Chanchala D. Kaddi

Omic and Electronic Health Record Big Data Analytics for Precision Medicine

<italic>Objective:</italic> Rapid advances of high-throughput technologies and wide adoption of electronic health records (EHRs) have led to fast accumulation of –omic and EHR data. These voluminous complex data contain abundant information for precision medicine, and big data analytics can extract such knowledge to improve the quality of healthcare. <italic>Methods:</italic> In this paper, we present –omic and EHR data characteristics, associated challenges, and data analytics including data preprocessing, mining, and modeling. <italic>Results:</italic> To demonstrate how big data analytics enables precision medicine, we provide two case studies, including identifying disease biomarkers from multi-omic data and incorporating –omic information into EHR. <italic>Conclusion: </italic> Big data analytics is able to address –omic and EHR data challenges for paradigm shift toward precision medicine. <italic>Significance:</italic> Big data analytics makes sense of –omic and EHR data to improve healthcare outcome. It has long lasting societal impact.OBJECTIVE Rapid advances of high-throughput technologies and wide adoption of electronic health records (EHRs) have led to fast accumulation of -omic and EHR data. These voluminous complex data contain abundant information for precision medicine, and big data analytics can extract such knowledge to improve the quality of health care. METHODS In this article, we present -omic and EHR data characteristics, associated challenges, and data analytics including data pre-processing, mining, and modeling. RESULTS To demonstrate how big data analytics enables precision medicine, we provide two case studies, including identifying disease biomarkers from multi-omic data and incorporating -omic information into EHR. CONCLUSION Big data analytics is able to address -omic and EHR data challenges for paradigm shift towards precision medicine. SIGNIFICANCE Big data analytics makes sense of -omic and EHR data to improve healthcare outcome. It has long lasting societal impact.

A Review of Emerging Technologies for the Management of Diabetes Mellitus

Objective: High prevalence of diabetes mellitus (DM) along with the poor health outcomes and the escalated costs of treatment and care poses the need to focus on prevention, early detection and improved management of the disease. The aim of this paper is to present and discuss the latest accomplishments in sensors for glucose and lifestyle monitoring along with clinical decision support systems (CDSSs) facilitating self-disease management and supporting healthcare professionals in decision making. Methods: A critical literature review analysis is conducted focusing on advances in: 1) sensors for physiological and lifestyle monitoring, 2) models and molecular biomarkers for predicting the onset and assessing the progress of DM, and 3) modeling and control methods for regulating glucose levels. Results: Glucose and lifestyle sensing technologies are continuously evolving with current research focusing on the development of noninvasive sensors for accurate glucose monitoring. A wide range of modeling, classification, clustering, and control approaches have been deployed for the development of the CDSS for diabetes management. Sophisticated multiscale, multilevel modeling frameworks taking into account information from behavioral down to molecular level are necessary to reveal correlations and patterns indicating the onset and evolution of DM. Conclusion: Integration of data originating from sensor-based systems and electronic health records combined with smart data analytics methods and powerful user centered approaches enable the shift toward preventive, predictive, personalized, and participatory diabetes care. Significance: The potential of sensing and predictive modeling approaches toward improving diabetes management is highlighted and related challenges are identified.

Computational nanomedicine: modeling of nanoparticle-mediated hyperthermal cancer therapy.

Nanoparticle-mediated hyperthermia for cancer therapy is a growing area of cancer nanomedicine because of the potential for localized and targeted destruction of cancer cells. Localized hyperthermal effects are dependent on many factors, including nanoparticle size and shape, excitation wavelength and power, and tissue properties. Computational modeling is an important tool for investigating and optimizing these parameters. In this review, we focus on computational modeling of magnetic and gold nanoparticle-mediated hyperthermia, followed by a discussion of new opportunities and challenges.

Multivariate Hypergeometric Similarity Measure

We propose a similarity measure based on the multivariate hypergeometric distribution for the pairwise comparison of images and data vectors. The formulation and performance of the proposed measure are compared with other similarity measures using synthetic data. A method of piecewise approximation is also implemented to facilitate application of the proposed measure to large samples. Example applications of the proposed similarity measure are presented using mass spectrometry imaging data and gene expression microarray data. Results from synthetic and biological data indicate that the proposed measure is capable of providing meaningful discrimination between samples, and that it can be a useful tool for identifying potentially related samples in large-scale biological data sets.

Hypergeometric Similarity Measure for Spatial Analysis in Tissue Imaging Mass Spectrometry

Tissue imaging mass spectrometry (TIMS) is a data-intensive technique for spatial biochemical analysis. TIMS contributes both molecular and spatial information to tissue analysis. We propose and evaluate a similarity measure, based on the hyper geometric distribution, for comparing m/z images from TIMS datasets, with the goal of identifying m/z values with similar spatial distributions. We compare the formulation and properties of the proposed method with those of other similarity measures, and examine the performance of each measure on synthetic and biological data. This study demonstrates that the proposed hyper geometric similarity measure is effective in identifying similar m/z images, and may be a useful addition to current methods in TIMS data analysis.

Comparison of clustering pipelines for the analysis of mass spectrometry imaging data

Mass spectrometry imaging (MSI) is valuable for biomedical applications because it links molecular and morphological information. However, MSI datasets can be very large, and analyzing them to identify important biological patterns is a challenging computational problem. Many types of unsupervised analysis have been applied to MSI data, and in particular, clustering has recently gained attention for this application. In this paper, we present an exploratory study of the performance of different analysis pipelines using k-means and fuzzy k-means clustering. The results indicate the effects of different pre-processing and parameter selections on identifying biologically relevant patterns in MSI data.

Pan-cancer analysis for studying cancer stage using protein expression data

Pan-cancer analyses attempt to discover similar features among multiple cancers in order to identify fundamental patterns common to cancer development and progression. Pan-cancer analysis at the level of protein expression is particularly important because protein expression is more immediately related to patient phenotype than genomic or transcriptomic data. This study aims to analyze differentially expressed (DE) proteins between early and advanced cases of multiple cancer types through the usage of reverse-phase protein array data. The relevance of these proteins is further investigated by developing predictive models using K-nearest neighbor and linear discriminant analysis classifiers. The results of this study suggest that a pan-cancer analysis may be highly complementary to standard analysis of an individual cancer for identifying biologically relevant DE proteins, and can assist in developing effective predictive models for cancer progression.

Models for predicting stage in head and neck squamous cell carcinoma using proteomic data.

Head and neck squamous cell carcinoma (HNSCC) that is detected at an advanced stage is associated with much worse patient outcomes than if detected at early stages. This study uses reverse phase protein array (RPPA) data to build predictive models that discriminate between early and advanced stage HNSCC. Individual and ensemble binary classifiers, using filter-based and wrapper-based feature selection, are used to build several models which achieve moderate MCC and AUC values. This study identifies informative protein feature sets which may contribute to an increased understanding of the molecular basis of HNSCC.

Quantitative metrics for bio-modeling algorithm selection

In this paper, we report our efforts in developing guidelines that are capable of helping researchers to select algorithms in systems biology modeling. We propose a set of metrics based on discrete observable units in terms of key bio-modeling considerations. We accomplish this by (i) reviewing classical metric definitions, (ii) implementing widely used modeling algorithms on a specific case study, and (iii) testing metrics that are a hybrid of classical metrics and key bio-modeling considerations. The modeling algorithms implemented are Michaelis-Menten kinetics, generalized mass action, flux balance analysis, and metabolic control analysis. This work extends our previous work in developing qualitative guidelines to select bio-modeling algorithms. Our results impact systems biology modeling specifically by increasing the level of confidence for users to select bio-modeling algorithms by using quantitative metrics appropriately.

DetectTLC: Automated Reaction Mixture Screening Utilizing Quantitative Mass Spectrometry Image Features

AbstractFull characterization of complex reaction mixtures is necessary to understand mechanisms, optimize yields, and elucidate secondary reaction pathways. Molecular-level information for species in such mixtures can be readily obtained by coupling mass spectrometry imaging (MSI) with thin layer chromatography (TLC) separations. User-guided investigation of imaging data for mixture components with known m/z values is generally straightforward; however, spot detection for unknowns is highly tedious, and limits the applicability of MSI in conjunction with TLC. To accelerate imaging data mining, we developed DetectTLC, an approach that automatically identifies m/z values exhibiting TLC spot-like regions in MS molecular images. Furthermore, DetectTLC can also spatially match m/z values for spots acquired during alternating high and low collision-energy scans, pairing product ions with precursors to enhance structural identification. As an example, DetectTLC is applied to the identification and structural confirmation of unknown, yet significant, products of abiotic pyrazinone and aminopyrazine nucleoside analog synthesis. Graphical Abstractᅟ