Reflect example

Reflect allows users to easily highlight the names of all genes, proteins, and small molecules in any web page, typically within one second. Clicking on a highlighted name opens a summary pop-up that provides links to more detailed information. Reflect is freely available at http://reflect.ws. It can also be installed as a plug-in for Firefox or Internet Explorer.

Evangelos is involved in the web page and browser extension development, the middleware deployment, the programmatic interface to the back-end tagging server, as well as the orchestration of the communication among all these components.

1st Prize Award

Reflect Team is the winner of the Elsevier Grand Challenge!

The Reflect Team: Lars Juhl Jensen, Evangelos Pafilis, Sean I. O'Donoghue, Heiko Horn, Sven Haag, Michael Kuhn, Venkata Satagopam, Nigel Brown and Reinhard Schneider


OnTheFly example

OnTheFly is a web-based application that applies biological named entity recognition to enrich Microsoft Office, PDF and plain text documents.

The input files are converted into the HTML format and then sent to the Reflect tagging server, which highlights biological entity names like genes, proteins and chemicals, and attaches to them code to invoke overviews of relevant information, such as a protein description, the domain composition, a link to the 3D structure and links to other relevant online resources.

OnTheFly is also able to extract the bioentities mentioned in a set of files and to produce a graphical representation of the networks of the known and predicted associations of these entities by retrieving the information from the STITCH database.

Evangelos involved in the development of this application and mainly in the back-end and the orchestration of the web-based communication.

The OnTheFly team: Georgios Pavlopoulos, Evangelos Pafilis, Michael Kuhn, Sean Hooper and Reinhard Schneider


bioTextQuest architecture

BioTextQuest (BTQ) is a system for large-scale document clustering applied on biological text, obtained from Medline abstracts. It accomplishes the task of grouping biological text records, while extracting terms of biomedical significance. Based on these features, a long list of results is replaced by groups of related records and by a graph of terms that co-exist-in and characterize each group.

BTQ web application offers the above mentioned capabilities in a user friendly manner, allowing the interactive navigation among clusters of biomedical records relevant to a user query. In addition it supports depiction of associations among the terms within clusters, offering an array of visualization tools for efficient navigation among biomedical records and concept extraction and association.

Evangelos is involved in the architecture design, the development of the web-based interface and the extension of the text sources to biological database records. Additionally, he is experimenting with invoking relevant web services, novel clustering algorithms and visualisation tools so as to improve performance and result rendering.

The BioTextQuest team: Evangelos Pafilis, Nikolaos Papanikolaou, Stavros Nikolaou, Vasilis Promponas, Ioannis Iliopoulos