Bio-Ontologies 2021

Bio-Ontologies (#bioontologies; http://www.bio-ontologies.org.uk/) is an ISMB Community of Special Interest (COSI) that covers the latest and most innovative research in the application of ontologies and more generally the organisation, presentation and dissemination of knowledge in biomedicine and the life sciences. Join our mailing list and our slack team! Have something to say? Tweet to @bioontologies or send an email to the organizers - bioontologies@gmail.com .

Bio-Ontologies will be in its 24th year at ISMB 2021 which will be held as a ONLINE CONFERENCE between July 25-29, 2021. Bio-ontologies strives to provide a vibrant environment for reporting novel methods and sharing experiences on the construction and application of ontologies in health care and the life sciences. The COSI offers a constructive environment to nurture discussion of innovative and scientifically sound work that range from preliminary to completed, from both young and experienced investigators alike. Bio-Ontologies participants also benefit from a strongly interdisciplinary setting, where ISMB attendees intermingle with members from American Medical Informatics Association (AMIA) and the W3C’s Healthcare and Life Sciences Community Group (HCLSCG), thereby increasing impact through broader dissemination and enabling new and exceptional collaborations. This year's event will be integrated into the main conference and will feature papers accepted for the ISMB proceedings.

Program is available at ISMB: https://www.iscb.org/cms_addon/conferences/ismb2020/tracks/bio-ontcosi

Keynote Presentations

Learning actionable network representations for finding safer and more effective treatments

Marinka Zitnik, Harvard University


Abstract:

The success of machine learning (ML) depends heavily on the choice of representations used for training ML models. Graph neural networks have emerged as a predominant choice for learning representations of networks. In this talk, I describe our efforts to expand the scope and ease the applicability of graph representation learning. First, I outline SubGNN, a subgraph neural network for learning disentangled subgraph representations. Second, I will describe G-Meta, a novel meta-learning approach for graphs. G-Meta can transfer knowledge to completely new graphs and previously unseen labels using only a handful of nodes or edges. G-Meta is theoretically justified and scales to orders of magnitude larger datasets than prior work. I will then discuss the applications of these methods in the area of therapeutics. The new techniques have enabled the repurposing of drugs for emerging diseases, where predictions were experimentally verified in the wet laboratory. Further, our knowledge graph methods enabled discovering dozens of combinations of medicines safe for patients with considerably fewer unwanted side effects than today's treatments. Lastly, I describe our efforts in learning fair and stable graph embeddings.

Bio:

Marinka Zitnik is an Assistant Professor at Harvard University with appointments in the Department of Biomedical Informatics, Broad Institute of MIT and Harvard, and Harvard Data Science. Dr. Zitnik's research is at the interface of machine learning and biomedical informatics, focusing on graph representation learning, knowledge graphs, data fusion, and their applications to network biology and therapeutics. Dr. Zitnik has published extensively in top ML venues and leading interdisciplinary journals. She has organized numerous workshops and tutorials in the nexus of AI, deep learning, drug discovery, and medical AI at leading conferences, where she is also in the organizing committees. Her research won numerous best paper and research awards from the International Society for Computational Biology, Bayer Early Excellence in Science Award, a Rising Star Award in Electrical Engineering and Computer Science, and a Next Generation Award in Biomedicine.


Aligning human and machine intelligence


Matthias Samwald, University of Vienna


Abstract:

Recent years were marked by outstanding advances in the capabilities of artificial intelligence (AI). Deep learning enabled rapid progress on many benchmarks that were previously deemed difficult to tackle for machine learning algorithms, often achieving human-level performance. Models such as GPT-3 demonstrated problem solving capabilities across a wide range of intelligence tasks. Given these developments, AI holds the potential to radically transform society through accelerating technological, biomedical and societal knowledge creation and innovation. The realization of this potential increasingly hinges on our understanding of how to best define, train, measure, interconnect and utilize AI capabilities. The development of a shared ontology of AI tasks and capabilities is instrumental towards achieving such an understanding. In this talk I will present recent work on the Intelligence Task Ontology, a large-scale ontology with broad coverage of artificial intelligence tasks, benchmarks and datasets. I will demonstrate how such ontological models can form the foundation for harnessing AI in biomedical research and clinical decision making.

Bio:

Matthias Samwald is associate professor for biomedical informatics and artificial intelligence at the Medical University of Vienna. His work is focused on speeding up scientific progress and the development of novel, personalized therapies through advanced AI technologies and knowledge-based systems. He co-authored over 100 peer-reviewed publications in the areas of personalized medicine, NLP, graph machine learning, information retrieval, biomedical ontologies and clinical decision support systems.


Call for Submissions - DEADLINE Thursday, May 6, 2021 (Key Dates as per ISMB)

We invite the submission of 1 page poster abstracts, and 2-4 page short papers for oral presentation. Please prepare your submission using the templates at the bottom of the site. Topics include but not limited to:

  • Ontologies to support COVID-19 research

  • Ontologies in annotation and metadata standards

  • Machine learning and ontologies

  • Text mining and ontologies

  • Ontology evolution, quality and evaluation

  • Ontologies, knowledge representation and reasoning

Submissions can be made on the ISMB site (). All submissions accepted for oral presentation can optionally also be presented as a poster. Accepted submissions require that one author register for the conference and present the work. The presenter should identify themselves as the corresponding author during the submission process. The presentations are normally allocated between 20 minutes.

Review Criteria

All submissions to Bio-Ontologies are reviewed. Review criteria include :

  1. Relevance of the topic to conference attendees.

  2. Significance of the problem, such that reviewers understand that it is a problem that is important and worth solving.

  3. Novelty of the approach, including critical discussion of related work.

  4. Soundness and potential for reproducibility of the study and/or methods.

  5. Quality of writing, including readability and clearly stated contribution(s)


Special Issue

Submissions accepted for oral presentation will be considered for invitation to a Special Issue in the Journal of Biomedical Semantics. Research that has been accepted as poster presentation may also be invited for further development to the JBMS special issue.


Organizing Committee

Michel Dumontier, Maastricht University, The Netherlands

Robert Hoehndorf, King Abdullah University of Science & Technology, Saudi Arabia

Tiffany Callahan, University of Colorado, United States

Nuria Queralt Rosinach, Leids Universitair Medisch Centrum, The Netherlands

Maxat Kulmanov, King Abdullah University of Science & Technology, Saudi Arabia

Xiaolin Yang, Institute of Basic Medical, Sciences Chinese Academy of Medical Sciences , China

Session Chairs:

  • Tiffany Callahan

  • Nuria Queralt Rosinach


Previous Meetings

Online (2020), Basel (2019), Chicago (2018), Prague (2017), Orlando (2016), Dublin (2015), Boston (2014), Berlin (2013), Long Beach (2012), Vienna (2011), Boston (2010), Stockholm (2009), Toronto (2008), Vienna (2007), Fortaleza (2006), Detroit (2005), Glasgow (2004), Brisbane (2003), Edmonton (2002), Copenhagen (2001), San Diego (2000), Heidelberg (1999), Montreal (1998).

Feedback

Have suggestions for this year? We'd love to hear from you at bioontologies@gmail.com

Templates for Bio-Ontologies submissions:

bio-ontologies-poster-or-flash-update-template.dot
bio-ontologies-paper-template.dot