A machine learning approach for predicting Antibody Properties

Oche Alexander Egaji; Seamus Ballard-Smith; Ikram Asghar; Mark Griffiths

doi:10.1145/3418981.3418983

A machine learning approach for predicting Antibody Properties

Oche Alexander Egaji, Seamus Ballard-Smith, Ikram Asghar, Mark Griffiths

Faculty of Computing, Engineering and Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

204 Downloads (Pure)

Abstract

This paper used an amino acid location-based sequence encoding as a feature extraction techniques to identify single chains antibody molecules that bind to B-lymphocyte stimulator (BLyS) antigen. The data were manually derived from the European patent (EP2275449B1) text. The dataset was cleaned and made suitable for the machine learning models. The accuracy, precision and recall achieved across individual descriptors (Membrane and Soluble) for Logistic regression, KNN, KSVM, and Random Forest Tree was above 80%. However, it was much lower for the Naïve Bayes except for the precision score. The promising accuracy value achieved from such a minimal dataset has significant implications for the drug discovery process – this includes considerable savings in time and resources.

Original language	English
Title of host publication	Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop
Subtitle of host publication	ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology
Place of Publication	Paris, France
Publisher	Association for Computing Machinery
Pages	20-24
Number of pages	5
ISBN (Electronic)	978-1-4503-8770-5
ISBN (Print)	978-1-4503-8770-5
DOIs	https://doi.org/10.1145/3418981.3418983
Publication status	Published - 28 Jun 2020

Publication series

Name	ACM International Conference Proceeding Series

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Amino acid sequence
Antibody
Antigen
Infectious disease
Machine learning

Access to Document

10.1145/3418981.3418983Licence: Other

FP2-8007-PublicationAccepted author manuscript, 647 KB

Cite this

Egaji, O. A., Ballard-Smith, S., Asghar, I., & Griffiths, M. (2020). A machine learning approach for predicting Antibody Properties. In Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop: ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology (pp. 20-24). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3418981.3418983

Egaji, Oche Alexander ; Ballard-Smith, Seamus ; Asghar, Ikram et al. / A machine learning approach for predicting Antibody Properties. Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop: ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology. Paris, France : Association for Computing Machinery, 2020. pp. 20-24 (ACM International Conference Proceeding Series).

@inproceedings{9f5bc2fb465249f29c9bdaabbc487a09,

title = "A machine learning approach for predicting Antibody Properties",

abstract = "This paper used an amino acid location-based sequence encoding as a feature extraction techniques to identify single chains antibody molecules that bind to B-lymphocyte stimulator (BLyS) antigen. The data were manually derived from the European patent (EP2275449B1) text. The dataset was cleaned and made suitable for the machine learning models. The accuracy, precision and recall achieved across individual descriptors (Membrane and Soluble) for Logistic regression, KNN, KSVM, and Random Forest Tree was above 80%. However, it was much lower for the Na{\"i}ve Bayes except for the precision score. The promising accuracy value achieved from such a minimal dataset has significant implications for the drug discovery process – this includes considerable savings in time and resources. ",

keywords = "Amino acid sequence, Antibody, Antigen, Infectious disease, Machine learning",

author = "Egaji, {Oche Alexander} and Seamus Ballard-Smith and Ikram Asghar and Mark Griffiths",

note = "Funding Information: The authors will like to acknowledge the European Regional Development Fund (ERDF) and the Welsh Government for funding this study. Our gratitude goes to all members of the Centre of Excellence in Mobile and Emerging Technologies (CEMET), the University of South Wales for their contribution in various capacity in this study. Publisher Copyright: {\textcopyright} 2020 ACM. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2020",

month = jun,

day = "28",

doi = "10.1145/3418981.3418983",

language = "English",

isbn = "978-1-4503-8770-5",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "20--24",

booktitle = "Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop",

}

Egaji, OA, Ballard-Smith, S, Asghar, I & Griffiths, M 2020, A machine learning approach for predicting Antibody Properties. in Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop: ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology. ACM International Conference Proceeding Series, Association for Computing Machinery, Paris, France, pp. 20-24. https://doi.org/10.1145/3418981.3418983

A machine learning approach for predicting Antibody Properties. / Egaji, Oche Alexander; Ballard-Smith, Seamus; Asghar, Ikram et al.
Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop: ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology. Paris, France: Association for Computing Machinery, 2020. p. 20-24 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A machine learning approach for predicting Antibody Properties

AU - Egaji, Oche Alexander

AU - Ballard-Smith, Seamus

AU - Asghar, Ikram

AU - Griffiths, Mark

N1 - Funding Information: The authors will like to acknowledge the European Regional Development Fund (ERDF) and the Welsh Government for funding this study. Our gratitude goes to all members of the Centre of Excellence in Mobile and Emerging Technologies (CEMET), the University of South Wales for their contribution in various capacity in this study. Publisher Copyright: © 2020 ACM. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/6/28

Y1 - 2020/6/28

N2 - This paper used an amino acid location-based sequence encoding as a feature extraction techniques to identify single chains antibody molecules that bind to B-lymphocyte stimulator (BLyS) antigen. The data were manually derived from the European patent (EP2275449B1) text. The dataset was cleaned and made suitable for the machine learning models. The accuracy, precision and recall achieved across individual descriptors (Membrane and Soluble) for Logistic regression, KNN, KSVM, and Random Forest Tree was above 80%. However, it was much lower for the Naïve Bayes except for the precision score. The promising accuracy value achieved from such a minimal dataset has significant implications for the drug discovery process – this includes considerable savings in time and resources.

AB - This paper used an amino acid location-based sequence encoding as a feature extraction techniques to identify single chains antibody molecules that bind to B-lymphocyte stimulator (BLyS) antigen. The data were manually derived from the European patent (EP2275449B1) text. The dataset was cleaned and made suitable for the machine learning models. The accuracy, precision and recall achieved across individual descriptors (Membrane and Soluble) for Logistic regression, KNN, KSVM, and Random Forest Tree was above 80%. However, it was much lower for the Naïve Bayes except for the precision score. The promising accuracy value achieved from such a minimal dataset has significant implications for the drug discovery process – this includes considerable savings in time and resources.

KW - Amino acid sequence

KW - Antibody

KW - Antigen

KW - Infectious disease

KW - Machine learning

U2 - 10.1145/3418981.3418983

DO - 10.1145/3418981.3418983

M3 - Conference contribution

SN - 978-1-4503-8770-5

T3 - ACM International Conference Proceeding Series

SP - 20

EP - 24

BT - Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop

PB - Association for Computing Machinery

CY - Paris, France

ER -

Egaji OA, Ballard-Smith S, Asghar I, Griffiths M. A machine learning approach for predicting Antibody Properties. In Proceedings of ICICM 2020 - 2020 10th International Conference on Information Communication and Management, Worshop: ICKET 2020 - 2020 9th International Conference on Knowledge and Education Technology. Paris, France: Association for Computing Machinery. 2020. p. 20-24. (ACM International Conference Proceeding Series). doi: 10.1145/3418981.3418983

A machine learning approach for predicting Antibody Properties

Abstract

Publication series

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this