ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features

MicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning...

Full description

Bibliographic Details
Main Authors: Prabina Kumar Meher, Shbana Begam, Tanmaya Kumar Sahu, Ajit Gupta, Anuj Kumar, Upendra Kumar, Atmakuri Ramakrishna Rao, Krishna Pal Singh, Om Parkash Dhankher
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:International Journal of Molecular Sciences
Subjects:
Online Access:https://www.mdpi.com/1422-0067/23/3/1612
_version_ 1797487327659950080
author Prabina Kumar Meher
Shbana Begam
Tanmaya Kumar Sahu
Ajit Gupta
Anuj Kumar
Upendra Kumar
Atmakuri Ramakrishna Rao
Krishna Pal Singh
Om Parkash Dhankher
author_facet Prabina Kumar Meher
Shbana Begam
Tanmaya Kumar Sahu
Ajit Gupta
Anuj Kumar
Upendra Kumar
Atmakuri Ramakrishna Rao
Krishna Pal Singh
Om Parkash Dhankher
author_sort Prabina Kumar Meher
collection DOAJ
description MicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning-based computational method for prediction of miRNAs associated with abiotic stresses. Three types of datasets were used for prediction, i.e., miRNA, Pre-miRNA, and Pre-miRNA + miRNA. The pseudo <i>K</i>-tuple nucleotide compositional features were generated for each sequence to transform the sequence data into numeric feature vectors. Support vector machine (SVM) was employed for prediction. The area under receiver operating characteristics curve (auROC) of 70.21, 69.71, 77.94 and area under precision-recall curve (auPRC) of 69.96, 65.64, 77.32 percentages were obtained for miRNA, Pre-miRNA, and Pre-miRNA + miRNA datasets, respectively. Overall prediction accuracies for the independent test set were 62.33, 64.85, 69.21 percentages, respectively, for the three datasets. The SVM also achieved higher accuracy than other learning methods such as random forest, extreme gradient boosting, and adaptive boosting. To implement our method with ease, an online prediction server “ASRmiRNA” has been developed. The proposed approach is believed to supplement the existing effort for identification of abiotic stress-responsive miRNAs and Pre-miRNAs.
first_indexed 2024-03-09T23:46:02Z
format Article
id doaj.art-ad1699c583be4cc2a5c27b1543fdd591
institution Directory Open Access Journal
issn 1661-6596
1422-0067
language English
last_indexed 2024-03-09T23:46:02Z
publishDate 2022-01-01
publisher MDPI AG
record_format Article
series International Journal of Molecular Sciences
spelling doaj.art-ad1699c583be4cc2a5c27b1543fdd5912023-11-23T16:43:25ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-01-01233161210.3390/ijms23031612ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional FeaturesPrabina Kumar Meher0Shbana Begam1Tanmaya Kumar Sahu2Ajit Gupta3Anuj Kumar4Upendra Kumar5Atmakuri Ramakrishna Rao6Krishna Pal Singh7Om Parkash Dhankher8ICAR-Indian Agricultural Statistics Research Institute, Indian Council of Agricultural Research, New Delhi 110012, IndiaICAR-National Institute for Plant Biotechnology, Indian Council of Agricultural Research, New Delhi 110012, IndiaICAR-National Bureau of Plant Genetic Resources, Indian Council of Agricultural Research, New Delhi 110012, IndiaICAR-Indian Agricultural Statistics Research Institute, Indian Council of Agricultural Research, New Delhi 110012, IndiaICAR-Indian Agricultural Statistics Research Institute, Indian Council of Agricultural Research, New Delhi 110012, IndiaDepartment of Molecular Biology, Biotechnology and Bioinformatics, College of Basic Sciences and Humanities, CCS Haryana Agricultural University, Hisar 125004, IndiaIndian Council of Agricultural Research (ICAR), New Delhi 110012, IndiaBiophysics Unit, College of Basic Sciences and Humanities, GB Pant University of Agriculture & Technology, Pantnagar 263145, IndiaStockbridge School of Agriculture, University of Massachusetts Amherst, Amherst, MA 01003, USAMicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning-based computational method for prediction of miRNAs associated with abiotic stresses. Three types of datasets were used for prediction, i.e., miRNA, Pre-miRNA, and Pre-miRNA + miRNA. The pseudo <i>K</i>-tuple nucleotide compositional features were generated for each sequence to transform the sequence data into numeric feature vectors. Support vector machine (SVM) was employed for prediction. The area under receiver operating characteristics curve (auROC) of 70.21, 69.71, 77.94 and area under precision-recall curve (auPRC) of 69.96, 65.64, 77.32 percentages were obtained for miRNA, Pre-miRNA, and Pre-miRNA + miRNA datasets, respectively. Overall prediction accuracies for the independent test set were 62.33, 64.85, 69.21 percentages, respectively, for the three datasets. The SVM also achieved higher accuracy than other learning methods such as random forest, extreme gradient boosting, and adaptive boosting. To implement our method with ease, an online prediction server “ASRmiRNA” has been developed. The proposed approach is believed to supplement the existing effort for identification of abiotic stress-responsive miRNAs and Pre-miRNAs.https://www.mdpi.com/1422-0067/23/3/1612abiotic stressmiRNAsstress-responsive genesmachine learningcomputational biology
spellingShingle Prabina Kumar Meher
Shbana Begam
Tanmaya Kumar Sahu
Ajit Gupta
Anuj Kumar
Upendra Kumar
Atmakuri Ramakrishna Rao
Krishna Pal Singh
Om Parkash Dhankher
ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
International Journal of Molecular Sciences
abiotic stress
miRNAs
stress-responsive genes
machine learning
computational biology
title ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
title_full ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
title_fullStr ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
title_full_unstemmed ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
title_short ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo <i>K</i>-Tuple Nucleotide Compositional Features
title_sort asrmirna abiotic stress responsive mirna prediction in plants by using machine learning algorithms with pseudo i k i tuple nucleotide compositional features
topic abiotic stress
miRNAs
stress-responsive genes
machine learning
computational biology
url https://www.mdpi.com/1422-0067/23/3/1612
work_keys_str_mv AT prabinakumarmeher asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT shbanabegam asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT tanmayakumarsahu asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT ajitgupta asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT anujkumar asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT upendrakumar asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT atmakuriramakrishnarao asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT krishnapalsingh asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures
AT omparkashdhankher asrmirnaabioticstressresponsivemirnapredictioninplantsbyusingmachinelearningalgorithmswithpseudoikituplenucleotidecompositionalfeatures