Clustering metagenome fragments using growing self organizing map

Overbeek, Marlinda Vasty; Kusuma, Wisnu Ananta; Buono, Agus

doi:10.1109/icacsis.2013.6761590

Cited by 5 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, using k = 12, chromosomes are formed consisting of 12 genes ( Figure 2). Using k = 12 this yields 4 12 features. Therefore, the concept of spaced seeds from PatternHunter [16] was adopted to modify the k-mer frequency feature, getting so-called spaced k-mer frequencies, which consist of match positions (1) and don't care positions (0).…”

Section: Data Collection and Pre-processingmentioning

confidence: 99%

“…BLAST (Basic Local Alignment Search Tool) [8] and MEGAN [9] are applications that use an homology-based approach for identifying species. Meanwhile, a composition-based approach was adopted by some applications for performing metagenome fragment binning, such as PhyloPythia, which uses SVM for performing metagenome fragment classification [10], classification based on the naïve Bayesian classifier [11], and metagenome fragment clustering based on a growing self organizing map (GSOM) [12].…”

Section: Introductionmentioning

confidence: 99%

“…The research concluded that the highest accuracy percentage was obtained with the use of 12 mers for 250 base pairs (bp) and 100 bp. Meanwhile, application of unsupervised learning using GSOM and k-mer frequency feature extraction [12] can be used to cluster short fragments of large communities.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of Spaced K-mer Frequency Feature Extraction using Genetic Algorithms for Metagenome Fragment Classification

Pekuwali¹,

Kusuma

Buono

2018

J. ICT Res. Appl.

Self Cite

View full text Add to dashboard Cite

K-mer frequencies are commonly used in extracting features from metagenome fragments. In spite of this, researchers have found that their use is still inefficient. In this research, a genetic algorithm was employed to find optimally spaced k-mers. These were obtained by generating the possible combinations of match positions and don't care positions (written as *). This approach was adopted from the concept of spaced seeds in PatternHunter. The use of spaced k-mers could reduce the size of the k-mer frequency feature's dimension. To measure the accuracy of the proposed method we used the naïve Bayesian classifier (NBC). The result showed that the chromosome 111111110001, representing spaced k-mer model [111 1111 10001], was the best chromosome, with a higher fitness (85.42) than that of the k-mer frequency feature. Moreover, the proposed approach also reduced the feature extraction time.

show abstract

Section: Data Collection and Pre-processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Spaced K-mer Frequency Feature Extraction using Genetic Algorithms for Metagenome Fragment Classification

Pekuwali¹,

Kusuma

Buono

2018

J. ICT Res. Appl.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The sample taken may contain fragments of genetic material (genome) from a variety of different species. When the sequencing and assembly procedures are carried out on this mixture of fragments simultaneously, the mismatch between the genomes of one species with another will result in chimeric contigs that lead to the phenomenon of interspecies chimerae, so that the species diversity of the sample cannot be known [1] [2]. The term "contig" itself is taken from the English word "contiguous", and is defined as a strand of genomic fragments (DNA) of a species that are close together, representing a subset of DNA [3].…”

Section: Introductionmentioning

confidence: 99%

Classification of Metagenome Fragments With Agglomerative Hierarchical Clustering

Kurniadi

Overbeek

2022

Ultimatics

Self Cite

View full text Add to dashboard Cite

Unlike genomics which study specifically culturable microorganisms, metagenomics is a field that studies microorganic samples retrieved directly from the environment. Such samples produce widely varying fragments when sequenced, many of which are still unidentified or unknown. Assembly of these fragments in the goals of identifying the species contained among them are thus prone to make said goals more difficult, so it becomes necessary for binning techniques to come in handy while trying to classify these mixed fragments onto certain levels in the phylogenetic tree. This research attempts to implement algorithms and methods such as k-mers to use for feature extraction, linear discriminant analysis (LDA) for dimensionality reduction, and agglomerative hierarchical clustering (AGNES) for taxonomic classification to the genus level. Experimentation is done across different objective measurements, including the length of the observed metagenome fragment that spans from 0,5 Kbp up to 10 Kbp for both the 3-mer and 4-mer contexts (k = 3 and k = 4). The averaged validity scores of the resulting data clusters generated from both the training and test sets, computed with the silhouette index metric, are 0.6945 and 0.0879 for the 3-mer context, along with 0.5219 and 0.1884 for the 4-mer context.

show abstract

“…Penelitian yang dilakukan pada [9] pun diklaim berhasil melakukan clustering pada data metagenome berskala besar dengan metode RAMMCAP. Growth Self Organizing Map (GSOM) telah berhasil dilakukan untuk melakukan clustering metagenome pada [10].…”

unclassified

Optimasi Parameter pada Fast Correlation Based Fiter Menggunakan Algoritme Genetika untuk Klasifikasi Metagenom

Haryanto¹,

Guritno²,

Kustiyo³

et al. 2018

JEPIN

View full text Add to dashboard Cite

Metagenome merupakan mikroorganisme yang diambil secara langsung dari alam. Proses sequencing genom dari metagenome mengakibatkan bercampurnya berbagai organisme. Hal ini menyebabkan kesulitan pada proses perakitan DNA. Oleh karena itu, dibutuhkan proses pemilahan yang disebut binning. Pada proses binning dengan pendekatan komposisi, teknik yang dilakukan adalah dengan supervised learning. Salah satu tahapan dalam supervised learning yaitu ekstraksi fitur, penelitian ini menggunakan metode ektraksi fitur n-mers. Besarnya parameter n pada metode ekstraksi fitur n-mers akan mengakibatkan dimensi fitur yang tinggi. Penelitian ini bertujuan untuk menerapkan algorime fast-correlation based filter (FCBF) untuk mereduksi dimensi fitur yang dihasilkan n-mers dan mengoptimasi parameter threshold pada fast-correlation based filter menggunakan algoritme genetika. Penelitian ini diuji menggunakan klasifikasi k-nearest neighbour. Performa terbaik diperoleh ketika n = 7 dan k = 3 dengan akurasi mencapai 99.41% dengan nilai threshold 0.67788. Dengan optimasi, waktu komputasi menjadi lebih efisien karena jumlah fitur sudah tereduksi.

show abstract

Clustering metagenome fragments using growing self organizing map

Cited by 5 publications

References 21 publications

Optimization of Spaced K-mer Frequency Feature Extraction using Genetic Algorithms for Metagenome Fragment Classification

Optimization of Spaced K-mer Frequency Feature Extraction using Genetic Algorithms for Metagenome Fragment Classification

Classification of Metagenome Fragments With Agglomerative Hierarchical Clustering

Optimasi Parameter pada Fast Correlation Based Fiter Menggunakan Algoritme Genetika untuk Klasifikasi Metagenom

Contact Info

Product

Resources

About