RESUMEN
Children infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) develop less severe coronavirus disease 2019 (COVID-19) than adults. The mechanisms for the age-specific differences and the implications for infection-induced immunity are beginning to be uncovered. We show by longitudinal multimodal analysis that SARS-CoV-2 leaves a small footprint in the circulating T cell compartment in children with mild/asymptomatic COVID-19 compared to adult household contacts with the same disease severity who had more evidence of systemic T cell interferon activation, cytotoxicity and exhaustion. Children harbored diverse polyclonal SARS-CoV-2-specific naïve T cells whereas adults harbored clonally expanded SARS-CoV-2-specific memory T cells. A novel population of naïve interferon-activated T cells is expanded in acute COVID-19 and is recruited into the memory compartment during convalescence in adults but not children. This was associated with the development of robust CD4+ memory T cell responses in adults but not children. These data suggest that rapid clearance of SARS-CoV-2 in children may compromise their cellular immunity and ability to resist reinfection.
Asunto(s)
COVID-19 , Humanos , Adulto , SARS-CoV-2 , Linfocitos T CD4-Positivos , Inmunidad Celular , Activación de Linfocitos , Anticuerpos AntiviralesRESUMEN
Wilms tumour is a childhood tumour that arises as a consequence of somatic and rare germline mutations, the characterisation of which has refined our understanding of nephrogenesis and carcinogenesis. Here we report that germline loss of function mutations in TRIM28 predispose children to Wilms tumour. Loss of function of this transcriptional co-repressor, which has a role in nephrogenesis, has not previously been associated with cancer. Inactivation of TRIM28, either germline or somatic, occurred through inactivating mutations, loss of heterozygosity or epigenetic silencing. TRIM28-mutated tumours had a monomorphic epithelial histology that is uncommon for Wilms tumour. Critically, these tumours were negative for TRIM28 immunohistochemical staining whereas the epithelial component in normal tissue and other Wilms tumours stained positively. These data, together with a characteristic gene expression profile, suggest that inactivation of TRIM28 provides the molecular basis for defining a previously described subtype of Wilms tumour, that has early age of onset and excellent prognosis.
Asunto(s)
Mutación de Línea Germinal , Neoplasias Renales/genética , Mutación con Pérdida de Función , Recurrencia Local de Neoplasia/genética , Proteína 28 que Contiene Motivos Tripartito/genética , Tumor de Wilms/genética , Adulto , Biomarcadores de Tumor/genética , Epigénesis Genética , Femenino , Perfilación de la Expresión Génica , Humanos , Riñón/patología , Neoplasias Renales/epidemiología , Neoplasias Renales/patología , Masculino , Recurrencia Local de Neoplasia/epidemiología , Recurrencia Local de Neoplasia/patología , Pronóstico , Urotelio/patología , Secuenciación del Exoma , Tumor de Wilms/epidemiología , Tumor de Wilms/patología , Adulto JovenRESUMEN
Although it is generally accepted that human tissue biobanks are important to facilitate progress in health and medical research, many academic biobanks face sustainability challenges. We propose that biobank sustainability is challenged by a lack of available data describing the outputs and benefits that are produced by biobanks, as reflected by a dearth of publications that enumerate biobank outputs. We further propose that boosting the available information on biobank outputs and using a broader range of output metrics will permit economic analyses such as cost-consequence analyses of biobank activity. Output metrics and cost-consequence analyses can allow biobanks to achieve efficiencies, and improve the quality and/or quantity of their outputs. In turn, biobank output measures provide all stakeholders with explicit and accountable data on biobank value, which could contribute to the evolution of biobank operations to best match research needs, and mitigate some threats to biobank sustainability.
Asunto(s)
Bancos de Muestras Biológicas/organización & administración , Investigación Biomédica/organización & administración , Modelos Econométricos , Bancos de Muestras Biológicas/economía , Investigación Biomédica/economía , Costos y Análisis de Costo , HumanosAsunto(s)
Investigación Biomédica , Nube Computacional , Bancos de Tejidos , Niño , Humanos , PediatríaRESUMEN
Co-regulations of miRNAs have been much less studied than the research on regulations between miRNAs and their target genes, although these two problems are equally important for understanding the entire mechanisms of complex post-transcriptional regulations. The difficulty to construct a miRNA-miRNA co-regulation network lies in how to determine reliable miRNA pairs from various resources of data related to the same disease such as expression levels, gene ontology (GO) databases, and protein-protein interactions. Here we take a novel integrative approach to the discovery of miRNA-miRNA co-regulation networks. This approach can progressively refine the various types of data and the computational analysis results. Applied to three lung cancer miRNA expression data sets of different subtypes, our method has identified a miRNA-miRNA co-regulation network and co-regulating functional modules common to lung cancer. An example of these functional modules consists of genes SMAD2, ACVR1B, ACVR2A and ACVR2B. This module is synergistically regulated by let-7a/b/c/f, is enriched in the same GO category, and has a close proximity in the protein interaction network. We also find that the co-regulation network is scale free and that lung cancer related miRNAs have more synergism in the network. According to our literature survey and database validation, many of these results are biologically meaningful for understanding the mechanism of the complex post-transcriptional regulations in lung cancer.
Asunto(s)
Redes Reguladoras de Genes , Neoplasias Pulmonares/genética , MicroARNs/genética , Biología Computacional , Conjuntos de Datos como Asunto , HumanosRESUMEN
BACKGROUND: Neuroblastoma Tumor (NT) is one of the most aggressive types of infant cancer. Essential to accurate diagnosis and prognosis is cellular quantitative analysis of the tumor. Counting enormous numbers of cells under an optical microscope is error-prone. There is therefore an urgent demand from pathologists for robust and automated cell counting systems. However, the main challenge in developing these systems is the inability of them to distinguish between overlapping cells and single cells, and to split the overlapping cells. We address this challenge in two stages by: 1) distinguishing overlapping cells from single cells using the morphological differences between them such as area, uniformity of diameters and cell concavity; and 2) splitting overlapping cells into single cells. We propose a novel approach by using the dominant concave regions of cells as markers to identify the overlap region. We then find the initial splitting points at the critical points of the concave regions by decomposing the concave regions into their components such as arcs, chords and edges, and the distance between the components is analyzed using the developed seed growing technique. Lastly, a shortest path determination approach is developed to determine the optimum splitting route between two candidate initial splitting points. RESULTS: We compare the cell counting results of our system with those of a pathologist as the ground-truth. We also compare the system with three state-of-the-art methods, and the results of statistical tests show a significant improvement in the performance of our system compared to state-of-the-art methods. The F-measure obtained by our system is 88.70%. To evaluate the generalizability of our algorithm, we apply it to images of follicular lymphoma, which has similar histological regions to NT. Of the algorithms tested, our algorithm obtains the highest F-measure of 92.79%. CONCLUSION: We develop a novel overlapping cell splitting algorithm to enhance the cellular quantitative analysis of infant neuroblastoma. The performance of the proposed algorithm promises a reliable automated cell counting system for pathology laboratories. Moreover, the high performance obtained by our algorithm for images of follicular lymphoma demonstrates the generalization of the proposed algorithm for cancers with similar histological regions and histological structures.
Asunto(s)
Recuento de Células/métodos , Neuroblastoma/patología , Algoritmos , Humanos , Linfoma Folicular/patología , Análisis de la Célula IndividualRESUMEN
Academic biobanks commonly report sustainability challenges, which may be exacerbated by a lack of information on biobank value. To better understand the costs and supported outputs that contribute to biobank value, we developed a systematic, generalizable methodology to determine biobank inputs and publications arising from biobank-supported research. We then tested this in a small cohort (n = 12) of academic cancer biobanks in New South Wales, Australia. A proforma was developed to capture monetary and in-kind biobank costing data from biobank managers and publicly available sources. Participating biobanks were grouped and compared according to the following two classifications: open- versus restricted-access and high versus low total annual costs. Our methodology provides a feasible approach for capturing comprehensive costing data for a defined period. Characterization of biobanks using this approach showed that median total costs, as well as median staffing and in-kind costs, were comparable for open- and restricted-access biobanks, as were the quantity and journal impact metrics of supported publications. High- and low-cost biobanks supported similar median numbers of publications; however, high-cost biobanks supported publications with higher median journal impact factor and Altmetric scores. Overall, 9 of 10 biobanks had higher Field-Weighted Citation Impact scores than the global average for similar publications. This is the first tested, generalizable approach to analyze the costs and publications arising from biobank-supported research. By determining explicit cost and output data, academic biobanks, funders, and policymakers can engage in or support informed redirection of resourcing and/or benchmark setting with the aim of improving biobank support of research.
RESUMEN
Wilms tumor, the most common pediatric kidney cancer, resembles embryonic renal progenitors. Currently, there are no ways to therapeutically target Wilms tumor driver mutations, such as in the microRNA processing gene DROSHA. In this study, we used a "multiomics" approach to define the effects of DROSHA mutation in Wilms tumor. We categorized Wilms tumor mutations into four mutational subclasses with unique transcriptional effects: microRNA processing, MYCN activation, chromatin remodeling, and kidney developmental factors. In particular, we find that DROSHA mutations are correlated with de-repressing microRNA target genes that regulate differentiation and proliferation and a self-renewing, mesenchymal state. We model these findings by inhibiting DROSHA expression in a Wilms tumor cell line, which led to upregulation of the cell cycle regulator cyclin D2 (CCND2). Furthermore, we observed that DROSHA mutations in Wilms tumor and DROSHA silencing in vitro were associated with a mesenchymal state with aberrations in redox metabolism. Accordingly, we demonstrate that Wilms tumor cells lacking microRNAs are sensitized to ferroptotic cell death through inhibition of glutathione peroxidase 4, the enzyme that detoxifies lipid peroxides. Implications: This study reveals genotype-transcriptome relationships in Wilms tumor and points to ferroptosis as a potentially therapeutic vulnerability in one subset of Wilms tumor.
Asunto(s)
Neoplasias Renales , Ribonucleasa III , Tumor de Wilms , Humanos , Tumor de Wilms/genética , Tumor de Wilms/patología , Tumor de Wilms/metabolismo , Ribonucleasa III/genética , Ribonucleasa III/metabolismo , Neoplasias Renales/genética , Neoplasias Renales/patología , Neoplasias Renales/metabolismo , Regulación Neoplásica de la Expresión Génica , Mutación , MicroARNs/genética , Línea Celular TumoralRESUMEN
BACKGROUND: The wealth of gene expression values being generated by high throughput microarray technologies leads to complex high dimensional datasets. Moreover, many cohorts have the problem of imbalanced classes where the number of patients belonging to each class is not the same. With this kind of dataset, biologists need to identify a small number of informative genes that can be used as biomarkers for a disease. RESULTS: This paper introduces a Balanced Iterative Random Forest (BIRF) algorithm to select the most relevant genes for a disease from imbalanced high-throughput gene expression microarray data. Balanced iterative random forest is applied on four cancer microarray datasets: a childhood leukaemia dataset, which represents the main target of this paper, collected from The Children's Hospital at Westmead, NCI 60, a Colon dataset and a Lung cancer dataset. The results obtained by BIRF are compared to those of Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Multi-class SVM-RFE (MSVM-RFE), Random Forest (RF) and Naive Bayes (NB) classifiers. The results of the BIRF approach outperform these state-of-the-art methods, especially in the case of imbalanced datasets. Experiments on the childhood leukaemia dataset show that a 7% â¼ 12% better accuracy is achieved by BIRF over MSVM-RFE with the ability to predict patients in the minor class. The informative biomarkers selected by the BIRF algorithm were validated by repeating training experiments three times to see whether they are globally informative, or just selected by chance. The results show that 64% of the top genes consistently appear in the three lists, and the top 20 genes remain near the top in the other three lists. CONCLUSION: The designed BIRF algorithm is an appropriate choice to select genes from imbalanced high-throughput gene expression microarray data. BIRF outperforms the state-of-the-art methods, especially the ability to handle the class-imbalanced data. Moreover, the analysis of the selected genes also provides a way to distinguish between the predictive genes and those that only appear to be predictive.
Asunto(s)
Biología Computacional/métodos , Perfilación de la Expresión Génica/métodos , Marcadores Genéticos/genética , Análisis de Secuencia por Matrices de Oligonucleótidos/métodos , Teorema de Bayes , Niño , Femenino , Humanos , Modelos Genéticos , Neoplasias/genética , Neoplasias/metabolismo , Reproducibilidad de los Resultados , Máquina de Vectores de SoporteRESUMEN
Wilms tumor, the most common kidney cancer in pediatrics, arises from embryonic renal progenitors. Although many patients are cured with multimodal therapy, outcomes remain poor for those with high-risk features. Recent sequencing efforts have provided few biological or clinically actionable insights. Here, we performed DNA and RNA sequencing on 94 Wilms tumors to understand how Wilms tumor mutations transform the transcriptome to arrest differentiation and drive proliferation. We show that most Wilms tumor mutations fall into four classes, each with unique transcriptional signatures: microRNA processing, MYCN activation, chromatin remodeling, and kidney development. In particular, the microRNA processing enzyme DROSHA is one of the most commonly mutated genes in Wilms tumor. We show that DROSHA mutations impair pri-microRNA cleavage, de-repress microRNA target genes, halt differentiation, and overexpress cyclin D2 (CCND2). Several mutational classes converge to drive CCND2 overexpression, which could render them susceptible to cell-cycle inhibitors.
RESUMEN
There is increasing evidence that changes in the variability or overall distribution of gene expression are important both in normal biology and in diseases, particularly cancer. Genes whose expression differs in variability or distribution without a difference in mean are ignored by traditional differential expression-based analyses. Using a Bayesian hierarchical model that provides tests for both differential variability and differential distribution for bulk RNA-seq data, we report here an investigation into differential variability and distribution in cancer. Analysis of eight paired tumour-normal datasets from The Cancer Genome Atlas confirms that differential variability and distribution analyses are able to identify cancer-related genes. We further demonstrate that differential variability identifies cancer-related genes that are missed by differential expression analysis, and that differential expression and differential variability identify functionally distinct sets of potentially cancer-related genes. These results suggest that differential variability analysis may provide insights into genetic aspects of cancer that would not be revealed by differential expression, and that differential distribution analysis may allow for more comprehensive identification of cancer-related genes than analyses based on changes in mean or variability alone.
RESUMEN
The article has been withdrawn at the request of the authors of the journal Current Molecular Pharmacology.Bentham Science apologizes to the readers of the journal for any inconvenience this may have caused.The Bentham Editorial Policy on Article Withdrawal can be found at https://benthamscience.com/editorial-policies-main.php. BENTHAM SCIENCE DISCLAIMER: It is a condition of publication that manuscripts submitted to this journal have not been published and will not be simultaneously submitted or published elsewhere. Furthermore, any data, illustration, structure or table that has been published elsewhere must be reported, and copyright permission for reproduction must be obtained. Plagiarism is strictly forbidden, and by submitting the article for publication the authors agree that the publishers have the legal right to take appropriate action against the authors, if plagiarism or fabricated information is discovered. By submitting a manuscript the authors agree that the copyright of their article is transferred to the publishers if and when the article is accepted for publication.
RESUMEN
Aims: The purpose of biobanking is to provide biospecimens and associated data to researchers, yet the perspectives of biobank research users have been under-investigated. This study aimed to ascertain biobank research users' needs and opinions about biobanking services. Methods: An online survey was developed, which requested information about researcher demographics, localities of biobanks accessed, methods of sourcing biospecimens, and opinions on topics including but not limited to, application processes, data availability, access fees, and return of research results. There were 27 multiple choice/check box questions, 4 questions with a 10-point Likert scale, and 8 questions with provision for further comment. A web link for the survey was distributed to researchers in late 2019/early 2020 in four Australian states: New South Wales, Victoria, Western Australia, and South Australia. Results: Respondents were generally satisfied with biobank application processes and the fit for purpose of received biospecimens/data. Nonetheless, most researchers (n = 61/99, 62%) reported creating their own collections owing to gaps in sample availability and a perceived increase in efficiency. Most accessed biobanks (n = 58/74, 78%) were in close proximity (local or intrastate) to the researcher. Most researchers had limited the scope of their research owing to difficulty of obtaining biospecimens (n = 55/86, 64%) and/or data (n = 52/85, 60%), with the top three responses for additional types of data required being "more long term follow up data," "more clinical data," and "more linked government data." The top influence to use a particular biobank was cost, and the most frequently suggested improvement was reduced direct "cost of obtaining biospecimens." Conclusion: Biobanks that do not meet the needs of their end-users are unlikely to be optimally utilized or sustainable. This survey provides valuable insights to guide biobanks and other stakeholders, such as developing marketing and client engagement plans to encourage local research users and discouraging the creation of unnecessary new collections.
Asunto(s)
Bancos de Muestras Biológicas , Investigación Biomédica , Australia , Humanos , Investigadores , Encuestas y CuestionariosRESUMEN
BACKGROUND: Rhabdomyosarcoma (RMS) is a malignant soft tissue sarcoma derived from skeletal muscle precursor cells, which accounts for 5-8% of all childhood malignancies. Disseminated RMS represents a major clinical obstacle, and the need for better treatment strategies for the clinically aggressive alveolar RMS subtype is particularly apparent. Previously, we have shown that the acridine-4-carboxamide derivative AS-DACA, a known topoisomerase II poison, is potently cytotoxic in the alveolar RMS cell line RH30, but is 190-fold less active in the embryonal RMS cell line RD. Here, we investigate the basis for this selectivity, and demonstrate in these RMS lines, and in an AS-DACA- resistant subclone of RH30, that AS-DACA-induced cytotoxicity correlates with the induction of DNA double strand breaks. RESULTS: We show that inhibition of the multidrug-resistance associated protein (MRP1) has no effect on AS-DACA sensitivity. By exploiting the pH-dependent fluorescence properties of AS-DACA, we have characterized its intracellular distribution, and show that it concentrates in the cell nucleus, as well as in acidic vesicles of the membrane trafficking system. We show that fluorescence microscopy can be used to determine the localization of AS-DACA to the nuclear and cytoplasmic compartments of RMS cells grown as spheroids, penetrance being much greater in RH30 than RD spheroids, and that the vesicular signal leads the way into the spheroid mass. EEA1 and Rab5 proteins, molecular markers expressed on early-endosomal vesicles, are reduced by >50% in the sensitive cell lines. CONCLUSION: Taking the evidence as a whole, suggests that endosomal vesicle trafficking influences the toxicity of AS-DACA in RMS cells.
Asunto(s)
Neoplasias Pulmonares/tratamiento farmacológico , Proteínas Asociadas a Resistencia a Múltiples Medicamentos/metabolismo , Células Madre Neoplásicas/efectos de los fármacos , Rabdomiosarcoma/tratamiento farmacológico , Proteínas de Transporte Vesicular/metabolismo , Aminoimidazol Carboxamida/farmacología , Antineoplásicos/farmacología , Biomarcadores/metabolismo , Línea Celular Tumoral , Roturas del ADN de Doble Cadena , Resistencia a Antineoplásicos/fisiología , Endosomas/metabolismo , Humanos , Neoplasias Pulmonares/patología , Células Madre Neoplásicas/patología , Rabdomiosarcoma/patología , Proteínas de Unión al GTP rab5/metabolismoRESUMEN
BACKGROUND: The reconstruction of gene regulatory networks from high-throughput "omics" data has become a major goal in the modelling of living systems. Numerous approaches have been proposed, most of which attempt only "one-shot" reconstruction of the whole network with no intervention from the user, or offer only simple correlation analysis to infer gene dependencies. RESULTS: We have developed MINER (Microarray Interactive Network Exploration and Representation), an application that combines multivariate non-linear tree learning of individual gene regulatory dependencies, visualisation of these dependencies as both trees and networks, and representation of known biological relationships based on common Gene Ontology annotations. MINER allows biologists to explore the dependencies influencing the expression of individual genes in a gene expression data set in the form of decision, model or regression trees, using their domain knowledge to guide the exploration and formulate hypotheses. Multiple trees can then be summarised in the form of a gene network diagram. MINER is being adopted by several of our collaborators and has already led to the discovery of a new significant regulatory relationship with subsequent experimental validation. CONCLUSION: Unlike most gene regulatory network inference methods, MINER allows the user to start from genes of interest and build the network gene-by-gene, incorporating domain expertise in the process. This approach has been used successfully with RNA microarray data but is applicable to other quantitative data produced by high-throughput technologies such as proteomics and "next generation" DNA sequencing.
Asunto(s)
Redes Reguladoras de Genes , Análisis de Secuencia por Matrices de Oligonucleótidos/métodos , Diseño de Software , Perfilación de la Expresión Génica , Internet , Dinámicas no LinealesRESUMEN
Visual analytics and visualisation can leverage the human perceptual system to interpret and uncover hidden patterns in big data. The advent of next-generation sequencing technologies has allowed the rapid production of massive amounts of genomic data and created a corresponding need for new tools and methods for visualising and interpreting these data. Visualising genomic data requires not only simply plotting of data but should also offer a decision or a choice about what the message should be conveyed in the particular plot; which methodologies should be used to represent the results must provide an easy, clear, and accurate way to the clinicians, experts, or researchers to interact with the data. Genomic data visual analytics is rapidly evolving in parallel with advances in high-throughput technologies such as artificial intelligence (AI) and virtual reality (VR). Personalised medicine requires new genomic visualisation tools, which can efficiently extract knowledge from the genomic data and speed up expert decisions about the best treatment of individual patient's needs. However, meaningful visual analytics of such large genomic data remains a serious challenge. This article provides a comprehensive systematic review and discussion on the tools, methods, and trends for visual analytics of cancer-related genomic data. We reviewed methods for genomic data visualisation including traditional approaches such as scatter plots, heatmaps, coordinates, and networks, as well as emerging technologies using AI and VR. We also demonstrate the development of genomic data visualisation tools over time and analyse the evolution of visualising genomic data.
RESUMEN
BACKGROUND: Neuroblastoma is the most common extracranial solid tumor in children younger than 5 years old. Optimal management of neuroblastic tumors depends on many factors including histopathological classification. The gold standard for classification of neuroblastoma histological images is visual microscopic assessment. In this study, we propose and evaluate a deep learning approach to classify high-resolution digital images of neuroblastoma histology into five different classes determined by the Shimada classification. SUBJECTS AND METHODS: We apply a combination of convolutional deep belief network (CDBN) with feature encoding algorithm that automatically classifies digital images of neuroblastoma histology into five different classes. We design a three-layer CDBN to extract high-level features from neuroblastoma histological images and combine with a feature encoding model to extract features that are highly discriminative in the classification task. The extracted features are classified into five different classes using a support vector machine classifier. DATA: We constructed a dataset of 1043 neuroblastoma histological images derived from Aperio scanner from 125 patients representing different classes of neuroblastoma tumors. RESULTS: The weighted average F-measure of 86.01% was obtained from the selected high-level features, outperforming state-of-the-art methods. CONCLUSION: The proposed computer-aided classification system, which uses the combination of deep architecture and feature encoding to learn high-level features, is highly effective in the classification of neuroblastoma histological images.
RESUMEN
Neuroblastoma is the most common extracranial solid malignancy in early childhood. Optimal management of neuroblastoma depends on many factors, including histopathological classification. Although histopathology study is considered the gold standard for classification of neuroblastoma histological images, computers can help to extract many more features some of which may not be recognizable by human eyes. This paper, proposes a combination of Scale Invariant Feature Transform with feature encoding algorithm to extract highly discriminative features. Then, distinctive image features are classified by Support Vector Machine classifier into five clinically relevant classes. The advantage of our model is extracting features which are more robust to scale variation compared to the Patched Completed Local Binary Pattern and Completed Local Binary Pattern methods. We gathered a database of 1043 histologic images of neuroblastic tumours classified into five subtypes. Our approach identified features that outperformed the state-of-the-art on both our neuroblastoma dataset and a benchmark breast cancer dataset. Our method shows promise for classification of neuroblastoma histological images.
RESUMEN
The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data.
Asunto(s)
Algoritmos , Perfilación de la Expresión Génica/estadística & datos numéricos , Genómica/estadística & datos numéricos , Máquina de Vectores de Soporte , Neoplasias de la Mama/genética , Neoplasias de la Mama/patología , Niño , Neoplasias del Colon/genética , Neoplasias del Colon/patología , Biología Computacional/métodos , Minería de Datos/métodos , Femenino , Perfilación de la Expresión Génica/métodos , Regulación Neoplásica de la Expresión Génica , Genómica/métodos , Humanos , Difusión de la Información/métodos , Leucemia/genética , Leucemia/patología , Reproducibilidad de los ResultadosRESUMEN
BACKGROUND: The process of retrieving similar cases in a case-based reasoning system is considered a big challenge for gene expression data sets. The huge number of gene expression values generated by microarray technology leads to complex data sets and similarity measures for high-dimensional data are problematic. Hence, gene expression similarity measurements require numerous machine-learning and data-mining techniques, such as feature selection and dimensionality reduction, to be incorporated into the retrieval process. METHODS: This article proposes a case-based retrieval framework that uses a k-nearest-neighbor classifier with a weighted-feature-based similarity to retrieve previously treated patients based on their gene expression profiles. RESULTS: The herein-proposed methodology is validated on several data sets: a childhood leukemia data set collected from The Children's Hospital at Westmead, as well as the Colon cancer, the National Cancer Institute (NCI), and the Prostate cancer data sets. Results obtained by the proposed framework in retrieving patients of the data sets who are similar to new patients are as follows: 96% accuracy on the childhood leukemia data set, 95% on the NCI data set, 93% on the Colon cancer data set, and 98% on the Prostate cancer data set. CONCLUSION: The designed case-based retrieval framework is an appropriate choice for retrieving previous patients who are similar to a new patient, on the basis of their gene expression data, for better diagnosis and treatment of childhood leukemia. Moreover, this framework can be applied to other gene expression data sets using some or all of its steps.