RSS 2.0
Critical Assessment of Information Extraction in Biology - data sets are available from Resources/Corpora and require registration.

Corpora

ChemProt corpus: BioCreative VI (Resources) [2017-11-21]

Text mining chemical-protein interactions (CHEMPROT) corpus, including:
  • ChemProt sample set
  • ChemProt training set
  • ChemProt development set
  • ChemProt test set

Downloads

BioCreative VI

store/images/2017/banner2.png

BioCreative VI Workshop Registration and Information (Events) [2017-07-05]

The BioCreative VI workshop will be held at DoubleTree by Hilton Hotel Bethesda - Bethesda, Maryland during October 18-20, 2017.

Registration


Registration to BioCreative VI Workshop is now closed

Registration includes:

  • Breakfast
  • Attendance to workshop
  • Coffee breaks
  • Lunch
  • Tour to the National Library of Medicine
  • Registration is in US dollars:

    Registration TypeEarly fee (until September 18)Late fee (after September 18)
    Student/post-doc$180$250
    Academic/non-profit/Government$330$400
    Industry$400$470

    Back to top

    Travel Awards


    Funds are available for US participants for the amount up to $700 to participate in the BioCreative workshop. To apply complete the application available here by September 1st. Women, under-represented minorities, students, and post-doctoral fellows are encouraged to apply. Submissions are now closed

    Back to top

    Scientific Program


    Venue: DoubleTree by Hilton Hotel, Bethesda, Maryland
    Talks: Ballroom D (2nd floor)
    Posters: Balance room (2nd floor)

    The scientific program includes the talks related to the individual tracks, a panel about Innovation in biomedical digital curation, a general session for BioCreative related topics, 2 keynote talks and a poster session. Detailed agenda is shown below

    Wednesday, October 18, 2017

    08:00 - 12:00Registration (EMC foyer, 2nd floor)
    08:00 - 09:00Breakfast (EMC foyer, 2nd floor)
    09:00 - 09:15Workshop opening PDF
    09:15 - 10:40TRACK 1 Interactive Bio-ID Assignment
    9:15-9:25 Introduction to Bio_ID track (Cecilia Arighi, University of Delaware) PDF
    9:25-9:40 Introduction to SourceData and data set (Thomas Lemberger, SourceData) PDF
    9:40-9:55 Overview of Bio_ID results – batch results (Lynette Hirschman, MITRE) PDF
    9:55-10:05 A Neural Named Entity Recognition Approach to Biological Entity Identification (Emily Sheng, Information Sciences Institute/USC) PDF
    10:05-10:15 A Study on Identification of Organism and micro-RNA Mentions in Figure Captions (Po-Ting Lai, National Central University) PDF
    10:15-10:40 Next steps and discussion
    10:40 - 11:00Break
    11:00 - 12:30Panel on Innovation on Digital Curation (Moderators: Fabio Rinaldi and Cecilia Arighi)
    11:00-11:10 Julio Collado-Vides, UNAM- Natural language processing to enhance accessibility to knowledge in RegulonDB
    11:10-11:20 Thomas Lemberger, EMBO- Data transparency in scientific publishing PDF
    11:20-11:30 Zhiyong Lu, NCBI- Text mining for improving the prioritization, curation, and integration of knowledge for clinically relevant variants PDF
    11:30-11:40 Johanna McEntyre, EMBL-EBI- How can text mining scale to meet diverse and precise curation needs? PDF
    11:40-12:30 Open discussion
    12:30 - 13:40Lunch (Restaurant first floor)
    13:40 - 15:40TRACK 4 Mining protein interactions and mutations for precision medicine
    1:40-2:10 Overview of the Precision Medicine Track (Rezarta Islamaj Dogan) PDF
    2:10-2:30 Identifying Relevant Literature for Precision Medicine Using Deep Neural Networks (Sergio Matos)
    2:30- 2:50 Exploring a Deep Learning Pipeline for the BioCreative VI Precision Medicine Task (Tung Tran)
    2:50- 3:10 Mining protein interactions affected by mutations using a NLP based machine learning approach (Albert Steppi and Jinchan Qu)
    3:10-3:30 Document Triage and Relation Extraction for Protein-Protein Interactions affected by Mutations (Dina Demner Fushman for Karin Verspoor and team)
    3:30-3:40 Poster spotlight and Open discussion
    15:40 - 16:00Break
    16:00 - 17:00Keynote- Dr. Patricia Flatley Brennan, Director of National Library of Medicine, NIH
    Towards a future of data-powered health
    17:00 - 18:00Panel on Funding Stakeholders (Moderator: Cathy Wu)
    Susan Gregurick, NIGMS, NIH PDF
    Jennifer Weller, NSF
    Jane Ye, NLM, NIH PDF
    Johanna McEntyre, EMBL-EBI

    Thursday, October 19, 2017

    08:00 - 12:00Registration (EMC foyer, 2nd floor)
    08:00 - 09:00Breakfast (EMC foyer, 2nd floor)
    09:00 - 10:15General session
    9:00-9:20 Efficient and Accurate Entity Recognition for Biomedical Text (Fabio Rinaldi, U. Zurich)
    9:20-9:40 iTextMine: Integrated Text Mining System for Large-Scale Knowledge Extraction from Literature (Jia Ren, U. Delaware)
    9:40-10:00 Large-scale Automated Reading with Reach Discovers New Cancer Driving Mechanisms (Dane Bell, U. Arizona)
    10:00-10:20 Evaluating without a Gold Standard (Lynette Hirschman, MITRE)
    10:20 - 10:40Break
    10:40 - 12:30 TRACK 2 Text-mining services for Kinome Curation
    10:40-11:10 Kinome Track Overview (Julien Gobeill & Patrick Ruch, SIB)
    11:10-11:35 Assisting Document Triage for Human Kinome Curation via Machine Learning (Alan Hsu, NCBI)
    11:35-11:55 KinDER: A Biocuration Tool for Extracting Kinase Knowledge from Biomedical Literature (Adam Morrone & Daniel Dopp, Montana State University)
    11:55-12:20 Discussion
    12:30 - 13:45Lunch (Restaurant first floor)
    13:45 - 15:45 TRACK 3 Extraction of causal network information using the Biological Expression Language
    1:45 - 2:15 BEL Track - Overview and Results (Sumit Madan, Fraunhofer SCAI, Germany) PDF
    2:15 - 2:30 Task 1 - BELMiner – Information extraction system to extract BEL relationships (Ravikumar Komandur Elayavilli, Mayo Clinic, USA) PDF
    2:30 - 2:45 Task 1 - Generating Biological Expression Language Statements with Pipeline Approach and Different Parsers (Po-Ting Lai, National Central University, Taiwan) PDF
    2:45 - 3:00 Task 1 - Automatic Extraction of BEL-Statements based on Neural Networks (Mehdi Ali, University of Bonn, Germany) PDF
    3:00 - 3:15 Task 2 - Semantic Information Retrieval: Exploring dependency and word embedding features in biomedical Information Retrieval (Majid Rastegar-Mojarad, Mayo Clinic, USA) PDF
    3:15 - 3:30 BEL Track - Next steps and discussion (Sumit Madan, Fraunhofer SCAI, Germany) PDF
    15:45 - 16:00Break
    16:00 - 17:00Keynote- Dr. Hongfang Liu, Professor Biomedical Informatics, Mayo Clinic
    Text mining in precision medicine: opportunities and challenges
    17:00 - 19:00Poster session and Reception

    Friday, October 20, 2017

    08:00 - 09:00Breakfast (EMC foyer, 2nd floor)
    08:30 - 10:30TRACK 5 Text mining chemical-protein interactions
    8:30-9:00 Overview of the Chemical-Protein relation extraction track (Martin Krallinger / Saber A. Akhondi (CNIO / Elsevier) PDF
    9:00-9:15 Chemical-protein relation extraction with SVM, CNN, RNN and ensemble systems (Yifan Peng, NCBI, NLM, NIH) PDF
    9:15-9:30 Extracting Chemical-Protein Interactions using Long Short-Term Memory Networks (Sérgio Matos, University of Aveiro, Portugal) PDF
    9:30-9:45 Attention based Neural Networks for Chemical Protein Relation Extraction (Ravikumar Komandur Elayavilli, Mayo Clinic, USA)
    9:45-10:00 Extracting protein-chemical compound interactions from literature (Pei-Yau Lung, Florida State University)
    10:00-10:15 Knowledge-base-enriched relation extraction (Ignacio Tripodi, University of Colorado, Boulder) PDF
    10:15 - 10:30 CTCPI - Convolution Tree Kernel-based Chemical-Protein interaction detection (Po-Ting Lai, National Tsing-Hua University, Hsinchu, Taiwan)
    10:30 - 10:45Break
    10:45 - 12:00Tracks open discussion/closing
    12:00 - 13:00Lunch (Restaurant first floor)
    13:00 - 15:30Tour to the National Library of Medicine

    Back to top

    Work Submissions


    Submission of abstracts/papers should be done via Easychair at the following URL: https://easychair.org/conferences/?conf=bc6. Format for submission:PDF.

    BioCreative VI proceedings will be published online and will be available at the time of the meeting.

    We will invite selected works for full publication in the Database Journal Special Issue for BioCreative.

    Track presentation submissions: Track participants should submit their work in the form of a short paper (up to 4 pages). See template with instructions here. Although template is a word document, the format for submission should be in PDF.

    Submission deadline: please follow the dates described in the track you are participating

    General session submissions: BioCreative VI will host a general session to provide an opportunity to discuss related work to BioCreative topics, including data set preparation, evaluation, biomedical information extraction. Then, we are soliciting submission of your bioNLP work that is related to any of these topics in the form of a 2 page abstracts (see template with instructions can be found here). Although template is a word document, the format for submission should be in PDF. Abstracts will be selected for oral presentation during the corresponding session.

    Submission deadline September 17, 2017

    POSTERS
    Poster size 32"x40"

    Back to top

    Venue and Access


    Conference venue | Map

    DoubleTree by Hilton Hotel Bethesda - Washington DC
    8120 Wisconsin Avenue, Bethesda, Maryland 20814
    Phone: (301) 652-2000

    Accommodations


    There are a number of rooms reserved for this event at the DoubleTree hotel with a special rate of US$219 per night. This special rate is available through September 22, 2017.
    Guests can go online to the BioCreative hotel page reservation http://doubletree.hilton.com/en/dt/groups/personalized/W/WASBHDT-BC0-20171017 (Preferred)
    OR
    Guests can call 1-800-955-7359 and request the group rate for the BioCreative VI Conference or the Group SRP/Code: BC0.
    OR
    Go to the hotel main page www.bethesda.doubletree.com, click on the Reservations Tab, enter dates and on the Special Accounts Section enter BC0 for the Group/Convention Code.
    The special rate applies for the nights 10/17/2017 through 10/20/2017.

    Directions


    Map & Directions to the hotel from local airports:

    The Doubletree Hotel in Bethesda is conveniently located near 3 airports. It is just 15 miles from Ronald Reagan Washington National Airport (DCA), 27 miles from Washington Dulles International Airport (IAD), and 38 miles from Baltimore Washington International Airport (BWI). All three airports should have private shuttle services available. Fees for these services vary based on distance to the hotel.

    Transportation options from DCA
    Transportation options from IAD
    Transportation options from BWI

    Maps and directions

    Parking

    The hotel offers paid parking (rate $12 for day parking and $23 for overnight). There are also meter spaces and public parking throughout Bethesda area. To check parking places and rates click here

    Back to top

    Visas


    You are responsible to inquire about visa requirements to enter the US. General information about US visas can be found here. If you need a letter of invitation to attend the workshop please send email to bcviworkshop@gmail.com with subject: visa letter request.

    Back to top

    Sponsors


    BioCreative workshop is sponsored by

  • NIH/MIGMS Conference grant 1R13GM109648-01A1
  • NIH/MIGMS Supplement 2R01GM08064
  • Database, Oxford University Press
  • International Society for Biocuration
  • Elsevier
  • OpenMinted (654021) H2020 project
  • encomienda MINETAD-CNIO/OTG Sanidad Plan TL
  • Back to top

    BioCreative VI Workshop Proceedings


    The proceedings is now available here PDF

    Back to top

    Downloads

    Publications

    BC V.5 - Workshop Proceedings (Resources) [2017-05-19]

    PDF

    Co-located: BioCreative V.5 Challenge Evaluation Workshop PDF and ELIXIR-EXCELERATE Workshop Text-mining infrastructure requirements PDF
    PDF
    Table of Contents: BC V.5 - Workshop Proceedings

      Editorial and track overview papers

    1. The BioCreative V.5 evaluation workshop: tasks, organization, sessions and topics . Krallinger et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 8-10 PDF
    2. Evaluation of chemical and gene/protein entity recognition systems at BioCreative V.5: the CEMP and GPRO patents tracks. Pérez-Pérez et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 11-18 PDF
    3. Benchmarking biomedical text mining web servers at BioCreative V.5: the technical Interoperability and Performance of annotation Servers - TIPS track . Pérez-Pérez et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 19-27 PDF
    4. Chemical/gene entity recognition tracks: CEMP & GPRO

    5. DUTIR at the BioCreative V.5.BeCalm Tasks: A BLSTM-CRF Approach for Biomedical Entity Recognition in Patents. Luo et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 28-39 PDF
    6. HITextracter System for Chemical and Gene/Protein Entity Mention Recognition in Patents. Liu et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 40-46 PDF
    7. CRFVoter: Chemical Entity Mention, Gene and Protein Related Object recognition using a conglomerate of CRF based tools. Liu et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 47-53 PDF
    8. Neji: Recognition of Chemical and Gene Mentions in Patent Texts. Santos and Matos. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 54-60 PDF
    9. Chemlistem - chemical named entity recognition using recurrent neural networks. Corbett and Boyle. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 61-68 PDF
    10. Recognition of Chemical Entity Mention in Patents Using Feature-rich CRF. Guo et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 69-72 PDF
    11. Towards Robust Chemical Recognition with TaggerOne at the BioCreative V.5 CEMP Task. Leaman and Lu. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 73-80 PDF
    12. A hybrid text mining system for chemical entity recognition and classification using dictionary look-up and pattern matching @ BeCalm challenge evaluation workshop. Raja et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 81-88 PDF
    13. IBEnt: Chemical Entity Mentions in Patents using ChEBI. Lamurias et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 89-95 PDF
    14. ChemGrab: Identification of Chemical Names Using a Combined Negative-Dictionary and Rule-Based Approach. Sharma and Sarkar. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 96-103 PDF
    15. Combining the BANNER tool with the DINTO ontology for the CEMP task of BioCreative V.5. Colon-Ruiz et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 104-107 PDF
    16. An Ensemble Algorithm for Sequential Labelling: A Case Study in Chemical Named Entity Recognition. Wang et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 108-114 PDF
    17. Statistical Principle-based Approach for Gene and Protein Related Object Recognition. Lai et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 115-121 PDF

    18. TIPS (Technical interoperability and performance of annotation servers) Track

    19. Tagger: BeCalm API for rapid named entity recognition. Jensen. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 122-129 PDF
    20. MER: a Minimal Named-Entity Recognition Tagger and Annotation Server. Couto et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 130-137 PDF
    21. SIA: Scalable Interoperable Annotation Server. Kirschnick and Thomas. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 138-145 PDF
    22. High-throughput, interoperability and benchmarking of text-mining with BeCalm biomedical metaserver. Madrid and Valencia. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 146-155 PDF
    23. Performance and interoperability assessment of Disease Extract Annotation Server (DEAS). Jonnagaddala et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 156-162 PDF
    24. TextImager as an interface to BeCalm. Hemati et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 163-166 PDF
    25. Olelo’s named-entity recognition web service in the BeCalm TIPS task. Folkerts and Neves. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 167-174 PDF
    26. OGER: OntoGene’s Entity Recogniser in the BeCalm TIPS Task. Furrer and Rinaldi. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 175-182 PDF
    27. READ-Biomed-Server: A Scalable Annotation Server Using the UIMA Concept Mapper. Teng and Verspoor. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 183-190 PDF
    28. Neji: DIY web services for biomedical concept recognition. Santos and Matos. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 191-195 PDF
    29. NTTMU-SCHEMA BeCalm API in BioCreative V.5. Dai et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 196-204 PDF
    30. Micro-RNA Recognition in Patents in BioCreative V.5. Wang et al. Proceedings of the BioCreative V.5 Challenge Evaluation Workshop, 205-209 PDF

    Downloads