@article{pathogens11060662,

title = {SARS-CoV-2 Mutant Spectra at Different Depth Levels Reveal an Overwhelming Abundance of Low Frequency Mutations},

author = {Brenda Martínez-González and María Eugenia Soria and Lucía Vázquez-Sirvent and Cristina Ferrer-Orta and Rebeca Lobo-Vega and Pablo Mínguez and Lorena Fuente and Carlos Llorens and Beatriz Soriano and Ricardo Ramos-Ruíz and Marta Cortón and Rosario López-Rodríguez and Carlos García-Crespo and Pilar Somovilla and Antoni Durán-Pastor and Isabel Gallego and Ana Isabel Ávila and Maria Soledad Delgado and Federico Morán and Cecilio López-Galíndez and Jordi Gómez and Luis Enjuanes and Llanos Salar-Vidal and Mario Esteban-Muñoz and Jaime Esteban and Ricardo Fernández-Roblas and Ignacio Gadea and Carmen Ayuso and Javier Ruíz-Hornillos and Nuria Verdaguer and Esteban Domingo and Celia Perales},

url = {https://www.mdpi.com/2076-0817/11/6/662},

doi = {10.3390/pathogens11060662},

issn = {2076-0817},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

journal = {Pathogens},

volume = {11},

number = {6},

abstract = {Populations of RNA viruses are composed of complex and dynamic mixtures of variant genomes that are termed mutant spectra or mutant clouds. This applies also to SARS-CoV-2, and mutations that are detected at low frequency in an infected individual can be dominant (represented in the consensus sequence) in subsequent variants of interest or variants of concern. Here we briefly review the main conclusions of our work on mutant spectrum characterization of hepatitis C virus (HCV) and SARS-CoV-2 at the nucleotide and amino acid levels and address the following two new questions derived from previous results: (i) how is the SARS-CoV-2 mutant and deletion spectrum composition in diagnostic samples, when examined at progressively lower cut-off mutant frequency values in ultra-deep sequencing; (ii) how the frequency distribution of minority amino acid substitutions in SARS-CoV-2 compares with that of HCV sampled also from infected patients. The main conclusions are the following: (i) the number of different mutations found at low frequency in SARS-CoV-2 mutant spectra increases dramatically (50- to 100-fold) as the cut-off frequency for mutation detection is lowered from 0.5% to 0.1%, and (ii) that, contrary to HCV, SARS-CoV-2 mutant spectra exhibit a deficit of intermediate frequency amino acid substitutions. The possible origin and implications of mutant spectrum differences among RNA viruses are discussed.},

keywords = {Health, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1128/Spectrum.01459-21,

title = {A Two-Level, Intramutant Spectrum Haplotype Profile of Hepatitis C Virus Revealed by Self-Organized Maps},

author = {Maria Soledad Delgado and Celia Perales and Carlos García-Crespo and María Eugenia Soria and Isabel Gallego and Ana Isabel Ávila and Brenda Martínez-González and Lucía Vázquez-Sirvent and Cecilio López-Galíndez and Federico Morán and Esteban Domingo and Benjamin W. Neuman},

doi = {10.1128/Spectrum.01459-21  URL = https://journals.asm.org/doi/abs/10.1128/Spectrum.01459-21},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Microbiology Spectrum},

volume = {9},

number = {3},

pages = {e01459-21},

abstract = {The study provides for the first time the haplotype profile and its variation in the course of its adaptation to a cell culture environment in the absence of external selective constraints. The deep sequencing-based self-organized maps document a two-layer haplotype distribution with an ample basal platform and a lower number of protruding peaks. RNA viruses replicate as complex mutant spectra termed viral quasispecies. The frequency of each individual genome in a mutant spectrum depends on its rate of generation and its relative fitness in the replicating population ensemble. The advent of deep sequencing methodologies allows for the first-time quantification of haplotype abundances within mutant spectra. There is no information on the haplotype profile of the resident genomes and how the landscape evolves when a virus replicates in a controlled cell culture environment. Here, we report the construction of intramutant spectrum haplotype landscapes of three amplicons of the NS5A-NS5B coding region of hepatitis C virus (HCV). Two-dimensional (2D) neural networks were constructed for 44 related HCV populations derived from a common clonal ancestor that was passaged up to 210 times in human hepatoma Huh-7.5 cells in the absence of external selective pressures. The haplotype profiles consisted of an extended dense basal platform, from which a lower number of protruding higher peaks emerged. As HCV increased its adaptation to the cells, the number of haplotype peaks within each mutant spectrum expanded, and their distribution shifted in the 2D network. The results show that extensive HCV replication in a monotonous cell culture environment does not limit HCV exploration of sequence space through haplotype peak movements. The landscapes reflect dynamic variation in the intramutant spectrum haplotype profile and may serve as a reference to interpret the modifications produced by external selective pressures or to compare with the landscapes of mutant spectra in complex in vivo environments. IMPORTANCE The study provides for the first time the haplotype profile and its variation in the course of virus adaptation to a cell culture environment in the absence of external selective constraints. The deep sequencing-based self-organized maps document a two-layer haplotype distribution with an ample basal platform and a lower number of protruding peaks. The results suggest an inferred intramutant spectrum fitness landscape structure that offers potential benefits for virus resilience to mutational inputs.},

keywords = {Data Projection, Health, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{9546766,

title = {Analysis of Students’ Behavior Through User Clustering in Online Learning Settings, Based on Self Organizing Maps Neural Networks},

author = {Maria Soledad Delgado and Federico Morán and José Carlos San José and Daniel Burgos},

doi = {10.1109/ACCESS.2021.3115024},

issn = {2169-3536 },

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {IEEE Access},

volume = {9},

pages = {132592-132608},

abstract = {An accurate analysis of user behaviour in online learning environments is a useful means of early follow up of students, so that they can be better supported to improve their performance and achieve the expected competences. However, that task becomes challenging due to the massive data that learning management systems store and categories. With the COVID-19 pandemic still on-going, face-to-face learning settings have migrate into online and blended ones, meaning an increase of online students and teachers in need for a tailored and effective support to their needs. A novel unsupervised clustering technique based on the Self-Organizing Map (SOM) artificial neural network model is used in this research to analyse 1,709,189 records of online students enrolled from 2015 to 2019 at Universidad Internacional de La Rioja (UNIR), a fully online Higher Education institution. SOM performs a precise and diverse user clustering based on those records. Results highlight that specific clusters are linked to the intake average profile at the university, with a clear relation between user interaction and a higher performance. Further, results show that, out of a targeted desk research compared to the analysis in this paper, face-to-face and online settings are connected through the methodological approach beyond the technology-based environment, which presents a similar behaviour in both contexts},

keywords = {Data Analysis, eLearning, Neural Networks, Self-organizing map, Unsupervised},

pubstate = {published},

tppubtype = {article}

}

@article{9380344,

title = {Classifying Model-View-Controller Software Applications Using Self-Organizing Maps},

author = {Daniel Guamán and Maria Soledad Delgado and Jennifer Pérez},

doi = {10.1109/ACCESS.2021.3066348},

isbn = {2169-3536},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {IEEE Access},

volume = {9},

pages = {45201-45229},

abstract = {The new era of information and the needs of our society require continuous change in software and technology. Changes are produced very quickly and software systems require evolving at the same velocity, which implies that the decision-making process of software architectures should be (semi-)automated to satisfy changing needs and to avoid wrong decisions. This issue is critical since suboptimal architecture design decisions may lead to high cost and poor software quality. Therefore, systematic and (semi-)automated mechanisms that help software architects during the decision-making process are required. Architectural patterns are one of the most important features of software applications, but the same pattern can be implemented in different ways, leaving to results of different quality. When an application requires to evolve, knowledge extracted from similar applications is useful for driving decisions, since quality pattern implementations can be reproduced in similar applications to improve specific quality attributes. Therefore, clustering methods are especially suitable for classifying similar pattern implementations. In this paper, we apply a novel unsupervised clustering technique, based on the well-known artificial neural network model Self-Organizing Maps, to classify Model-View-Controller (MVC) pattern from a quality point of view. Software quality is analyzed by 24 metrics organized into the categories of Count/Size, Maintainability, Duplications, Complexity, and Design Quality. The main goal of this work is twofold: to identify the quality features that establish the similarity of MVC applications without software architect bias, and to classify MVC applications by means of Self-Organizing Maps based on quality metrics. To that end, this work performs an exploratory study by conducting two analyses with a dataset of 87 Java MVC applications characterized by the 24 metrics and two attributes that describe the technology dimension of the application. The stated findings provide a knowledge base that can help in the decision-making process for the architecture of Java MVC applications.},

keywords = {Clustering, Neural Networks, Self-organizing map, Unsupervised},

pubstate = {published},

tppubtype = {article}

}

@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{DELGADO201714,

title = {A SOM prototype-based cluster analysis methodology},

author = {Maria Soledad Delgado and Clara Higuera and Jorge Calle-Espinosa and Federico Morán and Francisco Montero},

url = {https://www.sciencedirect.com/science/article/pii/S0957417417304396},

doi = {https://doi.org/10.1016/j.eswa.2017.06.022},

issn = {0957-4174},

year  = {2017},

date = {2017-01-01},

journal = {Expert Systems with Applications},

volume = {88},

pages = {14-28},

abstract = {Data clustering is aimed at finding groups of data that share common hidden properties. These kinds of techniques are especially critical at early stages of data analysis where no information about the dataset is available. One of the mayor shortcomings of the clustering algorithms is the difficulty for non-experts users to configure them and, in some cases, interpret the results. In this work a computational approach with a two-layer structure based on Self-Organizing Map (SOM) is presented for cluster analysis. In the first level, a quantization of the data samples using topology-preserving metrics to automatically determine the number of units in the SOM is proposed. In the second level the obtained SOM prototypes are clustered by means of a connectivity analysis to explore the quality of the partitioning with different number of clusters. The most important benefit of this two-layer procedure is that computational load decreases considerably in comparison with data based clustering methods, making it possible to cluster large data sets and to consider several different clustering alternatives in a limited time. This methodology produces a two-dimensional map representation of the, usually, high dimensional input space, along with quantitative information on viable clustering alternatives, which facilitates the exploration of the possible partitions in a dataset. The efficiency and interpretation of the methodology is illustrated by its application to artificial, benchmark and real complex biological datasets. The experimental results demonstrate the ability of the method to identify possible segmentations in a dataset, compared to algorithms that only yield a single clustering solution. The proposed algorithm tackles the intrinsic limitations of SOM and the parameter settings associated with the clustering methodology, without requiring the number of clusters or the SOM architecture as a prerequisite, among others. This way, it makes possible its application even by researchers with a limited expertise in machine learning.},

keywords = {Clustering, Metabolic network, Self-organizing map, Topology preserving, Unsupervised},

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{Lorenzo-Redondo2014,

title = {Realistic Three Dimensional Fitness Landscapes Generated by Self Organizing Maps for the Analysis of Experimental HIV-1 Evolution},

author = {Ramón Lorenzo-Redondo and Maria Soledad Delgado and Federico Morán and Cecilio Lopez-Galindez},

url = {https://plos.figshare.com/articles/dataset/_Realistic_Three_Dimensional_Fitness_Landscapes_Generated_by_Self_Organizing_Maps_for_the_Analysis_of_Experimental_HIV_1_Evolution_/948357},

doi = {10.1371/journal.pone.0088579},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

keywords = {Data Projection, Health, 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}

}