Denoising Autoencoder Self-Organizing Map (DASOM)

Ferles, Christos; Papanikolaou, Yannis; Naidoo, Kevin J.

doi:10.1016/j.neunet.2018.04.016

Cited by 46 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BLSOM A self-organizing map (SOM) is an unsupervised machine-learning algorithm that projects highdimensional data nonlinearly onto a two-dimensional plane (Kohonen et al, 1996); for recent SOM studies, see Rajashekar (https://pdfs.semanticscholar.org/eb2e/145085 ed3702b6768040230ab0a36d220087.pdf) and Ferles et al (2018). Kanaya et al (2001) modified Kohonen's SOM for genome informatics to make the learning process and resulting map independent of the order of data input on the basis of a batch-learning SOM.…”

Section: Methodsmentioning

confidence: 99%

Mb-level CpG and TFBS islands visualized by AI and their roles in the nuclear organization of the human genome

Wada

Ikemura

2020

Genes Genet. Syst.

View full text Add to dashboard Cite

Unsupervised machine learning that can discover novel knowledge from big sequence data without prior knowledge or particular models is highly desirable for current genome study. We previously established a batch-learning self-organizing map (BLSOM) for oligonucleotide compositions, which can reveal various novel genome characteristics from big sequence data, and found that transcription factor binding sequences (TFBSs) and CpG-containing oligonucleotides are enriched in human centromeric and pericentromeric regions, which support centromere clustering and form the condensed heterochromatin "chromocenter" in interphase nuclei. The number and size of chromocenters, as well as the type of centromeres gathered in individual chromocenters, vary depending on cell type. To study molecular mechanisms of cell type-dependent chromocenter formation, we analyzed distribution patterns of occurrence per Mb of hexa-and heptanucleotide TFBSs, which have been compiled by the SwissRegulon Portal, and of CpG-containing oligonucleotides. We found Mb-level islands enriched for TFBSs and CpG-containing oligonucleotides in centromeric and pericentromeric regions on all human chromosomes except chrY. Considering molecular mechanisms for cell type-dependent centromere clustering, the chromosome-dependent enrichment of a set of TFBSs and CpG-containing oligonucleotides is of particular interest, since the cellular content of TFs and methyl-CpG-binding proteins exhibits cell type-dependent regulation. A newly introduced BLSOM, which analyzed occurrences of a total of 3,946 octanucleotide TFBSs compiled by the SwissRegulon Portal, has self-organized (separated) the sequences that are characteristically enriched in TFBSs and shown that these sequences are derived primarily from centromeric and pericentromeric constitutive heterochromatin regions. Furthermore, the BLSOM identified and visualized characteristic TFBSs that are enriched in these regions. By analyzing Hi-C data for interchromosomal interactions, the present study showed that the chromatin segments supporting the interchromosomal interactions locate primarily in Mb-level TFBS and CpG islands and are thus enriched for a wide variety of TFBSs and CG-containing oligonucleotides.

show abstract

Section: Methodsmentioning

confidence: 99%

Mb-level CpG and TFBS islands visualized by AI and their roles in the nuclear organization of the human genome

Wada

Ikemura

2020

Genes Genet. Syst.

View full text Add to dashboard Cite

show abstract

“…The Denoising Autoencoder Self-Organization Map (DASOM) has been developed to handle unsupervised learning that requests unlabeled data or clustering problems [12]. It has been very promising in successfully solving "a comprehensive series of experiments comprising optical recognition of text and images" [12]. However, the proposed approach in this study aims at modeling systems with…”

Section: Remarkmentioning

confidence: 99%

Indirect disjunctive belief rule base modeling using limited conjunctive rules: Two possible means

Chang

Chen

Hao

et al. 2019

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

A traditional Belief Rule Base (BRB) is constructed under the conjunctive assumption (conjunctive BRB), which requires covering the traversal combinations of the referenced values for the attributes. Consequentially, a traditional conjunctive BRB may have to face the combinatorial explosion problem when there are too many attributes and/or referenced values for the attributes. It is difficult or at least expensive to construct a complete conjunctive BRB, while it is easy to derive one or several conjunctive rules. Comparatively, a BRB under the disjunctive assumption (disjunctive BRB) requires only covering the referenced values for the attributes instead of the traversal combination of them. Thus, the combinatorial explosion problem can be avoided. However, it is difficult to directly obtain a disjunctive BRB from either historical data or experts' knowledge. To combine the advantages of both conjunctive and disjunctive BRBs, a new approach is proposed to construct a disjunctive BRB using a limited number of conjunctive rules (insufficient to construct a complete conjunctive BRB). In the new disjunctive BRB modeling approach, each disjunctive rule is derived by quantifying its correlation with one or multiple conjunctive rules. To do so, two means for belief generation are proposed, namely, equal probability and self-organizing mapping (SOM). Two cases are studied for validating the efficiency of the proposed approach. The results by the disjunctive BRB show consistency with those derived by the conjunctive BRB as well as other approaches, which validates the efficiency of the proposed approach considering that the disjunctive BRB is constructed with only a limited number of conjunctive rules.

show abstract

“…The introduction of autoencoders was a significant innovation in unsupervised learning, in which the key features of the function in terms of backpropagation were discovered [19]. The learning structure is borrowed from the neurological process underlying global learning and the behaviour of intelligent beings [3].…”

Section: Autoencodersmentioning

confidence: 99%

“…Examples of technical objects from which the tomographic data show a high level of noise are: buildings, earthworks, flood embankments, dams, landfill protections, reservoirs, reactors, as well as many industrial infrastructure facilities [2]. The noise of electrical signals is one of the main barriers hindering the development of tomographic methods for such objects [3]. Thanks to the rapid technological development including data processing techniques, access to advanced computational methods is becoming easier each year.…”

Section: Introductionmentioning

confidence: 99%

Tomographic image correction with noise reduction algorithms

Kłosowski

Rymarczyk²,

Kozłowski

2019

MATEC Web Conf.

View full text Add to dashboard Cite

This article presents an original approach to improve the results of tomographic reconstructions by denoising the input data, which affects output images improving. The algorithms used in the research are based on autoencoders and Elastic Net - both related to artificial intelligence or machine-learning developed controllers. Due to the reduction of unnecessary features and removal of mutually correlated input variables generated by the tomography electrodes, good quality reconstructions of tomographic images were obtained. The simulation experiments proved that the presented methods could be effective in improving the quality of reconstructed tomographic images.

show abstract

Denoising Autoencoder Self-Organizing Map (DASOM)

Cited by 46 publications

References 23 publications

Mb-level CpG and TFBS islands visualized by AI and their roles in the nuclear organization of the human genome

Mb-level CpG and TFBS islands visualized by AI and their roles in the nuclear organization of the human genome

Indirect disjunctive belief rule base modeling using limited conjunctive rules: Two possible means

Tomographic image correction with noise reduction algorithms

Contact Info

Product

Resources

About