Mercurial > repos > tomnl > create_sqlite_db

comparison frag4feature.R @ 27:0d59d313d3f8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit a598583947118bd50cfe5ae12d955c20d6e502a6
author tomnl
date Tue, 17 Jul 2018 12:10:35 -0400
parents 906e8e2be944
children
comparison
equal deleted inserted replaced
26:e25e717386a6 27:0d59d313d3f8
1 library(optparse) 1 library(optparse)
2 library(msPurity) 2 library(msPurity)
3 library(xcms) 3 library(xcms)
4 print(sessionInfo()) 4 print(sessionInfo())
5 5
6 xset_pa_filename_fix <- function(opt, pa, xset){ 6 xset_pa_filename_fix <- function(opt, pa, xset=NULL){
7 7
8 8
9 if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){ 9 if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){
10 # NOTE: Relies on the pa@fileList having the names of files given as 'names' of the variables 10 # NOTE: Relies on the pa@fileList having the names of files given as 'names' of the variables
11 # needs to be done due to Galaxy moving the files around and screwing up any links to files 11 # needs to be done due to Galaxy moving the files around and screwing up any links to files
24 names(pa@fileList) <- nsave 24 names(pa@fileList) <- nsave
25 25
26 pa@puritydf$filename <- basename(pa@fileList[match(pa@puritydf$filename, old_filenames)]) 26 pa@puritydf$filename <- basename(pa@fileList[match(pa@puritydf$filename, old_filenames)])
27 pa@grped_df$filename <- basename(pa@fileList[match(pa@grped_df$filename, old_filenames)]) 27 pa@grped_df$filename <- basename(pa@fileList[match(pa@grped_df$filename, old_filenames)])
28 } 28 }
29 print(pa@fileList) 29 print(pa@fileList)
30 print(xset@filepaths)
31 30
32 if(!all(basename(pa@fileList)==basename(xset@filepaths))){ 31 if(!is.null(xset)){
33 if(!all(names(pa@fileList)==basename(xset@filepaths))){
34 print('FILELISTS DO NOT MATCH')
35 message('FILELISTS DO NOT MATCH')
36 quit(status = 1)
37 }else{
38 xset@filepaths <- unname(pa@fileList)
39 }
40 }
41 32
33 print(xset@filepaths)
34
35 if(!all(basename(pa@fileList)==basename(xset@filepaths))){
36 if(!all(names(pa@fileList)==basename(xset@filepaths))){
37 print('FILELISTS DO NOT MATCH')
38 message('FILELISTS DO NOT MATCH')
39 quit(status = 1)
40 }else{
41 xset@filepaths <- unname(pa@fileList)
42 }
43 }
44 }
42 45
43 return(list(pa, xset)) 46 return(list(pa, xset))
44 } 47 }
45 48
46 49
54 make_option("--mostIntense", action="store_true"), 57 make_option("--mostIntense", action="store_true"),
55 make_option("--createDB", action="store_true"), 58 make_option("--createDB", action="store_true"),
56 make_option("--cores", default=4), 59 make_option("--cores", default=4),
57 make_option("--mzML_files", type="character"), 60 make_option("--mzML_files", type="character"),
58 make_option("--galaxy_names", type="character"), 61 make_option("--galaxy_names", type="character"),
59 make_option("--grp_peaklist", type="character") 62 make_option("--grp_peaklist", type="character"),
63 make_option("--use_group", action="store_true")
60 ) 64 )
61 65
62 # store options 66 # store options
63 opt<- parse_args(OptionParser(option_list=option_list)) 67 opt<- parse_args(OptionParser(option_list=option_list))
68
69 print(opt)
64 70
65 loadRData <- function(rdata_path, name){ 71 loadRData <- function(rdata_path, name){
66 #loads an RData file, and returns the named xset object if it is there 72 #loads an RData file, and returns the named xset object if it is there
67 load(rdata_path) 73 load(rdata_path)
68 return(get(ls()[ls() %in% name])) 74 return(get(ls()[ls() %in% name]))
109 createDB = FALSE 115 createDB = FALSE
110 }else{ 116 }else{
111 createDB = TRUE 117 createDB = TRUE
112 } 118 }
113 119
120 if(is.null(opt$use_group)){
121 fix <- xset_pa_filename_fix(opt, pa, xset)
122 pa <- fix[[1]]
123 xset <- fix[[2]]
124 use_group=FALSE
125 }else{
126 # if are only aligning to the group not eah file we do not need to align the files between the xset and pa object
127 print('use_group')
128 fix <- xset_pa_filename_fix(opt, pa)
129 pa <- fix[[1]]
130 use_group=TRUE
131 }
114 132
115 fix <- xset_pa_filename_fix(opt, pa, xset)
116 pa <- fix[[1]]
117 xset <- fix[[2]]
118 133
119 if(is.null(opt$grp_peaklist)){ 134 if(is.null(opt$grp_peaklist)){
120 grp_peaklist = NA 135 grp_peaklist = NA
121 }else{ 136 }else{
122 grp_peaklist = opt$grp_peaklist 137 grp_peaklist = opt$grp_peaklist
128 saveRDS(pa, 'test_pa.rds') 143 saveRDS(pa, 'test_pa.rds')
129 144
130 pa <- msPurity::frag4feature(pa=pa, xset=xset, ppm=opt$ppm, plim=opt$plim, 145 pa <- msPurity::frag4feature(pa=pa, xset=xset, ppm=opt$ppm, plim=opt$plim,
131 intense=opt$mostIntense, convert2RawRT=convert2RawRT, 146 intense=opt$mostIntense, convert2RawRT=convert2RawRT,
132 db_name='alldata.sqlite', out_dir=opt$out_dir, grp_peaklist=grp_peaklist, 147 db_name='alldata.sqlite', out_dir=opt$out_dir, grp_peaklist=grp_peaklist,
133 create_db=createDB) 148 create_db=createDB, use_group=use_group)
134 149
135 save(pa, file=file.path(opt$out_dir, 'frag4feature.RData')) 150 save(pa, file=file.path(opt$out_dir, 'frag4feature.RData'))
136 151
137 print(head(pa@grped_df)) 152 print(head(pa@grped_df))
138 write.table(pa@grped_df, file.path(opt$out_dir, 'frag4feature.tsv'), row.names=FALSE, sep='\t') 153 write.table(pa@grped_df, file.path(opt$out_dir, 'frag4feature.tsv'), row.names=FALSE, sep='\t')