I have a set of array data with some missing values, and I want to use the K-nearest neighbor method to estimate values for the missing expression data. Has anyone written a routine in R/Bioconductor to do this? John Cornell

John, There may be other sources as well, but there is a function in pamr (from bioconductor), pamr.knnimpute A function to impute missing expression data Sean -- Sean Davis, M.D., Ph.D. Clinical Fellow National Institutes of Health National Cancer Institute National Human Genome Research Institute Clinical Fellow, Johns Hopkins Department of Pediatric Oncology -- On 1/7/04 9:44 PM, "John E. Cornell, Ph.D." <cornell@uthscsa.edu> wrote: > I have a set of array data with some missing values, and I want to use the > K-nearest neighbor method to estimate values for the missing expression > data. Has anyone written a routine in R/Bioconductor to do this? > > John Cornell > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://www.stat.math.ethz.ch/mailman/listinfo/bioconductor >

>I have a set of array data with some missing values, and I want to use the >K-nearest neighbor method to estimate values for the missing expression >data. Has anyone written a routine in R/Bioconductor to do this? > >John Cornell > You can use PAM(Prediction Analysis for Microarrays) package in R at http://www-stat.stanford.edu/%7Etibs/PAM/ . You will find the details of method to estimate the missing values. Regards, Reiji Teramoto ------------------------------------------------------- Genome Information Engineering Laboratory, Department of Bioinformatic Engineering, Graduate School of Information Science and Technology, Osaka University. Reiji Teramoto. E-mail:r-teramt@ics.es.osaka-u.ac.jp tel:+81-6-6850-6603,fax:+81-6-6850-6602

Look at function knn from package EMV in R. It's really simple. HTH, Xavier. ----- Original Message ----- From: "John E. Cornell, Ph.D." <cornell@uthscsa.edu> To: "bioconductor list" <bioconductor@stat.math.ethz.ch> Sent: Thursday, January 08, 2004 3:44 AM Subject: [BioC] K-nearest neighbor missing value estimation > I have a set of array data with some missing values, and I want to use the > K-nearest neighbor method to estimate values for the missing expression > data. Has anyone written a routine in R/Bioconductor to do this? > > John Cornell > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://www.stat.math.ethz.ch/mailman/listinfo/bioconductor >