Dear Sirs, I am running Bioconductor with Biobase 1.8.0, affy 1.8.1, siggenes 1.4.0, and affyPLM 1.6.0, under R 2.3.1 and MacOS X 10.3.9. I am trying to identify SNPs between two barley varieties on the basis of Affy chips, which ReadAffy reads without evident errors. The next paragraph gives two session histories, each ending in an error message that I do not really understand, unless something wants the data transposed. Could someone please tell me what I am doing wrong or leaving out? >library(affy) >library(siggenes) > sidata <- ReadAffy(filenames = c("000113_5hr_kindered_H20_inoc_2x2.CEL", "000114_12hr_kindered_H20_inoc_3bx1.CEL", + "000157_24hr_Kindered_H2O_Inoc_1.CEL", "000158_0hr_Kindered_H2O_Inoc_4.CEL", "000189_0hr_403-rep2_H2O_inoc_21b.CEL", + "000190_5hr_403-rep2_H2O_inoc_22b.CEL", "000191_12hr_403-rep2_H2O_inoc_23b.CEL", "000192_24hr_403-rep2_H2O_inoc_24b.CEL", + "000122_5hr_peruvian_H20_inoc_14bx1.CEL", "000123_12hr_peruvian_H20_inoc_15bx1.CEL", "000141_Non-host-resistant-barley_16bx2.CEL", + "000161_0hr_Peruvian_H2O_inoc_13.CEL", "000201_0hr_405-rep2_H2O_inoc_33b.CEL", "000202_5hr_405-rep2_H2O_inoc_34b.CEL", + "000203_12hr_405-rep2_H2O_inoc_35b.CEL", "000204_24hr_405-rep2_H2O_inoc_36b.CEL"), + sampleNames = c("000113_5hr_kindered_H20_inoc_2x2", "000114_12hr_kindered_H20_inoc_3bx1", "000157_24hr_Kindered_H2O_Inoc_1", + "000158_0hr_Kindered_H2O_Inoc_4", "000189_0hr_403-rep2_H2O_inoc_21b", "000190_5hr_403-rep2_H2O_inoc_22b", + "000191_12hr_403-rep2_H2O_inoc_23b", "000192_24hr_403-rep2_H2O_inoc_24b", "000122_5hr_peruvian_H20_inoc_14bx1", + "000123_12hr_peruvian_H20_inoc_15bx1", "000141_Non-host-resistant-barley_16bx2", "000161_0hr_Peruvian_H2O_inoc_13", + "000201_0hr_405-rep2_H2O_inoc_33b", "000202_5hr_405-rep2_H2O_inoc_34b", "000203_12hr_405-rep2_H2O_inoc_35b", + "000204_24hr_405-rep2_H2O_inoc_36b"), + phenoData = "Hordeumphenodata.txt") > sirma <- bg.correct(sidata, method = "rma") > sinorm <- normalize(sirma) > siprobeintensities <- as.data.frame(probes(sinorm, "pm")) > write.table(siprobeintensities, file = "siprobeintensities.txt") > samout <- sam(siprobeintensities, cl = c(1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 2, 2, 2, 2), method = "cat.stat", B = 1000, ran = 11279) Error in FUN(data, cl, ...) : There must be at least 10 observations in each group. I tried again with a fresh R session and an updated copy of Hordeumphenodata.txt: >library(affy) >library(siggenes) >sidata <- ReadAffy(filenames = c("000113_5hr_kindered_H20_inoc_2x2.CEL", "000114_12hr_kindered_H20_inoc_3bx1.CEL", "000122_5hr_peruvian_H20_inoc_14bx1.CEL", "000123_12hr_peruvian_H20_inoc_15bx1.CEL", "000141_Non-host-resistant-barley_16bx2.CEL", "000157_24hr_Kindered_H2O_Inoc_1.CEL", "000158_0hr_Kindered_H2O_Inoc_4.CEL", "000159_0hr_Kindered_S_passerini_inoc_5.CEL", "000161_0hr_Peruvian_H2O_inoc_13.CEL", "000162_0hr_Peruvian_S_passerini_17.CEL", "000189_0hr_403-rep2_H2O_inoc_21b.CEL", "000190_5hr_403-rep2_H2O_inoc_22b.CEL", "000191_12hr_403-rep2_H2O_inoc_23b.CEL", "000192_24hr_403-rep2_H2O_inoc_24b.CEL", "000193_0hr_403-rep2_inoc-s_pass_25b.CEL", "000201_0hr_405-rep2_H2O_inoc_33b.CEL", "000202_5hr_405-rep2_H2O_inoc_34b.CEL", "000203_12hr_405-rep2_H2O_inoc_35b.CEL", "000204_24hr_405-rep2_H2O_inoc_36b.CEL", "000205_0hr_405-rep2_inoc-s_pass_37b.CEL"), sampleNames = c("000113_5hr_kindered_H20_inoc_2x2", "000114_12hr_kindered_H20_inoc_3bx1", "000122_5hr_peruvian_H20_inoc_14bx1", "000123_12hr_peruvian_H20_inoc_15bx1", "000141_Non-host-resistant-barley_16bx2", "000157_24hr_Kindered_H2O_Inoc_1", "000158_0hr_Kindered_H2O_Inoc_4", "000159_0hr_Kindered_S_passerini_inoc_5", "000161_0hr_Peruvian_H2O_inoc_13", "000162_0hr_Peruvian_S_passerini_17", "000189_0hr_403-rep2_H2O_inoc_21b", "000190_5hr_403-rep2_H2O_inoc_22b", "000191_12hr_403-rep2_H2O_inoc_23b", "000192_24hr_403-rep2_H2O_inoc_24b", "000193_0hr_403-rep2_inoc-s_pass_25b", "000201_0hr_405-rep2_H2O_inoc_33b", "000202_5hr_405-rep2_H2O_inoc_34b", "000203_12hr_405-rep2_H2O_inoc_35b", "000204_24hr_405-rep2_H2O_inoc_36b", "000205_0hr_405-rep2_inoc-s_pass_37b"), phenoData = "Hordeumphenodata.txt") > sirma <- bg.correct(sidata, method = "rma") > sinorm <- normalize(sirma) > siprobeintensities <- as.data.frame(probes(sinorm, "pm")) > write.table(siprobeintensities, file = "siprobeintensities.txt") > sicl <- c(1, 1, 2, 2, 2, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2) > samout <- sam(siprobeintensities, sicl, method = "cat.stat", B = 1000, ran = 11279) Error in FUN(data, cl, ...) : There should be at least 25 samples. Also, how can I verify that the Affy intensities have been read correctly? I get this bad feeling that a Perl-style array could be read in orthogonal to its proper sequence. The file "siprobeintensities.txt" has 251438 rows and 20 numerical columns after the probe identifier. Thank you for your time, attention, and for pointing me to wherever the usage of sam for SNPs is more fully documented--it would help if a vignette would give the entire data flow from CEL file to output of the sam object. Charles Crane USDA-ARS, MWA, Crop Production and Pest Control Research Unit Department of Botany and Plant Pathology Purdue University