Graphical models for identifying pore‐forming proteins
Proteins: Structure, Function, and Bioinformatics · 2024
DOI: 10.1002/prot.26687 ↗At a glance
Journal article in Proteins: Structure, Function, and Bioinformatics, 2024. Written by Nan Xu and 3 co-authors. Institution: Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA. Major MEDLINE topics: Pore Forming Cytotoxic Proteins, Databases, Protein. 27 references. Funded by: BASF, Bar Association of San Francisco.
Abstract (original language)
Pore‐forming toxins (PFTs) are proteins that form lesions in biological membranes. Better understanding of the structure and function of these proteins will be beneficial in a number of biotechnological applications, including the development of new pest control methods in agriculture. When searching for new pore formers, existing sequence homology‐based methods fail to discover truly novel proteins with low sequence identity to known proteins. Search methodologies based on protein structures would help us move beyond this limitation. As the number of known structures for PFTs is very limited, it's quite challenging to identify new proteins having similar structures using computational approaches like deep learning. In this article, we therefore propose a sample‐efficient graphical model, where a protein structure graph is first constructed according to consensus secondary structures. A semi‐Markov conditional random fields model is then developed to perform protein sequence segmentation. We demonstrate that our method is able to distinguish structurally similar proteins even in the absence of sequence similarity (pairwise sequence identity < 0.4)—a feat not achievable by traditional approaches like HMMs. To extract proteins of interest from a genome‐wide protein database for further study, we also develop an efficient framework for UniRef50 with 43 million proteins.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA.
- BASF Corporation, Research Triangle Park, North Carolina, USA.
Funding
- BASF
- Bar Association of San Francisco
Cite
APA
Xu, N., Kahn, T. W., Jacob, T., & Liu, Y. (2024). Graphical models for identifying pore‐forming proteins. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.26687
Vancouver
Xu N, Kahn TW, Jacob T, Liu Y. Graphical models for identifying pore‐forming proteins. Proteins: Structure, Function, and Bioinformatics. 2024. doi:10.1002/prot.26687
BibTeX
@article{Xu2024,
author = {Xu, Nan and Kahn, Theodore W and Jacob, Theju and Liu, Yan},
title = {Graphical models for identifying pore‐forming proteins},
journal = {Proteins: Structure, Function, and Bioinformatics},
year = {2024},
doi = {10.1002/prot.26687}
}
EUVIMED