Into the Void: Cavities and Tunnels are Essential for Functional Protein Design
Zhang, J.; Peng, Z.
Show abstract
The design of functional proteins is crucial as it enables the creation of tailored proteins with specific capabilities, unlocking the potential solutions to various biomedical and industrial challenges. The exact relationship between structure, sequence, and function in protein design is intricate, however, a consensus has been reached that the function of a protein is mostly decided by its structure, which further decides its sequence. While the integration of biology with artificial intelligence has propelled significant advancements in protein design and engineering, structure-based functional protein design, especially de novo design, the quest for satisfactory outcomes remains elusive. In this work, we use backbone geometry to represent the cavities and tunnels of functional proteins and show that they are essential for functional protein design. Correct cavity enables specific biophysical processes or biochemical reactions, while appropriate tunnels facilitate the transport of biomolecules or ions. We also provide a package called CAvity Investigation Navigator (CAIN) to help to do the analysis, which is available at https://github.com/JiahuiZhangNCSU/CAIN.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Pathfinder: protein folding pathway prediction based on conformational sampling 95%
- Elucidation of Genome-wide Understudied Proteins targeted by PROTAC-induced degradation using Interpretable Machine Learning 95%
- Novel, provable algorithms for efficient ensemble-based computational protein design and their application to the redesign of the c-Raf-RBD:KRas protein-protein interface 93%
Similar papers in this journal
- CRFalign: A Sequence-structure alignment of proteins based on a combinationof HMM-HMM comparison and conditional random fields 96%
- DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Accurate Protein-Ligand Interaction Prediction 95%
- The Network Basis for the Structural Thermostability and the Functional Thermoactivity of Aldolase B 95%
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.