Search

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 healthcare. Methods: In this paper, we present –omic and EHR data characteristics, associated challenges, and data analytics including data preprocessing, 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 toward precision medicine. Significance: Big data analytics makes sense of –omic and EHR data to improve healthcare outcome. It has long lasting societal impact. [ABSTRACT FROM AUTHOR]

Pan-cancer analyses attempt to discover similar features among multiple cancers to identify fundamental patterns common to cancer development and progression. A pan-cancer analysis integrating both protein expression and transcriptomic data is important because it can identify genes that are linked to proteins potentially responsible for a patient's status. This study aims to identify differentially expressed (DE) genes between early and advanced cases of multiple cancer types through the usage of RNA sequencing data. The relevance of these genes is further investigated by developing predictive models using K-nearest neighbor and linear discriminant analysis classifiers. The use of cancer-specific and non-cancer specific features resulted in several moderately performing models. Highlighted genes were further investigated to determine if they encoded for proteins identified in a previously conducted pan-cancer analysis. The results of this study suggest that a pan-cancer analysis may be highly complementary to standard analyses of individual cancers for identifying biologically relevant DE genes and can assist in developing effective predictive models for cancer progression.

Increased understanding of the transcriptomic patterns underlying head and neck squamous cell carcinoma (HNSCC) can facilitate earlier diagnosis and better treatment outcomes. Integrating knowledge from multiple studies is necessary to identify fundamental, consistent gene expression signatures that distinguish HNSCC patient samples from disease-free samples, and particularly for detecting HNSCC at an early pathological stage. This study utilizes feature integration and heterogeneous ensemble modeling techniques to develop robust models for predicting HNSCC disease status in both microarray and RNAseq datasets. Several alternative models demonstrated good performance, with MCC and AUC values exceeding 0.8. These models were also applied to discriminate between early pathological stage HNSCC and normal RNA-seq samples, showing encouraging results. The predictive modeling workflow was integrated into a software tool with a graphical user interface. This tool enables HNSCC researchers to harness frequently observed transcriptomic features and ensembles of previously developed models when investigating new HNSCC gene expression datasets.

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.

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.

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.

We present an agent-based model of head and neck cancer cell population dynamics that investigates the effect of cooperative interactions between individual cancer cells during the course of cytotoxic drug treatment. A model of cooperative behavior based on the Lotka-Volterra competition equations is combined with a model of drug resistance and response. Predictions regarding the individual and combination effects of cooperation and drug treatment qualitatively match experimental observations from the literature.