Loading...
Classification of Local Protein Structural Motifs by Kohonen Networks
Schuchardt, Johannes Schneider, Gisbert Reichelt, Joachim Schomburg, Dietmar Wrede, Paul
Schuchardt, Johannes
Schneider, Gisbert
Reichelt, Joachim
Schomburg, Dietmar
Wrede, Paul
Citations
Altmetric:
Advisors
Editors
Other Contributors
Issue Date
1995
Submitted date
2024-05-29
Files
Loading...
PDF
Adobe PDF, 3.82 MB
Other Titles
Abstract
Kohonen networks were used for automatic classification of local structural elements derived from a set of 136 non-homologousproteins. A reduced representation of protein backbones based on dihedral phi and psi angles was employedfor construction of training patterns. Segments of nine residues were transformed into a 16-dimensional description by their angular values. Kohonen-mapping yielded a two-dimensional topological map of representative structural motifs. Helical structures and sheets are located on opposite sides of the feature map, and several intermediate forms are found. The map wasusedto trace protein backbones of two proteins, cytochrome bs and y-IV crystallin, leading to characteristic trajectories in the feature map.
Citation
Bioinformatics - from nucleic acids and proteins to cell metabolism, 85 - 92
DOI
PubMed ID
PubMed Central ID
Additional Links
Embedded video
Type
Book chapter
conference paper
conference paper
Language
en
Description
Series/Report no.
GBF monographs ; Volume 18
ISSN
0930-4320
EISSN
ISBN
3527300724
ISMN
Gov't Doc #
Sponsors
License
Attribution-NonCommercial-ShareAlike 4.0 International