Search

Background: Reactive Oxygen Species (ROS) play many roles in the body, such as cell signaling, homeostasis, or protection from harmful bacteria. However, an excess of ROS in the body will damage lipids, proteins, and DNA. Many studies have shown that various environmental factors increase the amount of ROS produced in the body. Antioxidant proteins are responsible for neutralizing these ROS or free radicals. Although the amount of data on protein sequences has increased over the last two decades, we still lack bioinformatics tools to be able to accurately identify antioxidant protein sequences. Furthermore, biochemical methods to determine antioxidant proteins are very expensive and time-consuming. Therefore, a machine learning approach must be used to speed up the computation. Methods: In this study, we propose a new method that combines a convolutional neural network and Random Forest using two features, the normalized PSSM and the best-selected feature of the ProtBert output. Results: Our model gave very good results on the independent test dataset with 97.3% sensitivity and 95.9% specificity. Comparison with current state-of-the-art models shows that our model is superior. We have also installed iAnt as an online website with a friendly interface available at a website: http: //antixiodant.nguyenhongquang.edu.vn. Conclusion: iAnt has been developed to accurately identify the antioxidant protein. It shows results outperforming the existing state-of-the-art methods; it is also available online.

Background Enhancers are non-coding DNA fragments which are crucial in gene regulation (e.g. transcription and translation). Having high locational variation and free scattering in 98% of non-encoding genomes, enhancer identification is, therefore, more complicated than other genetic factors. To address this biological issue, several in silico studies have been done to identify and classify enhancer sequences among a myriad of DNA sequences using computational advances. Although recent studies have come up with improved performance, shortfalls in these learning models still remain. To overcome limitations of existing learning models, we introduce iEnhancer-ECNN, an efficient prediction framework using one-hot encoding and k-mers for data transformation and ensembles of convolutional neural networks for model construction, to identify enhancers and classify their strength. The benchmark dataset from Liu et al.’s study was used to develop and evaluate the ensemble models. A comparative analysis between iEnhancer-ECNN and existing state-of-the-art methods was done to fairly assess the model performance. Results Our experimental results demonstrates that iEnhancer-ECNN has better performance compared to other state-of-the-art methods using the same dataset. The accuracy of the ensemble model for enhancer identification (layer 1) and enhancer classification (layer 2) are 0.769 and 0.678, respectively. Compared to other related studies, improvements in the Area Under the Receiver Operating Characteristic Curve (AUC), sensitivity, and Matthews’s correlation coefficient (MCC) of our models are remarkable, especially for the model of layer 2 with about 11.0%, 46.5%, and 65.0%, respectively. Conclusions iEnhancer-ECNN outperforms other previously proposed methods with significant improvement in most of the evaluation metrics. Strong growths in the MCC of both layers are highly meaningful in assuring the stability of our models.

Background Since protein-DNA interactions are highly essential to diverse biological events, accurately positioning the location of the DNA-binding residues is necessary. This biological issue, however, is currently a challenging task in the age of post-genomic where data on protein sequences have expanded very fast. In this study, we propose iProDNA-CapsNet – a new prediction model identifying protein-DNA binding residues using an ensemble of capsule neural networks (CapsNets) on position specific scoring matrix (PSMM) profiles. The use of CapsNets promises an innovative approach to determine the location of DNA-binding residues. In this study, the benchmark datasets introduced by Hu et al. (2017), i.e., PDNA-543 and PDNA-TEST, were used to train and evaluate the model, respectively. To fairly assess the model performance, comparative analysis between iProDNA-CapsNet and existing state-of-the-art methods was done. Results Under the decision threshold corresponding to false positive rate (FPR) ≈ 5%, the accuracy, sensitivity, precision, and Matthews’s correlation coefficient (MCC) of our model is increased by about 2.0%, 2.0%, 14.0%, and 5.0% with respect to TargetDNA (Hu et al., 2017) and 1.0%, 75.0%, 45.0%, and 77.0% with respect to BindN+ (Wang et al., 2010), respectively. With regards to other methods not reporting their threshold settings, iProDNA-CapsNet also shows a significant improvement in performance based on most of the evaluation metrics. Even with different patterns of change among the models, iProDNA-CapsNets remains to be the best model having top performance in most of the metrics, especially MCC which is boosted from about 8.0% to 220.0%. Conclusions According to all evaluation metrics under various decision thresholds, iProDNA-CapsNet shows better performance compared to the two current best models (BindN and TargetDNA). Our proposed approach also shows that CapsNet can potentially be used and adopted in other biological applications.

To assess the safety and effectiveness of Schlemm canal stenting for reducing intraocular pressure (IOP) in combination with cataract surgery in the United States cohort of the HORIZON study.Twenty-six clinical sites in the U.S.Prospective clinical trial.Eyes with mild to moderate primary open-angle glaucoma (POAG) on 1 to 4 medications, significant cataract, and an unmedicated diurnal IOP between 22 mm Hg and 34 mm Hg after medication washout were randomized 2:1 to receive the Hydrus microstent or no further treatment after successful cataract surgery. Patients were followed for 24 months. Medication washout and diurnal IOP measurements were repeated at 12 months and 24 months.Two hundred nineteen eyes were randomized to microstent implantation and 112 patients to phacoemulsification only. At 24 months, the diurnal IOP was reduced by 20.0% or more in a greater proportion of eyes in the microstent group (78.5% versus 54.5%; P .001). The mean change in the number of medications was -1.2 ± 0.9 (SD) in the microstent group and -0.8 ± 1.1 in the phaco-only group (P .001), and 78.5% of eyes and 39.2% of eyes, respectively, were medication free (difference 38.8%; P .001).Implantation of a Schlemm canal microstent after phacoemulsification significantly reduced diurnal IOP and medication use compared with phacoemulsification only in patients with mild to moderately severe POAG. The combination procedure was equivalent to cataract surgery alone in terms of visual acuity outcomes and the rate of adverse ocular events.

Hand pose estimation has recently attracted increasing research interest, especially with the advance of deep learning. Albeit many successes, the current state of research does present some opportunities for improvement of estimation accuracy. This paper presents several image enhancement techniques to embed with existing deep learning architectures to improve the performance of hand pose estimation. In particular, we propose a preprocessing approach for image data using a low light illuminance model or a dehazing algorithm before passing the image data to a hand pose estimation model. Both the preprocessing methods are evaluated on a rendered hand-pose dataset using different evaluation metrics. The experimental results shows success in boosting the performance of hand pose estimation for both 2D and 3D image data.

Rehabilitation of the hands is crucial for stroke survivors to regain their ability to perform activities of daily living. Various technologies were explored and found unmatured, expensive and uncomfortable. Existing devices to assist rehabilitation are typically costly, bulky and difficult to set up. Our proposed solution aims to provide an end-to-end hand rehabilitation system that can be produced at low cost with greater ease of use. It incorporates gamification to motivate stroke survivors to perform physical rehabilitation through an infra-red depth camera and computer system. MediaPipe was employed for hand detection and hand landmark extraction. A single-shot neural network model is proposed for hand gesture detection with an accuracy rate of 98%. Lastly, a visually interactive game was developed to promote engagement of the user during the performance of rehabilitation.

Using machine learning in health care for supporting doctors to diagnose diseases is receiving a lot of research interest. Currently, many hospitals use Electronic Health Records (EHR) to store medical records, which is an extremely valuable data source for machine learning. This paper uses the Medical Information Mart for Intensive Care (MIMIC-III) dataset to solve the problem of predicting mortality in hospitals. We have proposed standardizing numerical attributes in two ways: normalizing using mean and variance on Training set and standardizing using mean and variance according to 48 h of each sample. Neural network architectures based on CNN models have been proposed and tested. Ensemble technique has been applied to each parameter representation type and each model type. Test results show that the ensemble method has improved the performance of the system. Test results on the Test set achieve AUROC is 0.851, AUPRC is 0.452 and min (Se, + P) is 0.459.

This paper describes the method of building a X-ray database for Mammography on Vietnamese patients that we collected at Hanoi Medical University Hospital. This dataset has 4664 images (Dicom) corresponding to 1161 standard patients with uniform distribution according to BIRAD from 0 to 5. This paper also presents the method of detecting Region of Interest (ROI) in mammogram based on Mask R-CNN architecture. The method of determining the ROI for accuracy mAP@0.5 = 0.8109 and the accuracy of classification BIRAD levels is 58.44%.

Prostate MP-MRI scan is a non-invasive method of detecting early stage prostate cancer which is increasing in popularity. However, this imaging modality requires highly skilled radiologists to interpret the images which incurs significant time and cost. Convolutional neural networks may alleviate the workload of radiologists by discriminating between prostate tumor positive scans and negative ones, allowing radiologists to focus their attention on a subset of scans that are neither clearly positive nor negative. The major challenges of such a system are speed and accuracy. In order to address these two challenges, a new approach using ensemble learning of convolutional neural networks (CNNs) was proposed in this paper, which leverages different imaging modalities including T2 weight, B-value, ADC and Ktrans in a multi-parametric MRI clinical dataset with 330 samples of 204 patients for training and evaluation. The results of prostate tumor identification will display benign or malignant based on extracted features by the individual CNN models in seconds. The ensemble of the four individual CNN models for different image types improves the prediction accuracy to 92% with sensitivity at 94.28% and specificity at 86.67% among given 50 test samples. The proposed framework potentially provides rapid classification in high-volume quantitative prostate tumor samples.

This paper presents a method for building a real estate chatbot automatically to support customers in Vietnamese. The chatbot is trained with data set collected on Facebook groups and from the famous real estate website in Vietnam. Using Logistic Regression, user’s intent recognition task achieves precision = 0.93, recall = 0.87 and F1-score = 0.89, while the automatic entity labeling achieves 83% accuracy thanks to the development of a real estate knowledge base. Besides, we report our experience on the design of dialog management modules.

The number of smart phone and smartphone users has increased rapidly, boosting the growth of mobile advertising. Predicting the percentage of users who click on an advertisement when displayed on an application (CTR: Click Through Rate) plays an important role in choosing an advertising push strategy for each application. However, because the field of mobile advertising is still new, the study of solutions to these problems is only for Web advertising. This paper presents a new predictive method based on Matrix Factorization (MF) algorithm. The paper also proposes a method of integrating the reliability of data into MF algorithms. The method was tested on actual data provided by Amobi advertising company with 1.7 million records including 300 advertisements and 400 mobile device applications. The AUC (Area Under The Curve) value obtained on the test set is 0.9037 with MF and 0.9411 when integrating reliability into the MF algorithm. Thus, the results show that the predictive quality is significantly improved when integrating data reliability and evaluation into MF algorithms.

In meetings, whiteboards are a useful tool for speakers to illustrate information, show diagrams and charts. After meetings, users always need to store the information that has been written, drawn on the board in the form of appropriate digitization as PowerPoint format. In this study, we first used pre-processing techniques to detect the frame of whiteboard from the whiteboard image and perform defatting. Next, we built the Faster RCNN model to detect three basic types of shapes, including circles, triangles and rectangles. Finally we use Line Segment Detector to detect the line segments. The research results show that our method with Faster RCNN model accurately detected the basic shapes on the whiteboard image with the Faster RCNN model, resulting in mAP@0.5 reaching 92.35% and the rate of detection of straight line with recall = 93.8%.

Background Pseudouridine modification is most commonly found among various kinds of RNA modification occurred in both prokaryotes and eukaryotes. This biochemical event has been proved to occur in multiple types of RNAs, including rRNA, mRNA, tRNA, and nuclear/nucleolar RNA. Hence, gaining a holistic understanding of pseudouridine modification can contribute to the development of drug discovery and gene therapies. Although some laboratory techniques have come up with moderately good outcomes in pseudouridine identification, they are costly and required skilled work experience. We propose iPseU-NCP – an efficient computational framework to predict pseudouridine sites using the Random Forest (RF) algorithm combined with nucleotide chemical properties (NCP) generated from RNA sequences. The benchmark dataset collected from Chen et al. (2016) was used to develop iPseU-NCP and fairly compare its performances with other methods. Results Under the same experimental settings, comparing with three state-of-the-art methods including iPseU-CNN, PseUI, and iRNA-PseU, the Matthew’s correlation coefficient (MCC) of our model increased by about 20.0%, 55.0%, and 109.0% when tested on the H. sapiens (H_200) dataset and by about 6.5%, 35.0%, and 150.0% when tested on the S. cerevisiae (S_200) dataset, respectively. This significant growth in MCC is very important since it ensures the stability and performance of our model. With those two independent test datasets, our model also presented higher accuracy with a success rate boosted by 7.0%, 13.0%, and 20.0% and 2.0%, 9.5%, and 25.0% when compared to iPseU-CNN, PseUI, and iRNA-PseU, respectively. For majority of other evaluation metrics, iPseU-NCP demonstrated superior performance as well. Conclusions iPseU-NCP combining the RF and NPC-encoded features showed better performances than other existing state-of-the-art methods in the identification of pseudouridine sites. This also shows an optimistic view in addressing biological issues related to human diseases.