IDRWalker: A Random Walk based Modeling Tool for Disordered Regions in Proteins
Chen, G.; Zhang, Z.
Show abstract
MotivationWith the advancement of structural biology techniques, the elucidation of increasingly large protein structures has become possible. However, the structural modeling of intrinsically disordered regions in proteins remains challenging. Particularly in the case of large protein complexes, it is difficult to rapidly construct models for all intrinsically disordered regions using existing methods. In the nuclear pore complex, a gigantic protein machine of interest, intrinsically disordered regions play a crucial role in the function of the nuclear pore complex. Therefore, there is a need to develop a modeling tool suitable for intrinsically disordered regions in large protein complexes. ResultsWe have developed a program named IDRWalker based on self-avoiding random walks, enabling convenient and rapid modeling of intrinsically disordered regions in large protein complexes. Using this program, modeling of all disordered regions within the nuclear pore complex can be completed in a matter of minutes. Furthermore, we have addressed issues related to peptide chain connectivity and knot that may arise during the application of random walks. Availability and implementationIDRWalker is an open-source Python package. Its source code is publicly accessible on GitHub (https://github.com/zyzhangGroup/IDRWalker).
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
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 97%
- Distance-guided protein folding based on generalized descent direction 96%
- Accurate prediction of residue-residue contacts across homo-oligomeric protein interfaces through deep leaning 96%
Similar papers in this journal
- Accurate prediction of protein torsion angles using evolutionary signatures and recurrent neural network 97%
- Mechanistic insights into the deleterious role of nasu-hakola disease associated TREM2 variants 96%
- Deep Learning for Protein Peptide bindingPrediction: Incorporating Sequence, Structural andLanguage Model Features 96%
Similar papers in this journal
"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.