Event log

Plants make up the biggest biotic component of the biosphere and play essential roles in all ecosystems. Our survival and well-being depend on plants and this dependence will increase as the climate changes rapidly. To improve how we obtain food, energy, and materials from plants and steward the health of our environment for future generations, we need to understand how plants work at multiple scales from molecules to cells to ecosystems. A major challenge to achieving this goal is a limited understanding of functions of plant genes. The majority of genes in plant genomes are uncharacterized and many of them are found only in plant lineages. Traditional sequence-similarity based biochemical function inference cannot address this challenge. Another aspect of gene function that is critical but generally lacking is the spatial and temporal context under which gene products operate. These challenges have, in part, driven the spectacular advances and inventions in genomics, imaging, mass spectrometry and we are now capable of high-throughput, high-content, and high-resolution measurements of gene and protein function parameters. Along with these technologies and emerging datasets, we need advances in computational biology and bioinformatics tools, concepts, and methods. In this talk, I will describe these challenges and some of the efforts we are making in addressing them.

Artificial intelligence is now recognized as an on-going paradigm shift, with an emphasis on machine learning especially deep learning. Computer vision and image analysis are two major applications of deep learning. While computer vision and image analysis deal with existing images and produce features of these images (images to features), tomographic imaging produces images of multi-dimensional structures from experimentally measured data (line integrals, harmonic components, and so on, of underlying images) which are tomographic features (features to images). Since 2016, deep learning is being actively developed worldwide for tomographic imaging, forming a new area of imaging research. In this presentation, we present a perspective on deep imaging involving data processing, image reconstruction, radiomics, and beyond. We show deeptomographic results and also explore network innovations.

Slides from presentations:

Perspective on Deep Imaging

Medical Imaging in the Deep Learning Framework

The biological sciences are currently experiencing an increase in data size and complexity. Traditional methods are now reaching the point they can no longer keep up with the data output. Larger datasets, particularly when combined with other data sources, open opportunities to apply methods like deep learning on these complex data. NVIDIA is contributing to these needs by developing algorithms that can leverage graphics processing units (GPUs). These problems benefit from high memory bandwidth and very high parallelism inherent of the GPU architecture. This talk will explore some of the collaborations we have with industry and academia and share some of what our research team is currently working on.

GPUs for Genomics

 

Understanding the use of pattern mining algorithms and the development of a prototype system to visualize the relationships of frequent clinical events based on mined clinical sequences and associations.

Coordinated control of metabolic genes is crucial for plant development and adaptation to various environments. To discover general rules of metabolic regulation, we used omics data, machine learning, and experimental validation. To understand how metabolic genes are controlled by epigenetic marks, we mapped regulatory patterns of 16 epigenetic marks across metabolism in Arabidopsis and found a predominant regulatory pattern for specialized metabolic genes involved in controlling the precise timing of gene expression upon stimuli. To understand how transcription factors regulate metabolism, we constructed condition- and tissue-specific regulatory networks in Arabidopsis and identified patterns of transcriptional regulation at various levels. These studies elucidate metabolism coordination and contribute to developing toolkits for pathway engineering in plants.

There have been promising advances in brain machine interfaces. However, many challenges still remain before this technology can become practical. In this talk, we will discuss some of the main issues along with possible approaches to overcome them. In particular, methods to translate neural signals to control external devices using reinforcement learning will be introduced.

Irrespective of data size and complexity, query and exploration tools for accessing data resources remain a central linkage for human-data interaction. A fundamental barrier in making query interfaces easier to use,ultimately as easy as online shopping, is the lack of faceted, interactive capabilities. We propose to repurpose existing ontologies by transforming them into nested facet systems (NFS) to support human-data interaction. Two basic issues need to be addressed for this to happen: one is that the structure and quality of ontologies need to be examined and elevated for the purpose of NFS; the second is that mappings from data-source specific metadata to a corresponding NFS need to be developed to support this new generation of NFS-enabled web-interfaces. The purpose of this presentation is to motivate the concept of NFS, provide a preliminary order-theoretic formulation for NFS, and suggest topics for further investigation.

The outer membrane of gram-negative bacteria is a unique asymmetric membrane bilayer that is composed of phospholipids in the inner leaflet and lipopolysaccharides (LPS) in the outer leaflet. Its function as a selective barrier is crucial for the survival of bacteria in many distinct environments, and it also renders gram-negative bacteria more resistant to antibiotics than their gram-positive counterparts. LPS comprises three regions: lipid A, core oligosaccharide, and O-antigen polysaccharide. In this talk, I will present our ongoing efforts to understanding various bacterial outer membranes and their interactions with outer membrane proteins. In addition, I will also present other research projects in my lab, such as the CHARMM-GUI development, a local structure-centric bioinformatics for drug development, and structure.

This talk will address the importance of assessing lifestyle modification and behavior, and the challenges of using EHR data to identify lifestyle modifications and behavior in clinical narratives. Registration is required by January 8.

Principles and practical examples demonstrating how biomedical informatics enables translational biomedical sciences, precision medicine, and a learning health system. Registration required by January 7.

A presentation of the curriculum and requirements of the proposed MS in Data Science degree program to be implemented at the University of Kentucky

Featuring speakers from academia, industry, and government. Hosted by UK's Center for Computational Science. Must register to attend.

Speakers include William Douglas Figg Sr, NIH; Atul Butte, University of California; Jill Kolesar, University of Kentucky; and Tim Tracy, Aprecia Pharmaceuticals.

Dr. Chen will discuss work to improve the analysis of CT images by developing models that learn to identify features from a set of training images and also generate synthetic images that display these features.

Dr. Liu will review how text mining has been applied to precision medicine, and then discuss efforts at the Mayo Clinic.

Dr. Lu will discuss how artificial intelligence technologies can provide insight to disease mechanism of individual tumors, cancer pathways, the state of signaling machinery in tumor cells, and the efficacy of anti-cancer drugs.

Dr. White will discuss work at Cincinnati Children’s to educate stakeholders on informatics literacy and integrate biomedical and clinical data across the institution, as well as the social structures needed to support these efforts.

Dr. Weng will describe a high-throughput EHR phenotype extraction and analysis framework that performs Human Phenotype Ontology (HPO) concept extraction and normalization from EHR narratives and prioritizes disease genes based on the HPO-coded phenotypic manifestations.

The CCTS and IBI present a lecture by Dr. Lhatoo, Professor of Neurology at Case Western Reserve University and Director of the Epilepsy Center at University Hospitals in Cleveland, OH.

Dr. Olivier Bodenrider will discuss major biomedical ontolgies and their uses.

UK Center for Computational Science (CCS) is hosting this full day event for faculty, students, and industry professionals intrested in computational engineering, science, and data analytics.

Dr. Fei Wang will discuss similarity analytics, a computational tool for identification of the similarity between pairwise data objects, and its applications in precision medicine.

Nathan Jacobs, PhD, will discuss advances in machine learning that make it possible for computatal systems understand images of people. Hosted by CCTS. Registration required. Please email CCTS at CCTS@UKY.edu to reserve your place by Tuesday, May 9, 2017.

Dr. Jong Cheol Jeong will discuss his work in translational bioinformatics and analysis of molecular data.

Dr. Melissa Clarkson will present her research visualizing and auditing the Foundational Model of Antatomy, as well as her work combining visual and semantic representation.

Dr. Cheng will discuss his work developing machine learning algorithms for big data and the minimax pattern learning framework.

Fuyong Xing will discuss high-throughput biomedical image computing methods for digital health, focusing on object detection, segmentation, and image understanding in medical diagnosis.

The Center for Computational Sciences, College of Engineering, Department of Computer Science and the Institute for Biomedical Informatics presents a distinguished lecture by Dr. Moshe Y. Vardi, Rice University.

Shiqiang Tao, PhD, and Eric Durbin, DrPH, will present Trial prospector, a tool for management of clinical cancer trial recruitment workflow. Hosted by CCTS. Registration required. Please email CCTS at CCTS@UKY.edu to reserve your place by Tuesday, April 11, 2017.

Dr. Hua Xu will describe CLAMP (Clinical language annotation, modeling, and processing), a clinical NLP system and interface for building custom NLP pipelines.

Dr. Cameron McIntyre will discuss how an informatics approach to deep brain stimulation could reduce treatment outcome variability.