Mercurial > repos > davidvanzessen > shm_csr
diff merge_and_filter.r @ 38:05c62efdc393 draft
Uploaded
author | davidvanzessen |
---|---|
date | Tue, 20 Dec 2016 09:03:15 -0500 |
parents | 33a7c49d48a7 |
children | ca2512e1e3ab |
line wrap: on
line diff
--- a/merge_and_filter.r Fri Dec 16 10:17:16 2016 -0500 +++ b/merge_and_filter.r Tue Dec 20 09:03:15 2016 -0500 @@ -47,6 +47,9 @@ filtering.steps[,2] = as.character(filtering.steps[,2]) #filtering.steps[,3] = as.numeric(filtering.steps[,3]) +print("summary files columns") +print(names(summ)) + summ = merge(summ, gene_identification, by="Sequence.ID") summ = summ[summ$Functionality != "No results",] @@ -67,14 +70,23 @@ filtering.steps = rbind(filtering.steps, c("After functionality filter", nrow(summ))) +#print("mutation analysis files columns") +#print(names(mutationanalysis[,!(names(mutationanalysis) %in% names(summ)[-1])])) + result = merge(summ, mutationanalysis[,!(names(mutationanalysis) %in% names(summ)[-1])], by="Sequence.ID") print(paste("Number of sequences after merging with mutation analysis file:", nrow(result))) +#print("mutation stats files columns") +#print(names(mutationstats[,!(names(mutationstats) %in% names(result)[-1])])) + result = merge(result, mutationstats[,!(names(mutationstats) %in% names(result)[-1])], by="Sequence.ID") print(paste("Number of sequences after merging with mutation stats file:", nrow(result))) +#print("hotspots files columns") +#print(names(hotspots[,!(names(hotspots) %in% names(result)[-1])])) + result = merge(result, hotspots[,!(names(hotspots) %in% names(result)[-1])], by="Sequence.ID") print(paste("Number of sequences after merging with hotspots file:", nrow(result)))