Non-Negative Matrix Factorization for Selection of Near-Native Protein Tertiary Structures

Nasrin Akhter, Raviteja Vangara, Gopinath Chennupati, Boian S. Alexandrov, Hristo N. Djidjev, Amarda Shehu

Abstract

Identifying biologically-active protein structure(s) from an ensemble of computed three-dimensional structures is a major challenge. Clustering-based methods are time-consuming and often under perform on structure datasets that are highly imbalanced. Energy landscape-based methods improve performance over imbalanced datasets but incur significant time costs. In this paper we propose a novel method based on non-negative matrix factorization. The method outperforms energy landscape-based clustering methods, addressing both time costs and challenges with imbalanced structure datasets.
BibTeX
@inproceedings{akhter2019non,
  author = {Nasrin Akhter and Raviteja Vangara and Gopinath Chennupati and Boian S. Alexandrov and Hristo N. Djidjev and Amarda Shehu},
  title = {{Non-Negative Matrix Factorization for Selection of Near-Native Protein Tertiary Structures}},
  booktitle = {BIBM},
  year = {2019},
  doi = {10.1109/bibm47256.2019.8983409},
}

Loading related content...

Figure