity testing was conducted using a standardized recognition acuity chart (Snellen visual chart: at 3 m) and the baby vision model assessment. The baby vision device includes a screen, a near infrared camera and a computer. Children were seated at a measured distance of 33-40 cm from a display for testing. VA was estimated according to the highest resolution the children could follow. Decimal VA data were converted to logarithm of the minimum angle of resolution (logMAR) for statistical analysis. The VA results for each child were recorded and analyzed for consistency. RESULTS: The mean VA measured using the Snellen visual chart was 0.62±0.32, and that assessed using the baby vision test was 0.66±0.27. The 95% limit of agreement was -0.609 to 0.695, with 95.2% (100/105) plots within the 95% limits of agreement. VA values of the baby vision test were significantly correlated with those of the Snellen chart (R=0.274, P=0.005). CONCLUSION: The baby vision test can be used as a relatively reliable method for estimating VA in young children. This new acuity assessment might be a valid predictor of optotype-measured acuity later in preverbal children.

Efficacy and Mechanism Study of 6S-5-Methyltetrahydrofolate-Calcium Against Telencephalon Infarction Injury in Zebrafish Model of Ischemic Stroke.

Ischemic stroke is a heterogeneous brain injury with complex pathophysiology and it is also a time sensitive neurological injury disease. At present, the treatment options for ischemic stroke are still limited. 6S-5-methyltetrahydrofolate-calcium (MTHF-Ca) is the calcium salt of the predominant form of dietary folate in circulation. MTHF-Ca has potential neuroprotective effect on neurocytes, but whether it can be used for ischemic stroke treatment remains unknown. We established zebrafish ischemic stroke model through photothrombotic method to evaluate the protective effect of MTHF-Ca on the ischemic brain injury of zebrafish. We demonstrated that MTHF-Ca reduced the brain damage by reducing motor dysfunction and neurobehavioral defects of zebrafish with telencephalon infarction injury. MTHF-Ca counteracted oxidative damages after Tel injury by increasing the activities of GSH-Px and SOD and decreasing the content of MDA. RNA-seq and RT-qPCR results showed that MTHF-Ca played a neuroprotective role by alleviating neuroinflammation, inhibiting blood coagulation, and neuronal apoptosis processes. Overall, we have demonstrated that MTHF-Ca has neuroprotective effect in ischemic stroke and can be used as a potential treatment for ischemic stroke.

Development of a human glioblastoma model using humanized DRAG mice for immunotherapy.

Glioblastoma (GBM) is the most common and lethal primary brain tumor. The development of alternative humanized mouse models with fully functional human immune cells will potentially accelerate the progress of GBM immunotherapy. We successfully generated humanized DRAG (NOD.Rag1KO.IL2RγcKO) mouse model by transplantation of human DR4+ hematopoietic stem cells (hHSCs), and effectively grafted GBM patient-derived tumorsphere cells to form xenografted tumors intracranially. The engrafted tumors recapitulated the pathological features and the immune cell composition of human GBM. Administration of anti-human PD-1 antibodies in these tumor-bearing humanized DRAG mice decreased the major tumor-infiltrating immunosuppressive cell populations, including CD4+PD-1+ and CD8+PD-1+ T cells, CD11b+CD14+HLA-DR+ macrophages, CD11b+CD14+HLA-DR-CD15- and CD11b+CD14-CD15+ myeloid-derived suppressor cells, indicating the humanized DRAG mice as a useful model to test the efficacy of GBM immunotherapy. Taken together, these results suggest that the humanized DRAG mouse model is a reliable preclinical platform for studying brain cancer immunotherapy and beyond.

Acid-Responsive Aggregation of Gold Nanoparticles for the Photothermal Treatment of Bacterial Infections.

Photothermal therapy (PTT) is considered to be one of the promising methods to combat pathogenic bacteria. However, traditional PTT is prone to generate undesired temperature increase to surrounding normal tissues, which limits the application of PTT. Herein, an acid-responsive PTT system (Au nanoparticles system: AuNPs-S) was constructed based on the photothermal feature of spherical gold nanoparticles (AuNPs) and the low pH of the bacterial infected site. AuNPs-S is composed of two kinds of AuNPs: AuNPs modified with Asp-Asp-Asp-Asp-Asp-Cys (peptide A) were denoted as AuNPs-A; AuNPs modified with 2,3-dimethylmaleic anhydride (DA) grafted Lys-Gly-Gly-Lys-Gly-Gly-Lys-Cys (peptide B) were denoted as AuNPs-B/DA. AuNPs-B/DA with an acid-responsive moiety showed a charge-convertible feature. The negatively charged AuNPs-B/DA became positively charged AuNPs-B at low pH, aggregating with the negatively charged AuNPs-A via an electrostatic interaction, reaching the threshold to the interparticle plasmonic coupling effect among AuNPs, thereby killing bacteria precisely under the irradiation of near-infrared (NIR) light through the elevated temperature at the targeted area. This acid-responsive PTT strategy supplies an excellent mode for combating bacterial infections with no vital damage to normal tissues.

Multi-threshold image segmentation of 2D OTSU inland ships based on improved genetic algorithm.

Waterway transportation is a crucial mode of transportation, but ensuring navigational safety in waterways requires effective guidance of ships by the Water Resources Bureau. However, supervisors may only be interested in the ship portion of a complex image and need to quickly obtain relevant ship information. Therefore, this paper proposes a two-dimensional OTSU inland ships multi-threshold image segmentation algorithm based on the improved genetic algorithm. The improved algorithm enhances search accuracy and efficiency, improving image thresholding accuracy and reducing algorithm time complexity. Experimental verification shows the algorithm has excellent evaluation indexes and can achieve real-time segmentation of complex images. This method can not only address the challenges of complex inland navigation environments and difficult acquisition of target data sets, but also be applied to optimization problems in other fields by combining various metaheuristic algorithms.

Broadband Waterborne Multiphase Pentamode Metastructure with Simultaneous Wavefront Manipulation and Energy Absorption Capabilities.

Acoustic metastructures are artificial structures which can manipulate the wavefront in sub-wavelength dimensions, and previously proposed acoustic metastructures have been mostly realized with single materials. An acoustic metastructure with composite structure is proposed for underwater acoustic stealth considering both wavefront manipulation and sound absorption. The unit cells of the metastructure are composed of a metallic supporting lattice, interconnecting polymer materials and mass balancing columns. With the gradual modulations of equivalent physical properties along the horizontal direction of metastructure, the incident acoustic wave is reflected to other directions. Meanwhile, the polymer material inside the unit cells will dissipate the acoustic wave energy due to inherent damping properties. With the simultaneous modulations of reflected wave direction and scattering acoustic amplitude, significant improvement of the underwater stealth effect is achieved. Compared with single-phase metastructure, the Far-Field Sound Pressure Level (FFSPL) of multiphase metastructure decreases by 4.82 dB within the frequency range of 3 kHz~30 kHz. The linearized mean stress for multiphase metastructure is only 1/3 of that of single-phase metastructure due to it having much thicker struts and much more uniform stress distribution under the same hydrostatic pressure. The proposed composite structure possesses potential applications due to its acceptable thickness (80 mm) and low equivalent density (1100 kg/m3).

Repeatability and reproducibility of anterior lens zonule length measurement using ArcScan insight 100 very high-frequency ultrasound.

OBJECTIVES: This study aimed to evaluate the intra-examiner repeatability and inter-examiner reproducibility in lens zonular length measurements using very high-frequency digital ultrasound (Insight 100). METHODS: Two examiners performed ultrasound imaging independently in each subject. The length of temporal and nasal zonules were then measured with a built-in software. Coefficient of variations (CVs) of the three repeated measurements were used to determine intra-examiner variances. Inter-examiner reproducibility was evaluated using intraclass correlation coefficients (ICCs) and the Bland-Altman method. RESULTS: 40 eyes of 40 subjects (14male and 26female; mean age 23.9 ± 2.4 years) were included in the study. The CVs for intra-examiner measurement were 2.74% temporally and 4.32% nasally for Examiner 1, and were 1.96% temporally and 1.75% nasally for Examiner 2. For inter-examiner reproducibility, all ICCs were above 0.9. However, there were significant differences between the two examiners in temporal zonular length measurements (p = 0.001), and the differences mainly came from measuring the zonular length manually (p = 0.001) rather than recording images (p = 0.480). No significant differences were found between two measurements by the same examiner after one month (all p > 0.05, all ICCs > 0.8). CONCLUSION: The Insight 100 device can be used to measure the length of anterior lens zonule with relatively good repeatability and reproducibility. CLINICAL TRIAL REGISTRATION: www.clinicaltrials.gov identifier is NCT05657951.

Adult mice with noise-induced hearing loss exhibited temporal ordering memory deficits accompanied by microglia-associated neuroplastic changes in the medial prefrontal cortex.

Acquired peripheral hearing loss in midlife is considered the primary modifiable risk factor for dementia, while the underlying pathological mechanism remains poorly understood. Excessive noise exposure is the most common cause of acquired peripheral hearing loss in modern society. This study was designed to investigate the impact of noise-induced hearing loss (NIHL) on cognition, with a focus on the medial prefrontal cortex (mPFC), a brain region that is involved in both auditory and cognitive processes and is highly affected in patients with cognitive impairment. Adult C57BL/6 J mice were randomly assigned to a control group and seven noise groups: 0HPN, 12HPN, 1DPN, 3DPN, 7DPN, 14DPN, and 28DPN, which were exposed to broadband noise at a 123 dB sound pressure level (SPL) for 2 h and sacrificed immediately (0 h), 12 h, or 1, 3, 7, 14, or 28 days post-noise exposure (HPN, DPN), respectively. Hearing assessment, behavioral tests, and neuromorphological studies in the mPFC were performed in control and 28DPN mice. All experimental animals were included in the time-course analysis of serum corticosterone (CORT) levels and mPFC microglial morphology. The results illustrated that noise exposure induced early-onset transient serum CORT elevation and permanent moderate-to-severe hearing loss in mice. 28DPN mice, in which permanent NIHL has been verified, exhibited impaired performance in temporal order object recognition tasks concomitant with reduced structural complexity of mPFC pyramidal neurons. The time-course immunohistochemical analysis in the mPFC revealed significantly higher morphological microglial activation at 14 and 28 DPN, preceded by a remarkably higher amount of microglial engulfed postsynaptic marker PSD95 at 7 DPN. Additionally, lipid accumulation in microglia was observed in 7DPN, 14DPN and 28DPN mice, suggesting a driving role of lipid handling deficits following excessive phagocytosis of synaptic elements in delayed and sustained microglial abnormalities. These findings provide fundamentally novel information concerning mPFC-related cognitive impairment in mice with NIHL and empirical evidence suggesting the involvement of microglial malfunction in the mPFC neurodegenerative consequences of NIHL.

Evaluation of optic nerve head vessels density changes after phacoemulsification cataract surgery using optical coherence tomography angiography.

AIM: To evaluate optic nerve head (ONH) vessel density (VD) changes after cataract surgery using optical coherence tomography angiography (OCTA). METHODS: This was a prospective observational study. Thirty-four eyes with mild/moderate cataracts were included. ONH scans were obtained before and 3mo after cataract surgery using OCTA. Radial peripapillary capillary (RPC) density, all VD, large VD and retinal nerve fiber layer thickness (RNFLT) in total disc, inside disc, and different peripapillary sectors were assessed and analyzed. Image quality score (QS), fundus photography grading and best-corrected visual acuity (BCVA) were also collected, and correlation analyses were performed between VD change and these parameters. RESULTS: Compared with baseline, both RPC and all VD increased in inside disc area 3mo postoperatively (from 47.5%±5.3% to 50.2%±3.7%, and from 57.87%±4.30% to 60.47%±3.10%, all P<0.001), but no differences were observed in peripapillary area. However, large VD increased from 5.63%±0.77% to 6.47%±0.72% in peripapillary ONH region (P<0.001). RPC decreased in inferior and superior peripapillary ONH parts (P=0.019, <0.001 respectively). There were obvious negative correlations between RPC change and large VD change in inside disc, superior-hemi, and inferior-hemi (r=-0.419, -0.370, and -0.439, P=0.017, 0.044, and 0.015, respectively). No correlations were found between VD change and other parameters including QS change, fundus photography grading, postoperative BCVA, and postoperative peripapillary RNFLT. CONCLUSION: RPC density and all VD in the inside disc ONH region increase 3mo after surgery in patients with mild to moderate cataract. No obvious VD changes are found in peripapillary area postoperatively.

Effects of arbuscular mycorrhizae and extraradical mycelium of subtropical tree species on soil nitrogen mineralization and enzyme activities.

Through symbiosis with plants, arbuscular mycorrhizal (AM) fungi effectively improve the availability of soil nitrogen (N). However, the mechanism through which AM and associated extraradical mycelium affect soil N mineralization remains unknow. We carried out an in situ soil culture experiment by using in-growth cores in plantations of three subtropical tree species, Cunninghamia lanceolata, Schima superba, and Liquidambar formosana. We measured soil physical and chemical properties, net N mineralization rate, and the activities of four kinds of hydrolase (leucine aminopeptidase (LAP), ß-1,4-N-acetylglucosaminidase (NAG), ß-1,4-glucosidase (ßG), cellobiohydrolase (CB)) and two kinds of oxidases (polyphenol oxidase (POX) and peroxidase (PER)) involved in soil organic matter (SOM) mineralization in treatments of mycorrhiza (with absorbing roots and hyphae), hyphae (hyphae only), and control (mycorrhiza-free). The results showed that mycorrhizal treatments significantly affected soil total carbon and pH but did not affect N mineralization rates and all enzymatic activities. Tree species significantly affected net ammonification rate, net N mineralization rate and activities of NAG, ßG, CB, POX and PER. The net N mineralization rate and enzyme activities in the C. lanceolata stand were significantly higher than that in monoculture broad-leaved stands of either S. superba or L. formosana. There was no interactive effect of mycorrhizal treatment and tree species on any of soil properties, nor on enzymatic activities or net N mineralization rates. Soil pH was negatively and significantly correlated with five kinds of enzymatic activities except for LAP, while net N mineralization rate significantly correlated with ammonium nitrogen content, available phosphorus content, and the activity level of ßG, CB, POX, and PER. In conclusion, there was no difference in enzymatic activities and N mineralization rates between rhizosphere and hyphosphere soils of three subtropical tree species in the whole growing season. The activity of particular carbon cycle-related enzymes was closely related to soil N mineralization rate. It is suggested that differences in litter quality and root functional traits among different tree species affect soil enzyme activities and N mineralization rates through organic matter inputs and shaping soil condition.

Tumor Niches: Perspectives for Targeted Therapies in Glioblastoma.

Significance: Glioblastoma (GBM), the most common and lethal primary brain tumor with a median survival rate of only 15 months and a 5-year survival rate of only 6.8%, remains largely incurable despite the intensive multimodal treatment of surgical resection and radiochemotherapy. Developing effective new therapies is an unmet need for patients with GBM. Recent Advances: Targeted therapies, such as antiangiogenesis therapy and immunotherapy, show great promise in treating GBM based upon increasing knowledge about brain tumor biology. Single-cell transcriptomics reveals the plasticity, heterogeneity, and dynamics of tumor cells during GBM development and progression. Critical Issues: While antiangiogenesis therapy and immunotherapy have been highly effective in some types of cancer, the disappointing results from clinical trials represent continued challenges in applying these treatments to GBM. Molecular and cellular heterogeneity of GBM is developed temporally and spatially, which profoundly contributes to therapeutic resistance and tumor recurrence. Future Directions: Deciphering mechanisms of tumor heterogeneity and mapping tumor niche trajectories and functions will provide a foundation for the development of more effective therapies for GBM patients. In this review, we discuss five different tumor niches and the intercellular and intracellular communications among these niches, including the perivascular, hypoxic, invasive, immunosuppressive, and glioma-stem cell niches. We also highlight the cellular and molecular biology of these niches and discuss potential strategies to target these tumor niches for GBM therapy. Antioxid. Redox Signal. 39, 904-922.

Protocol to assess the antitumor efficacy of an immunotherapeutic peptide in syngeneic orthotopic glioma mouse models.

Understanding the glioblastoma (GBM) immune microenvironment and development of clinical treatment drugs rely on suitable preclinical GBM models. Here, we present a protocol to establish syngeneic orthotopic glioma mouse models. We also describe the steps to intracranially deliver immunotherapeutic peptides and monitor the treatment response. Finally, we show how to assess the tumor immune microenvironment with treatment outcomes. For complete details on the use and execution of this protocol, please refer to Chen et al. (2021).1.

Suppression of lncRNA OIP5-AS1 Attenuates Apoptosis and Inflammation, and Promotes Proliferation by Mediating miR-25-3p Expression in Lipopolysaccharide-Induced Myocardial Injury.

Purpose: Long non-coding RNAs (LncRNAs) OIP5-AS1 and miR-25-3p play important roles in myocardial injury, whereas their roles in lipopolysaccharide (LPS)-induced myocardial injury remain unknown. The purpose of our study was to investigate the functional mechanisms of OIP5-AS1 and miR-25-3p in LPS-induced myocardial injury. Methods: Rats and H9C2 cells were treated with LPS to establish the model of myocardial injury in vivo and in vitro, respectively. The expression levels of OIP5-AS1 and miR-25-3p were determined by quantitative reverse transcriptase-polymerase chain reaction. Enzyme-linked immunosorbent assay was performed to measure the serum levels of IL-6 and TNF-α. The relationship between OIP5-AS1 and miR-25-3p/NOX4 was determined by luciferase reporter assay and/or RNA immunoprecipitation assay. The apoptosis rate was detected by flow cytometry, and cell viability was detected by 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2-H-tetrazolium bromide assay. Western blot was performed to detect the protein levels of Bax, Bcl-2, caspase3, c-caspase3, NOX4, and p-NF-κB p65/NF-κB p65. Results: OIP5-AS1 was up-regulated, and miR-25-3p was down-regulated in myocardial tissues of LPS-induced rats and LPS-treated H9C2 cells. Knockdown of OIP5-AS1 relieved the myocardial injury in LPS-induced rats. Knockdown of OIP5-AS1 also inhibited the inflammation and apoptosis of myocardial cells in vivo, which was subsequently confirmed by in vitro experiments. In addition, OIP5-AS1 targeted miR-25-3p. MiR-25-3p mimics reversed the effects of OIP5-AS1 overexpression on promoting cell apoptosis and inflammation and on inhibiting cell viability. Besides, miR-25-3p mimics blocked the NOX4/NF-κB signalling pathway in LPS-induced H9C2 cells. Conclusion: Silencing of lncRNA OIP5-AS1 alleviated LPS-induced myocardial injury by regulating miR-25-3p.

SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing.

Over the recent years, WiFi sensing has been rapidly developed for privacy-preserving, ubiquitous human-sensing applications, enabled by signal processing and deep-learning methods. However, a comprehensive public benchmark for deep learning in WiFi sensing, similar to that available for visual recognition, does not yet exist. In this article, we review recent progress in topics ranging from WiFi hardware platforms to sensing algorithms and propose a new library with a comprehensive benchmark, SenseFi. On this basis, we evaluate various deep-learning models in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, and feature transferability. Extensive experiments are performed whose results provide valuable insights into model design, learning strategy, and training techniques for real-world applications. In summary, SenseFi is a comprehensive benchmark with an open-source library for deep learning in WiFi sensing research that offers researchers a convenient tool to validate learning-based WiFi-sensing methods on multiple datasets and platforms.

Development of a human glioblastoma model using humanized DRAG mice for immunotherapy.

Glioblastoma (GBM) is the most common and lethal primary brain tumor with high mortality rates and a short median survival rate of about 15 months despite intensive multimodal treatment of maximal surgical resection, radiotherapy, and chemotherapy. Although immunotherapies have been successful in the treatment of various cancers, disappointing results from clinical trials for GBM immunotherapy represent our incomplete understanding. The development of alternative humanized mouse models with fully functional human immune cells will potentially accelerate the progress of GBM immunotherapy. In this study, we developed a humanized DRAG (NOD.Rag1KO.IL2RγcKO) mouse model, in which the human hematopoietic stem cells (HSCs) were well-engrafted and subsequently differentiated into a full lineage of immune cells. Using this humanized DRAG mouse model, GBM patient-derived tumorsphere lines were successfully engrafted to form xenografted tumors, which can recapitulate the pathological features and the immune cell composition of human GBM. Importantly, the administration of anti-human PD-1 antibodies in these DRAG mice bearing a GBM patient-derived tumorsphere line resulted in decreasing the major tumor-infiltrating immunosuppressive cell populations, including CD4 + PD-1 + and CD8 + PD-1 + T cells, CD11b + CD14 + HLA-DR + macrophages, CD11b + CD14 + HLA-DR - CD15 - and CD11b + CD14 - CD15 + myeloid-derived suppressor cells, indicating the humanized DRAG mouse model as a useful model to test the efficacy of immune checkpoint inhibitors in GBM immunotherapy. Together, these results suggest that humanized DRAG mouse models are a reliable preclinical platform for brain cancer immunotherapy and beyond.

A neurodevelopmental epigenetic programme mediated by SMARCD3-DAB1-Reelin signalling is hijacked to promote medulloblastoma metastasis.

How abnormal neurodevelopment relates to the tumour aggressiveness of medulloblastoma (MB), the most common type of embryonal tumour, remains elusive. Here we uncover a neurodevelopmental epigenomic programme that is hijacked to induce MB metastatic dissemination. Unsupervised analyses of integrated publicly available datasets with our newly generated data reveal that SMARCD3 (also known as BAF60C) regulates Disabled 1 (DAB1)-mediated Reelin signalling in Purkinje cell migration and MB metastasis by orchestrating cis-regulatory elements at the DAB1 locus. We further identify that a core set of transcription factors, enhancer of zeste homologue 2 (EZH2) and nuclear factor I X (NFIX), coordinates with the cis-regulatory elements at the SMARCD3 locus to form a chromatin hub to control SMARCD3 expression in the developing cerebellum and in metastatic MB. Increased SMARCD3 expression activates Reelin-DAB1-mediated Src kinase signalling, which results in a MB response to Src inhibition. These data deepen our understanding of how neurodevelopmental programming influences disease progression and provide a potential therapeutic option for patients with MB.

Advancing Imbalanced Domain Adaptation: Cluster-Level Discrepancy Minimization With a Comprehensive Benchmark.

Unsupervised domain adaptation methods have been proposed to tackle the problem of covariate shift by minimizing the distribution discrepancy between the feature embeddings of source domain and target domain. However, the standard evaluation protocols assume that the conditional label distributions of the two domains are invariant, which is usually not consistent with the real-world scenarios such as long-tailed distribution of visual categories. In this article, the imbalanced domain adaptation (IDA) is formulated for a more realistic scenario where both label shift and covariate shift occur between the two domains. Theoretically, when label shift exists, aligning the marginal distributions may result in negative transfer. Therefore, a novel cluster-level discrepancy minimization (CDM) is developed. CDM proposes cross-domain similarity learning to learn tight and discriminative clusters, which are utilized for both feature-level and distribution-level discrepancy minimization, palliating the negative effect of label shift during domain transfer. Theoretical justifications further demonstrate that CDM minimizes the target risk in a progressive manner. To corroborate the effectiveness of CDM, we propose two evaluation protocols according to the real-world situation and benchmark existing domain adaptation approaches. Extensive experiments demonstrate that negative transfer does occur due to label shift, while our approach achieves significant improvement on imbalanced datasets, including Office-31, Image-CLEF, and Office-Home.

Sustainable Development Efficiency of Cultural Landscape Heritage in Urban Fringe Based on GIS-DEA-MI, a Case Study of Wuhan, China.

Cultural landscape heritage refers to the rare and irreplaceable cultural landscapes recognized by UNESCO and the World Heritage Committee. It is recognized as a "common works of nature and human beings" of outstanding significance and universal value, and is a type of world heritage. Dueto construction, land isincreasingly limited in urban and rural areasin the process of urbanization, and cultural landscape heritage faces a huge threat, especially larger culturallandscapeheritagelocated at the edgesof cities. However, most of the existing studies have mainly focused on the material protection of heritage but have not paid enough attention to the non-material aspects of heritage sites, failing to reveal the inseparable nature of heritage and land. Therefore, this study takes sustainable development efficiency as its analysis tool, examines two pieces of cultural landscape heritage (the Panlongcheng site and the Tomb of the King of the Ming Dynasty) in the urban edge area of Wuhan, China as examples, innovates and establishes a multidimensional evaluation method based on the GIS-DEA-Ml model, and compares the dynamic changes of the spatial development efficiency and non-spatial development efficiency of the above two cultural landscape heritage cases. The results show that: both the spatial development efficiency and non-spatial development efficiency of Panlongcheng from 2010 to 2019 are significantly higher than that of the Tomb. This method makes up for the deficiency of traditional subjective qualitative analysis. It can be used to study the development efficiency of cultural landscape heritage more objectively and comprehensively, and promote the overall sustainable development of material and intangible cultural heritage. It can provide the basis for early decision-making and post-implementation evaluation for the preservation and utilization of cultural landscape heritage under the background of urban renewal.