Non-linear molecular pattern classification using molecular beacons with multiple targets

In Hee Lee; Seung Hwan Lee; Tai Hyun Park; Byoung Tak Zhang

doi:10.1016/j.biosystems.2013.05.008

Non-linear molecular pattern classification using molecular beacons with multiple targets

In Hee Lee, Seung Hwan Lee, Tai Hyun Park, Byoung Tak Zhang

Department of Nutritional Science & Food Management

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

3 Scopus citations

Abstract

In vitro pattern classification has been highlighted as an important future application of DNA computing. Previous work has demonstrated the feasibility of linear classifiers using DNA-based molecular computing. However, complex tasks require non-linear classification capability. Here we design a molecular beacon that can interact with multiple targets and experimentally shows that its fluorescent signals form a complex radial-basis function, enabling it to be used as a building block for non-linear molecular classification in vitro. The proposed method was successfully applied to solving artificial and real-world classification problems: XOR and microRNA expression patterns.

Original language	English
Pages (from-to)	206-213
Number of pages	8
Journal	BioSystems
Volume	114
Issue number	3
DOIs	https://doi.org/10.1016/j.biosystems.2013.05.008
State	Published - Dec 2013

Bibliographical note

Funding Information:
This research was supported in part by the Ministry of Knowledge Economy (MKE) through the Molecular Evolutionary Computing (MEC) project, the National Research Foundation of Korea (NRF) grant funded by the Ministry of Education, Science & Technology (MEST) (No. 0421-20110032 ), and the BK21-IT Program. The ICT at Seoul National University provided research facilities for this study.

Keywords

Biological data analysis
DNA computing
Molecular beacons
Molecular pattern classification
Non-linear classification

Access to Document

10.1016/j.biosystems.2013.05.008

Cite this

@article{20e0f3b5121b4e06b4ea6689daa3b7de,

title = "Non-linear molecular pattern classification using molecular beacons with multiple targets",

abstract = "In vitro pattern classification has been highlighted as an important future application of DNA computing. Previous work has demonstrated the feasibility of linear classifiers using DNA-based molecular computing. However, complex tasks require non-linear classification capability. Here we design a molecular beacon that can interact with multiple targets and experimentally shows that its fluorescent signals form a complex radial-basis function, enabling it to be used as a building block for non-linear molecular classification in vitro. The proposed method was successfully applied to solving artificial and real-world classification problems: XOR and microRNA expression patterns.",

keywords = "Biological data analysis, DNA computing, Molecular beacons, Molecular pattern classification, Non-linear classification",

author = "Lee, {In Hee} and Lee, {Seung Hwan} and Park, {Tai Hyun} and Zhang, {Byoung Tak}",

note = "Funding Information: This research was supported in part by the Ministry of Knowledge Economy (MKE) through the Molecular Evolutionary Computing (MEC) project, the National Research Foundation of Korea (NRF) grant funded by the Ministry of Education, Science & Technology (MEST) (No. 0421-20110032 ), and the BK21-IT Program. The ICT at Seoul National University provided research facilities for this study. ",

year = "2013",

month = dec,

doi = "10.1016/j.biosystems.2013.05.008",

language = "English",

volume = "114",

pages = "206--213",

journal = "BioSystems",

issn = "0303-2647",

publisher = "Elsevier Ireland Ltd",

number = "3",

}

TY - JOUR

T1 - Non-linear molecular pattern classification using molecular beacons with multiple targets

AU - Lee, In Hee

AU - Lee, Seung Hwan

AU - Park, Tai Hyun

AU - Zhang, Byoung Tak

N1 - Funding Information: This research was supported in part by the Ministry of Knowledge Economy (MKE) through the Molecular Evolutionary Computing (MEC) project, the National Research Foundation of Korea (NRF) grant funded by the Ministry of Education, Science & Technology (MEST) (No. 0421-20110032 ), and the BK21-IT Program. The ICT at Seoul National University provided research facilities for this study.

PY - 2013/12

Y1 - 2013/12

N2 - In vitro pattern classification has been highlighted as an important future application of DNA computing. Previous work has demonstrated the feasibility of linear classifiers using DNA-based molecular computing. However, complex tasks require non-linear classification capability. Here we design a molecular beacon that can interact with multiple targets and experimentally shows that its fluorescent signals form a complex radial-basis function, enabling it to be used as a building block for non-linear molecular classification in vitro. The proposed method was successfully applied to solving artificial and real-world classification problems: XOR and microRNA expression patterns.

AB - In vitro pattern classification has been highlighted as an important future application of DNA computing. Previous work has demonstrated the feasibility of linear classifiers using DNA-based molecular computing. However, complex tasks require non-linear classification capability. Here we design a molecular beacon that can interact with multiple targets and experimentally shows that its fluorescent signals form a complex radial-basis function, enabling it to be used as a building block for non-linear molecular classification in vitro. The proposed method was successfully applied to solving artificial and real-world classification problems: XOR and microRNA expression patterns.

KW - Biological data analysis

KW - DNA computing

KW - Molecular beacons

KW - Molecular pattern classification

KW - Non-linear classification

UR - http://www.scopus.com/inward/record.url?scp=84885723333&partnerID=8YFLogxK

U2 - 10.1016/j.biosystems.2013.05.008

DO - 10.1016/j.biosystems.2013.05.008

M3 - Article

C2 - 23743339

AN - SCOPUS:84885723333

SN - 0303-2647

VL - 114

SP - 206

EP - 213

JO - BioSystems

JF - BioSystems

IS - 3

ER -

Non-linear molecular pattern classification using molecular beacons with multiple targets

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this