Effective statistical features for coding and non-coding DNA sequence classification for yeast, C. elegans and human

The application of signal processing techniques for identification of exons in Deoxyribonucleic acid (DNA) sequence is a challenging task. The objective of this paper is to introduce a combinational window approach for locating exons in DNA sequence. In contrast to the traditional single window function for evaluation of short time Fourier transform (STFT), this work proposes a novel method for evaluating STFT coefficients using a combinational window function comprising of Gaussian, Lanczos and Chebyshev (GLC) windows. The chosen combinational window GLC has the highest relative side lobe attenuation values compared to other window functions introduced by various researchers. The proposed algorithm incorporates GLC window function for evaluating STFT coefficients and in the design of FIR bandpass filter. Simulation results revealed its effectiveness in improving the evaluation parameters like Sensitivity, Specificity, Accuracy, Area under curve (AUC), Discrimination Measure (DM). Furthermore, the proposed algorithm has been applied successfully to some universal benchmark datasets like C. elegans, Homosapiens, etc., The proposed method has shown to be an efficient approach for the prediction of protein coding regions compared to other existing methods. All the simulations are done using the MATLAB 2016a.

Download Full-text

DNA Sequence Classification Using Power Spectrum and Wavelet Neural Network

Advances in Intelligent Systems and Computing - Proceedings of the 16th International Conference on Hybrid Intelligent Systems (HIS 2016) ◽

10.1007/978-3-319-52941-7_39 ◽

2017 ◽

pp. 391-402

Author(s):

Abdesselem Dakhli ◽

Wajdi Bellil ◽

Chokri Ben Amar

Keyword(s):

Neural Network ◽

Power Spectrum ◽

Dna Sequence ◽

Wavelet Neural Network ◽

Sequence Classification

Download Full-text

Enhanced Self-Organizing Map Neural Network for DNA Sequence Classification

Intelligent Information Management ◽

10.4236/iim.2013.51004 ◽

2013 ◽

Vol 05 (01) ◽

pp. 25-33 ◽

Cited By ~ 1

Author(s):

Marghny Mohamed ◽

Abeer A. Al-Mehdhar ◽

Mohamed Bamatraf ◽

Moheb R. Girgis

Keyword(s):

Neural Network ◽

Dna Sequence ◽

Self Organizing Map ◽

Sequence Classification ◽

Self Organizing

Download Full-text

Analysis of DNA Sequence Classification Using CNN and Hybrid Models

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/1835056 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Hemalatha Gunasekaran ◽

K. Ramalakshmi ◽

A. Rex Macedo Arokiaraj ◽

S. Deepa Kanmani ◽

Chandran Venkatesan ◽

...

Keyword(s):

Dna Sequence ◽

Selection Process ◽

High Accuracy ◽

Machine Learning Techniques ◽

Biomedical Data ◽

Sequence Classification ◽

Learning Techniques ◽

Testing Data ◽

Bidirectional Lstm

In a general computational context for biomedical data analysis, DNA sequence classification is a crucial challenge. Several machine learning techniques have used to complete this task in recent years successfully. Identification and classification of viruses are essential to avoid an outbreak like COVID-19. Regardless, the feature selection process remains the most challenging aspect of the issue. The most commonly used representations worsen the case of high dimensionality, and sequences lack explicit features. It also helps in detecting the effect of viruses and drug design. In recent days, deep learning (DL) models can automatically extract the features from the input. In this work, we employed CNN, CNN-LSTM, and CNN-Bidirectional LSTM architectures using Label and K -mer encoding for DNA sequence classification. The models are evaluated on different classification metrics. From the experimental results, the CNN and CNN-Bidirectional LSTM with K -mer encoding offers high accuracy with 93.16% and 93.13%, respectively, on testing data.

Download Full-text

The Detection of Early Epigenetic Inheritance of Mitochondrial Stress in C. Elegans with a Microfluidic Phenotyping Platform

Scientific Reports ◽

10.1038/s41598-019-55979-x ◽

2019 ◽

Vol 9 (1) ◽

Author(s):

H. B. Atakan ◽

K. S. Hof ◽

M. Cornaglia ◽

J. Auwerx ◽

M. A. M. Gijs

Keyword(s):

Dna Sequence ◽

Drug Exposure ◽

Model Organism ◽

Epigenetic Inheritance ◽

Short Term ◽

Mitochondrial Stress ◽

New Device ◽

C Elegans ◽

Short Lifespan ◽

Depth Analysis

AbstractFluctuations and deterioration in environmental conditions potentially have a phenotypic impact that extends over generations. Transgenerational epigenetics is the defined term for such intergenerational transient inheritance without an alteration in the DNA sequence. The model organism Caenorhabditis elegans is exceptionally valuable to address transgenerational epigenetics due to its short lifespan, well-mapped genome and hermaphrodite behavior. While the majority of the transgenerational epigenetics on the nematodes focuses on generations-wide heritage, short-term and in-depth analysis of this phenomenon in a well-controlled manner has been lacking. Here, we present a novel microfluidic platform to observe mother-to-progeny heritable transmission in C. elegans at high imaging resolution, under significant automation, and enabling parallelized studies. After approximately 24 hours of culture of L4 larvae under various concentrations and application periods of doxycycline, we investigated if mitochondrial stress was transferred from the mother nematodes to the early progenies. Automated and custom phenotyping algorithms revealed that a minimum doxycycline concentration of 30 µg/mL and a drug exposure time of 15 hours applied to the mothers could induce mitochondrial stress in first embryo progenies indeed, while this inheritance was not clearly observed later in L1 progenies. We believe that our new device could find further usage in transgenerational epigenetic studies modeled on C. elegans.

Download Full-text