MU-LOC

A Machine-Learning Method for Predicting Mitochondrially Localized Proteins in Plants

Ning Zhang, R Shyama Prasad Rao, Fernanda Salvato, Jesper Foged Havelund, Ian Max Møller, Jay J. Thelen, Dong Xu

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Targeting and translocation of proteins to the appropriate subcellular compartments are crucial for cell organization and function. Newly synthesized proteins are transported to mitochondria with the assistance of complex targeting sequences containing either an N-terminal pre-sequence or a multitude of internal signals. Compared with experimental approaches, computational predictions provide an efficient way to infer subcellular localization of a protein. However, it is still challenging to predict plant mitochondrially localized proteins accurately due to various limitations. Consequently, the performance of current tools can be improved with new data and new machine-learning methods. We present MU-LOC, a novel computational approach for large-scale prediction of plant mitochondrial proteins. We collected a comprehensive dataset of plant subcellular localization, extracted features including amino acid composition, protein position weight matrix, and gene co-expression information, and trained predictors using deep neural network and support vector machine. Benchmarked on two independent datasets, MU-LOC achieved substantial improvements over six state-of-the-art tools for plant mitochondrial targeting prediction. In addition, MU-LOC has the advantage of predicting plant mitochondrial proteins either possessing or lacking N-terminal pre-sequences. We applied MU-LOC to predict candidate mitochondrial proteins for the whole proteome of Arabidopsis and potato. MU-LOC is publicly available at http://mu-loc.org.
OriginalsprogEngelsk
Artikelnummer634
TidsskriftFrontiers in Plant Science
Vol/bind9
Antal sider14
ISSN1664-462X
DOI
StatusUdgivet - 23. maj 2018
Udgivet eksterntJa

Fingeraftryk

artificial intelligence
plant proteins
proteins
prediction
methodology
protein transport
proteome
amino acid composition
neural networks
mitochondria
Arabidopsis
potatoes

Citer dette

Zhang, Ning ; Rao, R Shyama Prasad ; Salvato, Fernanda ; Havelund, Jesper Foged ; Møller, Ian Max ; Thelen, Jay J. ; Xu, Dong. / MU-LOC : A Machine-Learning Method for Predicting Mitochondrially Localized Proteins in Plants. I: Frontiers in Plant Science. 2018 ; Bind 9.
@article{77677b5da1e7477790b4c26efe44c093,
title = "MU-LOC: A Machine-Learning Method for Predicting Mitochondrially Localized Proteins in Plants",
abstract = "Targeting and translocation of proteins to the appropriate subcellular compartments are crucial for cell organization and function. Newly synthesized proteins are transported to mitochondria with the assistance of complex targeting sequences containing either an N-terminal pre-sequence or a multitude of internal signals. Compared with experimental approaches, computational predictions provide an efficient way to infer subcellular localization of a protein. However, it is still challenging to predict plant mitochondrially localized proteins accurately due to various limitations. Consequently, the performance of current tools can be improved with new data and new machine-learning methods. We present MU-LOC, a novel computational approach for large-scale prediction of plant mitochondrial proteins. We collected a comprehensive dataset of plant subcellular localization, extracted features including amino acid composition, protein position weight matrix, and gene co-expression information, and trained predictors using deep neural network and support vector machine. Benchmarked on two independent datasets, MU-LOC achieved substantial improvements over six state-of-the-art tools for plant mitochondrial targeting prediction. In addition, MU-LOC has the advantage of predicting plant mitochondrial proteins either possessing or lacking N-terminal pre-sequences. We applied MU-LOC to predict candidate mitochondrial proteins for the whole proteome of Arabidopsis and potato. MU-LOC is publicly available at http://mu-loc.org.",
author = "Ning Zhang and Rao, {R Shyama Prasad} and Fernanda Salvato and Havelund, {Jesper Foged} and M{\o}ller, {Ian Max} and Thelen, {Jay J.} and Dong Xu",
year = "2018",
month = "5",
day = "23",
doi = "10.3389/fpls.2018.00634",
language = "English",
volume = "9",
journal = "Frontiers in Plant Science",
issn = "1664-462X",
publisher = "Frontiers Media S.A.",

}

MU-LOC : A Machine-Learning Method for Predicting Mitochondrially Localized Proteins in Plants. / Zhang, Ning; Rao, R Shyama Prasad; Salvato, Fernanda; Havelund, Jesper Foged; Møller, Ian Max; Thelen, Jay J.; Xu, Dong.

I: Frontiers in Plant Science, Bind 9, 634, 23.05.2018.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - MU-LOC

T2 - A Machine-Learning Method for Predicting Mitochondrially Localized Proteins in Plants

AU - Zhang, Ning

AU - Rao, R Shyama Prasad

AU - Salvato, Fernanda

AU - Havelund, Jesper Foged

AU - Møller, Ian Max

AU - Thelen, Jay J.

AU - Xu, Dong

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Targeting and translocation of proteins to the appropriate subcellular compartments are crucial for cell organization and function. Newly synthesized proteins are transported to mitochondria with the assistance of complex targeting sequences containing either an N-terminal pre-sequence or a multitude of internal signals. Compared with experimental approaches, computational predictions provide an efficient way to infer subcellular localization of a protein. However, it is still challenging to predict plant mitochondrially localized proteins accurately due to various limitations. Consequently, the performance of current tools can be improved with new data and new machine-learning methods. We present MU-LOC, a novel computational approach for large-scale prediction of plant mitochondrial proteins. We collected a comprehensive dataset of plant subcellular localization, extracted features including amino acid composition, protein position weight matrix, and gene co-expression information, and trained predictors using deep neural network and support vector machine. Benchmarked on two independent datasets, MU-LOC achieved substantial improvements over six state-of-the-art tools for plant mitochondrial targeting prediction. In addition, MU-LOC has the advantage of predicting plant mitochondrial proteins either possessing or lacking N-terminal pre-sequences. We applied MU-LOC to predict candidate mitochondrial proteins for the whole proteome of Arabidopsis and potato. MU-LOC is publicly available at http://mu-loc.org.

AB - Targeting and translocation of proteins to the appropriate subcellular compartments are crucial for cell organization and function. Newly synthesized proteins are transported to mitochondria with the assistance of complex targeting sequences containing either an N-terminal pre-sequence or a multitude of internal signals. Compared with experimental approaches, computational predictions provide an efficient way to infer subcellular localization of a protein. However, it is still challenging to predict plant mitochondrially localized proteins accurately due to various limitations. Consequently, the performance of current tools can be improved with new data and new machine-learning methods. We present MU-LOC, a novel computational approach for large-scale prediction of plant mitochondrial proteins. We collected a comprehensive dataset of plant subcellular localization, extracted features including amino acid composition, protein position weight matrix, and gene co-expression information, and trained predictors using deep neural network and support vector machine. Benchmarked on two independent datasets, MU-LOC achieved substantial improvements over six state-of-the-art tools for plant mitochondrial targeting prediction. In addition, MU-LOC has the advantage of predicting plant mitochondrial proteins either possessing or lacking N-terminal pre-sequences. We applied MU-LOC to predict candidate mitochondrial proteins for the whole proteome of Arabidopsis and potato. MU-LOC is publicly available at http://mu-loc.org.

U2 - 10.3389/fpls.2018.00634

DO - 10.3389/fpls.2018.00634

M3 - Journal article

VL - 9

JO - Frontiers in Plant Science

JF - Frontiers in Plant Science

SN - 1664-462X

M1 - 634

ER -