Mercurial > repos > davidvanzessen > shm_csr
changeset 10:4b695ca65213 draft
Uploaded
author | davidvanzessen |
---|---|
date | Wed, 09 Nov 2016 09:45:32 -0500 |
parents | 372ccdcf0b2d |
children | c4ab5034c4d4 |
files | merge_and_filter.r shm_csr.xml |
diffstat | 2 files changed, 7 insertions(+), 10 deletions(-) [+] |
line wrap: on
line diff
--- a/merge_and_filter.r Tue Nov 08 07:32:54 2016 -0500 +++ b/merge_and_filter.r Wed Nov 09 09:45:32 2016 -0500 @@ -25,7 +25,7 @@ gene_identification = read.table(gene_identification_file, header=T, sep="\t", fill=T, stringsAsFactors=F, quote="") if(method == "blastn"){ - "qseqid\tsseqid\tpident\tlength\tmismatch\tgapopen\tqstart\tqend\tsstart\tsend\tevalue\tbitscore" + #"qseqid\tsseqid\tpident\tlength\tmismatch\tgapopen\tqstart\tqend\tsstart\tsend\tevalue\tbitscore" gene_identification = gene_identification[!duplicated(gene_identification$qseqid),] ref_length = data.frame(sseqid=c("ca1", "ca2", "cg1", "cg2", "cg3", "cg4", "cm"), ref.length=c(81,81,141,141,141,141,52)) gene_identification = merge(gene_identification, ref_length, by="sseqid", all.x=T) @@ -144,12 +144,7 @@ higher_than=(result$chunk_hit_percentage >= chunk_hit_threshold & result$nt_hit_percentage >= nt_hit_threshold) -unmatched=result[NULL,c("Sequence.ID", "chunk_hit_percentage", "nt_hit_percentage", "start_locations", "best_match")] - if(!all(higher_than, na.rm=T)){ #check for no unmatched - unmatched = result[!higher_than,] - unmatched = unmatched[,c("Sequence.ID", "chunk_hit_percentage", "nt_hit_percentage", "start_locations", "best_match")] - unmatched$best_match = paste("unmatched,", unmatched$best_match) result[!higher_than,"best_match"] = paste("unmatched,", result[!higher_than,"best_match"]) } @@ -200,6 +195,8 @@ filtering.steps = rbind(filtering.steps, c("After remove duplicates based on filter", nrow(result))) +unmatched = result[grepl("^unmatched", result$best_match),c("Sequence.ID", "chunk_hit_percentage", "nt_hit_percentage", "start_locations", "best_match")] + print(paste("Number of rows in result:", nrow(result))) print(paste("Number of rows in unmatched:", nrow(unmatched)))
--- a/shm_csr.xml Tue Nov 08 07:32:54 2016 -0500 +++ b/shm_csr.xml Wed Nov 09 09:45:32 2016 -0500 @@ -17,12 +17,12 @@ <option value="remove_unknown">Productive and Unproductive (Productive, Productive see comment, Unproductive, Unproductive and Unproductive see comment)</option> </param> <param name="filter_uniques" type="select" label="Filter unique sequences" help="See below for an example."> - <option value="remove">Remove uniques (Based on nucleotide sequence + C)</option> + <option value="remove" selected="true">Remove uniques (Based on nucleotide sequence + C)</option> <option value="keep">Keep uniques (Based on nucleotide sequence + C)</option> - <option value="no" selected="true">No</option> + <option value="no">No</option> </param> <param name="unique" type="select" label="Remove duplicates based on" help="" > - <option value="VGene,AA.JUNCTION,best_match" selected="true">Top.V.Gene, CDR3 (AA), C region</option> + <option value="VGene,AA.JUNCTION,best_match">Top.V.Gene, CDR3 (AA), C region</option> <option value="VGene,AA.JUNCTION">Top.V.Gene, CDR3 (AA)</option> <option value="AA.JUNCTION,best_match">CDR3 (AA), C region</option> <option value="AA.JUNCTION">CDR3 (AA)</option> @@ -31,7 +31,7 @@ <option value="VGene,CDR3.IMGT.seq">Top.V.Gene, CDR3 (nt)</option> <option value="CDR3.IMGT.seq,best_match">CDR3 (nt), C region</option> <option value="CDR3.IMGT.seq">CDR3 (nt)</option> - <option value="Sequence.ID">Don't remove duplicates</option> + <option value="Sequence.ID" selected="true">Don't remove duplicates</option> </param> <param name="class_filter" type="select" label="Human Class/Subclass filter" help="" > <option value="70_70" selected="true">>70% class and >70% subclass</option>