Timezone: »
Convolutional neural networks are increasingly used outside the domain of image analysis, in particular in various areas of the natural sciences concerned with spatial data. Such networks often work out-of-the box, and in some cases entire model architectures from image analysis can be carried over to other problem domains almost unaltered. Unfortunately, this convenience does not trivially extend to data in non-euclidean spaces, such as spherical data. In this paper, we introduce two strategies for conducting convolutions on the sphere, using either a spherical-polar grid or a grid based on the cubed-sphere representation. We investigate the challenges that arise in this setting, and extend our discussion to include scenarios of spherical volumes, with several strategies for parameterizing the radial dimension. As a proof of concept, we conclude with an assessment of the performance of spherical convolutions in the context of molecular modelling, by considering structural environments within proteins. We show that the models are capable of learning non-trivial functions in these molecular environments, and that our spherical convolutions generally outperform standard 3D convolutions in this setting. In particular, despite the lack of any domain specific feature-engineering, we demonstrate performance comparable to state-of-the-art methods in the field, which build on decades of domain-specific knowledge.
Author Information
Wouter Boomsma (University of Copenhagen)
Jes Frellsen (IT University of Copenhagen)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Spotlight: Spherical convolutions and their application in molecular modelling »
Thu. Dec 7th 08:10 -- 08:15 PM Room Hall C
More from the Same Authors
-
2021 : A kernel for continuously relaxed, discrete Bayesian optimization of protein sequences »
Yevgen Zainchkovskyy · Simon Bartels · Søren Hauberg · Jes Frellsen · Wouter Boomsma -
2021 Workshop: Learning Meaningful Representations of Life (LMRL) »
Elizabeth Wood · Adji Bousso Dieng · Aleksandrina Goeva · Anshul Kundaje · Barbara Engelhardt · Chang Liu · David Van Valen · Debora Marks · Edward Boyden · Eli N Weinstein · Lorin Crawford · Mor Nitzan · Romain Lopez · Tamara Broderick · Ray Jones · Wouter Boomsma · Yixin Wang -
2021 Workshop: Machine Learning in Structural Biology »
Ellen Zhong · Raphael Townshend · Stephan Eismann · Namrata Anand · Roshan Rao · John Ingraham · Wouter Boomsma · Sergey Ovchinnikov · Bonnie Berger -
2020 : Frank Noe Intro »
Wouter Boomsma -
2020 Workshop: Machine Learning for Structural Biology »
Raphael Townshend · Stephan Eismann · Ron Dror · Ellen Zhong · Namrata Anand · John Ingraham · Wouter Boomsma · Sergey Ovchinnikov · Roshan Rao · Per Greisen · Rachel Kolodny · Bonnie Berger -
2020 Workshop: Learning Meaningful Representations of Life (LMRL.org) »
Elizabeth Wood · Debora Marks · Ray Jones · Adji Bousso Dieng · Alan Aspuru-Guzik · Anshul Kundaje · Barbara Engelhardt · Chang Liu · Edward Boyden · Kresten Lindorff-Larsen · Mor Nitzan · Smita Krishnaswamy · Wouter Boomsma · Yixin Wang · David Van Valen · Orr Ashenberg -
2018 Poster: 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data »
Maurice Weiler · Wouter Boomsma · Mario Geiger · Max Welling · Taco Cohen