ASCRB: Multi-view based attentional feature selection for CircRNA-binding site prediction.

CircRNA is a non-coding RNA with a special circular structure, which plays a key role in a variety of life activities by interacting with RNA-binding proteins through CircRNA binding sites. Therefore, accurately identifying CircRNA binding sites is of great importance for gene regulation. In previous studies, most of the methods are based on single-view or multi-view features. Considering that single-view methods provide less effective information, the current mainstream methods mainly focus on extracting rich relevant features by constructing multiple views. However, the increasing number of views leads to a large amount of redundant information, which is detrimental to the detection of CircRNA binding sites. Therefore, to solve this problem, we propose to use the channel attention mechanism to further obtain useful multi-view features by filtering out invalid information in each view. First, we use five feature encoding schemes to construct multi-view. Then, we calibrate the features by generating the global representation of each view, filtering out redundant information to retain important feature information. Finally, features obtained from multiple views are fused to detect RNA binding sites. To validate the effectiveness of the method, we compared its performance on 37 CircRNA-RBP datasets with existing methods. Experimental results show that the average AUC performance of our method is 93.85%, which is better than the current state-of-the-art methods. We also provide the source code, which can be accessed at https://github.com/dxqllp/ASCRB for access.

A Double-Teacher Model Capable of Exploiting Isomorphic and Heterogeneous Discrepancy Information for Medical Image Segmentation.

Deep learning, with continuous development, has achieved relatively good results in the field of left atrial segmentation, and numerous semi-supervised methods in this field have been implemented based on consistency regularization to obtain high-performance 3D models by training. However, most semi-supervised methods focus on inter-model consistency and ignore inter-model discrepancy. Therefore, we designed an improved double-teacher framework with discrepancy information. Herein, one teacher learns 2D information, another learns both 2D and 3D information, and the two models jointly guide the student model for learning. Simultaneously, we extract the isomorphic/heterogeneous discrepancy information between the predictions of the student and teacher model to optimize the whole framework. Unlike other semi-supervised methods based on 3D models, ours only uses 3D information to assist 2D models, and does not have a fully 3D model, thus addressing the large memory consumption and limited training data of 3D models to some extent. Our approach shows excellent performance on the left atrium (LA) dataset, similar to that of the best performing 3D semi-supervised methods available, compared to existing techniques.

TSRL-Net: Target-aware supervision residual learning for stroke segmentation.

Accurate stroke segmentation is a crucial task in establishing a computer-aided diagnostic system for brain diseases. However, reducing false negatives and accurately segmenting strokes in MRI images is often challenging because of the class imbalance and intraclass ambiguities problems. To address these issues, we propose a novel target-aware supervision residual learning framework for stroke segmentation. Considering the problem of imbalance of positive and negative samples, a creatively target-aware loss function is designed to dilate strong attention regions, pay high attention to the positive sample losses, and compensate for the loss of negative samples around the target. Then, a coarse-grained residual learning module is developed to gradually fix the lost residual features during the decoding phase to alleviate the problem of high number of false negatives caused by intraclass ambiguities. Here, our reverse/positive attention unit suppresses redundant target/background noise and allows relatively more focused highlighting of important features in the target residual region. Extensive experiments were performed on the Anatomical Tracings of Lesions After Stroke and Ischemic Stroke Lesion Segmentation public datasets, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.

Multimodal adversarial representation learning for breast cancer prognosis prediction.

With the increasing incidence of breast cancer, accurate prognosis prediction of breast cancer patients is a key issue in current cancer research, and it is also of great significance for patients' psychological rehabilitation and assisting clinical decision-making. Many studies that integrate data from different heterogeneous modalities such as gene expression profile, clinical data, and copy number alteration, have achieved greater success than those with only one modality in prognostic prediction. However, many of these approaches that exist fail to dramatically reduce the modality gap by aligning multimodal distributions. Therefore, it is crucial to develop a method that fully considers a modality-invariant embedding space to effectively integrate multimodal data. In this study, to reduce the modality gap, we propose a multimodal data adversarial representation framework (MDAR) to reduce the modal heterogeneity by translating source modalities into distributions for the target modality. Additionally, we apply reconstruction and classification losses to embedding space to further constrain it. Then, we design a multi-scale bilinear convolutional neural network (MS-B-CNN) for uni-modality to improve the feature expression ability. In addition, the embedding space generates predictions as stacked feature inputs to the extremely randomized trees classifier. With 10-fold cross-validation, our results show that the proposed adversarial representation learning improves prognostic performance. A comparative study of this method and other existing methods on the METABRIC (1980 patients) dataset showed that Matthews correlation coefficient (Mcc) was significantly enhanced by 7.4% in the prognosis prediction of breast cancer patients.

Deep Multi-Label Joint Learning for RNA and DNA-Binding Proteins Prediction.

The recognition of DNA- (DBPs) and RNA-binding proteins (RBPs) is not only conducive to understanding cell function, but also a challenging task. Previous studies have shown that these proteins are usually considered separately due to different binding domains. In addition, due to the high similarity between DBPs and RBPs, it is possible for DBPs predictor to predict RBPs as DBPs, and vice versa, which leads to high cross-prediction rate. In this study, we creatively propose a novel deep multi-label joint learning framework to leverage the relationship between multiple labels and binding proteins. First, a multi-label variant network is designed to explore multi-scale context hidden information. Then, multi-label Long Short-Term Memory (multiLSTM) is used to mine the potential relationship between labels. Finally, the calibrated hidden features from variant network are considered for different levels of joint learning so that multiLSTM can better explore the correlation between them. Extensive experiments are also carried out to compare the proposed method with other existing methods. Furthermore, we also provide further insights into the importance of the relevant bioanalysis of proteins obtained from our model and summarize these binding proteins that are significantly related to a disease. Our method is freely available at http://39.108.90.186/dmlj.

JLCRB: A unified multi-view-based joint representation learning for CircRNA binding sites prediction.

CircRNAs usually bind to the corresponding RBPs(RNA Binding proteins) and play a key role in gene regulation. Therefore, it is important to identify the binding sites of RBPs on CircRNAs for the regulation of certain diseases. Due to the information provided by the single view feature is limited, the current mainstream methods are mainly to detect the RBP binding sites by constructing multi-view models. However, with the number of view features increases, the invalid information also increases, and the existing methods only simply concatenate together various features from different views, while ignoring the intrinsic connection between multi-view data. To solve this problem, we propose a new multi-view joint representation learning network by improving the consistency of multi-view feature information. First, the network uses different feature encoding methods to fully extract the feature information of RNA, respectively. Then we construct the intrinsic connection between the views by generating a global joint representation of multiple views, and this is used for feature calibration of each view to highlight important features and suppress unimportant ones. Finally, the depth features obtained from the fusion of multiple views are used to detect the binding sites of RNAs. The average AUC of our method is 93.68% in 37 CircRNA-RBP datasets. The experimental results show that the prediction performance of the method is better than existing methods. The code and datasets are obtained at https://github.com/Xuezg/JLCRB. In addition, we also provide a free web server that is freely available at http://82.157.188.204/JLCRB/.

AGMR-Net: Attention-guided multiscale recovery framework for stroke segmentation.

Automatic and accurate lesion segmentation is critical to the clinical estimation of the lesion status of stroke diseases and appropriate diagnostic systems. Although existing methods have achieved remarkable results, their further adoption is hindered by: (1) intraclass inconsistency, i.e., large variability between different areas of the lesion; and (2) interclass indistinction, in which normal brain tissue resembles the lesion in appearance. To meet these challenges in stroke segmentation, we propose a novel method, namely attention-guided multiscale recovery framework (AGMR-Net) in this paper. Firstly, a coarse-grained patch attention (CPA) module in the encoding is adopted to obtain a patch-based coarse-grained attention map in a multistage, explicitly supervised way, enabling target spatial context saliency representation with a patch-based weighting technique that eliminates the effect of intraclass inconsistency. Secondly, to obtain more detailed boundary partitioning to meet the challenge of interclass indistinction, a newly designed cross-dimensional feature fusion (CFF) module is used to capture global contextual information to further guide the selective aggregation of 2D and 3D features, which can compensate for the lack of boundary learning capability of 2D convolution. Lastly, in the decoding stage, an innovative designed multiscale deconvolution upsampling (MDU) is used for enhanced recovery of target spatial and boundary information. AGMR-Net is evaluated on the open-source dataset Anatomical Tracings of Lesions After Stroke, achieving the highest Dice similarity coefficient of 0.594, Hausdorff distance of 27.005 mm, and average symmetry surface distance of 7.137 mm, which demonstrates that our proposed method outperforms state-of-the-art methods and has great potential for stroke diagnosis.

DeepBtoD: Improved RNA-binding proteins prediction via integrated deep learning.

RNA-binding proteins (RBPs) have crucial roles in various cellular processes such as alternative splicing and gene regulation. Therefore, the analysis and identification of RBPs is an essential issue. However, although many computational methods have been developed for predicting RBPs, a few studies simultaneously consider local and global information from the perspective of the RNA sequence. Facing this challenge, we present a novel method called DeepBtoD, which predicts RBPs directly from RNA sequences. First, a [Formula: see text]-BtoD encoding is designed, which takes into account the composition of [Formula: see text]-nucleotides and their relative positions and forms a local module. Second, we designed a multi-scale convolutional module embedded with a self-attentive mechanism, the ms-focusCNN, which is used to further learn more effective, diverse, and discriminative high-level features. Finally, global information is considered to supplement local modules with ensemble learning to predict whether the target RNA binds to RBPs. Our preliminary 24 independent test datasets show that our proposed method can classify RBPs with the area under the curve of 0.933. Remarkably, DeepBtoD shows competitive results across seven state-of-the-art methods, suggesting that RBPs can be highly recognized by integrating local [Formula: see text]-BtoD and global information only from RNA sequences. Hence, our integrative method may be useful to improve the power of RBPs prediction, which might be particularly useful for modeling protein-nucleic acid interactions in systems biology studies. Our DeepBtoD server can be accessed at http://175.27.228.227/DeepBtoD/.

Two-stage segmentation network with feature aggregation and multi-level attention mechanism for multi-modality heart images.

Accurate segmentation of cardiac substructures in multi-modality heart images is an important prerequisite for the diagnosis and treatment of cardiovascular diseases. However, the segmentation of cardiac images remains a challenging task due to (1) the interference of multiple targets, (2) the imbalance of sample size. Therefore, in this paper, we propose a novel two-stage segmentation network with feature aggregation and multi-level attention mechanism (TSFM-Net) to comprehensively solve these challenges. Firstly, in order to improve the effectiveness of multi-target features, we adopt the encoder-decoder structure as the backbone segmentation framework and design a feature aggregation module (FAM) to realize the multi-level feature representation (Stage1). Secondly, because the segmentation results obtained from Stage1 are limited to the decoding of single scale feature maps, we design a multi-level attention mechanism (MLAM) to assign more attention to the multiple targets, so as to get multi-level attention maps. We fuse these attention maps and concatenate the output of Stage1 to carry out the second segmentation to get the final segmentation result (Stage2). The proposed method has better segmentation performance and balance on 2017 MM-WHS multi-modality whole heart images than the state-of-the-art methods, which demonstrates the feasibility of TSFM-Net for accurate segmentation of heart images.

DFpin: Deep learning-based protein-binding site prediction with feature-based non-redundancy from RNA level.

The interaction between proteins and RNA is closely related to various human diseases. Computer-aided drug design can be facilitated by detecting the RNA sites that bind proteins. However, due to the aggregation of binding sites in RNA sequences, high sample similarity occurs when extracting RNA fragments by using a sliding window. Considering these problems, we present a method, DFpin, to predict protein-interacting nucleotides in RNA. To retain more key nucleotide sites, we used the redundancy method based on feature similarity, that is, feature redundancy is removed based on the RNA mono-nucleotide composition to maintain the diversity of RNA samples and avoid the residue of redundant data. In addition, to extract key abstract features and avoid over-fitting, we used the cascade structure of a deep forest model to predict protein-interacting nucleotides. Overall, DFpin demonstrated excellent classification with 85.4% accuracy and 93.3% area under the curve. Compared with other methods, the accuracy of DFpin was better, suggesting that feature-based redundancy removal and deep forest can help predict nucleotides of protein interactions. The source code and all dataset are available at: https://github.com/zhaoxj-tech/DFpin.git.

Constraint-Based Unsupervised Domain Adaptation Network for Multi-Modality Cardiac Image Segmentation.

The cardiac CT and MRI images depict the various structures of the heart, which are very valuable for analyzing heart function. However, due to the difference in the shape of the cardiac images and imaging techniques, automatic segmentation is challenging. To solve this challenge, in this paper, we propose a new constraint-based unsupervised domain adaptation network. This network first performs mutual translation of images between different domains, it can provide training data for the segmentation model, and ensure domain invariance at the image level. Then, we input the target domain into the source domain segmentation model to obtain pseudo-labels and introduce cross-domain self-supervised learning between the two segmentation models. Here, a new loss function is designed to ensure the accuracy of the pseudo-labels. In addition, a cross-domain consistency loss is also introduced. Finally, we construct a multi-level aggregation segmentation network to obtain more refined target domain information. We validate our method on the public whole heart image segmentation challenge dataset and obtain experimental results of 82.9% and 5.5 on dice and average symmetric surface distance (ASSD), respectively. These experimental results prove that our method can provide important assistance in the clinical evaluation of unannotated cardiac datasets.

TSU-net: Two-stage multi-scale cascade and multi-field fusion U-net for right ventricular segmentation.

Accurate segmentation of the right ventricle from cardiac magnetic resonance images (MRI) is a critical step in cardiac function analysis and disease diagnosis. It is still an open problem due to some difficulties, such as a large variety of object sizes and ill-defined borders. In this paper, we present a TSU-net network that grips deeper features and captures targets of different sizes with multi-scale cascade and multi-field fusion in the right ventricle. TSU-net mainly contains two major components: Dilated-Convolution Block (DB) and Multi-Layer-Pool Block (MB). DB extracts and aggregates multi-scale features for the right ventricle. MB mainly relies on multiple effective field-of-views to detect objects at different sizes and fill boundary features. Different from previous networks, we used DB and MB to replace the convolution layer in the encoding layer, thus, we can gather multi-scale information of right ventricle, detect different size targets and fill boundary information in each encoding layer. In addition, in the decoding layer, we used DB to replace the convolution layer, so that we can aggregate the multi-scale features of the right ventricle in each decoding layer. Furthermore, the two-stage U-net structure is used to further improve the utilization of DB and MB through a two-layer encoding/decoding layer. Our method is validated on the RVSC, a public right ventricular data set. The results demonstrated that TSU-net achieved an average Dice coefficient of 0.86 on endocardium and 0.90 on the epicardium, thereby outperforming other models. It effectively assists doctors to diagnose the disease and promotes the development of medical images. In addition, we also provide an intuitive explanation of our network, which fully explain MB and TSU-net's ability to detect targets of different sizes and fill in boundary features.

Prediction of DNA binding proteins using local features and long-term dependencies with primary sequences based on deep learning.

DNA-binding proteins (DBPs) play pivotal roles in many biological functions such as alternative splicing, RNA editing, and methylation. Many traditional machine learning (ML) methods and deep learning (DL) methods have been proposed to predict DBPs. However, these methods either rely on manual feature extraction or fail to capture long-term dependencies in the DNA sequence. In this paper, we propose a method, called PDBP-Fusion, to identify DBPs based on the fusion of local features and long-term dependencies only from primary sequences. We utilize convolutional neural network (CNN) to learn local features and use bi-directional long-short term memory network (Bi-LSTM) to capture critical long-term dependencies in context. Besides, we perform feature extraction, model training, and model prediction simultaneously. The PDBP-Fusion approach can predict DBPs with 86.45% sensitivity, 79.13% specificity, 82.81% accuracy, and 0.661 MCC on the PDB14189 benchmark dataset. The MCC of our proposed methods has been increased by at least 9.1% compared to other advanced prediction models. Moreover, the PDBP-Fusion also gets superior performance and model robustness on the PDB2272 independent dataset. It demonstrates that the PDBP-Fusion can be used to predict DBPs from sequences accurately and effectively; the online server is at http://119.45.144.26:8080/PDBP-Fusion/.

Using Chou's 5-Step Rule to Predict DNA-Protein Binding with Multi-scale Complementary Feature.

It is well known that DNA-protein binding (DPB) prediction is not only beneficial to understand the regulation mechanism of gene expression but also a challenging task in the field of computational biology. Traditional methods for DPB prediction that depend on manually extracted features may lead to classification errors. Recently, deep learning such as convolutional neural network (CNN) has been successfully applied to classification tasks and improved DPB prediction performance significantly. Yet, these methods are based on the original DNA sequence modeling, ignoring the hidden complex dependency and complementarity between multiple sequence features. In consideration of this problem, we propose a method to fuse different sequence features and analyze them systematically through multi-scale CNN. First, sliding windows of specified lengths are set on distinct DNA sequences to generate multiple sequence features with unequal lengths. Second, multiple feature sequences are fused and encoded for feature representation. Third, multi-scale CNN with different binding motif lengths is used to automatically learn and mine the influence of internal attributes and hidden complex relations between the fusion sequence features and make full use of the complementary advantages of extracted CNN features to predict DPB. When our model is applied to 690 ChIP-seq datasets, it achieves an average AUC of 0.9112, which is significantly better than the latest methods. The results show that our method is effective for DPB prediction and is freely available at http://121.5.71.120/mscDPB/.

Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention.

Three-dimensional late gadolinium enhanced (LGE) cardiac MR (CMR) of left atrial scar in patients with atrial fibrillation (AF) has recently emerged as a promising technique to stratify patients, to guide ablation therapy and to predict treatment success. This requires a segmentation of the high intensity scar tissue and also a segmentation of the left atrium (LA) anatomy, the latter usually being derived from a separate bright-blood acquisition. Performing both segmentations automatically from a single 3D LGE CMR acquisition would eliminate the need for an additional acquisition and avoid subsequent registration issues. In this paper, we propose a joint segmentation method based on multiview two-task (MVTT) recursive attention model working directly on 3D LGE CMR images to segment the LA (and proximal pulmonary veins) and to delineate the scar on the same dataset. Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently ( ∼ 0.27 s to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices). Compared to conventional unsupervised learning and other state-of-the-art deep learning based methods, the proposed MVTT model achieved excellent results, leading to an automatic generation of a patient-specific anatomical model combined with scar segmentation for patients in AF.

An integrated deep learning framework for joint segmentation of blood pool and myocardium.

Simultaneous and automatic segmentation of the blood pool and myocardium is an important precondition for early diagnosis and pre-operative planning in patients with complex congenital heart disease. However, due to the high diversity of cardiovascular structures and changes in mechanical properties caused by cardiac defects, the segmentation task still faces great challenges. To overcome these challenges, in this study we propose an integrated multi-task deep learning framework based on the dilated residual and hybrid pyramid pooling network (DRHPPN) for joint segmentation of the blood pool and myocardium. The framework consists of three closely connected progressive sub-networks. An inception module is used to realize the initial multi-level feature representation of cardiovascular images. A dilated residual network (DRN), as the main body of feature extraction and pixel classification, preliminary predicts segmentation regions. A hybrid pyramid pooling network (HPPN) is designed for facilitating the aggregation of local information to global information, which complements DRN. Extensive experiments on three-dimensional cardiovascular magnetic resonance (CMR) images (the available dataset of the MICCAI 2016 HVSMR challenge) demonstrate that our approach can accurately segment the blood pool and myocardium and achieve competitive performance compared with state-of-the-art segmentation methods.

Segmentation and visualization of left atrium through a unified deep learning framework.

PURPOSE: Left atrium segmentation and visualization serve as a fundamental and crucial role in clinical analysis and understanding of atrial fibrillation. However, most of the existing methods are directly transmitting information, which may cause redundant information to be passed to affect segmentation performance. Moreover, they did not further consider atrial visualization after segmentation, which leads to a lack of understanding of the essential atrial anatomy. METHODS: We propose a novel unified deep learning framework for left atrium segmentation and visualization simultaneously. At first, a novel dual-path module is used to enhance the expressiveness of cardiac image representation. Then a multi-scale context-aware module is designed to effectively handle complex appearance and shape variations of the left atrium and associated pulmonary veins. The generated multi-scale features are feed to gated bidirectional message passing module to remove irrelevant information and extract discriminative features. Finally, the features after message passing are efficiently combined via a deep supervision mechanism to produce the final segmentation result and reconstruct 3D volumes. RESULTS: Our approach primarily against the 2018 left atrium segmentation challenge dataset, which consists of 100 3D gadolinium-enhanced magnetic resonance images. Our method achieves an average dice of 0.936 in segmenting the left atrium via fivefold cross-validation, which outperforms state-of-the-art methods. CONCLUSIONS: The performance demonstrates the effectiveness and advantages of our network for the left atrium segmentation and visualization. Therefore, our proposed network could potentially improve the clinical diagnosis and treatment of atrial fibrillation.

DeepCQ: Deep multi-task conditional quantification network for estimation of left ventricle parameters.

BACKGROUND AND OBJECTIVE: Automatic cardiac left ventricle (LV) quantification plays an important role in assessing cardiac function. Although many advanced methods have been put forward to quantify related LV parameters, automatic cardiac LV quantification is still a challenge task due to the anatomy construction complexity of heart. METHODS: In this work, we propose a novel deep multi-task conditional quantification learning model (DeepCQ) which contains Segmentation module, Quantification encoder, and Dynamic analysis module. Besides, we also use task uncertainty loss function to update the parameters of the network in training. RESULTS: The proposed framework is validated on the dataset from Left Ventricle Full Quantification Challenge MICCAI 2018 (https://lvquan18.github.io/). The experimental results show that DeepCQ outperforms the other advanced methods. CONCLUSIONS: It illustrates that our method has a great potential in comprehensive cardiac function assessment and could play an auxiliary role in clinicians' diagnosis.

econvRBP: Improved ensemble convolutional neural networks for RNA binding protein prediction directly from sequence.

RNA binding proteins (RBPs) determine RNA process from synthesis to decay, which play a key role in RNA transport, translation and degradation. Therefore, exploring RBPs' function from the amino acid sequence using computational methods has become one of the momentous topics in genome annotation. However, there still have some challenges: (1) shallow feature: Although the sequence determines structure is self-evident, it is difficult to analyze the essential features from simple sequence. (2) Poorly understand: feature-based prediction methods mainly emphasize feature extraction, while in-depth understanding of protein mysteries limits the application of feature engineering. (3) Feature fusion: multi-feature fusion is often used, but the features are not well integrated. In view of these challenges, we propose a novel ensemble convolutional neural network (econvRBP) to predict RBPs. In order to capture the local and global features of RNA binding proteins simultaneously, first of all, One Hot and Conjoint Triad encoding methods are used to transform amino acid sequence into local and global features, respectively. After that the local and global features are combined for further high-level feature extraction using convolutional neural networks. Some experiments are constructed to evaluate our method with 10-fold cross validation and the results show that it has achieved the best performance among all the predictors so far. We correctly predicted 99% of 2875 RBPs and 99% of 6782 non-RBPs with accuracy of 0.99. In addition, the datasets provided by RBPPred are also used to validate our models with an accuracy of 0.87. These results indicate that the econvRBP is the most excellent method at present, and will provide reliable guidance for the detection of RBPs. econvRBP is available at http://47.100.203.218:3389/home.html/.

MsDBP: Exploring DNA-Binding Proteins by Integrating Multiscale Sequence Information via Chou's Five-Step Rule.

DNA-binding proteins are crucial to alternative splicing, methylation, and the structural composition of the DNA. The existing experimental methods for identifying DNA-binding proteins are expensive and time-consuming; thus, it is necessary to develop a fast and accurate computational method to address the problem. In this Article, we report a novel predictor MsDBP, a DNA-binding protein prediction method that combines the multiscale sequence feature into a deep neural network. First of all, instead of developing a narrow-application structured-based method, we are committed to a sequenced-based predictor. Second, instead of characterizing the whole protein directly, we divide the protein into subsequences with different lengths and then encode them into a vector based on composition information. In this way, the multiscale sequence feature can be obtained. Finally, a branch of dense layers is applied for learning multilevel abstract features to discriminate DNA-binding proteins. When MsDBP is tested on the independent data set PDB2272, it achieves an overall accuracy of 66.99% with the SE of 70.69%. In addition, we also perform extensive experiments to compare the proposed method with other existing methods. The results indicate that MsDBP would be a useful tool for the identification of DNA-binding proteins. MsDBP is freely available at a web server on http://47.100.203.218/MsDBP/ .