A Novel Approach to Prediction of the 3-Dimensional Structures of Protein Backbones by Neural Networks
Abstract
Three-dimensional (3D) structures of protein backbones have been pre(cid:173) dicted using neural networks. A feed forward neural network was trained on a class of functionally, but not structurally, homologous proteins, us(cid:173) ing backpropagation learning. The network generated tertiary structure information in the form of binary distance constraints for the Co atoms in the protein backbone. The binary distance between two Co atoms was o if the distance between them was less than a certain threshold distance, and 1 otherwise. The distance constraints predicted by the trained neu(cid:173) ral network were utilized to generate a folded conformation of the protein backbone, using a steepest descent minimization approach.
Cite
Text
Fredholm et al. "A Novel Approach to Prediction of the 3-Dimensional Structures of Protein Backbones by Neural Networks." Neural Information Processing Systems, 1990.Markdown
[Fredholm et al. "A Novel Approach to Prediction of the 3-Dimensional Structures of Protein Backbones by Neural Networks." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/fredholm1990neurips-novel/)BibTeX
@inproceedings{fredholm1990neurips-novel,
title = {{A Novel Approach to Prediction of the 3-Dimensional Structures of Protein Backbones by Neural Networks}},
author = {Fredholm, Henrik and Bohr, Henrik and Bohr, Jakob and Brunak, Søren and Cotterill, Rodney M. J. and Lautrup, Benny and Petersen, Steffen B.},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {523-529},
url = {https://mlanthology.org/neurips/1990/fredholm1990neurips-novel/}
}