Genetics and Genomics Commons^™

A Comparative Evaluation Of The Generalised Predictive Ability Of Eight Machine Learning Algorithms Across Ten Clinical Metabolomics Data Sets For Binary Classification, Kevin M. Mendez, Stacey N. Reinke, David I. Broadhurst

Research outputs 2014 to 2021

Introduction:

Metabolomics is increasingly being used in the clinical setting for disease diagnosis, prognosis and risk prediction. Machine learning algorithms are particularly important in the construction of multivariate metabolite prediction. Historically, partial least squares (PLS) regression has been the gold standard for binary classification. Nonlinear machine learning methods such as random forests (RF), kernel support vector machines (SVM) and artificial neural networks (ANN) may be more suited to modelling possible nonlinear metabolite covariance, and thus provide better predictive models.

Objectives:

We hypothesise that for binary classification using metabolomics data, non-linear machine learning methods will provide superior generalised predictive ability when …

Implementing And Evaluating A Gaussian Mixture Framework For Identifying Gene Function From Tnseq Data, Kevin Li, Rachel Chen, William Lindsey, Aaron Best, Matthew Dejongh, Christopher Henry, Nathan L. Tintle

Faculty Work Comprehensive List

The rapid acceleration of microbial genome sequencing increases opportunities to understand bacterial gene function. Unfortunately, only a small proportion of genes have been studied. Recently, TnSeq has been proposed as a cost-effective, highly reliable approach to predict gene functions as a response to changes in a cell's fitness before-after genomic changes. However, major questions remain about how to best determine whether an observed quantitative change in fitness represents a meaningful change. To address the limitation, we develop a Gaussian mixture model framework for classifying gene function from TnSeq experiments. In order to implement the mixture model, we present the Expectation-Maximization …

Adapts: Automated Deconvolution Augmentation Of Profiles For Tissue Specific Cells., Samuel A Danziger, David L Gibbs, Ilya Shmulevich, Mark Mcconnell, Matthew W B Trotter, Frank Schmitz, David J Reiss, Alexander V Ratushny

Articles, Abstracts, and Reports

Immune cell infiltration of tumors and the tumor microenvironment can be an important component for determining patient outcomes. For example, immune and stromal cell presence inferred by deconvolving patient gene expression data may help identify high risk patients or suggest a course of treatment. One particularly powerful family of deconvolution techniques uses signature matrices of genes that uniquely identify each cell type as determined from single cell type purified gene expression data. Many methods from this family have been recently published, often including new signature matrices appropriate for a single purpose, such as investigating a specific type of tumor. The …

Maternal Inflammation At 0.7 Gestation In Ewes Leads To Intrauterine Growth Restriction And Impaired Glucose Metabolism In Offspring At 30 D Of Age, Robert J. Posont, Caitlin N. Cadaret, Kristin A. Beede, Joslyn K. Beard, Rebecca M. Swanson, Rachel L. Gibbs, Jessica L. Petersen, Dustin T. Yates

Department of Animal Science: Faculty Publications

Fetal programming associated with intrauterine growth restriction (IUGR) leads to lifelong deficits in growth and metabolic function (Hales and Barker, 2013). IUGR arises when fetuses respond to poor in utero conditions by developing adaptations that repartition nutrients to critical tissues and away from skeletal muscle (Yates et al., 2012, 2018). This fetal programming is beneficial in utero but leads to persistent reductions in muscle mass and glucose homeostasis in offspring (DeFronzo et al., 1981). Recent studies by our laboratory in sheep and rats demonstrate that maternal inflammation during gestation induces fetal inflammatory adaptations that impair growth and disrupt muscle glucose …

Body Composition Estimated By Bioelectrical Impedance Analyses Is Diminished By Prenatal Stress In Neonatal Lambs And By Heat Stress In Feedlot Wethers, Rachel L. Gibbs, Caitlin N. Cadaret, Rebecca M. Swanson, Kristin A. Beede, Robert J. Posont, Ty B. Schmidt, Jessica Lynn Petersen, Dustin T. Yates

Department of Animal Science: Faculty Publications

Body composition correlates to carcass value in livestock, which makes the ability to accurately estimate body composition in the live animal beneficial (Berg and Marchello, 1994). Bioelectrical impedance analysis (BIA) is a clinical tool used to assess body composition in humans (Lukaski et al., 1985), but its use in livestock has been minimal. Lean and fat content contribute to profitability for livestock producers, and poor body composition can be caused by stress that occurs either during in utero development (De Blasio et al., 2007) or during postnatal growth (Boyd et al., 2015). Maternal hyperthermia-induced placental insufficiency (Brown et al., 2015) …

Ractopamine Hcl Improved Cardiac Hypertrophy But Not Poor Growth, Metabolic Inefficiency, Or Greater White Blood Cells Associated With Heat Stress In Concentrate-Fed Lambs, Rebecca M. Swanson, Kristin A. Beede, Micayla D. Freeman, Morgan L. Eggleston, Ty B. Schmidt, Jessica L. Petersen, Dustin T. Yates

Department of Animal Science: Faculty Publications

Heat stress decreases livestock performance and well-being (Hahn, 1999; Nienaber and Hahn, 2007), causes metabolic dysfunction that decreases growth efficiency (O’Brien et al., 2010), and alters cardiovascular function (Crandall et al., 2008). Each year, heat stress costs the livestock industry up to $2.5 billion (St-Pierre et al., 2003). Ractopamine HCl acts as a nutrient repartitioning agent (Beermann, 2002); classified as a β adrenergic agonist (βAA), it shares pharmacological properties with adrenaline (Beermann, 2002). βAA increase muscle mass and decreases fat deposition through unknown mechanisms (Beermann, 2002). In feedlot cattle, they increase growth efficiency and improve carcass yield and merit (Scramlin …

Lymphatic Migration Of Immune Cells., Henry R Hampton, Tatyana Chtanova

Articles, Abstracts, and Reports

Lymphatic vessels collect interstitial fluid that has extravasated from blood vessels and return it to the circulatory system. Another important function of the lymphatic network is to facilitate immune cell migration and antigen transport from the periphery to draining lymph nodes. This migration plays a crucial role in immune surveillance, initiation of immune responses and tolerance. Here we discuss the significance and mechanisms of lymphatic migration of innate and adaptive immune cells in homeostasis, inflammation and cancer.

Single-Cell Glia And Neuron Gene Expression In The Central Amygdala In Opioid Withdrawal Suggests Inflammation With Correlated Gut Dysbiosis., Sean J O'Sullivan, Evangelia Malahias, James Park, Ankita Srivastava, Beverly A S Reyes, Jon Gorky, Rajanikanth Vadigepalli, Elisabeth J Van Bockstaele, James S Schwaber

Articles, Abstracts, and Reports

Drug-seeking in opioid dependence is due in part to the severe negative emotion associated with the withdrawal syndrome. It is well-established that negative emotional states emerge from activity in the amygdala. More recently, gut microflora have been shown to contribute substantially to such emotions. We measured gene expression in single glia and neurons gathered from the amygdala using laser capture microdissection and simultaneously measured gut microflora in morphine-dependent and withdrawn rats to investigate drivers of negative emotion in opioid withdrawal. We found that neuroinflammatory genes, notably

Proximate Grassland And Shrub-Encroached Sites Show Dramatic Restructuring Of Soil Bacterial Communities., Xingjia Xiang, Sean M Gibbons, He Li, Haihua Shen, Haiyan Chu

Articles, Abstracts, and Reports

Background: Changes in aboveground community composition and diversity following shrub encroachment have been studied extensively. Recently, shrub encroachment was associated with differences in belowground bacterial communities relative to non-encroached grassland sites hundreds of meters away. This spatial distance between grassland and shrub sites left open the question of how soil bacterial communities associated with different vegetation types might differ within the same plot location.

Methods: We examined soil bacterial communities between shrub-encroached and adjacent (one m apart) grassland soils in Chinese Inner Mongolian, using high-throughput sequencing method (Illumina, San Diego, CA, USA).

Results: Shrub-encroached sites were associated with dramatic restructuring …

New Bathynellidae (Crustacea) Taxa And Their Relationships In The Fortescue Catchment Aquifers Of The Pilbara Region, Western Australia [Dataset], Giulia Perina, Ana I. Camacho, Joel Huey, Pierre Horwitz, Annette Koenders

Research Datasets

In the past 20 years, the number of subterranean taxa discovered in Australia, especially in the Pilbara bioregion, has considerably increased due to incidental environmental surveys often associated with mining development. Bathynellidae are an important component of stygofauna and they occur in most Australian aquifers, but their collection and identification are difficult due to their habitat, and small and fragile bodies with conservative morphology. The study of Pilbaranella ethelensis in the upper Fortescue catchment contributed to a better understanding of the group at local scale, but knowledge at larger catchment scale is still limited. Abundant material collected by different environmental …

Genomic Dysregulation By Overexpression Of Transcription Factors, Mackenzie Scroggins

Undergraduate Honors Theses

As one of the major organs, the liver plays vital roles in the homeostasis of an individual. Being able to identify master regulator genes, genes whose product can affect the activation or deactivation of other genes, will enrich our understanding of hepatic function and liver disease. Previously, our lab used genome-wide microarray data to identify several transcription factors that may play a key role in liver expression. Here we ask whether overexpression of these transcription factors in a non-liver cell would result in liver phenotype activation or general disruption of gene regulation. To this end, we stably introduced seven transcription …

Exploration Of Sonic Hedgehog Gene Expression In Fathead Minnows (Pimephales Promelas), Brooke Renee Greiner

Undergraduate Honors Theses

Pollutants, as a result of wastewater treatments, have been shown to have negative impacts on aquatic ecosystems. To better understand the possible consequences caused by effluents on ecosystems, it is important to examine ecotoxicology data. One of the most commonly used species for water quality testing is the fathead minnow, Pimephales promelas. Ecotoxicology can then be taken one step further to understand the effects of pollutants on a molecular level. Previous research had identified effluents as causes for abnormal minnow fin morphology. In order to collect additional data on development, tanks with fathead minnows were placed at the Charleston …

Fe Limitation Decreases Transcriptional Regulation Over The Diel Cycle In The Model Diatom Thalassiosira Pseudonana., Johanna A L Goldman, Megan J Schatz, Chris T Berthiaume, Sacha N Coesel, Mónica V Orellana, E Virginia Armbrust

Articles, Abstracts, and Reports

Iron (Fe) is an important growth factor for diatoms and its availability is further restricted by changes in the carbonate chemistry of seawater. We investigated the physiological attributes and transcriptional profiles of the diatom Thalassiosira pseudonana grown on a day: night cycle under different CO2/pH and iron concentrations, that in combination generated available iron (Fe') concentrations of 1160, 233, 58 and 12 pM. We found the light-dark conditions to be the main driver of transcriptional patterns, followed by Fe' concentration and CO2 availability, respectively. At the highest Fe' (1160 pM), 55% of the transcribed genes were differentially expressed between day …

Reproducible Big Data Science: A Case Study In Continuous Fairness., Ravi Madduri, Kyle Chard, Mike D'Arcy, Segun C Jung, Alexis Rodriguez, Dinanath Sulakhe, Eric W Deutsch, Cory C Funk, Ben Heavner, Matthew A Richards, Paul Shannon, Gustavo Glusman, Nathan D Price, Carl Kesselman, Ian Foster

Articles, Abstracts, and Reports

Big biomedical data create exciting opportunities for discovery, but make it difficult to capture analyses and outputs in forms that are findable, accessible, interoperable, and reusable (FAIR). In response, we describe tools that make it easy to capture, and assign identifiers to, data and code throughout the data lifecycle. We illustrate the use of these tools via a case study involving a multi-step analysis that creates an atlas of putative transcription factor binding sites from terabytes of ENCODE DNase I hypersensitive sites sequencing data. We show how the tools automate routine but complex tasks, capture analysis algorithms in understandable and …

An Inflammatory Landscape For Preoperative Neurologic Deficits In Glioblastoma., Amal Katrib, Hyun-Hwan Jeong, Nina L Fransen, Kristin S Henzel, Jeremy A Miller

Articles, Abstracts, and Reports

No abstract provided.