Cover Image

Predictive Analytics in Genetic Engineering as an Optimization Problem

In genetic engineering, developing a breed with a desired trait is a search and optimization problem that sometimes requires many generations of field and laboratory experiments for an optimal solution to be found. The nature of the problem requires that a stochastic optimization algorithm be applie...

Full description

Saved in:
Bibliographic Details
Main Authors: Okewu, Emmanuel, Okewu Kehinde, Bukola
Format: Article
Language:English
Published: INTI International University 2024
Subjects:
QA76 Computer software
QH426 Genetics
SB Plant culture
Online Access:http://eprints.intimal.edu.my/1970/1/512
http://eprints.intimal.edu.my/1970/
http://ipublishing.intimal.edu.my/jods.html
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-inti-eprints.1970
record_format eprints
spelling my-inti-eprints.19702024-08-06T04:20:25Z http://eprints.intimal.edu.my/1970/ Predictive Analytics in Genetic Engineering as an Optimization Problem Okewu, Emmanuel Okewu Kehinde, Bukola QA76 Computer software QH426 Genetics SB Plant culture In genetic engineering, developing a breed with a desired trait is a search and optimization problem that sometimes requires many generations of field and laboratory experiments for an optimal solution to be found. The nature of the problem requires that a stochastic optimization algorithm be applied in the metaheuristic search rather than using a deterministic or mathematical approach. In the search for drought-tolerant cowpea, this study applied a genetic algorithm as a predictive analytics tool in the genetic engineering of three native cowpea landraces (Dan muzakkari, Gidigiwa, and Dan mesera) selected from Northern Nigeria (specifically from Kontagora in Niger State of Nigeria). The three cowpea species were subjected to mutagenic treatments using gamma irradiation and Ethyl Methane Sulphonate (EMS). Doses applied include 200, 400, 600, and 800 Gray of gamma irradiation and 0.372% v/v of EMS. Both treated and untreated cowpea landraces were planted and observed. Mutation-induced breeding aims to deepen the drought-tolerant trait of the cowpea mutants to survive conditions in drought-prone Northern Nigeria. The statistical analysis of the agro-morphological and yield parameters of the first mutant generation (M1 generation) indicates that mutagenic treatments have a positive impact on both the yield and the survival of the three landraces as all the treated landraces yielded better than the control, particularly the treatments combination of 600gray and 372% v/v of EMS. Also, the predictive outcomes of the computational simulation that was implemented in Python programming indicate that these local cultivars are developing drought-tolerant genetic variability. For the three computational experiments, the stochastic optimizer (genetic algorithm) converged at the 9412th, 9717th, and 14338th generations respectively. Such predictive analytics information is useful for guiding decision-making by researchers and breeders in the crop improvement program. INTI International University 2024-08 Article PeerReviewed text en cc_by_4 http://eprints.intimal.edu.my/1970/1/512 Okewu, Emmanuel and Okewu Kehinde, Bukola (2024) Predictive Analytics in Genetic Engineering as an Optimization Problem. Journal of Data Science, 2024 (30). pp. 1-17. ISSN 2805-5160 http://ipublishing.intimal.edu.my/jods.html
institution INTI International University
building INTI Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider INTI International University
content_source INTI Institutional Repository
url_provider http://eprints.intimal.edu.my
language English
topic QA76 Computer software
QH426 Genetics
SB Plant culture
spellingShingle QA76 Computer software
QH426 Genetics
SB Plant culture
Okewu, Emmanuel
Okewu Kehinde, Bukola
Predictive Analytics in Genetic Engineering as an Optimization Problem
description In genetic engineering, developing a breed with a desired trait is a search and optimization problem that sometimes requires many generations of field and laboratory experiments for an optimal solution to be found. The nature of the problem requires that a stochastic optimization algorithm be applied in the metaheuristic search rather than using a deterministic or mathematical approach. In the search for drought-tolerant cowpea, this study applied a genetic algorithm as a predictive analytics tool in the genetic engineering of three native cowpea landraces (Dan muzakkari, Gidigiwa, and Dan mesera) selected from Northern Nigeria (specifically from Kontagora in Niger State of Nigeria). The three cowpea species were subjected to mutagenic treatments using gamma irradiation and Ethyl Methane Sulphonate (EMS). Doses applied include 200, 400, 600, and 800 Gray of gamma irradiation and 0.372% v/v of EMS. Both treated and untreated cowpea landraces were planted and observed. Mutation-induced breeding aims to deepen the drought-tolerant trait of the cowpea mutants to survive conditions in drought-prone Northern Nigeria. The statistical analysis of the agro-morphological and yield parameters of the first mutant generation (M1 generation) indicates that mutagenic treatments have a positive impact on both the yield and the survival of the three landraces as all the treated landraces yielded better than the control, particularly the treatments combination of 600gray and 372% v/v of EMS. Also, the predictive outcomes of the computational simulation that was implemented in Python programming indicate that these local cultivars are developing drought-tolerant genetic variability. For the three computational experiments, the stochastic optimizer (genetic algorithm) converged at the 9412th, 9717th, and 14338th generations respectively. Such predictive analytics information is useful for guiding decision-making by researchers and breeders in the crop improvement program.
format Article
author Okewu, Emmanuel
Okewu Kehinde, Bukola
author_facet Okewu, Emmanuel
Okewu Kehinde, Bukola
author_sort Okewu, Emmanuel
title Predictive Analytics in Genetic Engineering as an Optimization Problem
title_short Predictive Analytics in Genetic Engineering as an Optimization Problem
title_full Predictive Analytics in Genetic Engineering as an Optimization Problem
title_fullStr Predictive Analytics in Genetic Engineering as an Optimization Problem
title_full_unstemmed Predictive Analytics in Genetic Engineering as an Optimization Problem
title_sort predictive analytics in genetic engineering as an optimization problem
publisher INTI International University
publishDate 2024
url http://eprints.intimal.edu.my/1970/1/512
http://eprints.intimal.edu.my/1970/
http://ipublishing.intimal.edu.my/jods.html
_version_ 1806694096665837568
score 13.211869

Similar Items