A5038041060- Advanced Text Analysis Techniques
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Big Data and Business Intelligence
- Web Data Mining and Analysis
- Sentiment Analysis and Opinion Mining
- Bioinformatics and Genomic Networks
- Scientific Computing and Data Management
- Advanced Database Systems and Queries
- Data Mining Algorithms and Applications
- Topic Modeling
- Complex Network Analysis Techniques
- Particle physics theoretical and experimental studies
- High-Energy Particle Collisions Research
- Quantum Chromodynamics and Particle Interactions
- Metabolomics and Mass Spectrometry Studies
- Information Retrieval and Search Behavior
- Knowledge Management and Sharing
- Rough Sets and Fuzzy Logic
- Health, Environment, Cognitive Aging
- Data Quality and Management
- Data Visualization and Analytics
- Nutritional Studies and Diet
- Computational Drug Discovery Methods
- Service-Oriented Architecture and Web Services
Georgia State University
2016-2022
Middle Georgia State College
2019-2022
IBM Research - Almaden
2009-2021
IBM (United States)
2003-2019
Bridge University
2015
California University of Pennsylvania
2014
Pennsylvania State University
2012
Johns Hopkins University
2007
General Motors (Poland)
2003
Amyotrophic lateral sclerosis (ALS) is a devastating neurodegenerative disease with no effective treatments. Numerous RNA-binding proteins (RBPs) have been shown to be altered in ALS, mutations 11 RBPs causing familial forms of the disease, and 6 more showing abnormal expression/distribution ALS albeit without any known mutations. RBP dysregulation widely accepted as contributing factor pathobiology. There are at least 1542 human genome; therefore, other unidentified may also linked...
Keeping up with the ever-expanding flow of data and publications is untenable poses a fundamental bottleneck to scientific progress. Current search technologies typically find many relevant documents, but they do not extract organize information content these documents or suggest new hypotheses based on this organized content. We present an initial case study KnIT, prototype system that mines contained in literature, represents it explicitly queriable network, then further reasons upon...
Concurrent exposure to a wide variety of xenobiotics and their combined toxic effects can play pivotal role in health disease, yet are largely unexplored. Investigating the totality these exposures, i.e., "exposome", specific biological constitutes new paradigm for environmental but still lacks high-throughput, user-friendly technology. We demonstrate utility mass spectrometry-based global metabolomics with tailored database queries cognitive computing comprehensive assessment...
Significance We adapted natural language processing to the biological literature and demonstrated end-to-end automated knowledge discovery by exploring subtle word connections. General text mining scanned 21 million publication abstracts selected a reliable 130,000 from which hypothesis generation algorithms predicted kinases not known phosphorylate p53, but likely do so. Six of these p53 kinase candidates passed experimental validation. Among them NEK2 was examined in depth shown repress...
The emergence of new social media such as blogs, message boards, news, and Web content in general has dramatically changed the ecosystems corporations. Consumers, non-profit organizations, other forms communities are extremely vocal about their opinions perceptions on companies brands Web. ability to leverage "voice Web" gain consumer, brand, market insights can be truly differentiating valuable todaypsilas In particular, one important form derived from sentiment analysis content. Sentiment...
We present KnIT, the Knowledge Integration Toolkit, a system for accelerating scientific discovery and predicting previously unknown protein-protein interactions. Such predictions enrich biological research are pertinent to drug understanding of disease. Unlike prior study, KnIT is now fully automated demonstrably scalable. It extracts information from literature, automatically identifying direct indirect references protein interactions, which knowledge that can be represented in network...
In this paper we introduce a new Web mining and search technique - Topic Initiator Detection (TID) on the Web. Given topic query Internet resulting collection of time-stamped web documents which contain keywords, task TID is to automatically return document (or its author) initiated or was first discuss about topic.
The emergence of new social media such as blogs, message boards, news, and web content in general has dramatically changed the ecosystems corporations. Consumers, non-profit organizations, other forms communities are extremely vocal about t
Patents are of crucial importance for businesses, because they provide legal protection the invented techniques, processes or products. A patent can be held up to 20 years. However, large maintenance fees need paid keep it enforceable. If is deemed not valuable, owner may decide abandon by stopping paying reduce cost. For companies organizations, making such decisions difficult too many patents investigated. In this paper, we introduce new mining problem automatic prediction, and propose a...
Parkinson's disease is a disabling neurodegenerative movement disorder characterized by dopaminergic neuron loss induced α-synuclein oligomers. There an urgent need for disease-modifying therapies disease, but drug discovery challenged lack of in vivo models that recapitulate early stages neurodegeneration. Invertebrate organisms, such as the nematode worm Caenorhabditis elegans, provide human processes can be instrumental initial pharmacological studies.To identify motor impairment animals...
Abstract We present a novel system and methodology for generating then browsing multiple taxonomies over document collection. Taxonomies are generated using broad set of capabilities, including meta data, key word queries, automated clustering techniques that serve as seed taxonomy.The taxonomy editor, eClassifier, provides powerful tools to visualize edit each make it reflective the desired theme. Cluster validation allow editor verify documents received in future can be automatically...
Corporations are extremely sensitive to issues such as brand stewardship and product reputation. Traditional image reputation tracking is limited news wires contact centres analysis. However, with the emergence of Web, consumer generated media (COM), blogs, forums, message boards, Web pages/sites, rapidly becoming "voice people". This paper describes a COBRA (corporate analysis) solution that mines wide range COM contents for The contains flexible ETL (Extract, Transform, Load) engine...
Corporations are extremely sensitive to issues such as brand stewardship and product reputation. Traditional image reputation tracking is limited news wires contact centre analysis. However, with the emergence of web, Consumer Genera
Abstract Purpose Drug repurposing is an effective means of increasing treatment options for diseases, however identifying candidate molecules the indication interest from thousands approved drugs challenging. We have performed a computational analysis published literature to rank existing according predicted ability reduce alpha synuclein (aSyn) oligomerization and analyzed real‐world data investigate association between exposure highly ranked PD. Methods Using IBM Watson Discoveryâ (WDD) we...
In this paper, we propose two novel web-based metrics for semantic similarity computation between words. Both use a web search engine in order to exploit the retrieved information words of interest. The first metric considers only page counts returned by engine, based on work [1]. second downloads number top ranked documents and applies "widecontext" "narrow-context" metrics. proposed automatically, without consulting any human annotated knowledge resource. are compared with WordNet-based...
Intellectual Properties (IP), such as patents and trademarks, are one of the most critical assets in today's enterprises research organizations. They represent core innovation differentiators an organization. When leveraged effectively, they not only protect a business from its competition, but also generate significant opportunities licensing, execution, long term innovation. In certain industries, e. g., Pharmaceutical industry, lead to multi-billion dollar revenue per year. this paper, we...
Taxonomies are meaningful hierarchical categorizations of documents into topics reflecting the natural relationships between and their business objectives. Improving quality these taxonomies reducing overall cost required to create them is an important area research. Supervised unsupervised text clustering technologies that comprise only a part complete solution. However, there exists great need for ability human efficiently interact with taxonomy during editing validation phase. We have...
ABSTRACT The explosion of social and other digital media now provides virtually a continuous stream information about organizations, their people, products. Although CEOs others see the use that as potential opportunity for creating value, they also recently have noted one biggest risks organizations face is threat to organizational brand reputations from those same media. Accordingly, are seeking out systems allow them continuously review monitor in time respond both threats opportunities....