The specific applications of the TSR-based method in identifying Zn2+ binding sites of proteases and ACE/ACE2.

We have developed an alignment-free TSR (Triangular Spatial Relationship)-based computational method for protein structural comparison and motif identification and discovery. To demonstrate the potential applications of the method, we have generated two datasets. One dataset contains five classes: Actin/Hsp70, serine protease (chymotrypsin/trypsin/elastase), ArsC/Prdx2, PKA/PKB/PKC, and AChE/BChE at the hierarchical level 1 and twelve groups at the level 2. The other dataset includes representative proteases and ACE/ACE2. The x,y, z coordinates of the structures were obtained from PDB. We calculated the keys (or features) that represent each structure using the TSR-based method. The dataset and data presented here include additional information that help the readers become aware of specific applications of the TSR-based method in protein clustering, identification and discovery of metal ion binding sites as well as to understand the effect of amino acid grouping on protein 3D structural relationships at both global and local levels.

Exploring the effectiveness of the TSR-based protein 3-D structural comparison method for protein clustering, and structural motif identification and discovery of protein kinases, hydrolases, and SARS-CoV-2's protein via the application of amino acid grouping.

Development of protein 3-D structural comparison methods is essential for understanding protein functions. Some amino acids share structural similarities while others vary considerably. These structures determine the chemical and physical properties of amino acids. Grouping amino acids with similar structures potentially improves the ability to identify structurally conserved regions and increases the global structural similarity between proteins. We systematically studied the effects of amino acid grouping on the numbers of Specific/specific, Common/common, and statistically different keys to achieve a better understanding of protein structure relations. Common keys represent substructures found in all types of proteins and Specific keys represent substructures exclusively belonging to a certain type of proteins in a data set. Our results show that applying amino acid grouping to the Triangular Spatial Relationship (TSR)-based method, while computing structural similarity among proteins, improves the accuracy of protein clustering in certain cases. In addition, applying amino acid grouping facilitates the process of identification or discovery of conserved structural motifs. The results from the principal component analysis (PCA) demonstrate that applying amino acid grouping captures slightly more structural variation than when amino acid grouping is not used, indicating that amino acid grouping reduces structure diversity as predicted. The TSR-based method uniquely identifies and discovers binding sites for drugs or interacting proteins. The binding sites of nsp16 of SARS-CoV-2, SARS-CoV and MERS-CoV that we have defined will aid future antiviral drug design for improving therapeutic outcome. This approach for incorporating the amino acid grouping feature into our structural comparison method is promising and provides a deeper insight into understanding of structural relations of proteins.

Macro influencers of electronic health records adoption.

While adoption rates for electronic health records (EHRs) have improved, the reasons for significant geographical differences in EHR adoption within the USA have remained unclear. To understand the reasons for these variations across states, we have compiled from secondary sources a profile of different states within the USA, based on macroeconomic and macro health-environment factors. Regression analyses were performed using these indicator factors on EHR adoption. The results showed that internet usage and literacy are significantly associated with certain measures of EHR adoption. Income level was not significantly associated with EHR adoption. Per capita patient days (a proxy for healthcare need intensity within a state) is negatively correlated with EHR adoption rate. Health insurance coverage is positively correlated with EHR adoption rate. Older physicians (>60 years) tend to adopt EHR systems less than their younger counterparts. These findings have policy implications on formulating regionally focused incentive programs.

Exploitation of 3D stereotactic surface projection for predictive modelling of Alzheimer's disease.

Alzheimer's Disease (AD) is one major cause of dementia. Previous studies have indicated that the use of features derived from Positron Emission Tomography (PET) scans lead to more accurate and earlier diagnosis of AD, compared to the traditional approaches that use a combination of clinical assessments. In this study, we compare Naive Bayes (NB) with variations of Support Vector Machines (SVMs) for the automatic diagnosis of AD. 3D Stereotactic Surface Projection (3D-SSP) is utilised to extract features from PET scans. At the most detailed level, the dimensionality of the feature space is very high. Hence we evaluate the benefits of a correlation-based feature selection method to find a small number of highly relevant features; we also provide an analysis of selected features, which is generally supportive of the literature. However, we have also encountered patterns that may be new and relevant to prediction of the progression of AD.

Hypotheses generation as supervised link discovery with automated class labeling on large-scale biomedical concept networks.

Computational approaches to generate hypotheses from biomedical literature have been studied intensively in recent years. Nevertheless, it still remains a challenge to automatically discover novel, cross-silo biomedical hypotheses from large-scale literature repositories. In order to address this challenge, we first model a biomedical literature repository as a comprehensive network of biomedical concepts and formulate hypotheses generation as a process of link discovery on the concept network. We extract the relevant information from the biomedical literature corpus and generate a concept network and concept-author map on a cluster using Map-Reduce frame-work. We extract a set of heterogeneous features such as random walk based features, neighborhood features and common author features. The potential number of links to consider for the possibility of link discovery is large in our concept network and to address the scalability problem, the features from a concept network are extracted using a cluster with Map-Reduce framework. We further model link discovery as a classification problem carried out on a training data set automatically extracted from two network snapshots taken in two consecutive time duration. A set of heterogeneous features, which cover both topological and semantic features derived from the concept network, have been studied with respect to their impacts on the accuracy of the proposed supervised link discovery process. A case study of hypotheses generation based on the proposed method has been presented in the paper.