Filters








17,335 Hits in 9.5 sec

Classification based upon gene expression data: bias and precision of error rates

I. A. Wood, P. M. Visscher, K. L. Mengersen
2007 Bioinformatics  
Downward bias of 3-5% was found in an existing study of classification based on gene expression data and may be endemic in similar studies.  ...  Motivation: Gene expression data offer a large number of potentially useful predictors for the classification of tissue samples into classes, such as diseased and non-diseased.  ...  ACKNOWLEDGEMENTS The authors appreciate discussions with Geoff McLachlan, David Duffy, Ross McVinish, Clair Alston and Georgia Chenevix-Trench and the helpful comments of two anonymous reviewers.  ... 
doi:10.1093/bioinformatics/btm117 pmid:17392326 fatcat:surozg6qnbbqxjlb6wqclci3oi

BagBoosting for tumor classification with gene expression data

M. Dettling
2004 Bioinformatics  
gene expression data.  ...  Motivation: Microarray experiments are expected to contribute significantly to the progress in cancer treatment by enabling a precise and early diagnosis.  ...  METHODS Class prediction with gene expression data The main goal in class prediction with gene expression data is a precise and early diagnosis of cancerous malignancies that allows to tailor the patients  ... 
doi:10.1093/bioinformatics/bth447 pmid:15466910 fatcat:f5qjnqpfs5d6dgum4qdjkr2gsu

SUPERVISED MACHINE LEARNING MODEL FOR MICRORNA EXPRESSION DATA IN CANCER

Indra Waspada, Adi Wibowo, Noel Segura Meraz
2017 Jurnal Ilmu Komputer dan Informasi  
The cancer cell gene expression data in general has a very large feature and requires analysis to find out which genes are strongly influencing the specific disease for diagnosis and drug discovery.  ...  In this paper several methods of supervised learning (decisien tree, naïve bayes, neural network, and deep learning) are used to classify cancer cells based on the expression of the microRNA gene to obtain  ...  Classification techniques of cancer cells based on gene expression data using machine learning methods have been developed rapidly in the analysis and diagnosis of cancer [7] .  ... 
doi:10.21609/jiki.v10i2.481 fatcat:oj4rd3dawzgfneqtyzwlufbflm

An Empirical Study of Univariate and Genetic Algorithm-Based Feature Selection in Binary Classification with Microarray Data

Michael Lecocke, Kenneth Hess
2006 Cancer Informatics  
clinical applications of gene expression microarrays.  ...  An Empirical Study of Feature Selection in Binary Classification with DNA Microarray Data by Michael Louis Lecocke Motivation: Binary classification is a common problem in many types of research including  ...  for performing binary classification based on gene expression data from a given dataset.  ... 
doi:10.1177/117693510600200016 fatcat:fbivbpap7rhltkdc3eavqjnile

Evolutionary Computational Algorithm by Blending of PPCA and EP-Enhanced Supervised Classifier for Microarray Gene Expression Data

Manaswini Pradhan
2018 IAES International Journal of Artificial Intelligence (IJ-AI)  
The well-trained ANN has the capacity of classifying the gene expression data to the associated classes.  ...  In this paper, a classification technique is proposed that classifies the microarray gene expression data well.  ...  Classification of Microarray Gene Expression using the Enhanced Classifier In the classification of microarray gene expression data, two phases of operation are performed that include training phase and  ... 
doi:10.11591/ijai.v7.i2.pp95-104 fatcat:etcvgc4rybg3pnrkdbfvnndw7e

Cancer Subtype Discovery Using Prognosis-Enhanced Neural Network Classifier in Multigenomic Data

Prasanna Vasudevan, Thangamani Murugesan
2018 Technology in Cancer Research and Treatment  
We analyzed the heterogeneity and identified the subtypes of glioblastoma multiforme, an aggressive adult brain tumor, from 215 samples with microRNA expression (12 042 genes).  ...  The samples were classified into 4 different classes such as mesenchymal, classical, proneural, and neural subtypes owing to mutations and gene expression.  ...  weights and bias error in the modified error function.  ... 
doi:10.1177/1533033818790509 pmid:30092720 pmcid:PMC6088521 fatcat:cjptqm3gdrgjzc754v3idtpyba

The properties of high-dimensional data spaces: implications for exploring gene and protein expression data

Robert Clarke, Habtom W. Ressom, Antai Wang, Jianhua Xuan, Minetta C. Liu, Edmund A. Gehan, Yue Wang
2008 Nature Reviews. Cancer  
From the perspective of translational science, this Review discusses the properties of high-dimensional data spaces that arise in genomic and proteomic studies and the challenges they can pose for data  ...  The properties of high dimensionality are often poorly understood or overlooked in data modelling and analysis.  ...  Many of the engineering and computer science works published in 'proceedings' represent peer-reviewed publications.  ... 
doi:10.1038/nrc2294 pmid:18097463 pmcid:PMC2238676 fatcat:72e62lj4vjcwpfrewtrh7b2ptq

Cancer classification using gene expression data

Ying Lu, Jiawei Han
2003 Information Systems  
With this abundance of gene expression data, researchers have started to explore the possibilities of cancer classification using gene expression data.  ...  Cancer classification using gene expression data is known to contain the keys for addressing the fundamental problems relating to cancer diagnosis and drug discovery.  ...  This is not adequate in the case of cancer classification. In classifying normal vs. cancerous data, the errors can be grouped into misclassification rate and non-classification rate.  ... 
doi:10.1016/s0306-4379(02)00072-8 fatcat:telrkleownbq5epdcderjevhwy

A comprehensive survey on computational learning methods for analysis of gene expression data in genomics [article]

Nikita Bhandari, Rahee Walambe, Ketan Kotecha, Satyajeet Khare
2022 arXiv   pre-print
High-throughput gene expression analysis methods such as microarray technology and RNA sequencing produce enormous amounts of data.  ...  We have described the process of generation of a microarray gene expression data along with advantages and limitations of the above-mentioned techniques.  ...  It lowers the bias and increases the variance of all genes.  ... 
arXiv:2202.02958v4 fatcat:uipvs7ribzdondwraf64n5mzf4

A comprehensive evaluation of machine learning techniques for cancer class prediction based on microarray data

Khalid Raza, Atif N. Hasan
2015 International Journal of Bioinformatics Research and Applications  
Machine learning is effective when number of attributes (genes) are larger than the number of samples which is rarely possible with gene expression data.  ...  The genomic level changes can be detected in gene expression data and those changes may serve as standard model for any random cancer data for class prediction.  ...  Raza acknowledges the funding from University Grants Commission, Govt. of India through research grant 42-1019/2013(SR).  ... 
doi:10.1504/ijbra.2015.071940 pmid:26558300 fatcat:r5ps5bualngcxfof4lixn5kqh4

Probabilistic classifiers with high-dimensional data

Kyung In Kim, Richard Simon
2010 Biostatistics  
Based on simulation studies and analysis of gene expression microarray data, we found that proper probabilistic classification is more difficult than deterministic classification.  ...  We also present a cross-validation method for evaluating the calibration and refinement of any probabilistic classifier on any data set.  ...  ACKNOWLEDGMENT Conflict of Interest: None declared.  ... 
doi:10.1093/biostatistics/kxq069 pmid:21087946 pmcid:PMC3138069 fatcat:ukokk2ugu5affkfsynzmvuq7na

Enhanced Cancer Subtyping via Pan-Transcriptomics Data Fusion, Monte-Carlo Consensus Clustering, and Auto Classifier Creation [article]

Kristofer Linton-Reid, Joe Thompson, Harry Clifford
2019 bioRxiv   pre-print
However, the reproducibility of these subtyping based studies is poor. There are multiple reports which have conflicting subtype and gene-survival time relationship results.  ...  This problem arises from the routine analysis of small cohorts (< 100 individuals) and use of biased traditional consensus clustering techniques.  ...  ACKNOWLEDGMENTS The authors would like to thank everyone at and involved with Cambridge Cancer Genomics whom made this project possible and offered insightful constructive feedback throughout this study  ... 
doi:10.1101/2019.12.16.870188 fatcat:fnvd3almbzc6tp4fjljpne6tdm

Improved shrunken centroid classifiers for high-dimensional class-imbalanced data

Rok Blagus, Lara Lusa
2013 BMC Bioinformatics  
The NSC methods base their classification rules on shrunken centroids; in practice the amount of shrinkage is estimated minimizing the overall cross-validated (CV) error rate.  ...  PAM, a nearest shrunken centroid method (NSC), is a popular classification method for high-dimensional data. ALP and AHP are NSC algorithms that were proposed to improve upon PAM.  ...  Acknowledgements The high-performance computation facilities were kindly provided by Bioinformatics and Genomics unit at Department of Molecular Biotechnology and Heath Sciences, University of Torino,  ... 
doi:10.1186/1471-2105-14-64 pmid:23433084 pmcid:PMC3687811 fatcat:co5erqwmkvhufop5uuabt6dkhe

Entropy-based gene ranking without selection bias for the predictive classification of microarray data

Cesare Furlanello, Maria Serafini, Stefano Merler, Giuseppe Jurman
2003 BMC Bioinformatics  
Thus, a process for gene selection and error estimation is made practical, ensuring control of the selection bias, and providing additional diagnostic indicators of gene importance.  ...  The method supports a practical modeling scheme designed to avoid the construction of classification rules based on the selection of too small gene subsets (an effect known as the selection bias, in which  ...  BJ is supported by the FUPAT post-graduate project 'Algorithms and software environments for microarray gene expression experiments'. We thank T. Poggio, G. Anzellotti and B.  ... 
doi:10.1186/1471-2105-4-54 pmid:14604446 pmcid:PMC293475 fatcat:6cvsarfcfjhdri5o22xn3h5zs4

A fuzzy based feature selection from independent component subspace for machine learning classification of microarray data

Rabia Aziz, C.K. Verma, Namita Srivastava
2016 Genomics Data  
Feature (gene) selection and classification of microarray data are the two most interesting machine learning challenges.  ...  The curve between the average error rate and number of genes with each dataset represents the selection of required number of genes for the highest accuracy with our proposed method for both the classifiers  ...  Figs. 9 and 10 show the graph of the average error rate of SVM and NB classifiers respectively, for the five datasets with different gene selection methods.  ... 
doi:10.1016/j.gdata.2016.02.012 pmid:27081632 pmcid:PMC4818349 fatcat:wfvdu4zkwbddzltbmfsrskzfom
« Previous Showing results 1 — 15 out of 17,335 results