Journal
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
Volume -, Issue -, Pages -Publisher
WILEY
DOI: 10.1002/mma.9608
Keywords
3D modeling; conformal geometric algebra; geometric algebra; graph transformer; protein modeling; protein structure prediction
Categories
Ask authors/readers for more resources
Protein structure prediction involves predicting the folding of a protein from its amino acid sequence. This paper demonstrates the relevance of geometric algebra (GA) in instantiating orientational features for protein structure prediction. The authors propose two GA-based metrics which contain information on relative orientations of amino acid residues and show that these features yield comparable results to classical angle-based metrics in terms of accuracy of the predicted coordinates.
Protein structure prediction (PSP) is the prediction of the three-dimensional (3D) folding of a protein (its tertiary structure) starting from its amino acid sequence (its primary structure). The state of the art in PSP is achieved by deep learning pipelines that require several input features extracted from amino acid sequences. It has been demonstrated that features that grasp the relative orientation of amino acids positively impact the prediction accuracy of the 3D coordinates of atoms in the protein backbone. In this paper, we demonstrate the relevance of geometric algebra (GA) in instantiating orientational features for PSP problems. We do so by proposing two novel GA-based metrics which contain information on relative orientations of amino acid residues. We then employ these metrics as additional input features to a graph transformer (GT) architecture to aid the prediction of the 3D coordinates of a protein, and compare them to classical angle-based metrics. We show how our GA features yield comparable results to angle maps in terms of accuracy of the predicted coordinates. This is despite being constructed from less initial information about the protein backbone. The features are also fewer and more informative and can be (i) closely associated to protein secondary structures and (ii) more easily predicted compared to angle maps. We hence deduce that GA can be employed as a tool to simplify the modeling of protein structures and pack orientational information in a more natural and meaningful way.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available