STINGAllo: a web server for high-throughput prediction of allosteric site-forming residues using internal protein nanoenvironment descriptors

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Web server STINGAllo predicts allosteric site-forming residues in protein structures, suggesting better identification methods for drug discovery.

STINGAllo achieves a success rate of approximately 78% for predicting allosteric residues, greatly enhancing accuracy.
The server employs a residue-centric machine-learning model using 54 descriptors of the protein nanoenvironment.
Integration of hydrophobic interaction networks and a unique sponge effect metric allows predictions independent of surface geometry.
This tool enhances understanding of protein regulation and facilitates allosteric drug discovery efforts across various proteins.

Omage et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Web server STINGAllo predicts allosteric site-forming residues in protein structures, suggesting better identification methods for drug discovery.

STINGAllo achieves a success rate of approximately 78% for predicting allosteric residues, greatly enhancing accuracy.
The server employs a residue-centric machine-learning model using 54 descriptors of the protein nanoenvironment.
Integration of hydrophobic interaction networks and a unique sponge effect metric allows predictions independent of surface geometry.
This tool enhances understanding of protein regulation and facilitates allosteric drug discovery efforts across various proteins.

Omage et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark