Notice of Violation of IEEE Publication Principles: Species Identification Using Partial DNA Sequence: A Machine Learning Approach

Kabir, Tasnim; Shemonti, Abida Sanjana; Rahman, Atif

doi:10.1109/bibe.2018.00052

Cited by 5 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure the efficacy of our model, we ran our Naïve Bayes classifier on the first five of the COI gene-based empirical datasets presented in Table I considering their full length barcode sequences. By comparing the results to the maximum accuracy from related studies [12], [49], where comparative performance analysis of different supervised machine learning approaches on those same COI gene-based empirical datasets are provided, we found our Naïve Bayes classifier was competent in its performance (as shown in Figure 2). I to analyze the accuracy responses while varying the barcode sequence lengths.…”

Section: Resultsmentioning

confidence: 96%

“…SVM, Jrip, J48 (C4.5), Naïve Bayes were compared on WEKA platforms against those ad-hoc methods by Weitschek et al and it was observed that SVM and Naïve Bayes outperform on average in both synthetic and empirical datasets [12]. Simple-logistic, IBK, PART, Attribute-selected Classifier, Bagging approaches were also implemented in another study [49] in this regard. SMO, BP-NN [50], RF [51], k-mer based approaches [52] [53] can also be perceived in recent studies.…”

Section: Related Workmentioning

confidence: 99%

“…Although supervised statistical classification methods such as: Classification And Regression Tree, Random Forest, and Kernel methods have been studied previously [22], supervised machine learning algorithms e.g., SVM, Jrip, J48 (C4.5), and Naïve Bayes were compared on WEKA platforms to the ad-hoc methods by Weitschek et al and SVM and Naïve Bayes outperformed the other methods for synthetic and empirical datasets [12]. Simple-logistic, IBK, PART, attribute-selected classifier, and bagging approaches were also implemented in [49]. SMO, BP-NN [50], RF [51], and k-mer based approaches [52], [53] can be seen in recent studies.…”

Section: Related Workmentioning

confidence: 99%

“…Performance competency of our Naïve Bayes classifier. The accuracy comparison of our model and the maximum accuracy score giving models of the works of[12] and[49] is depicted in this figure. Our model yields very competing performance in each cases.After testing our Naïve Bayes classifier on the first five empirical COI-based datasets, we ran our model on all of the COI-based empirical datasets presented in TableIto analyze the accuracy responses while varying the barcode sequence lengths.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Karim

Abid

2020

Preprint

View full text Add to dashboard Cite

Specific gene regions in DNA, like COI (Cytochrome c oxidase I) in case of animals, have been defined as DNA barcode and many studies proved that it can be used as an identifier to distinguish species. The standard length of a DNA barcode is approximately 650 bp. But because of the challenges in sequencing technologies or unavailability of high-quality genomic DNA, it is not always possible to get the full barcode sequence of an organism. As a result, recent studies suggest that mini-barcodes can provide a good contribution in the species identification process. Among various methods proposed for the identification task, supervised machine learning methods have been shown effective. In this study, we have analyzed the effect of different barcode lengths on species identification from the perspective of supervised machine learning and suggested a general approximation of required length of mini-barcode in this regard. We have implemented a Naïve Bayes classifier as our model and implied the effectiveness of mini-barcode by demonstrating the accuracy responses varying the length of DNA barcode sequences.

show abstract

Section: Resultsmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Karim

Abid

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Kabir et al [20] explores the power of different supervised learning methods for DNA barcode-based classification. To this end, they evaluate different classifiers including Simple Logistic Function [21], (ii) IBk from Lazy classifier [22], (iii) PART from Rule based classifier [23], (iv) Random Forest from Tree based classifier [24], (v) Attribute Selected Classifier, and (vi) Bagging from Meta classifiers [25].…”

Section: Introductionmentioning

confidence: 99%

Scalable Classification of Organisms into a Taxonomy Using Hierarchical Supervised Learners

Sohsah

Ibrahimzada

Ayaz

et al. 2020

Preprint

View full text Add to dashboard Cite

Taxonomy of living organisms gains major importance in making the study of vastly heterogeneous living things easier. In addition, various fields of applied biology (e.g., agriculture) depend on classification of living creatures. Specific fragments of the DNA sequence of a living organism have been defined as DNA barcodes and can be used as markers to identify species efficiently and effectively. The existing DNA barcode-based classification approaches suffer from three major issues: (i) most of them assume that the classification is done within a given taxonomic class and/or input sequences are prealigned, (ii) highly performing classifiers, such as SVM, cannot scale to large taxonomies due to high memory requirements, (iii) mutations and noise in input DNA sequences greatly reduce the taxonomic classification accuracy. In order to address these issues, we propose a multi-level hierarchical classifier framework to automatically assign taxonomy labels to DNA sequences. We utilize an alignment-free approach called spectrum kernel method for feature extraction. We build a proof-of-concept hierarchical classifier with two levels, and evaluated it on real DNA sequence data from BOLD systems. We demonstrate that the proposed framework provides higher accuracy than regular classifiers. Besides, hierarchical framework scales better to large datasets enabling researchers to employ classifiers with high accuracy and high memory requirement on large datasets. Furthermore, we show that the proposed framework is more robust to mutations and noise in sequence data than the non-hierarchical classifiers.

show abstract

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Karim

Abid

2021

2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)

View full text Add to dashboard Cite

show abstract

Notice of Violation of IEEE Publication Principles: Species Identification Using Partial DNA Sequence: A Machine Learning Approach

Cited by 5 publications

References 32 publications

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Scalable Classification of Organisms into a Taxonomy Using Hierarchical Supervised Learners

Efficacy and accuracy responses of DNA mini-barcodes in species identification under a supervised machine learning approach

Contact Info

Product

Resources

About