Explore the vast range of titles available.

Depression, a pervasive global mental disorder, profoundly impacts daily lives. Despite numerous deep learning studies focused on depression detection through speech analysis, the shortage of annotated bulk samples hampers the development of effective models. In response to this challenge, our research introduces a transfer learning approach for detecting depression in speech, aiming to overcome constraints imposed by limited resources. In the context of feature representation, we obtain depression-related features by fine-tuning wav2vec 2.0. By integrating 1D-CNN and attention pooling structures, we generate advanced features at the segment level, thereby enhancing the model's capability to capture temporal relationships within audio frames. In the realm of prediction results, we integrate LSTM and self-attention mechanisms. This incorporation assigns greater weights to segments associated with depression, thereby augmenting the model's discernment of depression-related information. The experimental results indicate that our model has achieved impressive F1 scores, reaching 79% on the DAIC-WOZ dataset and 90.53% on the CMDC dataset. It outperforms recent baseline models in the field of speech-based depression detection. This provides a promising solution for effective depression detection in low-resource environments.

Temperature forecasting plays an important role in human production and operational activities. Traditional temperature forecasting mainly relies on numerical forecasting models to operate, which takes a long time and has higher requirements for the computing power and storage capacity of computers. In order to reduce computation time and improve forecast accuracy, deep learning-based temperature forecasting has received more and more attention. Based on the atmospheric temperature, dew point temperature, relative humidity, air pressure, and cumulative wind speed data of five cities in China from 2010 to 2015 in the UCI database, multivariate time series atmospheric temperature forecast models based on recurrent neural networks (RNN) are established. Firstly, the temperature forecast modeling of five cities in China is established by RNN for five different model configurations; secondly, the neural network training process is controlled by using the Ridge Regularizer (L2) to avoid overfitting and underfitting; and finally, the Bayesian optimization method is used to adjust the hyper-parameters such as network nodes, regularization parameters, and batch size to obtain better model performance. The experimental results show that the atmospheric temperature prediction error based on LSTM RNN obtained a minimum error compared to using the base models, and these five models obtained are the best models for atmospheric temperature prediction in the corresponding cities. In addition, the feature selection method is applied to the established models, resulting in simplified models with higher prediction accuracy.

In recent years, the number of people suffering from depression has gradually increased, and early detection is of great significance for the well-being of the public. However, the current methods for detecting depression are relatively limited, typically relying on the self-rating depression scale (SDS) and interviews. These methods are influenced by subjective or environmental factors. To improve the objectivity and efficiency of diagnosis, deep learning techniques have been applied to the field of automatic depression detection (ADD), providing a more accurate and objective approach. During interviews, transcribed interview data is one of the most commonly used modalities in ADD. However, previous studies have only utilized response texts or selected question–answer pairs, resulting in information redundancy and loss. This paper is the first to apply the multiple instance learning (MIL) framework to the field of textual interview data, aiming to overcome issues of inadequate text representation and ineffective information extraction in long texts. In the MIL framework, each instance undergoes an independent feature extraction process, ensuring that the local features of each instance are fully captured. This not only enhances the overall text representation capability but also alleviates the issue of sample imbalance in the dataset. Additionally, this paper improves upon previous aggregation strategies by introducing two hyper-parameters to accommodate the uncertainties in the field of text sentiment. An ensemble model of MT5 and RoBERTa (referred to as multi-MTRB) was constructed to extract features from each instance and output confidence scores indicating the presence of depressive information in the instances. Due to the unique design of the MIL framework, the proposed method is highly interpretable and is able to identify specific sentences that identify people from depressed patients, while introducing LIME techniques to provide more in-depth interpretation of negative instance sentences. This provides a promising approach for depression detection in the context of text interview data patterns. We evaluated the proposed method on DAIC-WOZ and E-DAIC datasets with excellent results. The F1 score is 0.88 on the DAIC-WOZ dataset and 0.86 on the E-DAIC dataset.

Background Accumulating evidence demonstrates the oncogenic roles of lncRNA (long non-coding RNA) molecules in a wide variety of cancer types including glioma. Equally important, However, tumorigenic functions of lncRNA in glioma remain largely unclear. A recent study suggested lncRNA SNHG15 played a role for regulating angiogenesis in glioma but its role in the tumor microenvironment (TME) was not investigated. Methods First, we showed that SNHG15 was upregulated in GBM cells and associated with a poor prognosis for the patients of GBM using public databases. Next, we collected temozolomide sensitive (TMZ-S) and resistant (TMZ-R) clinical samples and demonstrated that co-culturing TMZ-R cells with HMC3 (microglial) cells promoted M2-polarization of HMC3 and the secretion of pro-GBM cytokines TGF-β and IL-6. Results Comparative qPCR analysis of TMZ-S and TMZ-R cells showed that a significantly higher level of SNHG15, coincidental with a higher level of Sox2, β-catenin, EGFR, and CDK6 in TMZ-R cells. Subsequently, using bioinformatics tool, a potential mechanistic route for SNHG15 to promote GBM tumorigenesis was by inhibiting tumor suppressor, miR-627-5p which leads to activation of CDK6. Gene-silencing technique was employed to demonstrate that suppression of SNHG15 indeed led to the suppression of GBM tumorigenesis, accompanied by an increase miR-627-5p and decreased its two oncogenic targets, CDK6 and SOX-2. In addition, SNHG15-silenced TMZ-R cells became significantly sensitive towards TMZ treatment and less capable of promoting M2-phenotype in the HMC3 microglial cells. We then evaluated the potential anti-GBM activity of CDK6 inhibitor, palbociclib, using TMZ-R PDX mouse models. Palbociclib treatment significantly reduced tumorigenesis in TMZ-R/HMC3 bearing mice and SNHG15 and CDK6 expression was significantly reduced while miR-627-5p level was increased. Additionally, palbociclib treatment appeared to overcome TMZ resistance as well as reduced M2 markers in HMC3 cells. Conclusion Together, we provided evidence supporting the usage of CDK6 inhibitor for TMZ-resistant GBM cases. Further investigation is warranted for the consideration of clinical trials. Graphical abstract

Alzheimer’s disease (AD) is a debilitating progressively neurodegenerative disease. The best-characterized hallmark of AD, which is marked by behavioral alterations and cognitive deficits, is the aggregation of deposition of amyloid-beta (Aβ) and hyper-phosphorylated microtubule-associated protein Tau. Despite decades of experimental progress, the control rate of AD remains poor, and more precise deciphering is needed for potential therapeutic targets and signaling pathways involved. In recent years, phosphoinositide 3-kinase (PI3K) and Akt have been recognized for their role in the neuroprotective effect of various agents, and glycogen synthase kinase 3 (GSK3), a downstream enzyme, is also crucial in the tau phosphorylation and Aβ deposition. An overview of the function of PI3K/Akt pathway in the pathophysiology of AD is provided in this review, along with a discussion of recent developments in the pharmaceuticals and herbal remedies that target the PI3K/Akt signaling pathway. In conclusion, despite the challenges and hurdles, cumulative findings of novel targets and agents in the PI3K/Akt signaling axis are expected to hold promise for advancing AD prevention and treatment.

Objective Soybean seeds are an important source of vegetable proteins for both food and industry worldwide. Conglycinins (7S) and glycinins (11S), which are two major families of storage proteins encoded by a small family of genes, account for about 70% of total soy seed protein. Mutant alleles of these genes are often necessary in certain breeding programs, as the relative abundance of these protein subunits affect amino acid composition and soy food properties. In this study, we set out to test the efficiency of the CRISPR/Cas9 system in editing soybean storage protein genes using Agrobacterium rhizogenes -mediated hairy root transformation system. Results We designed and tested sgRNAs to target nine different major storage protein genes and detected DNA mutations in three storage protein genes in soybean hairy roots, at a ratio ranging from 3.8 to 43.7%. Our work provides a useful resource for future soybean breeders to engineer/develop varieties with mutations in seed storage proteins.

Background Treacher Collins syndrome (TCS) is a congenital disorder primarily caused by the mutation in the Treacle Ribosome Biogenesis Factor 1 ( TCOF1 ) gene. However, the significance of many TCOF1 mutations remains uncertain. Results We report two novel mutations identified in two TCS families and assess their pathogenicity alongside two previously reported mutations. Both novel mutations, c.2115dupG (p.T706DfsTer52) and c.2142+23_2142+52 del (p.A715VfsTer31), result in truncated proteins lacking nuclear location signals (NLSs), which impedes their entry into the nucleus and reduces mRNA expression level. Notably, the mutation c.2142+23_2142+52 del, leading to the retention of a 62 bp intron and disrupting RNA splicing, represents the first documented case of intron retention in TCS patients. Additionally, the previously reported mutation c.136 C> G (p.L46V) hinders protein nuclear location, while mutation c.1719del (p.N574TfsTer22) significantly decreases mRNA levels. Conclusions Our research expands the spectrum of TCOF1 mutations and provides evidence clarifying their pathogenic nature. These findings are crucial for genetic counseling and prenatal diagnosis for TCS patients.

Yuhai Cui and colleagues report that the H3K27 demethylase REF6 targets genomic loci containing a specific DNA motif via its zinc-finger domains. They show that REF6 facilitates the recruitment of BRM and that deleting the DNA motif from a target gene in Arabidopsis makes it inaccessible to REF6. SWI/SNF-type chromatin remodelers, such as BRAHMA (BRM), and H3K27 demethylases both have active roles in regulating gene expression at the chromatin level 1 , 2 , 3 , 4 , 5 , but how they are recruited to specific genomic sites remains largely unknown. Here we show that RELATIVE OF EARLY FLOWERING 6 (REF6), a plant-unique H3K27 demethylase 6 , targets genomic loci containing a CTCTGYTY motif via its zinc-finger (ZnF) domains and facilitates the recruitment of BRM. Genome-wide analyses showed that REF6 colocalizes with BRM at many genomic sites with the CTCTGYTY motif. Loss of REF6 results in decreased BRM occupancy at BRM–REF6 co-targets. Furthermore, REF6 directly binds to the CTCTGYTY motif in vitro , and deletion of the motif from a target gene renders it inaccessible to REF6 in vivo . Finally, we show that, when its ZnF domains are deleted, REF6 loses its genomic targeting ability. Thus, our work identifies a new genomic targeting mechanism for an H3K27 demethylase and demonstrates its key role in recruiting the BRM chromatin remodeler.

Rampant terrorism poses a serious threat to the national security of many countries worldwide, particularly due to separatism and extreme nationalism. This paper focuses on the development and application of a temporal self-exciting point process model to the terror data of three countries: the US, Turkey, and the Philippines. To account for occurrences with the same time-stamp, this paper introduces the order mark and reward term in parameter selection. The reward term considers the triggering effect between events in the same time-stamp but different order. Additionally, this paper provides comparisons between the self-exciting models generated by day-based and month-based arrival times. Another highlight of this paper is the development of a model to predict the number of terror events using a combination of simulation and machine learning, specifically the random forest method, to achieve better predictions. This research offers an insightful approach to discover terror event patterns and forecast future occurrences of terror events, which may have practical application towards national security strategies.

Brain metastasis (BM) frequently occurs in advanced non-small cell lung cancer (NSCLC) and is associated with poor clinical prognosis. Due to the location of metastatic lesions, the surgical resection is limited and the chemotherapy is ineffective because of the existence of the blood brain barrier (BBB). Therefore, it is essential to enhance our understanding about the underlying mechanisms associated with brain metastasis in NSCLC. In the present study, we explored the RNA-Seq data of brain metastasis cells from the GEO database, and extracted RNA collected from primary NSCLC tumors as well as paired brain metastatic lesions followed by microRNA PCR array. Meanwhile, we improved the in vivo model and constructed a cancer stem cell-derived transplantation model of brain metastasis in mice. Our data indicated that the level of miR-596-3p is high in primary NSCLC tumors, but significantly downregulated in the brain metastatic lesion. The prediction target of microRNA suggested that miR-596-3p was considered to modulate two genes essential in the brain invasion process, YAP1 and IL-8 that restrain the invasion of cancer cells and permeability of BBB, respectively. Moreover, in vivo experiments suggested that our model mimics the clinical aspect of NSCLC and improves the success ratio of brain metastasis model. The results demonstrated that miR-596-3p significantly inhibited the capacity of NSCLC cells to metastasize to the brain. Furthermore, these finding elucidated that miR-596-3p exerts a critical role in brain metastasis of NSCLC by modulating the YAP1-IL8 network, and this miRNA axis may provide a potential therapeutic strategy for brain metastasis.