DeepTracer-LowResEnhance is a novel computational tool that significantly improves protein structure prediction from low-resolution cryo-EM maps by integrating deep learning-based map enhancement with AlphaFold structure prediction.
MSAGPT is a novel approach that leverages the power of generative pre-training to create high-quality virtual Multiple Sequence Alignments (MSAs), significantly improving protein structure prediction accuracy, especially for proteins with limited homologous sequence information.
CPE-Pro is a novel deep learning model that effectively distinguishes between experimentally determined and computationally predicted protein structures by leveraging a "structure-sequence" representation learned from protein structure data.
SGNet proposes a protein folding framework to model symmetrical protein assemblies, addressing challenges in structure determination.
Deep learning framework SGNet models symmetrical protein complexes effectively, addressing challenges in structure determination.
Proposing SGNet for modeling symmetrical protein structures, leveraging relative position maps and symmetry generators.
The author proposes SGNet, a protein folding framework leveraging deep learning to model symmetrical protein complexes. By addressing challenges like sequence length and label assignment ambiguity, SGNet demonstrates improved performance in predicting global symmetry types.