Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Enhancing web search result clustering model based on multiview multirepresentation consensus cluster ensemble (mmcc) approach.

In PloS one ; h5-index 176.0

Existing text clustering methods utilize only one representation at a time (single view), whereas multiple views can represent documents. The multiview multirepresentation method enhances clustering quality. Moreover, existing clustering methods that utilize more than one representation at a time (multiview) use representation with the same nature. Hence, using multiple views that represent data in a different representation with clustering methods is reasonable to create a diverse set of candidate clustering solutions. On this basis, an effective dynamic clustering method must consider combining multiple views of data including semantic view, lexical view (word weighting), and topic view as well as the number of clusters. The main goal of this study is to develop a new method that can improve the performance of web search result clustering (WSRC). An enhanced multiview multirepresentation consensus clustering ensemble (MMCC) method is proposed to create a set of diverse candidate solutions and select a high-quality overlapping cluster. The overlapping clusters are obtained from the candidate solutions created by different clustering methods. The framework to develop the proposed MMCC includes numerous stages: (1) acquiring the standard datasets (MORESQUE and Open Directory Project-239), which are used to validate search result clustering algorithms, (2) preprocessing the dataset, (3) applying multiview multirepresentation clustering models, (4) using the radius-based cluster number estimation algorithm, and (5) employing the consensus clustering ensemble method. Results show an improvement in clustering methods when multiview multirepresentation is used. More importantly, the proposed MMCC model improves the overall performance of WSRC compared with all single-view clustering models.

Sabah Ali, Tiun Sabrina, Sani Nor Samsiah, Ayob Masri, Taha Adil Yaseen

2021

General General

Deep learning for intelligent diagnosis in thyroid scintigraphy.

In The Journal of international medical research

OBJECTIVE : To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy.

METHODS : We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model's performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents.

RESULTS : The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided "diagnostic assistance" to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents.

CONCLUSION : DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves' disease and subacute thyroiditis.

Qiao Tingting, Liu Simin, Cui Zhijun, Yu Xiaqing, Cai Haidong, Zhang Huijuan, Sun Ming, Lv Zhongwei, Li Dan

2021-Jan

Graves’ disease, Intelligent diagnosis, deep learning, diagnostic performance, nuclear medicine residents, subacute thyroiditis, thyroid disease, thyroid scintigraphy

General General

Discovery of beta-lactamase CMY-10 inhibitors for combination therapy against multi-drug resistant Enterobacteriaceae.

In PloS one ; h5-index 176.0

β-lactam antibiotics are the most widely used antimicrobial agents since the discovery of benzylpenicillin in the 1920s. Unfortunately, these life-saving antibiotics are vulnerable to inactivation by continuously evolving β-lactamase enzymes that are primary resistance determinants in multi-drug resistant pathogens. The current study exploits the strategy of combination therapeutics and aims at identifying novel β-lactamase inhibitors that can inactivate the β-lactamase enzyme of the pathogen while allowing the β-lactam antibiotic to act against its penicillin-binding protein target. Inhibitor discovery applied the Site-Identification by Ligand Competitive Saturation (SILCS) technology to map the functional group requirements of the β-lactamase CMY-10 and generate pharmacophore models of active site. SILCS-MC, Ligand-grid Free Energy (LGFE) analysis and Machine-learning based random-forest (RF) scoring methods were then used to screen and filter a library of 700,000 compounds. From the computational screens 74 compounds were subjected to experimental validation in which β-lactamase activity assay, in vitro susceptibility testing, and Scanning Electron Microscope (SEM) analysis were conducted to explore their antibacterial potential. Eleven compounds were identified as enhancers while 7 compounds were recognized as inhibitors of CMY-10. Of these, compound 11 showed promising activity in β-lactamase activity assay, in vitro susceptibility testing against ATCC strains (E. coli, E. cloacae, E. agglomerans, E. alvei) and MDR clinical isolates (E. cloacae, E. alvei and E. agglomerans), with synergistic assay indicating its potential as a β-lactam enhancer and β-lactamase inhibitor. Structural similarity search against the active compound 11 yielded 28 more compounds. The majority of these compounds also exhibited β-lactamase inhibition potential and antibacterial activity. The non-β-lactam-based β-lactamase inhibitors identified in the current study have the potential to be used in combination therapy with lactam-based antibiotics against MDR clinical isolates that have been found resistant against last-line antibiotics.

Parvaiz Nousheen, Ahmad Faisal, Yu Wenbo, MacKerell Alexander D, Azam Syed Sikander

2021

General General

Machine Learning Model For Computational Tracking and Forecasting the COVID-19 Dynamic Propagation.

In IEEE journal of biomedical and health informatics

A computational model with intelligent machine learning for analysis of epidemiological data, is proposed. The innovations of adopted methodology consist of an interval type-2 fuzzy clustering algorithm based on adaptive similarity distance mechanism for defining specific operation regions associated to the behavior and uncertainty inherited to epidemiological data, and an interval type-2 fuzzy version of Observer/Kalman Filter Identification (OKID) algorithm for adaptive tracking and real time forecasting according to unobservable components computed by recursive spectral decomposition of experimental epidemiological data. Experimental results and comparative analysis illustrate the efficiency and applicability of proposed methodology for adaptive tracking and real time forecasting the dynamic propagation behavior of novel coronavirus 2019 (COVID-19) outbreak in Brazil.

Serra Ginalber L O, Gomes Daiana Caroline Dos Santos

2021-Jan-15

General General

A Visually Interpretable Deep Learning Framework for Histopathological Image-based Skin Cancer Diagnosis.

In IEEE journal of biomedical and health informatics

Owing to the high incidence rate and the severe impact of skin cancer, the precise diagnosis of malignant skin tumors is a significant goal, especially considering treatment is normally effective if the tumor is detected early. Limited published histopathological image sets and the lack of an intuitive correspondence between the features of lesion areas and a certain type of skin cancer pose a challenge to the establishment of high-quality and interpretable computer-aided diagnostic (CAD) systems. To solve this problem, a light-weight attention mechanism-based deep learning framework, namely, DRANet, is proposed to differentiate 11 types of skin diseases based on a real histopathological image set collected by us during the last 10 years. The CAD system can output not only the name of a certain disease but also a visualized diagnostic report showing possible areas related to the disease. The experimental results demonstrate that the DRANet obtains significantly better performance than baseline models (i.e., InceptionV3, ResNet50, VGG16, and VGG19) with comparable parameter size and competitive accuracy with fewer model parameters. Visualized results produced by the hidden layers of the DRANet actually highlight part of the class-specific regions of diagnostic points and are valuable for decision making in the diagnosis of skin diseases.

Jiang Shancheng, Li Huichuan, Jin Zhi

2021-Jan-15

General General

A Hierarchical Graph Convolution Network for Representation Learning of Gene Expression Data.

In IEEE journal of biomedical and health informatics

The curse of dimensionality, which is caused by high-dimensionality and low-sample-size (HDLSS), is a major challenge in gene expression data analysis. However, the real situation is even worse: labelling data is laborious and time-consuming, so only a small part of the limited samples will be labelled. Having such few labelled samples further increases the difficulty of training deep learning models. Interpretability is an important requirement in biomedicine. Many existing deep learning methods are trying to provide interpretability, but rarely apply to gene expression data. Recent semi-supervised graph convolution network methods try to address these problems by smoothing the label information over a graph. However, to the best of our knowledge, these methods only utilize graphs in either the feature space or sample space, which may restrict their performance. We propose a transductive semi-supervised representation learning method called a hierarchical graph convolution network (HiGCN) to aggregate the information of gene expression data in both feature and sample spaces. HiGCN first utilizes external knowledge to construct a feature graph and a similarity kernel to construct a sample graph. Then, two spatial-based GCNs are used to aggregate information on these graphs. To validate the model's performance, synthetic and real datasets are provided to lend empirical support. Compared with two recent models and three traditional models, HiGCN learns better representations of gene expression data, and these representations improve the performance of downstream tasks, especially when the model is trained on a few labelled samples. Important features can be extracted from our model to provide reliable interpretability.

Tan Kaiwen, Huang Weixian, Liu Xiaofeng, Hu Jinlong, Dong Shoubin

2021-Jan-15