This article is part of the supplement: The Third BioCreative - Critical Assessment of Information Extraction in Biology Challenge
Research
The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text
-
* Corresponding author: Martin Krallinger mkrallinger@cnio.es
1 Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre (CNIO), Madrid, Spain
2 Australian Regenerative Medicine Institute, Monash University, Australia
3 School of Biological Sciences, University of Edinburgh, Edinburgh, UK
4 Department of Biology, University of Rome Tor Vergata, Rome, Italy
5 IRCSS, Fondazione Santa Lucia, Rome, Italy
6 Institute of Computational Linguistics, University of Zurich, Zurich, Switzerland
7 School of Computing, Informatics and Decision Systems Engineering, Arizona State University, Tempe, Arizona, USA
8 Department of Biomedical Informatics, Arizona State University, Tempe, Arizona, USA
9 Institute of Electronics and Telematics Engineering of Aveiro, University of Aveiro Campus Universitario de Santiago, 3810-193 Aveiro, Portugal
10 National Center for Biotechnology Information (NCBI), 8600 Rockville Pike, Bethesda, Maryland, 20894, USA
11 School of Informatics and Computing, Indiana University, 919 E. 10th St Bloomington IN, 47408, USA
12 Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA
13 Department of Computer Science and Engineering, IIT Madras, Chennai-600 036, India
14 Medical Informatics, University of Wisconsin-Milwaukee, Milwaukee, Wisconsin, USA
15 National Centre for Text Mining and School of Computer Science, University of Manchester, Manchester, UK
16 Department of Computer Science, Tufts University, 161 College Ave, Medford, MA 02155, USA
17 Department of Computer Science and Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, CA 92093, USA
18 Computational Biology and Data Mining Group, Max-Delbrück-Centrum für Molekulare Medizin, Robert-Rössle-Str. 10, 13125 Berlin, Germany
BMC Bioinformatics 2011, 12(Suppl 8):S3 doi:10.1186/1471-2105-12-S8-S3
Published: 3 October 2011Additional files
Additional file 1:
ACT annotation guidelines. Basic classification criteria for PPI abstracts.
Format: ZIP Size: 326KB Download file
Additional file 4:
Evaluation metrics overview. Details on the calculation of the used evaluation scores.
Format: PDF Size: 157KB Download file
This file can be viewed with: Adobe Acrobat Reader
Additional file 2:
ACT example run. iP/R curve of the best team (73, S. Kim and W. J. Wilbur) in the Article Classification Task. Circle 1: Of the top 2% (130) of all results, approx. 90% (120) are relevant abstracts. Circle 2: To find half (295) of all relevant abstracts (Recall around 50%), a human going over the ranked list only has to look at the first 7% (421) of all results; and approx. 2/3 (Precision around 70%) of those abstracts will be relevant.
Format: PNG Size: 36KB Download file
Additional file 3:
IMT method distribution. Distribution of interaction detection methods across the different IMT data sets.
Format: PNG Size: 709KB Download file
