Wavelet Analysis of DNA Walks on the Human and Chimpanzee MAGE/CSAG-Palindromes

Qi, Yanjiao; Jin, Neng-Zhi; Ai, Duiyuan

doi:10.1016/j.gpb.2012.07.004

Cited by 3 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite this improvement, all variations of DNAwalk encoding methods lead to output images whose size depends on the length and distribution of the nucleotides. Nonetheless, almost all variations of DNA-walk encoding methods achieve good accuracy in comparing and classifying biological sequences [32,39].…”

Section: Plos Onementioning

confidence: 99%

“…To address these challenges, and many other ones, WalkIm encoding method is proposed to generate fixed-size output images, with fixed range of pixel values, which can be fed to any imagebased CNN classifier. Finally, although many studies target accuracy improvement of DNAwalk encoding, a few of them [32,39] discuss variety of its applications.…”

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

WalkIm: Compact image-based encoding for high-performance classification of biological sequences using simple tuning-free CNNs

2022

View full text Add to dashboard Cite

The classification of biological sequences is an open issue for a variety of data sets, such as viral and metagenomics sequences. Therefore, many studies utilize neural network tools, as the well-known methods in this field, and focus on designing customized network structures. However, a few works focus on more effective factors, such as input encoding method or implementation technology, to address accuracy and efficiency issues in this area. Therefore, in this work, we propose an image-based encoding method, called as WalkIm, whose adoption, even in a simple neural network, provides competitive accuracy and superior efficiency, compared to the existing classification methods (e.g. VGDC, CASTOR, and DLM-CNN) for a variety of biological sequences. Using WalkIm for classifying various data sets (i.e. viruses whole-genome data, metagenomics read data, and metabarcoding data), it achieves the same performance as the existing methods, with no enforcement of parameter initialization or network architecture adjustment for each data set. It is worth noting that even in the case of classifying high-mutant data sets, such as Coronaviruses, it achieves almost 100% accuracy for classifying its various types. In addition, WalkIm achieves high-speed convergence during network training, as well as reduction of network complexity. Therefore WalkIm method enables us to execute the classifying neural networks on a normal desktop system in a short time interval. Moreover, we addressed the compatibility of WalkIm encoding method with free-space optical processing technology. Taking advantages of optical implementation of convolutional layers, we illustrated that the training time can be reduced by up to 500 time. In addition to all aforementioned advantages, this encoding method preserves the structure of generated images in various modes of sequence transformation, such as reverse complement, complement, and reverse modes.

show abstract

Section: Plos Onementioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

WalkIm: Compact image-based encoding for high-performance classification of biological sequences using simple tuning-free CNNs

2022

View full text Add to dashboard Cite

show abstract

“…Starting from only a fasta file for a given chromosome, RepeatOBserver produces Fourier spectra showing locations of tandem repeats (including their length and how perfectly they repeat). Fourier transforms and wavelet analyses have previously been used to study DNA, including exploring DNA periodicity (Elloumi et al ., 2012; Nagai et al ., 2001, 2020), DNA palindromes (Qi et al ., 2012), sequence comparison (MAFFT) (Katoh et al ., 2002), sequence evolution (Machado, 2013), exon/intron identification (Haimovich et al ., 2006), visualization of regular features (Dodin et al ., 2000) and even tandem repeats (Sharma et al ., 2004; Brodzik, 2007; Buchner and Janjarasjitt, 2003; Yadav et al ., 2022). DNA sequence variations in Fourier transforms have previously been shown to have biological importance (Haimovich et al ., 2006) and are known to show periodicity and tandem repeats (Elloumi et al ., 2012; Sharma et al ., 2004; Brodzik, 2007; Buchner and Janjarasjitt, 2003; Yadav et al ., 2022).…”

Section: Introductionmentioning

confidence: 99%

RepeatOBserver: tandem repeat visualization and centromere detection

Elphinstone,

Todesco

et al. 2023

Preprint

View full text Add to dashboard Cite

Tandem repeats can play an important role in centromere structure, subtelomeric regions, DNA methylation, recombination, and the regulation of gene activity. There is a growing need for bioinformatics tools that can visualize and explore chromosome-scale repeats. Here we present RepeatOBserver, a new tool for visualizing tandem repeats and clustered transposable elements and for identifying potential natural centromere locations, using a Fourier transform of DNA walks: https://github.com/celphin/RepeatOBserverV1. RepeatOBserver can identify a broad range of repeats (3-20,000bp long) in genome assemblies without any a priori knowledge of repeat sequences or the need for optimizing parameters. RepeatOBserver allows for easy visualization of the positions of both perfect and imperfect repeating sequences across each chromosome. We use RepeatOBserver to compare DNA walks, repeat patterns and centromere positions across genome assemblies in a wide range of well-studied species (e.g., human, mouse-ear cress), crops, and non-model organisms (e.g., fern, yew). Analyzing 107 chromosomes with known centromere positions, we find that centromeres consistently occur in regions that have the least diversity in repeat types (i.e. one or a few repeated sequences are present in very high numbers). Taking advantage of this information, we use a genomic Shannon diversity index to predict centromere locations in several other chromosome-scale genome assemblies. The Fourier spectra produced by RepeatOBserver can help visualize historic centromere positions, potential neocentromeres, retrotransposon clusters and gene copy variation. Identification of patterns of split and inverted tandem repeats at inversion boundaries suggests that at least some chromosomal inversions can be predicted with RepeatOBserver. RepeatOBserver is therefore a flexible tool for comprehensive characterization of tandem repeat patterns that can be used to visualize and identify a variety of regions of interest in genome assemblies.

show abstract