CoCoNat: A Deep Learning-Based Tool for the Prediction of Coiled-coil Domains in Protein Sequences.

ABSTRACT: Coiled-coil domains (CCDs) are structural motifs observed in proteins in all organisms that perform several crucial functions. The computational identification of CCD segments over a protein sequence is of great importance for its functional characterization. This task can essentially be divided into three separate steps: the detection of segment boundaries, the annotation of the heptad repeat pattern along the segment, and the classification of its oligomerization state. Several methods have been proposed over the years addressing one or more of these predictive steps. In this protocol, we illustrate how to make use of CoCoNat, a novel approach based on protein language models, to characterize CCDs. CoCoNat is, at its release (August 2023), the state of the art for CCD detection. The web

SUBMITTER: Manfredi M 

PROVIDER: S-EPMC10883893 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature