Bayesian Networks for Biological Discovery

Bayesian Networks for Biological Discovery

Presented at the 7th Annual BayesiaLab Conference at the North Carolina Biotechnology Center.


Biological systems consist of interlinked interacting elements, and unravelling these interactions for understanding system behaviour, such as neuronal activity during behaviour, gene regulation in response to cancer treatment, and ecological shifts in changing climate, is of great interest for biologists. Bayesian networks hold promise for revealing interactions in these complex biological systems due to their ability to simultaneously model multiple types of interactions from the heterogeneous and noisy data common in biological data collection. Here, we present first an overview of research in the Smith lab advancing Bayesian network algorithms for structure discovery from observational data in three types of biological systems: neuronal systems, genetic systems, and ecological systems. Each system presents both its own particulars of data kind and availability, as well as differing goals for interpretation: what the biological researcher cares to learn from the model. We briefly discuss algorithm developments for handling features such as small data amount, differing data distributions, and making use of spatially explicit observations, then concentrate on the types of biological discovery Bayesian networks support in each system. In neuronal systems, the perspective of the network scientist and biologist are the most congruent, where entire networks are of interest: their structure changing during behaviour and informing features of neural control of behaviour. In contrast, genetic researchers are more often interested in identifying only a small set of genes or pathways that can direct future experimental research, such as into mechanisms of drug resistance. Ecologists can make use of both detailed features, such as identification of 'keystone' interacting species, as well as using networks for further analysis of species constellations, such as identifying groups that respond similarly to environmental gradients. We finish with a case study of applying Bayesian networks to rocky shore ecosystems, looking at networks of interactions in areas of differing species composition.

Presentation Video

Presentation Slides

About the Presenters

V Anne Smith is on the Biology faculty at the University of St Andrews in Scotland, where she runs an integrative computational biology research programme. She traces her dual interest in biology and computation back to her undergraduate days, with a degree in Biology with a Mathematics minor from the College of William and Mary. Her Ph.D. work at Indiana University examined animal behaviour from a complex systems perspective. She has since researched areas as diverse as neuroscience, genetics, cancer, and ecology. She is active in decision-making bodies for several Scottish and UK organisations in both biology and computer science.

Edwin Hui is a Master's student from the University of St Andrews, where he is currently focusing on applying machine learning algorithms to study community ecology. Through the use of different types of machine learning techniques, he hopes to bring a new perspective to the study of ecological dynamics.

For North America

Bayesia USA

4235 Hillsboro Pike
Suite 300-688
Nashville, TN 37215, USA

+1 888-386-8383

Head Office

Bayesia S.A.S.

Parc Ceres, Batiment N 21
rue Ferdinand Buisson
53810 Change, France

For Asia/Pacific

Bayesia Singapore

1 Fusionopolis Place
#03-20 Galaxis
Singapore 138522

Copyright © 2024 Bayesia S.A.S., Bayesia USA, LLC, and Bayesia Singapore Pte. Ltd. All Rights Reserved.