Comprehensive Database of Circular Permutations: Systematic Detection and Analysis Using Deep Learning
Hu, Y.; Huang, B.
Show abstract
This study developed a robust method to detect circular permutations in the Protein Data Bank, analyzing 287,081 proteins with sequence lengths under 800 residues. By employing Foldseek and MMseqs2 for similarity searches and refining results with TM-align, icarus, and plmCP, we identified 20,801 potential circular permutation pairs and 3,351 unique circular permutation proteins. These findings have been compiled into PermuStructDB, a comprehensive database dedicated to circular permutation proteins. This approach, along with the establishment of PermuStructDB, significantly advances our understanding of protein structural variations and evolutionary adaptations, providing a valuable resource for future research in protein engineering and design.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map 96%
- Fast Local Alignment of Protein Pockets (FLAPP): A system-compiled program for large-scale binding site alignment 96%
- PDBminer to Find and Annotate Protein Structures for Computational Analysis 95%
Similar papers in this journal
Similar papers in this journal
- OPUS-Rota4: A Gradient-Based Protein Side-Chain Modeling Framework Assisted by Deep Learning-Based Predictors 96%
- SPDesign: protein sequence designer based on structural sequence profile using ultrafast shape recognition 96%
- A Unified Protein Embedding Model with Local and Global Structural Sensitivity 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.