A k-mer-based barcode DNA classification methodology based on spectral representation and a neural gas network

Fiannaca, Antonino; Rosa, Massimo La; Rizzo, Riccardo; Urso, Alfonso

doi:10.1016/j.artmed.2015.06.002

Cited by 26 publications

(14 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The k-mer abundance analysis is widely used in genomics research [1][2][3][4][5][6][7][8][9][10]. The term k-mer refers to all possible substrings (in the 5′-3′ direction) of length k in a DNA sequence and, therefore, the k-mer frequency is a good variable for characterizing the composition of a genome's DNA sequence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Methylation-driven model for analysis of dinucleotide evolution in genomes

Sun

Liu

2020

Theor Biol Med Model

View full text Add to dashboard Cite

Background: CpGs, the major methylation sites in vertebrate genomes, exhibit a high mutation rate from the methylated form of CpG to TpG/CpA and, therefore, influence the evolution of genome composition. However, the quantitative effects of CpG to TpG/CpA mutations on the evolution of genome composition in terms of the dinucleotide frequencies/proportions remain poorly understood. Results: Based on the neutral theory of molecular evolution, we propose a methylation-driven model (MDM) that allows predicting the changes in frequencies/proportions of the 16 dinucleotides and in the GC content of a genome given the known number of CpG to TpG/CpA mutations. The application of MDM to the 10 published vertebrate genomes shows that, for most of the 16 dinucleotides and the GC content, a good consistency is achieved between the predicted and observed trends of changes in the frequencies and content relative to the assumed initial values, and that the model performs better on the mammalian genomes than it does on the lowervertebrate genomes. The model's performance depends on the genome composition characteristics, the assumed initial state of the genome, and the estimated parameters, one or more of which are responsible for the different application effects on the mammalian and lower-vertebrate genomes and for the large deviations of the predicted frequencies of a few dinucleotides from their observed frequencies. Conclusions: Despite certain limitations of the current model, the successful application to the higher-vertebrate (mammalian) genomes witnesses its potential for facilitating studies aimed at understanding the role of methylation in driving the evolution of genome dinucleotide composition.

show abstract

Section: Introductionmentioning

confidence: 99%

“…After removing CpG islands, NpCpG and CpGpM trinucleotides in each of the 10 vertebrate genomes were counted using an in-house Java program (for results, see Supplementary Table 7, Additional file 1), and the eight parameters were then obtained with eqs. (4) and (5). Table 4 lists the estimated parameters for all the 10 vertebrate genomes.…”

mentioning

confidence: 99%

Methylation-driven model for analysis of dinucleotide evolution in genomes

Sun

Liu

2020

Theor Biol Med Model

View full text Add to dashboard Cite

show abstract

“…For example, in the case of the machine learning methodology for nucleosome identification, an effective way of representing the sequences is by the so called k-mers representation as demonstrated by several methodologies [ 19 – 25 ]. This representation maps a DNA sequence into a numerical space by means of a fixed-length vectors whose components are the count of each of the substrings belonging to a finite set of words.…”

Section: Introductionmentioning

confidence: 99%

Deep learning architectures for prediction of nucleosome positioning from sequences data

2018

Self Cite

View full text Add to dashboard Cite

BackgroundNucleosomes are DNA-histone complex, each wrapping about 150 pairs of double-stranded DNA. Their function is fundamental for one of the primary functions of Chromatin i.e. packing the DNA into the nucleus of the Eukaryote cells. Several biological studies have shown that the nucleosome positioning influences the regulation of cell type-specific gene activities. Moreover, computational studies have shown evidence of sequence specificity concerning the DNA fragment wrapped into nucleosomes, clearly underlined by the organization of particular DNA substrings. As the main consequence, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using a sequence features representation.ResultsIn this work, we propose a deep learning model for nucleosome identification. Our model stacks convolutional layers and Long Short-term Memories to automatically extract features from short- and long-range dependencies in a sequence. Using this model we are able to avoid the feature extraction and selection steps while improving the classification performances.ConclusionsResults computed on eleven data sets of five different organisms, from Yeast to Human, show the superiority of the proposed method with respect to the state of the art recently presented in the literature.

show abstract

“…Machine learning (ML) methods have been applied in many research areas in healthcare sector and medical science including, predicting mortality (Cooper et al, 1997;Verplancke et al, 2008), medical diagnosis (Kononenko, 2001;Li et al, 2015), cancer prediction and prognosis (Jerez et al, 2010), applications in the intensive care units (Hanson III and Marshall, 2001), heart disease prediction (Parthiban and Subramanian, 2007;Anbarasi et al, 2010;Soni et al, 2011), drug design (Duch et al, 2007), diabetic nephropathy prediction (Cho et al, 2008), molecular classification of multiple tumor types (Yeang et al, 2001), liver disease diagnosis (Lin, 2009), disease risks prediction (Khalilia et al, 2011), DNA classification (Fiannaca et al, 2015), automatic evidence quality prediction (Sarker et al, 2015), detection of healthcare-associated infections (De Bruin et al,2016), medication adherence prediction (Kalantarian et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Comparing Various Machine Learning Methods for Prediction of Patient Revisit Intention: A Case Study

Demirdöğen

Erdal

Akbaba

2017

Scitech

View full text Add to dashboard Cite

Numerous methods have been suggested for analysis of costumer intention, from surveys to statistical models. The most recent couple of years, various machine learning methods have effectively been utilized to costumer-centric decision-making problems. The trend of patient revisit intention analysis has an improved reliance on computerized decision making models. Computerized decisionmaking may never take the place of the hospital managers, but it can provide decision support via a simple questionnaire. In this paper, it is carried on a comparative evaluation of the performance of ten widely used machine learning methods, (i.e., logistic regression, multilayer perceptron, support vector machines, IBk, KStar, locally weighted learning, decisionstump, C4.5., randomtree and reduced error pruning tree) for the aim of suggesting appropriate machine learning techniques in the context of patient revisit intention prediction problem. Experimental results reveal that the C4.5 tree demonstrates to be the most suitable predictive model since it has the highest overall average accuracy (95.24%) and a very low percentage error on both Type I (3.40%) and Type II (23.53%) errors, closely followed by the locally weighted learning (94.44%, 3.43%, 31.58%) and decisionstump (94.05%, 3,85%, 30.00%), whereas the logistic regression and the IBk algorithms appear to be the worst in terms of average accuracy (87.30% and 88.49%, respectively) and Type II error (70.37% and 68.18%, respectively). Besides the randomtree (6.36%) and the IBk (6.09%) algorithms appear to be the worst in terms of type I error. As a result, this study has demonstrated the promising attempt of incorporating sentiment classification into patient revisit intention.

show abstract

A k-mer-based barcode DNA classification methodology based on spectral representation and a neural gas network

Cited by 26 publications

References 45 publications

Methylation-driven model for analysis of dinucleotide evolution in genomes

Methylation-driven model for analysis of dinucleotide evolution in genomes

Deep learning architectures for prediction of nucleosome positioning from sequences data

Comparing Various Machine Learning Methods for Prediction of Patient Revisit Intention: A Case Study

Contact Info

Product

Resources

About