inst/buildScripts/chipTypes/Mapping50K_Hind240/Mapping50K_Hind240,UFL.R

In HenrikBengtsson/aroma.affymetrix: Analysis of Large Affymetrix Microarray Data Sets

if (interactive()) savehistory();
library("aroma.affymetrix");
verbose <- Verbose(threshold=-50, timestamp=TRUE);
options(width=60);


chipType <- "Mapping50K_Hind240";


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# User settings
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
## setOption(aromaSettings, "user/initials", "HB");
## setOption(aromaSettings, "user/fullname", "Henrik Bengtsson");
## email <- sprintf("%s@%s", "henrik.bengtsson", "aroma-project.org")
## setOption(aromaSettings, "user/email", email);
## saveAnywhere(aromaSettings);

fullname <- getOption(aromaSettings, "user/fullname");
stopifnot(!is.null(fullname));
email <- getOption(aromaSettings, "user/email");
stopifnot(!is.null(email));
user <- getOption(aromaSettings, "user/initials");
stopifnot(!is.null(user));


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# Settings
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
genomeVersions <- c("30"="hg18", "31"="hg19");
naVersions <- names(genomeVersions);
choices <- sprintf("na%s (%s)", naVersions, genomeVersions);
choice <- textMenu(choices, title="Choose NetAffx version: ", value=FALSE);
naVersion <- naVersions[choice];
genomeVersion <- genomeVersions[naVersion];
datestamp <- format(Sys.Date(), format="%Y%m%d");


enzyme <- c("Mapping50K_Hind240"="HindIII", "Mapping50K_Xba240"="XbaI")[chipType];
print(enzyme);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# Setup required annotation files
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
cdf <- AffymetrixCdfFile$byChipType(chipType);
rm(csv);
print(cdf);

tags <- sprintf(".na%s", naVersion);
pathname <- AffymetrixNetAffxCsvFile$findByChipType(chipType, tags=tags);
if (isFile(pathname)) {
  csv <- AffymetrixNetAffxCsvFile(pathname);
}
rm(tags);
print(csv);



# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# Import UFL from CSV files
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
tags <- sprintf("na%s,%s,%s%s", naVersion, genomeVersion, user, datestamp);
ufl <- NULL;
tryCatch({
  ufl <- AromaUflFile$byChipType(getChipType(cdf), tags=tags);
}, error = function(ex) {})
if (is.null(ufl)) {
  ufl <- AromaUflFile$allocateFromCdf(cdf, tags=tags);
}
print(ufl);


stopifnot(!is.na(enzyme));
units <- importFrom(ufl, csv, enzymes=enzyme, verbose=verbose);
str(units);


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# Update the file footer
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
srcFileTags <- list();
srcFiles <- list(cdf, csv);
for (kk in seq_along(srcFiles)) {
  srcFile <- srcFiles[[kk]];
  tags <- list(
    filename=getFilename(srcFile), 
    filesize=getFileSize(srcFile), 
    checksum=getChecksum(srcFile)
  );
  srcFileTags[[kk]] <- tags;
}
print(srcFileTags);

footer <- readFooter(ufl);
footer$createdOn <- format(Sys.time(), "%Y%m%d %H:%M:%S", usetz=TRUE);
footer$createdBy = list(
  fullname = fullname, 
  email = email
);
names(srcFileTags) <- sprintf("srcFile%d", seq_along(srcFileTags));
footer$srcFiles <- srcFileTags;
writeFooter(ufl, footer);


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# Statistics
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
print(ufl);
x <- summaryOfUnits(ufl);
print(x);

## Mapping50K_Hind240,na31,hg19,HB20110328
##                snp cnp affxSnp other total
## enzyme1-only 56862   0       0     0 56862
## missing        382   0       0    55   437
## total        57244   0       0    55 57299