Genetic polymorphism of circumsporozoite protein of Plasmodium falciparum among Chinese migrant workers returning from Africa to Henan Province.

BACKGROUND: Plasmodium falciparum malaria is recognized as a major global public health problem. The malaria vaccine was important because the case fatality rate of falciparum malaria was high. Plasmodium falciparum circumsporozoite protein (PfCSP) is one of the potential vaccine candidates, but the genetic polymorphism of PfCSP raises concerns regarding the efficacy of the vaccine. This study aimed to investigate the genetic polymorphism of PfCSP and provide data for the improvement of PfCSP-based vaccine (RTS,S malaria vaccine). METHODS: Blood samples were collected from 287 Chinese migrant workers who were infected with P. falciparum and returning from Africa to Henan Province during 2016-2018. The Pfcsp genes were analysed to estimate the genetic diversity of this parasite. RESULTS: The results showed that there were two mutations at the N-terminus of imported Pfcsp in Henan Province, including insertion amino acids (58.71%, 118/201) and A → G (38.81%, 78/201). The number of repeats of tetrapeptide motifs (NANP/NVDP/NPNP/NVDA) in the central repeat region ranged mainly from 39 to 42 (97.51%, 196/201). A total of 14 nonsynonymous amino acid changes were found at the C-terminus. The average nucleotide difference (K) of imported Pfcsp in Henan Province was 5.719, and the haplotype diversity (Hd) was 0.964 ± 0.004. The estimated value of dN-dS was 0.047, indicating that the region may be affected by positive natural selection. The minimum number of recombination events (Rm) of imported Pfcsp in Henan Province was close to that in Africa. The analysis of genetic differentiation showed that there may be moderate differentiation between East Africa and North Africa (Fst = 0.06484), and the levels of differentiation in the other regions were very small (Fst < 0.05). CONCLUSIONS: The N-terminus of Pfcsp was relatively conserved, and the central repeat region and the Th2R and Th3R regions of the C-terminus were highly polymorphic. The gene polymorphism pattern among Chinese migrant workers returning from Africa to Henan Province was consistent with that in Africa. The geographical pattern of population differentiation and the evidence of natural selection and gene recombination suggested that the effect of polymorphism on the efficacy of PfCSP-based vaccines should be considered.

Changes in peripheral blood cytokines in patients with severe fever with thrombocytopenia syndrome.

Severe fever with thrombocytopenia syndrome (SFTS) is recognized as an emerging infectious disease. This study aimed to investigate the pathogenic mechanism of SFTS. A total of 100 subjects were randomly included in the study. Cytokine levels were detected by enzyme-linked immunosorbent assay and the viral load was detected by micro drop digital PCR. The results showed that levels of interleukin-6 (IL-6), IL-8, IL-10, IFN-inducible protein-10 (IP-10), monocyte chemoattractant protein-1 (MCP-1), macrophage inflammatory protein-1α (MIP-1α), transforming growth factor-ß1 (TGF-ß1), and regulated upon activation normal T cell expressed and secreted factor (RANTES) differed significantly among the SFTS patient group, healthy people group, and asymptomatic infection group (p < .05). Compared to the healthy people group, the patient group had increased cytokine levels (IL-6, IL-10, IP-10, MCP-1, and IFN-γ) but reduced levels of IL-8, TGF-ß1, and RANTES (p < .0167). IL-6, IL-8, IL-10, IP-10, MCP-1, MIP-1α, TGF-ß1, and the RANTES levels had different trends after the onset of the disease. IL-6, IL-10, IP-10, and MCP-1 levels in severe patients were higher than those in mild patients (p < .05). There was a positive correlation between viral load and IL-6 and IP-10 but a negative correlation between viral load and RANTES. SFTSV could cause a cytokine change: the cytokine levels of patients had different degrees of fluctuation after the onset of the disease. The levels of IL-6 and IL-8 in the asymptomatic infection group were found between the SFTS patients group and the healthy people group. The levels of IL-6, IL-10, IP-10, and MCP-1 in the serum could reflect the severity of the disease, and the levels of IL-6, IP-10, and RANTES were correlated with the viral load.

Severe fever with thrombocytopenia syndrome: a systematic review and meta-analysis of epidemiology, clinical signs, routine laboratory diagnosis, risk factors, and outcomes.

BACKGROUND: Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease with the high case-fatality rate, and lack of vaccines. We aimed to systematically analysed the epidemiological characteristics, clinical signs, routine laboratory diagnosis, risk factors, and outcomes. METHODS: Documents on SFTS were collected by searching the Chinese National Knowledge Infrastructure, Wan Fang Data, PubMed, Embase, and Web of Science databases from 2011 to 2018. Meta-analysis was performed by using Review Manager and Stata software. RESULTS: Twenty-five articles involving 4143 cases were included. Diarrhea (odds ratio (OR) =1.60, 95% confidence interval (CI): 1.06 to 2.42, P = 0.02), and vomiting (OR = 1.56, 95% CI: 1.01 to 2.39, P = 0.04) on admission were associated with the fatal outcomes of SFTS. Compared to patients with mild symptoms, patients with severe symptoms had significantly elevated levels of lactic acid dehydrogenase (standard mean difference (SMD) =1.27, 95% CI: 0.59 to 1.94), alanine aminotransferase (SMD = 0.55, 95% CI: 0.24 to 0.85), aspirate aminotransferase (SMD = 1.01, 95% CI: 0.69 to 1.32), and creatine kinase (SMD = 1.04, 95% CI: 0.74 to 1.33) but had reduced platelet counts (SMD = -0.87, 95% CI: - 1.16 to - 0.58) and albumin levels (SMD = -1.00, 95% CI: - 1.32 to - 0.68). The risk factors for poor prognosis included age (mean difference (MD) =6.88, 95% CI: 5.41 to 8.35) and farming (OR = 2.01, 95% CI: 1.06 to 3.80). For the risk factors of contracting SFTS, the incidence of SFTS related to tick bites was 24% [95% CI: 0.18 to 0.31]. The pooled case-fatality rate of SFTS patients was 18% [95% CI: 0.16 to 0.21]. CONCLUSIONS: China is the country with the highest incidence of SFTS. May to July was the peak of the epidemic, and farmers were a high-risk group. The risk factor for SFTS included age (poor prognosis) and tick bites (contracting SFTS). Patients with severe diarrhea and vomiting symptoms on admission should be noted. Clinicians could use routine laboratory parameters and clinical symptoms as references for clinically suspected cases, classification of SFTS, and timely treatment, especially in basic hospitals.

A New Hidden Markov Model for Protein Quality Assessment Using Compatibility Between Protein Sequence and Structure.

Protein structure Quality Assessment (QA) is an essential component in protein structure prediction and analysis. The relationship between protein sequence and structure often serves as a basis for protein structure QA. In this work, we developed a new Hidden Markov Model (HMM) to assess the compatibility of protein sequence and structure for capturing their complex relationship. More specifically, the emission of the HMM consists of protein local structures in angular space, secondary structures, and sequence profiles. This model has two capabilities: (1) encoding local structure of each position by jointly considering sequence and structure information, and (2) assigning a global score to estimate the overall quality of a predicted structure, as well as local scores to assess the quality of specific regions of a structure, which provides useful guidance for targeted structure refinement. We compared the HMM model to state-of-art single structure quality assessment methods OPUSCA, DFIRE, GOAP, and RW in protein structure selection. Computational results showed our new score HMM.Z can achieve better overall selection performance on the benchmark datasets.

MUFOLD-DB: a processed protein structure database for protein structure prediction and analysis.

BACKGROUND: Protein structure data in Protein Data Bank (PDB) are widely used in studies of protein function and evolution and in protein structure prediction. However, there are two main barriers in large-scale usage of PDB data: 1) PDB data are highly redundant in terms of sequence and structure similarity; and 2) many PDB files have issues due to inconsistency of data and standards as well as missing residues, so that automated retrieval and analysis are often difficult. DESCRIPTION: To address these issues, we have created MUFOLD-DB http://mufold.org/mufolddb.php, a web-based database, to collect and process the weekly PDB files thereby providing users with non-redundant, cleaned and partially-predicted structure data. For each of the non-redundant sequences, we annotate the SCOP domain classification and predict structures of missing regions by loop modelling. In addition, evolutional information, secondary structure, disorder region, and processed three-dimensional structure are computed and visualized to help users better understand the protein. CONCLUSIONS: MUFOLD-DB integrates processed PDB sequence and structure data and multiple computational results, provides a friendly interface for users to retrieve, browse and download these data, and offers several useful functionalities to facilitate users' data operation.

Neglected Time Intervals Before "1-3-7" Approach About Imported Malaria Cases - China, 2014-2021.

What is already known about this topic?: China's "1-3-7" approach outlines specific targets to guide and monitor the processes of case reporting, investigation, and response. However, few studies have examined the time intervals preceding the initial step, and the timeline from the arrival of imported malaria cases in China to their diagnosis has been largely overlooked. What is added by this report?: The study demonstrated that the median duration from arrival in China to the onset of symptoms for P. ovale was 78 days, with 71.59% of imported cases manifesting symptoms after more than one month. For P. vivax, the median interval was 42 days, with 55.91% exceeding one month. Additionally, the median time from symptom onset to malaria treatment in China between 2014 and 2021 was 2 days, with an interquartile range (IQR) of 1-4 days. What are the implications for public health practice?: This study represents the initial effort to delineate the chronology of imported malaria cases, from their arrival in China to their subsequent treatment. The results underscore the importance of providing malaria health education to populations arriving from overseas. Furthermore, enhancing physician training is crucial for improving the diagnosis of malaria.

Corrigendum: An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction.

[This corrects the article DOI: 10.3389/fncom.2023.1145209.].

Corrigendum: Accurate few-shot object counting with Hough matching feature enhancement.

[This corrects the article DOI: 10.3389/fncom.2023.1145219.].

Accurate few-shot object counting with Hough matching feature enhancement.

Introduction: Given some exemplars, few-shot object counting aims to count the corresponding class objects in query images. However, when there are many target objects or background interference in the query image, some target objects may have occlusion and overlap, which causes a decrease in counting accuracy. Methods: To overcome the problem, we propose a novel Hough matching feature enhancement network. First, we extract the image feature with a fixed convolutional network and refine it through local self-attention. And we design an exemplar feature aggregation module to enhance the commonality of the exemplar feature. Then, we build a Hough space to vote for candidate object regions. The Hough matching outputs reliable similarity maps between exemplars and the query image. Finally, we augment the query feature with exemplar features according to the similarity maps, and we use a cascade structure to further enhance the query feature. Results: Experiment results on FSC-147 show that our network performs best compared to the existing methods, and the mean absolute counting error on the test set improves from 14.32 to 12.74. Discussion: Ablation experiments demonstrate that Hough matching helps to achieve more accurate counting compared with previous matching methods.

An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction.

Human motion prediction is one of the fundamental studies of computer vision. Much work based on deep learning has shown impressive performance for it in recent years. However, long-term prediction and human skeletal deformation are still challenging tasks for human motion prediction. For accurate prediction, this paper proposes a GCN-based two-stage prediction method. We train a prediction model in the first stage. Using multiple cascaded spatial attention graph convolution layers (SAGCL) to extract features, the prediction model generates an initial motion sequence of future actions based on the observed pose. Since the initial pose generated in the first stage often deviates from natural human body motion, such as a motion sequence in which the length of a bone is changed. So the task of the second stage is to fine-tune the predicted pose and make it closer to natural motion. We present a fine-tuning model including multiple cascaded causally temporal-graph convolution layers (CT-GCL). We apply the spatial coordinate error of joints and bone length error as loss functions to train the fine-tuning model. We validate our model on Human3.6m and CMU-MoCap datasets. Extensive experiments show that the two-stage prediction method outperforms state-of-the-art methods. The limitations of proposed methods are discussed as well, hoping to make a breakthrough in future exploration.

Contrastive Bayesian Analysis for Deep Metric Learning.

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabilities of image labels conditioned by their features similarity in a contrastive learning setting. This contrastive Bayesian analysis leads to a new loss function for deep metric learning. To improve the generalization capability of the proposed method onto new classes, we further extend the contrastive Bayesian loss with a metric variance constraint. Our experimental results and ablation studies demonstrate that the proposed contrastive Bayesian metric learning method significantly improves the performance of deep metric learning in both supervised and pseudo-supervised scenarios, outperforming existing methods by a large margin.

Reemergence of Visceral Leishmaniasis in Henan Province, China.

Visceral leishmaniasis (VL) was widely prevalent in Henan Province in the 1950s. Through active efforts by the government, there were no local cases reported from 1984 to 2015. In 2016, local VL cases reoccurred, and there was an increasing trend of VL cases in Henan Province. To provide a scientific control of VL, an investigation was conducted in Henan Province from 2016 to 2021. The data from VL cases were obtained from the Disease Surveillance Reporting System of the Chinese Center for Disease Control and Prevention. The rK39 immunochromatographic test (ICT) and PCR assay were performed among high-risk residents and all dogs in the patients' village. ITS1 was amplified, sequenced, and subjected to phylogenetic analyses. A total of 47 VL cases were reported in Henan Province during 2016-2021. Of the cases, 35 were local, and they were distributed in Zhengzhou, Luoyang, and Anyang. The annual average incidence was 0.008/100,000, showing an upward trend year by year (χ2 = 3.987, p = 0.046). Their ages ranged from 7 months to 71 years, with 44.68% (21/47) in the age group of 0-3 years and 46.81% (22/47) in the age group ≥15 years. The cases occurred throughout the year. The high-risk populations were infants and young children (age ≤3), accounting for 51.06% (24/47), followed by farmers at 36.17% (17/47). The ratio of males to females was 2.13:1. The positive rates of rK39 ICT and PCR were 0.35% (4/1130) and 0.21% (1/468) in the residents. The positive rates of rK39 ICT and PCR were 18.79% (440/2342) and 14.92% (139/929) in the dogs. The ITS1 amplification products in the patients and positive dogs were sequenced. The homology between the target sequence and Leishmania infantum was more than 98%. The phylogenetic analysis indicated that the patients and the positive dogs were infected by the same type of Leishmania, which was consistent with the strains in the hilly endemic areas in China. This paper showed that patients and domestic dogs were infected by the same type of L. infantum and that the positive rate in dogs was relatively high in Henan Province. Because the measures of patient treatment and culling of infected dogs were not effective in reducing VL incidence in Henan Province, it is urgent to develop new approaches for the control of VL, such as wearing insecticide-impregnated collars on dogs, treating the positive dogs, spraying insecticide for sandflies control, and improving residents' self-protection awareness to prevent the further spread of VL in Henan Province.

A Lysosome-Targeted Near-Infrared Fluorescent Probe with Excellent Water Solubility for Surgery Navigation in Breast Cancer.

To get a tumor-targeted contrast agent for imaging guide resection of tumors, we designed a novel fluorescent probe based on the heptamethine cyanine core, Cy7-MO, which has excellent water solubility and near-infrared photophysical and lysosomal targeting properties. The chemical structure of Cy7-MO was characterized by nuclear magnetic resonance spectroscopy and high-resolution mass spectrometry. The toxicity of Cy7-MO was evaluated by cell counting kit-8. Then, a cellular-level study was conducted to evaluate the suborganelle localization in 4T1-Luc1 cells, and it was also used for surgical navigation in orthotopic breast tumor resection in vivo. The results showed that Cy7-MO was well targeted to lysosomes. Importantly, the Cy7-MO probe was found to be well tolerable and exhibited excellent biocompatibility. Moreover, the orthotopic breast tumor margin was clearly visualized through fluorescence guiding of Cy7-MO. Finally, the correct tumor tissues were completely removed, and a negative margin was obtained successfully, which demonstrated an enhanced precision of surgery.

Insecticide resistance of Anopheles sinensis after elimination of malaria in Henan Province, China.

BACKGROUND: Historically, malaria due to Plasmodium vivax has been epidemic in Henan Province, China, with Anopheles sinensis as the main vector. The most effective measures to prevent malaria transmission are based on vector control through the use of insecticides. However, insecticides exert a strong selective pressure on mosquito populations for insecticide resistance. The aim of this study was to investigate the susceptibility profile and population genetic characteristics of An. sinensis to provide basic data and scientific guidance for the study of resistance mechanisms and the control of An. sinensis in Henan Province. METHODS: Adult Anopheles mosquitoes were collected at sites near local farmers' sheepfolds, pigsties and/or cowsheds located in Pingqiao, Xiangfu, Xiangcheng and Tanghe counties/districts of Henan Province during July-September 2021 for insecticide susceptibility testing. Molecular identification of collected mosquitoes as belonging to genus Anopheles was by PCR, and the frequencies of mutations in the knockdown resistance gene (kdr) and acetylcholinesterase-1 gene (ace-1) were detected using gene amplification. The mitochondrial DNA cytochrome oxidase subunit I (COI) gene was amplified in deltamethrin-resistant and deltamethrin-sensitive mosquitoes to analyze the genetic evolutionary relationship. RESULTS: A total of 1409 Anopheles mosquitoes were identified by molecular identification, of which 1334 (94.68%) were An. sinensis, 28 (1.99%) were An. yatsushiroensis, 43 (3.05%) were An. anthropophagus and four (0.28%) were An. belenrae. The 24-h mortality rates of An. sinensis in Pingqiao, Tanghe, Xiangcheng and Xiangfu counties/districts exposed to deltamethrin were 85.85%, 25.38%, 29.73% and 7.66%, respectively; to beta-cyfluthrin, 36.24%, 70.91%, 34.33% and 3.28%, respectively; to propoxur, 68.39%, 80.60%, 37.62% and 9.29%, respectively; and to malathion, 97.43%, 97.67%, 99.21% and 64.23%, respectively. One mutation, G119S, was detected in the ace-1 gene. The frequencies of the main genotypes were 84.21% of specimens collected in Xiangfu (G/S), 90.63% of speciments collected in Xiangcheng (G/G) and 2.44% of speciments collected in Tanghe (S/S). Significantly higher G119S allele frequencies were observed in both propoxur- and malathion-resistant mosquitoes than in their sensitive counterparts in the Tanghe population (P < 0.05). Three mutations, L1014F (41.38%), L1014C (9.15%) and L1014W (0.12%), were detected in the kdr gene. The genotypes with the highest frequency in the populations of An. sinensis in Xiangfu and Tanghe were the mutant TTT (F/F) and wild-type TTG (L/L), at 67.86% (57/84) and 74.29% (52/70), respectively. In Pingqiao and Xiangfu, higher frequencies of the L1014F allele and lower frequencies of the L1014C allele were observed in mosquitoes resistant for beta-cyfluthrin than in those which were sensitive for this insecticide (P < 0.05). The results of Tajima's D and of Fu and Li's D and F were not significantly negative (P > 0.10), and each haplotype was interlaced and did not form two distinct branches. CONCLUSIONS: High resistance to pyrethroids and propoxur was observed at four sites, but the resistance to malathion varied according to the location. Anopheles belenrae and the L1014W (TGG) mutation in An. sinensis were first discovered in Henan Province. The deltamethrin-resistant and deltamethrin-sensitive mosquito populations showed no genetic differentiation. The generation of resistance might be the result of the combination of multiple factors.

Two-Dimensional TiVC Solid-Solution MXene as Surface-Enhanced Raman Scattering Substrate.

Two-dimensional (2D) MXenes are attractive candidates as surface-enhanced Raman scattering (SERS) substrates because of their metallic conductivity and abundant surface terminations. Herein, we report the facile synthesis of bimetallic solid-solution TiVC (MXene) and its application in SERS. The few-layered MXene nanosheets with high crystallinity were successfully prepared using a one-step chemical etching method without ultrasonic and organic solvent intercalation steps. SERS activity of the as-prepared MXene was investigated by fabricating free-standing TiVC film as the substrate. A SERS enhancement factor of 1012 and femtomolar-level detection limit were confirmed using rhodamine 6G as a model dye with 532 nm excitation. The fluorescent signal of the rhodamine 6G dye was effectively quenched, making the SERS spectrum clearly distinguishable. Furthermore, we demonstrate that the TiVC-analyte system with ultrahigh sensitivity is dominated by the chemical mechanism (CM) based on the experimental and simulation results. The abundant density of states near the Fermi level of the TiVC and the strong interaction between the TiVC and analyte promote the intermolecular charge transfer resonance in the TiVC-analyte complex, resulting in significant Raman enhancement. Additionally, several other probe molecules were used for SERS detection to further verify CM-based selectivity enhancement on the TiVC substrates. This work provides guidance for the facile synthesis of 2D MXene and its application in ultrasensitive SERS detection.

Epidemiological characteristics, routine laboratory diagnosis, clinical signs and risk factors for hand, -foot -and -mouth disease: A systematic review and meta-analysis.

BACKGROUND: For the past few years, only a few monovalent EV71 vaccines have been developed, while other enterovirus vaccines are in short supply. We conducted a quantitative meta-analysis to explore the epidemiological characteristics, routine laboratory diagnosis, clinical signs and risk factors for hand, foot and mouth disease (HFMD). METHODS: PubMed, Embase and the Web of Science were searched for eligible reports published before April 16, 2021, with no publication time or language restrictions. The primary outcome was the odds ratio of the epidemiological characteristics, routine laboratory diagnosis, and clinical signs associated with HFMD severity and death. RESULTS: After screening 10522 records, we included 32 articles comprising 781903 cases of hand, foot and mouth disease. Patients with severe illness developed some clinical signs (hypersomnia (OR = 21.97, 95% CI: 4.13 to 116.74), convulsion (OR = 16.18, 95% CI: 5.30 to 49.39), limb shaking (OR = 47.96, 95% CI: 15.17 to 151.67), and breathlessness (OR = 7.48, 95% CI: 1.90 to 29.40)) and had some changes in laboratory parameters (interleukin-6 levels standardized mean difference (SMD) = 1.57, 95%CI: 0.55 to 2.60), an increased neutrophils ratio (SMD = 0.55, 95%CI: 0.17 to 0.93), cluster of differentiation 4 (CD4+) (SMD = -1.38, 95%CI: -2.33 to -0.43) and a reduced lymphocytes ratio (SMD = -0.48, 95%CI: -0.93 to -0.33)) compared with patients with mild illness. The risk factors for death included cyanosis (OR = 5.82, 95% CI: 2.29 to 14.81), a fast heart rate (OR = 3.22, 95% CI: 1.65 to 6.30), vomiting (OR = 2.70, 95% CI: 1.33 to 5.49) and an increased WBC count (SMD = 0.60, 95% CI: 0.27 to 0.93). CONCLUSIONS: China has the highest incidence of HFMD. Our meta-analyses revealed important risk factors that are associated with the severity and mortality of HFMD.

One Health approach to improve the malaria elimination programme in Henan Province.

One Health is a collaborative, multi-sectoral, trans-disciplinary approach with the goal of achieving optimal health outcomes by recognizing the interconnection between people, animals, plants, and the environment and determining how this relates to the control of infectious diseases such as malaria, schistosomiasis and so on. Malarias caused by Plasmodium that commonly infects female Anopheles mosquitoes, which feed on human blood and act as a disease vector. It has been a worldwide important public health problem from ancient times. Also, malaria is one of the infectious diseases with the longest epidemic time and the most serious harm in the history of Henan Province, China. During the past decades, the multi-sectoral, cross-regional, and multi-disciplinary One Health approach contributed to a significant reduction in malaria incidence, resulting in initiation of the Henan Malaria Elimination Action Plan. Herein, we reviewed the history of the fight against malaria in Henan Province. A full picture of malaria epidemics, prevention, and control strategies were showed, with the objective that it will help stakeholders, and policy-makers to take informed decisions on public health issues and intervention designs on malaria control towards elimination in the similar areas.

A multilayer evaluation approach for protein structure prediction and model quality assessment.

Protein tertiary structures are essential for studying functions of proteins at molecular level. An indispensable approach for protein structure solution is computational prediction. Most protein structure prediction methods generate candidate models first and select the best candidates by model quality assessment (QA). In many cases, good models can be produced, but the QA tools fail to select the best ones from the candidate model pool. Because of incomplete understanding of protein folding, each QA method only reflects partial facets of a structure model and thus has limited discerning power with no one consistently outperforming others. In this article, we developed a set of new QA methods, including two QA methods for evaluating target/template alignments, a molecular dynamics (MD)-based QA method, and three consensus QA methods with selected references to reveal new facets of protein structures complementary to the existing methods. Moreover, the underlying relationship among different QA methods were analyzed and then integrated into a multilayer evaluation approach to guide the model generation and model selection in prediction. All methods are integrated and implemented into an innovative and improved prediction system hereafter referred to as MUFOLD. In CASP8 and CASP9, MUFOLD has demonstrated the proof of the principles in terms of both QA discerning power and structure prediction accuracy.

Deformable adversarial registration network with multiple loss constraints.

Deformable medical image registration has the necessary value of theoretical research and clinical application. Traditional methods cannot meet clinical application standards in terms of registration accuracy and efficiency. This article proposes a deformable generate adversarial registration framework, which avoids the dependence on ground-truth deformation. The proposed residual registration network based on Nested U-Net has excellent feature extraction ability and robustness. Multiple constraints that incorporate the potential information of anatomical segmentation extracted by the discriminator can help the model adapt to different modal registration tasks. Through interpatient X-ray chest registration, the deep-supervised training method, and the proposed loss constraint are proved to improve the model's performance and training stability. The experimental results show that our model, compared with state-of-the-art methods, provides a more accurate spatial alignment relationship between different patients' lung organs while ensuring the displacement field's authenticity. Finally, we explored the relationship between the accuracy and validity of the model.

MMDD-Ensemble: A Multimodal Data-Driven Ensemble Approach for Parkinson's Disease Detection.

Parkinson's disease (PD) is the second most common neurological disease having no specific medical test for its diagnosis. In this study, we consider PD detection based on multimodal voice data that was collected through two channels, i.e., Smart Phone (SP) and Acoustic Cardioid (AC). Four types of data modalities were collected through each channel, namely sustained phonation (P), speech (S), voiced (V), and unvoiced (U) modality. The contributions of this paper are twofold. First, it explores optimal data modality and features having better information about PD. Second, it proposes a MultiModal Data-Driven Ensemble (MMDD-Ensemble) approach for PD detection. The MMDD-Ensemble has two levels. At the first level, different base classifiers are developed that are driven by multimodal voice data. At the second level, the predictions of the base classifiers are fused using blending and voting methods. In order to validate the robustness of the propose method, six evaluation measures, namely accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and area under the curve (AUC), are adopted. The proposed method outperformed the best results produced by optimal unimodal framework from both the key evaluation aspects, i.e., accuracy and AUC. Furthermore, the proposed method also outperformed other state-of-the-art ensemble models. Experimental results show that the proposed multimodal approach yields 96% accuracy, 100% sensitivity, 88.88% specificity, 0.914 of MCC, and 0.986 of AUC. These results are promising compared to the recently reported results for PD detection based on multimodal voice data.