@inproceedings{6a6bdd70246c464f8a36e779373e52f8,
title = "Data repository mapping for influenza protein sequence analysis",
abstract = "This paper introduces a new method for creating an interactive sequence similarity map of all known influenza virus protein sequences and integrating the map with existing general purpose analytical tools. The NCBI data model was designed to provide a high degree of interconnectedness amongst data objects. Substantial and continuous increase in data volume has led to a large and highly connected information space. Researchers seeking to explore this space are challenged to identify a starting point. They often choose data that is popular in the literature. Reference in the literature follow a power law distribution and popular data points may bias explorers toward paths that lead only to a dead-end of what is already known. To help discover the unexpected we developed an interactive visual analytics system to map the information space of influenza protein sequence data. The design is motivated by the needs of eScience researchers.",
author = "Donald Pellegrino and Chaomei Chen",
year = "2011",
doi = "10.1117/12.872266",
language = "English",
isbn = "9780819484055",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Visualization and Data Analysis 2011",
note = "Visualization and Data Analysis 2011 ; Conference date: 24-01-2011 Through 25-01-2011",
}