BioCreative 2017 - BioCreative VI Challenge and Workshop

BioCreative: Critical Assessment of Information Extraction in Biology (http://www.biocreative.org/ ) is a community-wide effort for evaluating text mining and information extraction systems applied to the biological domain. These are the tracks for BioCreative VI:
• Track 1: Interactive Bio-ID Assignment (IAT-ID) Track on innovations in Biomedical Digital Curation
Organizers: Lynette Hirschman, Cecilia Arighi, Thomas Lemberger and Cathy Wu
The Bio-ID track will explore the ID assignment to selected bioentities both at the pre- and post-publication stages, with the aim of facilitating downstream article curation. To do this we are bringing together the various stakeholders to discuss functional requirements and develop interoperable digital curation tools. Built on previous BioCreative experiments, including the interactive tracks, the BioC, gene/protein/chemical extraction tracks, and BeCalm framework, the task is designed to foster the development of an integrated and interoperable workflow of multiple text mining tools for real-world testing in pilot publishing frameworks.
More information about this track can be found at http://www.biocreative.org/tasks/biocreative-vi/tr...
• Track 2: Text-mining services for Kinome Curation
Organizers: Julien Gobeill, Patrick Ruch and Pascale Gaudet
Literature triage (selection of relevant articles for curation) is a basic task performed by virtually all curated molecular biology databases. This task will focus on triage for both Protein-Disease and Protein-GO annotations related to human kinases. The full data set covers a significant fraction of the Human Kinome (300 proteins out ~500 kinases), with 30,000 annotations from 13,000 articles ready to be integrated in the neXtProt database by 2017. It contains comprehensive annotations about kinase substrates, GO Biological Processes and Diseases. Each annotation is provided with a PMID.
The first two tasks deal with triage of abstracts or full-texts. The third task deals with passage selection: given a kinase, an axis, and a full-text regarded as relevant after SIB curation, the systems will return a snippet of max. 500 characters containing enough information to make an annotation.
More information about this track can be found at http://www.biocreative.org/tasks/biocreative-vi/tr...
• Track 3: Extraction of causal network information using the Biological Expression Language (BEL)
Organizer: Juliane Fluck and Sumit Madan
Automatic extraction of biological network information is one of the most desired and most complex tasks in biological and medical text mining.
In BioCreative V, we tackled this complexity by extracting causal relationships represented in Biological Expression Language (BEL). BEL is an advanced knowledge representation format which has been designed to be both human readable and machine processable. The smallest unit is a BEL statement or BEL nanopub, expressing a single causal relationship. In the last BioCreative, there was only a limited time for participants to train on the data and, in addition, the evaluation environment became only available for the test phase. Furthermore, for the second subtask, the sentence classification, no training data was available. Therefore, we decide to present the same task based on new test data. This time, the training data for both subtask is available and, the evaluation environment can be used during the training time. As before, the challenge is organized into two tasks which will evaluate the complementary aspects of the problem:
1-Given selected textual evidence, construct the corresponding BEL statement
2-Given a BEL statement, detect all available textual evidence
The description of the task, the training data and links to the papers and to the evaluation website can be found under the following URL:
https://wiki.openbel.org/display/BIOC/BioCreative+...
• Track 4: Mining protein interactions and mutations for precision medicine (PM)
Organizers: Rezarta Islamaj Dogan, Andrew Chatr-aryamontri, Sun Kim, Donald C. Comeau, Zhiyong Lu
We aim to bring together the biomedical text mining community in a new challenge for precision medicine, focusing on identifying and extracting protein-protein interactions affected by mutations described in the biomedical literature. Two subtasks are proposed:
1-Document Triage:
Identifying relevant PubMed citations describing genetic mutations affecting protein-protein interactions
2-Relation Extraction:
Extracting PPI pairs experimentally verified to be affected by the presence of a genetic mutation
Task datasets will be available in multiple formats (e.g. BioC) and consist of PubMed articles curated for BioGRID and other PPI databases.
More information about this track can be found at http://www.biocreative.org/tasks/biocreative-vi/tr...
• Track 5: Text mining chemical-protein interactions
Organizers: Martin Krallinger, Alfonso Valencia, Analia Lourenço
Considerable work has been done on the detection of genes/proteins and also chemical compound mentions, but despite the relevance of relations between them for both biological and well as pharmacological and clinical research only a limited number of strategies have been published to detect interactions between them. A range of different types chemical-protein/gene interactions are of key relevance for biology, including metabolic relations (e.g. substrates, products) inhibition, binding or induction associations. Our aim is to promote research in this field, and to focus on chemical-protein interactions that might be of relevance for precision medicine as well as for drug discovery and basic biomedical research. This task will consist of two subtasks:
1- Chemical-protein interaction pair detection task:
Extracting relations between chemical entities and protein/genes belonging to at least one of a pre-defined set of relation types.
2- Chemical-protein interaction type detection task:
Providing for previously detected interaction pairs (of task 1) the corresponding relation type qualifier).
Task training and test datasets will prepared and consist of abstracts curated for chemical entity and protein/gene mentions (including mention offsets) as well as relationships between them according to a predefined set of interaction types.
More information about this track can be found at http://www.biocreative.org/tasks/biocreative-vi/tr...
Team Registration
Teams can participate in one or more of these tracks. Team registration will continue until final commitment is requested by the individual tracks.
To register a team go to the team registration page
BioCreative Organizing Committee
• Cecilia Arighi, University of Delaware, USA
• Andrew Chatr-aryamontri, Institute for Research in Immunology and Cancer, Université de Montréal, Canada
• Donald Comeau, National Center for Biotechnology Information (NCBI), NIH, USA
• Kevin Cohen, University of Colorado, USA
• Juliane Fluck, Fraunhofer Institute for Algorithms and Scientific Computing SCAI, Germany
• Sumit Madan, Fraunhofer Institute for Algorithms and Scientific Computing SCAI, Germany
• Rezarta Islamaj Dogan, National Center for Biotechnology Information (NCBI), NIH, USA
• Pascale Gaudet, Swiss Bioinformatics Institute, Switzerland
• Julien Gobeill, Swiss Bioinformatics Institute, Switzerland
• Lynette Hirschman, MITRE Corporation, USA
• Sun Kim, National Center for Biotechnology Information (NCBI), NIH, USA
• Martin Krallinger, Spanish National Cancer Centre, CNIO, Spain
• Zhiyong Lu, National Center for Biotechnology Information (NCBI), NIH, USA
• Fabio Rinaldi, Swiss Bioinformatics Institute, Switzerland
• Patrick Ruch, Swiss Bioinformatics Institute, Switzerland
• Alfonso Valencia, Spanish National Cancer Centre, CNIO, Spain
• Cathy Wu, University of Delaware and Georgetown University, USA