#5563. FoldHSphere: deep hyperspherical embeddings for protein fold recognition

July 2026publication date
Proposal available till 21-05-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Applied Mathematics;
Computer Science Applications;
Biochemistry;
Structural Biology;
Molecular Biology;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №5563.1 Contract №5563.2 Contract №5563.3 Contract №5563.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Background: Current state-of-the-art deep learning approaches for protein fold recognition learn protein embeddings that improve prediction performance at the fold level. However, there still exists aperformance gap at the fold level and the (relatively easier) family level, suggesting that it might be possible to learn an embedding space that better represents the protein folds.
Keywords:
Deep neural networks; Embedding learning; Hyperspherical space; Protein fold recognition; Residual convolutions; Thomson problem

Contacts :
0