Predicted protein-protein interaction sites from local sequence information

Yanay Ofran; Burkhard Rost

doi:10.1016/s0014-5793(03)00456-3

Predicted protein-protein interaction sites from local sequence information

Yanay Ofran, Burkhard Rost

Columbia University

Research output: Contribution to journal › Article › peer-review

227 Scopus citations

Abstract

Protein-protein interactions are facilitated by a myriad of residue-residue contacts on the interacting proteins. Identifying the site of interaction in the protein is a key for deciphering its functional mechanisms, and is crucial for drug development. Many studies indicate that the compositions of contacting residues are unique. Here, we describe a neural network that identifies protein-protein interfaces from sequence. For the most strongly predicted sites (in 34 of 333 proteins), 94% of the predictions were confirmed experimentally. When 70% of our predictions were right, we correctly predicted at least one interaction site in 20% of the complexes (66/333). These results indicate that the prediction of some interaction sites from sequence alone is possible. Incorporating evolutionary and predicted structural information may improve our method. However, even at this early stage, our tool might already assist wet-lab biology.

Original language	English
Pages (from-to)	236-239
Number of pages	4
Journal	FEBS Letters
Volume	544
Issue number	1-3
DOIs	https://doi.org/10.1016/s0014-5793(03)00456-3
State	Published - 5 Jun 2003
Externally published	Yes

Bibliographical note

Funding Information:
Thanks to Rana Samuels (Columbia) for her invaluable comments on the manuscript. Thanks to Jinfeng Liu (Columbia) for computer assistance and to Kaz Wrzeszczynski (Columbia) for crucial insights. Thanks also to the anonymous referee and to Rob Russell (EMBL) for helpful comments. The work was supported by Grants 1-P50-GM62413-01 and RO1-GM63029-01 from the National Institute of Health. Last, but not least, thanks to all those who deposit their experimental data in public databases, and to those who maintain these databases.

Funding

Thanks to Rana Samuels (Columbia) for her invaluable comments on the manuscript. Thanks to Jinfeng Liu (Columbia) for computer assistance and to Kaz Wrzeszczynski (Columbia) for crucial insights. Thanks also to the anonymous referee and to Rob Russell (EMBL) for helpful comments. The work was supported by Grants 1-P50-GM62413-01 and RO1-GM63029-01 from the National Institute of Health. Last, but not least, thanks to all those who deposit their experimental data in public databases, and to those who maintain these databases.

Funders	Funder number
National institute of Health
National Institute of General Medical Sciences	R01GM063029

Keywords

Bioinformatics
Data mining
Neural network
Protein function
Protein structure
Protein-protein interaction
Sequence analysis

Access to Document

10.1016/s0014-5793(03)00456-3

Cite this

@article{73bc4f23230841beb7a89d86dd5acee8,

title = "Predicted protein-protein interaction sites from local sequence information",

abstract = "Protein-protein interactions are facilitated by a myriad of residue-residue contacts on the interacting proteins. Identifying the site of interaction in the protein is a key for deciphering its functional mechanisms, and is crucial for drug development. Many studies indicate that the compositions of contacting residues are unique. Here, we describe a neural network that identifies protein-protein interfaces from sequence. For the most strongly predicted sites (in 34 of 333 proteins), 94% of the predictions were confirmed experimentally. When 70% of our predictions were right, we correctly predicted at least one interaction site in 20% of the complexes (66/333). These results indicate that the prediction of some interaction sites from sequence alone is possible. Incorporating evolutionary and predicted structural information may improve our method. However, even at this early stage, our tool might already assist wet-lab biology.",

keywords = "Bioinformatics, Data mining, Neural network, Protein function, Protein structure, Protein-protein interaction, Sequence analysis",

author = "Yanay Ofran and Burkhard Rost",

note = "Funding Information: Thanks to Rana Samuels (Columbia) for her invaluable comments on the manuscript. Thanks to Jinfeng Liu (Columbia) for computer assistance and to Kaz Wrzeszczynski (Columbia) for crucial insights. Thanks also to the anonymous referee and to Rob Russell (EMBL) for helpful comments. The work was supported by Grants 1-P50-GM62413-01 and RO1-GM63029-01 from the National Institute of Health. Last, but not least, thanks to all those who deposit their experimental data in public databases, and to those who maintain these databases. ",

year = "2003",

month = jun,

day = "5",

doi = "10.1016/s0014-5793(03)00456-3",

language = "אנגלית",

volume = "544",

pages = "236--239",

journal = "FEBS Letters",

issn = "0014-5793",

publisher = "John Wiley and Sons Inc.",

number = "1-3",

}

TY - JOUR

T1 - Predicted protein-protein interaction sites from local sequence information

AU - Ofran, Yanay

AU - Rost, Burkhard

N1 - Funding Information: Thanks to Rana Samuels (Columbia) for her invaluable comments on the manuscript. Thanks to Jinfeng Liu (Columbia) for computer assistance and to Kaz Wrzeszczynski (Columbia) for crucial insights. Thanks also to the anonymous referee and to Rob Russell (EMBL) for helpful comments. The work was supported by Grants 1-P50-GM62413-01 and RO1-GM63029-01 from the National Institute of Health. Last, but not least, thanks to all those who deposit their experimental data in public databases, and to those who maintain these databases.

PY - 2003/6/5

Y1 - 2003/6/5

N2 - Protein-protein interactions are facilitated by a myriad of residue-residue contacts on the interacting proteins. Identifying the site of interaction in the protein is a key for deciphering its functional mechanisms, and is crucial for drug development. Many studies indicate that the compositions of contacting residues are unique. Here, we describe a neural network that identifies protein-protein interfaces from sequence. For the most strongly predicted sites (in 34 of 333 proteins), 94% of the predictions were confirmed experimentally. When 70% of our predictions were right, we correctly predicted at least one interaction site in 20% of the complexes (66/333). These results indicate that the prediction of some interaction sites from sequence alone is possible. Incorporating evolutionary and predicted structural information may improve our method. However, even at this early stage, our tool might already assist wet-lab biology.

AB - Protein-protein interactions are facilitated by a myriad of residue-residue contacts on the interacting proteins. Identifying the site of interaction in the protein is a key for deciphering its functional mechanisms, and is crucial for drug development. Many studies indicate that the compositions of contacting residues are unique. Here, we describe a neural network that identifies protein-protein interfaces from sequence. For the most strongly predicted sites (in 34 of 333 proteins), 94% of the predictions were confirmed experimentally. When 70% of our predictions were right, we correctly predicted at least one interaction site in 20% of the complexes (66/333). These results indicate that the prediction of some interaction sites from sequence alone is possible. Incorporating evolutionary and predicted structural information may improve our method. However, even at this early stage, our tool might already assist wet-lab biology.

KW - Bioinformatics

KW - Data mining

KW - Neural network

KW - Protein function

KW - Protein structure

KW - Protein-protein interaction

KW - Sequence analysis

UR - http://www.scopus.com/inward/record.url?scp=0038356582&partnerID=8YFLogxK

U2 - 10.1016/s0014-5793(03)00456-3

DO - 10.1016/s0014-5793(03)00456-3

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 12782323

SN - 0014-5793

VL - 544

SP - 236

EP - 239

JO - FEBS Letters

JF - FEBS Letters

IS - 1-3

ER -

Predicted protein-protein interaction sites from local sequence information

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this