Mercurial > repos > davidvanzessen > shm_csr
changeset 51:8fa8836bd605 draft
Uploaded
author | davidvanzessen |
---|---|
date | Tue, 16 May 2017 08:52:48 -0400 (2017-05-16) |
parents | 75ee66a691a0 |
children | 22dddabe3637 |
files | merge_and_filter.r shm_csr.xml |
diffstat | 2 files changed, 6 insertions(+), 9 deletions(-) [+] |
line wrap: on
line diff
--- a/merge_and_filter.r Mon May 15 03:13:16 2017 -0400 +++ b/merge_and_filter.r Tue May 16 08:52:48 2017 -0400 @@ -224,16 +224,13 @@ if(filter.unique == "remove"){ result = result[duplicated(result$unique.def) | duplicated(result$unique.def, fromLast=T),] + unique.defs = data.frame(table(result$unique.def)) + unique.defs = unique.defs[unique.defs$Freq >= filter.unique.count,] + result = result[result$unique.def %in% unique.defs$Var1,] } - + result$unique.def = paste(result$unique.def, gsub(",.*", "", result$best_match)) #keep the unique sequences that are in multiple classes, gsub so the unmatched don't have a class after it - - if(filter.unique == "remove"){ - unique.defs = data.frame(table(result$unique.def)) - unique.defs = unique.defs[unique.defs$Freq >= filter.unique.count,] - result = result[result$unique.def %in% unique.defs$Var1,] - } - + result = result[!duplicated(result$unique.def),] }
--- a/shm_csr.xml Mon May 15 03:13:16 2017 -0400 +++ b/shm_csr.xml Tue May 16 08:52:48 2017 -0400 @@ -20,7 +20,7 @@ <option value="unproductive">Unproductive (Unproductive and Unproductive see comment)</option> <option value="remove_unknown">Productive and Unproductive (Productive, Productive see comment, Unproductive, Unproductive and Unproductive see comment)</option> </param> - <conditional name="filter_unique"> + <conditional name="filter_unique"> <param name="filter_unique_select" type="select" label="Filter unique sequences" help="See below for an example."> <option value="remove" selected="true">Remove uniques (Based on nucleotide sequence + C)</option> <option value="keep">Keep uniques (Based on nucleotide sequence + C)</option>