muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance

Bodhayan Prasad; AJ Bjourson; Priyank Shukla

doi:10.1002/pmic.202200252

muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance

Bodhayan Prasad
, AJ Bjourson
, Priyank Shukla

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

100 Downloads (Pure)

Abstract

Multidimensional omic datasets often have correlated features leading to the possibility of discovering multiple biological signatures with similar predictive performance for a phenotype. However, their exploration is limited by low sample size and the exponential nature of the combinatorial search leading to high computational cost. To address these issues, we have developed an algorithm muSignAl (multiple signature algorithm) which selects multiple signatures with similar predictive performance while systematically bypassing the requirement of exploring all the combinations of features. We demonstrated the workflow of this algorithm with an example of proteomics dataset. muSignAl is applicable in various bioinformatics driven explorations, such as understanding the relationship between multiple biological feature sets and phenotypes, and discovery and development of biomarker panels while providing the opportunity of optimising their development cost with the help of equally good multiple signatures. Source code of muSignAl is freely available at https://github.com/ShuklaLab/muSignAl.

Original language	English
Article number	2200252
Pages (from-to)	1-4
Number of pages	4
Journal	Proteomics
Volume	23
Issue number	2
Early online date	8 Sept 2022
DOIs	https://doi.org/10.1002/pmic.202200252
Publication status	Published (in print/issue) - 16 Jan 2023

Bibliographical note

Funding Information:
B.P. would like to acknowledge the funding support of Vice‐Chancellor's Research Scholarship (VCRS), Ulster University. A.J.B. would like to acknowledge funding support by a programme grant jointly from the European Union (EU) Regional Development Fund (ERDF) EU Sustainable Competitiveness Programme for Northern Ireland, the Northern Ireland Public Health Agency (HSC R&D) and Ulster University. P.S. would like to acknowledge funding support from Innovate UK NxNW ICURe programme and UKRI NCSi4P programme ‘Optimal cellular assays for SARS‐CoV‐2 T‐cell, B‐cell and innate immunity’. A.J.B. and P.S. would like to acknowledge funding support by a programme grant jointly from Science Foundation Ireland (SFI), Republic of Ireland and Department for the Economy (DfE), Northern Ireland, UK, ‘COVRES: Understanding the host‐virus response in patients with mild versus serious disease’. A.J.B. and P.S. would like to acknowledge funding support by Northern Ireland Public Health Agency (HSC R&D Division), ‘COVRES2: Identifying temporal immune responses associated with Covid‐19 severity’.

Publisher Copyright:
© 2022 The Authors. Proteomics published by Wiley-VCH GmbH.

Funding

Funding Information: B.P. would like to acknowledge the funding support of Vice‐Chancellor's Research Scholarship (VCRS), Ulster University. A.J.B. would like to acknowledge funding support by a programme grant jointly from the European Union (EU) Regional Development Fund (ERDF) EU Sustainable Competitiveness Programme for Northern Ireland, the Northern Ireland Public Health Agency (HSC R&D) and Ulster University. P.S. would like to acknowledge funding support from Innovate UK NxNW ICURe programme and UKRI NCSi4P programme ‘Optimal cellular assays for SARS‐CoV‐2 T‐cell, B‐cell and innate immunity’. A.J.B. and P.S. would like to acknowledge funding support by a programme grant jointly from Science Foundation Ireland (SFI), Republic of Ireland and Department for the Economy (DfE), Northern Ireland, UK, ‘COVRES: Understanding the host‐virus response in patients with mild versus serious disease’. A.J.B. and P.S. would like to acknowledge funding support by Northern Ireland Public Health Agency (HSC R&D Division), ‘COVRES2: Identifying temporal immune responses associated with Covid‐19 severity’. Publisher Copyright: © 2022 The Authors. Proteomics published by Wiley-VCH GmbH.

Keywords

Bioinformatics
Algorithm
Biomarkers
Proteomics
Olink
proteomics
biomarkers
bioinformatics
algorithm

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/pmic.202200252

Final Published versionFinal published version, 379 KBLicence: CC BY

Cite this

@article{16b7a4225bf849299b2e40231cb13971,

title = "muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance",

abstract = "Multidimensional omic datasets often have correlated features leading to the possibility of discovering multiple biological signatures with similar predictive performance for a phenotype. However, their exploration is limited by low sample size and the exponential nature of the combinatorial search leading to high computational cost. To address these issues, we have developed an algorithm muSignAl (multiple signature algorithm) which selects multiple signatures with similar predictive performance while systematically bypassing the requirement of exploring all the combinations of features. We demonstrated the workflow of this algorithm with an example of proteomics dataset. muSignAl is applicable in various bioinformatics driven explorations, such as understanding the relationship between multiple biological feature sets and phenotypes, and discovery and development of biomarker panels while providing the opportunity of optimising their development cost with the help of equally good multiple signatures. Source code of muSignAl is freely available at https://github.com/ShuklaLab/muSignAl.",

keywords = "Bioinformatics, Algorithm, Biomarkers, Proteomics, Olink, proteomics, biomarkers, bioinformatics, algorithm",

author = "Bodhayan Prasad and AJ Bjourson and Priyank Shukla",

note = "Funding Information: B.P. would like to acknowledge the funding support of Vice‐Chancellor's Research Scholarship (VCRS), Ulster University. A.J.B. would like to acknowledge funding support by a programme grant jointly from the European Union (EU) Regional Development Fund (ERDF) EU Sustainable Competitiveness Programme for Northern Ireland, the Northern Ireland Public Health Agency (HSC R\&D) and Ulster University. P.S. would like to acknowledge funding support from Innovate UK NxNW ICURe programme and UKRI NCSi4P programme {\textquoteleft}Optimal cellular assays for SARS‐CoV‐2 T‐cell, B‐cell and innate immunity{\textquoteright}. A.J.B. and P.S. would like to acknowledge funding support by a programme grant jointly from Science Foundation Ireland (SFI), Republic of Ireland and Department for the Economy (DfE), Northern Ireland, UK, {\textquoteleft}COVRES: Understanding the host‐virus response in patients with mild versus serious disease{\textquoteright}. A.J.B. and P.S. would like to acknowledge funding support by Northern Ireland Public Health Agency (HSC R\&D Division), {\textquoteleft}COVRES2: Identifying temporal immune responses associated with Covid‐19 severity{\textquoteright}. Publisher Copyright: {\textcopyright} 2022 The Authors. Proteomics published by Wiley-VCH GmbH.",

year = "2023",

month = jan,

day = "16",

doi = "10.1002/pmic.202200252",

language = "English",

volume = "23",

pages = "1--4",

journal = "Proteomics",

issn = "1615-9853",

publisher = "Wiley-VCH Verlag",

number = "2",

}

TY - JOUR

T1 - muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance

AU - Prasad, Bodhayan

AU - Bjourson, AJ

AU - Shukla, Priyank

N1 - Funding Information: B.P. would like to acknowledge the funding support of Vice‐Chancellor's Research Scholarship (VCRS), Ulster University. A.J.B. would like to acknowledge funding support by a programme grant jointly from the European Union (EU) Regional Development Fund (ERDF) EU Sustainable Competitiveness Programme for Northern Ireland, the Northern Ireland Public Health Agency (HSC R&D) and Ulster University. P.S. would like to acknowledge funding support from Innovate UK NxNW ICURe programme and UKRI NCSi4P programme ‘Optimal cellular assays for SARS‐CoV‐2 T‐cell, B‐cell and innate immunity’. A.J.B. and P.S. would like to acknowledge funding support by a programme grant jointly from Science Foundation Ireland (SFI), Republic of Ireland and Department for the Economy (DfE), Northern Ireland, UK, ‘COVRES: Understanding the host‐virus response in patients with mild versus serious disease’. A.J.B. and P.S. would like to acknowledge funding support by Northern Ireland Public Health Agency (HSC R&D Division), ‘COVRES2: Identifying temporal immune responses associated with Covid‐19 severity’. Publisher Copyright: © 2022 The Authors. Proteomics published by Wiley-VCH GmbH.

PY - 2023/1/16

Y1 - 2023/1/16

N2 - Multidimensional omic datasets often have correlated features leading to the possibility of discovering multiple biological signatures with similar predictive performance for a phenotype. However, their exploration is limited by low sample size and the exponential nature of the combinatorial search leading to high computational cost. To address these issues, we have developed an algorithm muSignAl (multiple signature algorithm) which selects multiple signatures with similar predictive performance while systematically bypassing the requirement of exploring all the combinations of features. We demonstrated the workflow of this algorithm with an example of proteomics dataset. muSignAl is applicable in various bioinformatics driven explorations, such as understanding the relationship between multiple biological feature sets and phenotypes, and discovery and development of biomarker panels while providing the opportunity of optimising their development cost with the help of equally good multiple signatures. Source code of muSignAl is freely available at https://github.com/ShuklaLab/muSignAl.

AB - Multidimensional omic datasets often have correlated features leading to the possibility of discovering multiple biological signatures with similar predictive performance for a phenotype. However, their exploration is limited by low sample size and the exponential nature of the combinatorial search leading to high computational cost. To address these issues, we have developed an algorithm muSignAl (multiple signature algorithm) which selects multiple signatures with similar predictive performance while systematically bypassing the requirement of exploring all the combinations of features. We demonstrated the workflow of this algorithm with an example of proteomics dataset. muSignAl is applicable in various bioinformatics driven explorations, such as understanding the relationship between multiple biological feature sets and phenotypes, and discovery and development of biomarker panels while providing the opportunity of optimising their development cost with the help of equally good multiple signatures. Source code of muSignAl is freely available at https://github.com/ShuklaLab/muSignAl.

KW - Bioinformatics

KW - Algorithm

KW - Biomarkers

KW - Proteomics

KW - Olink

KW - proteomics

KW - biomarkers

KW - bioinformatics

KW - algorithm

UR - https://pure.ulster.ac.uk/en/publications/16b7a422-5bf8-4929-9b2e-40231cb13971

UR - https://www.scopus.com/pages/publications/85139231386

U2 - 10.1002/pmic.202200252

DO - 10.1002/pmic.202200252

M3 - Article

SN - 1615-9853

VL - 23

SP - 1

EP - 4

JO - Proteomics

JF - Proteomics

IS - 2

M1 - 2200252

ER -

muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Development of machine learning based computational tools for stratified healthcare and personalised medicine

Cite this

muSignAl: An algorithm to search for multiple omic signatures with similar predictive performance

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Student theses

Development of machine learning based computational tools for stratified healthcare and personalised medicine

Cite this