Jörg Hakenberg

Coordinates

Office:	Department of Computer Science and Engineering
	Arizona State University
	699 S. Mill Avenue
	Brickyard, Office Suite 574
	Tempe, AZ 85281-8809, U.S.A.
	N33°25'21" W111°56'23"
E-Mail:

Research interest

I'm currently working as a research associate in the BioAI lab at ASU. My research interests are in text mining and natural language processing for biomedical applications. I have also worked on immunoinformatics and protein structure analysis. My current focus is on:

Text mining & network analysis
Data integration for pharmacogenetics; in particular, changes in enzymatic acticity and drug response - see SNPshot
Entity mention normalization - mapping entity mentions found in biomedical texts (genes etc.) to database entries - see GNAT for more information
Knowledge integration - making use of information extracted from texts (in addition to databases) to address research questions in bioinformatics
Learning language patterns for information extraction - for a short intro, see this paper

Projects

SNPshot - a repository of genetic variants linked to phenotypic effects on drug response
CBioC2 - An environment for collaborative curation of biomedical publications
GNAT - Inter-species gene mention normalization; also see GNN, which normalizes lists of gene names
YAPPIE - generating patterns for information extraction - see BioCreative
Ali Baba - a tool that searches PubMed abstracts for relations between proteins, diseases, drugs, tissues, cells, and species, and displays them as a graph
BioCreative - participated in BioCreative 1, 2, 2.5; our system for gene mention normalization came in first in BioCreative 2 (see GNAT); our methods for normalization and protein interaction extraction scored 1st for f-score in BioCreative 2.5
MAPPP - MHC-I Antigenic Peptide Processing Prediction; combines predictions for proteasomal cleavage and MHC transport of antigenic peptides
PDep - correlated mutation analysis in protein domains
Please also visit my webpage at Humboldt-Universität zu Berlin for further information.

Teaching & seminars

Fall 2009: CSE 591, Analysis of biomolecular networks and their components, TTh 4:30-5:45pm, BYAC 190.
Spring 2009: NLP+ML+applications journal club, together with Dr. Ye; Mo 3-4pm, BYENG 510.
Fall 2008: CSE 591, Natural Language Processing with Biomedical and Archaeological Applications, MoWe 3:30-4:45pm, BYAC 240.
Fall 2008: NLP+ML+applications journal club, together with Dr. Ye; Tu 3pm, BYENG 510.
Fall 2007-Spring 2008: BioNLP journal club.

Recent publications

Vo Ha Nguyen, Jörg Hakenberg, Luis Tari, Chitta Baral, Illes Solt, Domonkos Tikk, Quang Long Nguyen, Ulf Leser: Molecular event extraction from Link Grammar parse trees in the BioNLP'09 Shared Task. Computational Intelligence (COIN), 2010, accepted.
Luis Tari, Phan Huy Tu, Jörg Hakenberg, Yi Chen, Tran Cao Son, Graciela Gonzalez, and Chitta Baral: GenerIE: Information Extraction Using Database Queries. Demo at ICDE 2010, Los Angeles, USA, March 2010, accepted.
Luis Tari, Saadat Anwar, Shanshan Liang, Jörg Hakenberg, Chitta Baral: Synthesis of Pharmacokinetic Pathways through Knowledge Acquisition and Automated Reasoning. In: Proc Pac Symp Biocomput, Big Island of Hawaii, USA, January 4-8 2010.
Jörg Hakenberg, Dmitry Voronov, Vo Ha Nguyen, Shanshan Liang, Barry Lumpkin, Saadat Anwar, Robert Leaman, Luis Ng Tari, and Chitta Baral: Taking a SNPshot of PubMed - a repository of genetic variants and their drug response phenotypes. In: Proc GPD-Rxn Workshop: Genotype-Phenotype-Drug Relationship Extraction from Text at PSB 2010, Big Island of Hawaii, USA, January 4-8 2010.
Jörg Hakenberg, Robert J. Leaman, Nguyen Ha Vo, Siddhartha Jonnalagadda, Ryan Sullivan, Christopher Miller, Luis Tari, Chitta Baral, Graciela Gonzalez: Online protein interaction extraction and normalization at Arizona State University. Presentation at BioCreative II.5 workshop, Madrid, Spain, October 7-9 2009.
Conrad Plake, Loic Royer, Rainer Winnenburg, Jörg Hakenberg, Michael Schroeder: GoGene: gene annotation on the fast lane. Nucl. Acids Res., Web Server Issue, 34(Suppl. 2):W300-304, 2009.
Jörg Hakenberg, Illes Solt, Domonkos Tikk, Nguyen Quang Long, Astrid Rheinländer, Luis Tari, Graciela Gonzalez, Ulf Leser: Molecular event extraction from Link Grammar parse trees. Proc. Natural Language Processing in Biomedicine (BioNLP) NAACL 2009 Workshop, June 4-5, Boulder, CO, USA.
more >>>