@article{<LineBreak>	10261_210788,

title = {Morphology Clustering Software for AFM Images, Based on Particle Isolation and Artificial Neural Networks},

author = {Maria Soledad Delgado and Miguel Moreno and Luis Vázquez and José A. Martín-Gago and Carlos Briones},

doi = {10.1109/ACCESS.2019.2950984},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

organization = {This work was supported in part by the Spanish Ministry of Economy and Competitiveness (MINECO) funded by the EU through the FEDER Programme under Grant BIO2016-79618-R and Grant MAT2017-85089-C2-1-R, in part by the Spanish State Research Agency (AEI) through the Unidad de Excelencia María de Maeztu-Centro de Astrobiología (CSIC-INTA) under Project MDM-2017-0737, and in part by the Comunidad de Madrid under Grant S2018/NMT-4349.},

abstract = {[EN] Advanced microscopy techniques currently allow scientists to visualize biomolecules at high resolution. Among them, atomic force microscopy (AFM) shows the advantage of imaging molecules in their native state, without requiring any staining or coating of the sample. Biopolymers, including proteins and structured nucleic acids, are flexible molecules that can fold into alternative conformations for any given monomer sequence, as exemplified by the different three-dimensional structures adopted by RNA in solution. Therefore, the manual analysis of images visualized by AFM and other microscopy techniques becomes very laborious and time-consuming (and may also be inadvertently biased) when large populations of biomolecules are studied. Here we present a novel morphology clustering software, based on particle isolation and artificial neural networks, which allows the automatic image analysis and classification of biomolecules that can show alternative conformations. It has been tested with a set of AFM images of RNA molecules (a 574 nucleotides-long functinal region of the hepatitis C virus genome that contains its internal ribosome entry site element) structured in folding buffers containing 0, 2, 4, 6 or 10 mM Mg. The developed software shows a broad applicability in the microscopy-based analysis of biopolymers and other complex biomolecules.},

keywords = {Clustering, Growing cell structures, Health, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/bioinformatics/btu708,

title = {A novel representation of genomic sequences for taxonomic clustering and visualization by means of self-organizing maps},

author = {Maria Soledad Delgado and Federico Morán and Antonio Mora and Juan Julián Merelo and Carlos Briones},

url = {https://doi.org/10.1093/bioinformatics/btu708},

doi = {10.1093/bioinformatics/btu708},

issn = {1367-4803},

year  = {2015},

date = {2015-03-01},

urldate = {2015-03-01},

journal = {Bioinformatics},

volume = {31},

number = {5},

pages = {736-744},

abstract = {Motivation: Self-organizing maps (SOMs) are readily available bioinformatics methods for clustering and visualizing high-dimensional data, provided that such biological information is previously transformed to fixed-size, metric-based vectors. To increase the usefulness of SOM-based approaches for the analysis of genomic sequence data, novel representation methods are required that automatically and bijectively transform aligned nucleotide sequences into numeric vectors, dealing with both nucleotide ambiguity and gaps derived from sequence alignment.Results: Six different codification variants based on Euclidean space, just like SOM processing, have been tested using two SOM models: the classical Kohonen’s SOM and growing cell structures. They have been applied to two different sets of sequences: 32 sequences of small sub-unit ribosomal RNA from organisms belonging to the three domains of life, and 44 sequences of the reverse transcriptase region of the pol gene of human immunodeficiency virus type 1 belonging to different groups and sub-types. Our results show that the most important factor affecting the accuracy of sequence clustering is the assignment of an extra weight to the presence of alignment-derived gaps. Although each of the codification variants shows a different level of taxonomic consistency, the results are in agreement with sequence-based phylogenetic reconstructions and anticipate a broad applicability of this codification method.Contact:sole@eui.upm.esSupplementary information:Supplementary Data are available at Bioinformatics online.},

keywords = {Clustering, Distance Measures, Growing cell structures, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{article,

title = {Gait patterns in a reference dataset of healthy children},

author = {Maria Soledad Delgado and David Gómez and Irene Pulido-Valdeolivas and Javier Lopez and J. A. Martín and F. Morán and Estrella Rausell},

doi = {10.1016/j.gaitpost.2011.10.345},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

journal = {Gait & Posture},

volume = {36},

pages = {S97},

keywords = {Data Analysis, Growing cell structures, Health, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{DELGADO20112624,

title = {A combined measure for quantifying and qualifying the topology preservation of growing self-organizing maps},

author = {Maria Soledad Delgado and Consuelo Gonzalo and Estibaliz Martinez and Agueda Arquero},

url = {https://www.sciencedirect.com/science/article/pii/S0925231211002396},

doi = {https://doi.org/10.1016/j.neucom.2011.03.021},

issn = {0925-2312},

year  = {2011},

date = {2011-01-01},

journal = {Neurocomputing},

volume = {74},

number = {16},

pages = {2624-2632},

abstract = {The Self-Organizing Map (SOM) is a neural network model that performs an ordered projection of a high dimensional input space in a low-dimensional topological structure. The process in which such mapping is formed is defined by the SOM algorithm, which is a competitive, unsupervised and nonparametric method, since it does not make any assumption about the input data distribution. The feature maps provided by this algorithm have been successfully applied for vector quantization, clustering and high dimensional data visualization processes. However, the initialization of the network topology and the selection of the SOM training parameters are two difficult tasks caused by the unknown distribution of the input signals. A misconfiguration of these parameters can generate a feature map of low-quality, so it is necessary to have some measure of the degree of adaptation of the SOM network to the input data model. The topology preservation is the most common concept used to implement this measure. Several qualitative and quantitative methods have been proposed for measuring the degree of SOM topology preservation, particularly using Kohonen's model. In this work, two methods for measuring the topology preservation of the Growing Cell Structures (GCSs) model are proposed: the topographic function and the topology preserving map.},

note = {Advances in Extreme Learning Machine: Theory and Applications Biological Inspired Systems. Computational and Ambient Intelligence},

keywords = {Delaunay triangulation, Growing cell structures, Self-organizing map, Topology preserving, Visualization methods},

pubstate = {published},

tppubtype = {article}

}