SGNet: Folding Symmetrical Protein Complex with Deep Learning

arXiv:2403.04395v1 Announce Type: cross
Abstract: Deep learning has made significant progress in protein structure prediction, advancing the development of computational biology. However, despite the high accuracy achieved in predicting single-chain structures, a significant number of large homo-oligomeric assemblies exhibit internal symmetry, posing a major challenge in structure determination. The performances of existing deep learning methods are limited since the symmetrical protein assembly usually has a long sequence, making structural computation infeasible. In addition, multiple identical subunits in symmetrical protein complex …

abstract accuracy arxiv biology challenge computational computational biology cs.cl deep learning development however major performances prediction progress protein protein structure protein structure prediction q-bio.bm symmetry type