Association analysis of PLIN2 gene polymorphisms and lambing performance in Qianbei Ma goats.

Qianbei Ma goats are one of the three most valued local goat breeds in Guizhou, China; furthermore, it has lower litter size performance. The purpose of this study was to explore the correlation between SNP (single-nucleotide polymorphisms) of PLIN2 gene and lambing performance. The bioinformatics analysis, DNA sequencing, RT-qPCR and correlation analysis methods were used to analyse the evolutionary relationship of PLIN2 protein in 13 species, to detect the expression pattern of PLIN2 gene in the gonad axis of Qianbei sheep, to explore the dominant genotype of PLIN2 related to lambing traits and to screen molecular markers related to lambing performance to guide the breeding of Qianbei Ma goats. Results showed that the Qianbei Ma goat PLIN2 protein had the closest genetic relationship with sheep and the furthest from mice, there were significant or extremely significant differences in the expression levels of the PLIN2 gene in the gonadal axis of the mothers of single- and multi-lamb groups. Compared with the reference sequence, four SNPs were found, which were g.1006 C → A and g.1171 A → G in the first and second intron regions of the PLIN2 gene, g.8514 C → T in the exon 8 region and g.9122 A → T in the 3'UTR. The correlation analysis showed that g.1006 C → A, g.8514 C → T and g.9122 A → T had significant indigenous effects on the lambing performance of Qianbei Ma goats (p < .05). The number of third births for diploid H2H5 was significantly higher than that of diploid H1H2, and the number of first to third births for diploid H2H5 was large and stable. The results showed that PLIN2 gene could be used as a candidate gene related to lambing traits of Qianbei Ma goat.

Separating Xylene Isomers with a Calcium Metal-Organic Framework.

The purification of p-xylene (pX) from its xylene isomers represents a challenging but important industrial process. Herein, we report the efficient separation of pX from its ortho- and meta- isomers by a microporous calcium-based metal-organic framework material (HIAM-203) with a flexible skeleton. At 30 °C, all three isomers are accommodated but the adsorption kinetics of o-xylene (oX) and m-xylene (mX) are substantially slower than that of pX, and at an elevated temperature of 120 °C, oX and mX are fully excluded while pX can be adsorbed. Multicomponent column breakthrough measurements and vapor-phase/liquid-phase adsorption experiments have demonstrated the capability of HIAM-203 for efficient separation of xylene isomers. Ab initio calculations have provided useful information for understanding the adsorption mechanism.

A Microporous Metal-Organic Framework Incorporating Both Primary and Secondary Building Units for Splitting Alkane Isomers.

We demonstrate the assembly of a mononuclear metal center, a hexanuclear cluster, and a V-shaped, trapezoidal tetracarboxylate linker into a microporous metal-organic framework featuring an unprecedented 3-nodal (4,4,8)-c lyu topology. The compound, HIAM-302, represents the first example that incorporates both a primary building unit and a hexanuclear secondary building unit in one structure, which should be attributed to the desymmetrized geometry of the organic linker. HIAM-302 possesses optimal pore dimensions and can separate monobranched and dibranched alkanes through selective molecular sieving, which is of significant value in the petrochemical industry.

Predictability influences whether outcomes are processed in terms of original or relative values.

Previous studies have provided insights into the representations of original and relative values and the influence of predictability on decision making. However, whether the predictability of outcomes can influence the processing manner of outcomes (i.e. whether the outcomes are processed in terms of original or relative values) is still unknown. To investigate this issue, we had participants perform a monetary decision task which resulted in two outcomes with the same relative values but different original values in either a predictable or unpredictable condition, while recording event-related potentials (ERP). ERP results showed that the outcome processing in the unpredictable condition elicited more positive deflections in the time window of 300-500ms (P300) than did those in the predictable condition. More importantly, the outcome with high original value elicited a greater P300 component than did that with low original value in the unpredictable condition even though these two outcomes had the same relative values, while in the predictable condition no significant difference was observed between ERPs elicited by the two outcomes even though their original values were different. These results suggest that the outcomes might be processed in terms of relative values in the predictable condition but original values in the unpredictable condition.

Tissue expression and promoter activity analysis of the porcine TNFSF11 gene.

Tumour necrosis factor (TNF) superfamily member 11 (TNFSF11), also known as RANKL, plays a crucial role in regulating several physiological and pathological activities. Additionally, it is a vital factor in bone physiology, and the sex hormone progesterone regulates the expansion of stem cells and the proliferation of mammary epithelial cells. It is essential for animal growth and reproductive physiological processes. This study aimed to evaluate the tissue-specific expression characteristics and promoter activity of the TNFSF11 gene in pigs. As a result, the study examined the presence of TNFSF11 expression in the tissues of Xiangsu pigs at 0.6 and 12 months of age. Moreover, the core promoter region of TNFSF11 was also identified by utilizing a combination of bioinformatic prediction and dual-luciferase activity tests. Finally, the effect of transcription factors on the transcriptional activity of the core promoter region was determined using site-directed mutagenesis. TNFSF11 was uniformly expressed in all tissues; however, its expression in muscles was comparatively low. The core promoter region of TNFSF11 was located in the -555 to -1 region. The prediction of the transcription start site of TNFSF11 gene-2000 ∼ + 500bp showed that there was a CpG site in 17 ∼ + 487bp. Analysis of mutations in the transcription factor binding sites revealed that mutations in the Stat5b, Myog, Trl, and EN1 binding sites had significant effects on the transcriptional activity of the TNFSF11 gene, particularly following the EN1 binding site mutation (P < 0.001). This study provides insights into both the tissue-specific expression patterns of TNFSF11 in the tissues of Xiangsu pigs and the potential regulatory effects of transcription factors on its promoter activity. These results may be helpful for future research aimed at clarifying the expression and role of the porcine TNFSF11 gene.

Association analysis between Acetyl-Coenzyme A Acyltransferase-1 gene polymorphism and growth traits in Xiangsu pigs.

Introduction: Acetyl-Coenzyme A Acyltransferase-1 (ACAA1) is a peroxisomal acyltransferase involved in fatty acid metabolism. Current evidence does not precisely reveal the effect of the ACAA1 gene on pig growth performance. Methods: The present study assessed the mRNA expression levels of the ACAA1 gene in the heart, liver, spleen, lung, kidney of 6-month-old Xiangsu pigs and in the longissimus dorsi muscle at different growth stages (newborn, 6 months and 12 months of age) using RT-qPCR. The relationship between single-nucleotide polymorphisms (SNPs) of ACAA1 gene and growth traits in 6-month-old and 12-month-old Xiangsu pigs was investigated on 184 healthy Xiangsu pigs using Sanger sequencing. Results: The ACAA1 gene was expressed in heart, liver, spleen, lung, kidney, and longissimus dorsi muscle of 6-month-old pigs, with the highest level of expression in the liver. ACAA1 gene expression in the longissimus dorsi muscle decreased with age (p < 0.01). In addition, four SNPs were identified in the ACAA1 gene, including exon g.48810 A>G (rs343060194), intron g.51546 T>C (rs319197012), exon g.55035 T>C (rs333279910), and exon g.55088 C>T (rs322138947). Hardy-Weinberg equilibrium (p > 0.05) was found for the four SNPs, and linkage disequilibrium (LD) analysis revealed a strong LD between g.55035 T>C (rs333279910) and g.55088 C>T (rs322138947) (r 2 = 1.000). Association analysis showed that g.48810 A>G (rs343060194), g.51546 T>C (rs319197012), g.55035 T>C (rs333279910), and g.55088 C>T (rs322138947) varied in body weight, body length, body height, abdominal circumference, leg and hip circumference and living backfat thickness between 6-month-old and 12-month-old Xiangsu pigs. Conclusion: These findings strongly demonstrate that the ACAA1 gene can be exploited for marker-assisted selection to improve growth-related phenotypes in Xiangsu pigs and present new candidate genes for molecular pig breeding.

Estimating the Heterogeneous Causal Effects of Parent-Child Relationships among Chinese Children with Oppositional Defiant Symptoms: A Machine Learning Approach.

Oppositional defiant symptoms are some of the most common developmental symptoms in children and adolescents with and without oppositional defiant disorder. Research has addressed the close association of the parent-child relationship (PCR) with oppositional defiant symptoms. However, it is necessary to further investigate the underlying mechanism for forming targeted intervention strategies. By using a machine learning-based causal forest (CF) model, we investigated the heterogeneous causal effects of the PCR on oppositional defiant symptoms in children in Chinese elementary schools. Based on the PCR improvement in two consecutive years, 423 children were divided into improved and control groups. The assessment of oppositional defiant symptoms (AODS) in the second year was set as the dependent variable. Additionally, several factors based on the multilevel family model and the baseline AODS in the first year were included as covariates. Consistent with expectations, the CF model showed a significant causal effect between the PCR and oppositional defiant symptoms in the samples. Moreover, the causality exhibited heterogeneity. The causal effect was greater in those children with higher baseline AODS, a worse family atmosphere, and lower emotion regulation abilities in themselves or their parents. Conversely, the parenting style played a positive role in causality. These findings enhance our understanding of how the PCR contributes to the development of oppositional defiant symptoms conditioned by factors from a multilevel family system. The heterogeneous causality in the observation data, established using the machine learning approach, could be helpful in forming personalized family-oriented intervention strategies for children with oppositional defiant symptoms.

Genetic variation in the BLM gene and its expression in the ovaries is closely related to kidding number in goats.

Bloom (BLM) helicase plays an important role in DNA replication and the maintenance of genome integrity. BLM protein deficiency, which plays a vital role in the sperm-egg union and germ-cell development during reproduction, can lead to severe DNA damage in goats. However, the effect of BLM protein deficiency on goat litter size has not been reported. Herein, we studied the association between the genetic variation in the BLM gene and the number of kids per litter in Guizhou white goats. We explored differences in the expression of the BLM protein in the follicles of single and multi-kid nanny goats. We also analyzed the effects of dysregulated BLM gene expression on the proliferation and apoptosis of ovarian granulosa cells and the expression of genes related to follicle development in goats. Five single nucleotide polymorphism (SNP) loci, including the non-synonymous mutations g.38179 A > G, g.40626 G > C and g.89621 T > G; the intron synonymous mutation g.56961 G > A and the exon synonymous mutation g.65796 C > T were found in the BLM gene. All SNPs loci were in Hardy-Weinberg equilibrium, and correlation analysis showed that the g.65796 C > T and g.89621 T > G loci polymorphism was strongly associated with litter size in the first three litters (P < 0.05). The diplogenotype Hap 2/2 (AAGGAACCTT) showed no significant difference in litter size between different births, indicating that the diploid genotype is stable in different litter sizes. Bioinformatics analysis showed that three non-synonymous mutation loci (p.T488A, p.A662S, and p.S1373A) could affect BLM protein stability, and mutations in p.T488A and p.S1373A led to changes in amino acid polarity and associated interactions. qPCR results showed that the expression level of the BLM gene in the uterus and ovaries of TT genotype nanny goats was significantly higher than that of GG genotype nanny goats. Indirect immunofluorescence assay (IF) showed that the BLM protein was significantly overexpressed in both the primordial and growing follicles of nanny goats with multiple kids (P < 0.01). Disrupting BLM gene expression in the ovarian granulosa cells down-regulated the expression of the Cyp19A1 gene. It also significantly inhibited the proliferation of follicles and induces early apoptosis of the granulosa cells. These findings confirm that polymorphism in the BLM gene is closely related to the littering traits of Guizhou white goats, and it affects the reproductive performance of nanny goats by regulating the development of the oocytes and granulosa cells. This work provides new evidence on the regulatory effect of the BLM gene on the litter size of nanny goats.

Association between polymorphisms in NOBOX and litter size traits in Xiangsu pigs.

The newborn ovary homeobox gene (NOBOX) regulates ovarian and early oocyte development, and thus plays an essential role in reproduction. In this study, the mRNA expression level and single nucleotide polymorphism (SNP) of NOBOX in various tissues of Xiangsu pigs were studied to explore the relationship between its polymorphism and litter size traits. Also, bioinformatics was used to evaluate the effects of missense substitutions on protein structure and function. The results revealed that NOBOX is preferentially expressed in the ovary. Six mutations were detected in the NOBOX sequence, including g.1624 T>C, g.1858 G>A, g.2770 G>A, g.2821 A>G, g.5659 A>G, and g.6025 T>A, of which g.1858 G>A was a missense mutation. However, only g.1858 G>A, g.5659 A>G, and g.6025 T>A were significantly associated with litter size traits (p < 0.05). Further prediction of the effect of the missense mutation g.1858 G>A on protein function revealed that p.V82M is a non-conservative mutation that significantly reduces protein stability and thus alters protein function. Overall, these findings suggest that NOBOX polymorphism is closely related to the litter size of Xiangsu pigs, which may provide new insights into pig breeding.

Air-sea exchange of PAHs in the Taiwan Strait: Seasonal dynamics and regulation mechanisms revealed by machine learning approach.

In this study, to understand the seasonal dynamics of air-sea exchange and its regulation mechanisms, we investigated polycyclic aromatic hydrocarbons (PAHs) at the air-sea interface in the western Taiwan Strait in combination with measurements and machine learning (ML) predictions. For 3-ring PAHs and most of 4- to 6-ring, volatilization and deposition fluxes were observed, respectively. Seasonal variations in air-sea exchange flux suggest the influence of monsoon transitions. Results of interpretable ML approach (XGBoost) indicated that volatilization of 3-ring PAHs was significantly controlled by dissolved PAH concentrations (contributed 24.0 %), and the gaseous deposition of 4- to 6-ring PAHs was related to more contaminated air masses originating from North China during the northeast monsoon. Henry's law constant emerged as a secondary factor, influencing the intensity of air-sea exchange, particularly for low molecular weight PAHs. Among environmental parameters, notably high wind speed emerges as the primary factor and biological pump's depletion of PAHs in surface seawater amplifies the gaseous deposition process. The distinct dynamics of exchanges at the air-water interface for PAHs in the western TWS can be attributed to variations in primary emission intensities, biological activity, and the inconsistent pathways of long-range atmospheric transport, particularly within the context of the monsoon transition.

EEGformer: A transformer-based brain activity classification method using EEG signal.

Background: The effective analysis methods for steady-state visual evoked potential (SSVEP) signals are critical in supporting an early diagnosis of glaucoma. Most efforts focused on adopting existing techniques to the SSVEPs-based brain-computer interface (BCI) task rather than proposing new ones specifically suited to the domain. Method: Given that electroencephalogram (EEG) signals possess temporal, regional, and synchronous characteristics of brain activity, we proposed a transformer-based EEG analysis model known as EEGformer to capture the EEG characteristics in a unified manner. We adopted a one-dimensional convolution neural network (1DCNN) to automatically extract EEG-channel-wise features. The output was fed into the EEGformer, which is sequentially constructed using three components: regional, synchronous, and temporal transformers. In addition to using a large benchmark database (BETA) toward SSVEP-BCI application to validate model performance, we compared the EEGformer to current state-of-the-art deep learning models using two EEG datasets, which are obtained from our previous study: SJTU emotion EEG dataset (SEED) and a depressive EEG database (DepEEG). Results: The experimental results show that the EEGformer achieves the best classification performance across the three EEG datasets, indicating that the rationality of our model architecture and learning EEG characteristics in a unified manner can improve model classification performance. Conclusion: EEGformer generalizes well to different EEG datasets, demonstrating our approach can be potentially suitable for providing accurate brain activity classification and being used in different application scenarios, such as SSVEP-based early glaucoma diagnosis, emotion recognition and depression discrimination.

Spatial distribution, source, and ecological risk of polybrominated diphenyl ethers (PBDEs) and hexabromocyclododecanes (HBCDs) in Jiaozhou Bay, China.

Polybrominated diphenyl ethers (PBDEs) and hexabromocyclododecanes (HBCDs) are commonly found in the environment as components of brominated flame retardants. Due to their potential impact on human health and wildlife, it is imperative to closely monitor and manage their levels in the environment. This study investigated the spatial distribution, sources, and ecological risks of PBDEs and HBCDs in Jiaozhou Bay (JZB), a large bay situated on the eastern coast of China. The results showed that PBDE concentrations ranged from not detected (ND) to 7.93 ng/L in the water and ND to 65.76 ng/g in the sediment, while HBCD concentrations ranged from ND to 0.31 ng/L in the water and ND to 16.63 ng/g in the sediment. Furthermore, we observed significantly higher concentrations of PBDEs and HBCDs in the inner JZB compared to the outer JZB. Our source apportionment analysis showed that PBDEs primarily originated from the production and debromination of BDE-209, as well as the emission of commercial PeBDEs, whereas HBCDs in sediments mostly stemmed from anthropogenic activities and river input. Finally, our eco-logical risk assessment highlighted the need for continuous monitoring of PBDEs in JZB sediments. Overall, our study aims to provide valuable assistance for the environmental management of the JZB bay area, which is characterized by a complex net-work of rivers and a thriving economy.

Upwelling impact and lateral transport of dissolved PAHs in the Taiwan Strait and adjacent South China Sea.

The spatial distribution and depth profile of dissolved polycyclic aromatic hydrocarbons (PAHs) were investigated in the western Taiwan Strait (TWS) and northeastern South China Sea (SCS) during the southwest monsoon for a comprehensive study of spatial distribution, potential sources, upwelling, and lateral PAHs transport flux to assess the impacts of oceanic processes. The concentrations of ∑14PAHs were 33 ± 14 ng L-1 and 23 ± 11 ng L-1 in western TWS and northeastern SCS, respectively. A minor difference in potential sources in different areas was shown in principle component analysis results, which illustrated mixed sources (petrogenic and pyrogenic) in western TWS and petrogenic sources in northeastern SCS. An "enrichment in surface or deep but depletion in medium water" distribution pattern of PAHs depth profile during summertime was observed in Taiwan Bank, which was potentially influenced by the upwelling. The greatest lateral ∑14PAHs transport flux was found along the Taiwan Strait Current area (43.51 g s-1), followed by those along South China Sea Warm Current and Guangdong Coastal Current areas. Though the oceanic response to PAHs varied relatively slowly, the ocean current was a less-dominant pathway for PAHs exchange between the SCS and the East China Sea (ECS).

Association Analysis of PRKAA2 and MSMB Polymorphisms and Growth Traits of Xiangsu Hybrid Pigs.

In this study, Xiangsu hybrid pig growth traits were evaluated via PRKAA2 and MSMB as candidate genes. Sanger sequencing revealed three mutation sites in PRKAA2, namely, g.42101G>T, g.60146A>T, and g.61455G>A, and all these sites were intronic mutations. Moreover, six mutation sites were identified in MSMB: intronic g.4374G>T, exonic g.4564T>C, exonic g.6378G>A, exonic g.6386C>T, intronic g.8643G>A, and intronic g.8857A>G. Association analysis revealed that g.42101G>T, g.60146A>T, g.61455G>A, g.4374G>T, g.4564T>C, g.6378G>A, g.6386C>T, g.8643G>A, and g.8857A>G showed different relationship patterns among body weight, body length, body height, chest circumference, abdominal circumference, tube circumference, and chest depth. Real-time polymerase chain reaction results revealed that the expression of PRKAA2 was highest in the longissimus dorsi muscle, followed by that in the heart, kidney, liver, lung, and spleen. The expression of MSMB was highest in the spleen, followed by that in the liver, kidney, lung, heart, and longissimus dorsi muscle. These results suggest that PRKAA2 and MSMB can be used in marker-assisted selection to improve growth related traits in Xiangsu hybrid pigs, providing new candidate genes for Pig molecular breeding.

Systematic Fusion of Multi-Source Cognitive Networks With Graph Learning - A Study on Fronto-Parietal Network.

Cognitive tasks induce fluctuations in the functional connectivity between brain regions which constitute cognitive networks in the human brain. Although several cognitive networks have been identified, consensus still cannot be achieved on the precise borders and distribution of involved brain regions for each network, due to the multifarious use of diverse brain atlases in different studies. To address the problem, the current study proposed a novel approach to generate a fused cognitive network with the optimal performance in discriminating cognitive states by using graph learning, following the synthesization of one cognitive network defined by different brain atlases, and the construction of a hierarchical framework comprised of one main version and other supplementary versions of the specific cognitive network. As a result, the proposed method demonstrated better results compared with other machine learning methods for recognizing cognitive states, which was revealed by analyzing an fMRI dataset related to the mental arithmetic task. Our findings suggest that the fused cognitive network provides the potential to develop new mind decoding approaches.

Determination of multiple organic flame retardants in maricultural water using High-volume/High-throughput Solid-phase extraction followed by liquid/gas chromatography tandem mass spectrometry.

A rapid and efficient analytical method is proposed and optimized for the enrichment, extraction and instrument analysis of four typical organic flame retardants (OFRs), including organophosphate esters (OPEs), polybrominated diphenyl ethers (PBDEs), hexabromocyclododecane (HBCDs) and dechlorane compounds (Dechloranes) in maricultural waters using High-volume/High-throughput Solid-phase extraction with in-situ ultrasonic technique followed by high performance liquid chromatography tandem mass spectrometry (HPLC-MS/MS) and gas chromatography tandem mass spectrometry (GC-MS) instrumental detection. The optimized pretreatment conditions were that the analytes were enriched by XAD-2 resins and eluted repeatedly with 50 mL hexane/acetone (1:1, v:v) for 5 min. The results of method validation exhibited that the developed method can be used for quantitative detection of 11 OPEs, 13 PBDEs, 3 HBCDs and 5 Dechloranes in water samples. The method detection limits (MDLs) and limits of quantification (LOQs) are 0.4-26.2 pg/L and 1.5-87.4 pg/L for OPEs, 23.3-35.4 pg/L and 77.5-117.9 pg/L for HBCDs, 0.8-97.4 pg/L and 2.6-324.7 pg/L for PBDEs and 9.3-78.5 pg/L and 31.0-261.8 pg/L for Dechloranes, respectively. The method was successfully applied in lagoon maricultural areas in Hainan province, and the results showed that 4 OFRs were detected in almost all water samples. Total concentrations of 18 water samples were 1.89-39.97 ng/L for OPEs, 0.18-5.40 ng/L for PBDEs, ND-0.24 ng/L for HBCDs and 0.01-1.77 ng/L for Dechloranes, respectively. The optimized analytical method is highly sensitive and efficient with expectation to play an essential role in monitoring the ultra-trace organic pollutants and providing an effective risk assessment in ecological environment.

Exploring highly reliable substructures in auto-reconstructions of a neuron.

The digital reconstruction of a neuron is the most direct and effective way to investigate its morphology. Many automatic neuron tracing methods have been proposed, but without manual check it is difficult to know whether a reconstruction or which substructure in a reconstruction is accurate. For a neuron's reconstructions generated by multiple automatic tracing methods with different principles or models, their common substructures are highly reliable and named individual motifs. In this work, we propose a Vaa3D-based method called Lamotif to explore individual motifs in automatic reconstructions of a neuron. Lamotif utilizes the local alignment algorithm in BlastNeuron to extract local alignment pairs between a specified objective reconstruction and multiple reference reconstructions, and combines these pairs to generate individual motifs on the objective reconstruction. The proposed Lamotif is evaluated on reconstructions of 163 multiple species neurons, which are generated by four state-of-the-art tracing methods. Experimental results show that individual motifs are almost on corresponding gold standard reconstructions and have much higher precision rate than objective reconstructions themselves. Furthermore, an objective reconstruction is mostly quite accurate if its individual motifs have high recall rate. Individual motifs contain common geometry substructures in multiple reconstructions, and can be used to select some accurate substructures from a reconstruction or some accurate reconstructions from automatic reconstruction dataset of different neurons.

Classifying the tracing difficulty of 3D neuron image blocks based on deep learning.

Quickly and accurately tracing neuronal morphologies in large-scale volumetric microscopy data is a very challenging task. Most automatic algorithms for tracing multi-neuron in a whole brain are designed under the Ultra-Tracer framework, which begins the tracing of a neuron from its soma and traces all signals via a block-by-block strategy. Some neuron image blocks are easy for tracing and their automatic reconstructions are very accurate, and some others are difficult and their automatic reconstructions are inaccurate or incomplete. The former are called low Tracing Difficulty Blocks (low-TDBs), while the latter are called high Tracing Difficulty Blocks (high-TDBs). We design a model named 3D-SSM to classify the tracing difficulty of 3D neuron image blocks, which is based on 3D Residual neural Network (3D-ResNet), Fully Connected Neural Network (FCNN) and Long Short-Term Memory network (LSTM). 3D-SSM contains three modules: Structure Feature Extraction (SFE), Sequence Information Extraction (SIE) and Model Fusion (MF). SFE utilizes a 3D-ResNet and a FCNN to extract two kinds of features in 3D image blocks and their corresponding automatic reconstruction blocks. SIE uses two LSTMs to learn sequence information hidden in 3D image blocks. MF adopts a concatenation operation and a FCNN to combine outputs from SIE. 3D-SSM can be used as a stop condition of an automatic tracing algorithm in the Ultra-Tracer framework. With its help, neuronal signals in low-TDBs can be traced by the automatic algorithm and in high-TDBs may be reconstructed by annotators. 12732 training samples and 5342 test samples are constructed on neuron images of a whole mouse brain. The 3D-SSM achieves classification accuracy rates 87.04% on the training set and 84.07% on the test set. Furthermore, the trained 3D-SSM is tested on samples from another whole mouse brain and its accuracy rate is 83.21%.

Detecting depression using an ensemble classifier based on Quality of Life scales.

Major depressive disorder (MDD) is an issue that affects 350 million people worldwide. Traditional approaches have been to identify depressive symptoms in datasets, but recently, research is beginning to explore the association between psychosocial factors such as those on the quality of life scale and mental well-being, which will lead to earlier diagnosis and prediction of MDD. In this research, an ensemble binary classifier is proposed to analyse health survey data against ground truth from the SF-20 Quality of Life scales. The classifier aims to improve the performance of machine learning techniques on large datasets and identify depressed cases based on associations between items on the QoL scale and mental illness by increasing predictive performance. On the experimental evaluation on the National Health and Nutrition Examination Survey (NHANES), the classifier demonstrated an F1 score of 0.976 in the prediction, without any incorrectly identified depression instances. Only about 4% of instances had been mistakenly classified into depressed cases, with a significant accuracy of 95.4% comparing to the result from PHQ-9 mental screen inventory. The presented ensemble binary classifier performed comparably better than each baseline algorithm in all measures and all experiments. We trained the ensemble model on the processed NHANES dataset, tested and evaluated the results of its performance against mental screen inventory and discussed the comparable predictions. Finally, we provided future research directions.

Medication Combination Prediction Using Temporal Attention Mechanism and Simple Graph Convolution.

Medication combination prediction can be applied to the clinical treatment for critical patients with multi-morbidity. The suitable medication combination can help cure patients and keep the treatment medication safe. However, the complexity and uncertainty of clinical circumstances limit the predictive accuracy of medication combination. Thus, this paper proposes a new medication combination prediction model based on the temporal attention mechanism (TAM) and the simple graph convolution (SGC), named as TAMSGC. More specifically, the TAM can capture the temporal sequence information in the medical records, and the SGC is implemented to acquire the medication knowledge from the complicated medication combination. Experiments in a real dataset show that TAMSGC surpasses the baseline models on the predictive accuracy of medication combination.