Mercurial > repos > tomnl > track_rt_raw

comparison frag4feature.R @ 1:e2635fa802bd 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 2e847122cf605951c334858455fc1d3ebdb189e9-dirty
author tomnl
date Tue, 27 Mar 2018 05:36:22 -0400
parents b96fc0da0a32
children 26fd52ed6d21
comparison
equal deleted inserted replaced
0:b96fc0da0a32 1:e2635fa802bd
1 library(optparse)
1 library(msPurity) 2 library(msPurity)
2 library(optparse) 3 library(xcms)
4
5 xset_pa_filename_fix <- function(opt, pa, xset){
6
7
8 if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){
9 # NOTE: Relies on the pa@fileList having the names of files given as 'names' of the variables
10 # needs to be done due to Galaxy moving the files around and screwing up any links to files
11
12 filepaths <- trimws(strsplit(opt$mzML_files, ',')[[1]])
13 filepaths <- filepaths[filepaths != ""]
14 new_names <- basename(filepaths)
15
16 galaxy_names <- trimws(strsplit(opt$galaxy_names, ',')[[1]])
17 galaxy_names <- galaxy_names[galaxy_names != ""]
18
19 nsave <- names(pa@fileList)
20 old_filenames <- basename(pa@fileList)
21 pa@fileList <- filepaths[match(names(pa@fileList), galaxy_names)]
22 names(pa@fileList) <- nsave
23
24 pa@puritydf$filename <- basename(pa@fileList[match(pa@puritydf$filename, old_filenames)])
25 pa@grped_df$filename <- basename(pa@fileList[match(pa@grped_df$filename, old_filenames)])
26 }
27
28
29 if(!all(basename(pa@fileList)==basename(xset@filepaths))){
30 if(!all(names(pa@fileList)==basename(xset@filepaths))){
31 print('FILELISTS DO NOT MATCH')
32 message('FILELISTS DO NOT MATCH')
33 quit(status = 1)
34 }else{
35 xset@filepaths <- unname(pa@fileList)
36 }
37 }
38
39
40 return(list(pa, xset))
41 }
42
3 43
4 option_list <- list( 44 option_list <- list(
5 make_option(c("-o", "--out_dir"), type="character"), 45 make_option(c("-o", "--out_dir"), type="character"),
6 make_option("--pa", type="character"), 46 make_option("--pa", type="character"),
7 make_option("--xset", type="character"), 47 make_option("--xset", type="character"),
8 make_option("--ppm", default=10), 48 make_option("--ppm", default=10),
9 make_option("--plim", default=0.0), 49 make_option("--plim", default=0.0),
10 make_option("--convert2RawRT", action="store_true"), 50 make_option("--convert2RawRT", action="store_true"),
11 make_option("--mostIntense", action="store_true"), 51 make_option("--mostIntense", action="store_true"),
52 make_option("--createDB", action="store_true"),
12 make_option("--cores", default=4), 53 make_option("--cores", default=4),
13 make_option("--mzML_files", type="character"), 54 make_option("--mzML_files", type="character"),
14 make_option("--galaxy_names", type="character"), 55 make_option("--galaxy_names", type="character"),
15 make_option("--grp_peaklist", type="character") 56 make_option("--grp_peaklist", type="character")
16 ) 57 )
28 pa <- loadRData(opt$pa, 'pa') 69 pa <- loadRData(opt$pa, 'pa')
29 xset <- loadRData(opt$xset, 'xset') 70 xset <- loadRData(opt$xset, 'xset')
30 71
31 pa@cores <- opt$cores 72 pa@cores <- opt$cores
32 73
74 print(pa@fileList)
75 print(xset@filepaths)
76
33 if(is.null(opt$mostIntense)){ 77 if(is.null(opt$mostIntense)){
34 mostIntense = FALSE 78 mostIntense = FALSE
35 }else{ 79 }else{
36 mostIntense = TRUE 80 mostIntense = TRUE
37 } 81 }
40 convert2RawRT = FALSE 84 convert2RawRT = FALSE
41 }else{ 85 }else{
42 convert2RawRT= TRUE 86 convert2RawRT= TRUE
43 } 87 }
44 88
45 # Makes sure the same files are being used 89 if(is.null(opt$createDB)){
46 if(!all(basename(pa@fileList)==basename(xset@filepaths))){ 90 createDB = FALSE
47 if(!all(names(pa@fileList)==basename(xset@filepaths))){ 91 }else{
48 quit(status = 1) 92 createDB = TRUE
49 }else{
50 xset@filepaths <- unname(pa@fileList)
51 }
52 } 93 }
53 94
54 if (!is.null(opt$mzML_files) && !is.null(opt$galaxy_names)){
55 # NOTE: This only works if the pa file was generated IN Galaxy!! Relies on
56 # the pa@fileList having the names of files given as 'names' of the variables (done in frag4feature)
57 # Will update in the next version of msPurity
58 filepaths <- trimws(strsplit(opt$mzML_files, ',')[[1]])
59 filepaths <- filepaths[filepaths != ""]
60 new_names <- basename(filepaths)
61 95
62 galaxy_names <- trimws(strsplit(opt$galaxy_names, ',')[[1]]) 96 fix <- xset_pa_filename_fix(opt, pa, xset)
63 galaxy_names <- galaxy_names[galaxy_names != ""] 97 pa <- fix[[1]]
64 98 xset <- fix[[2]]
65 nsave <- names(pa@fileList)
66 old_filenames <- basename(pa@fileList)
67 pa@fileList <- filepaths[match(names(pa@fileList), galaxy_names)]
68
69 pa@puritydf$filename <- basename(pa@fileList[match(pa@puritydf$filename, old_filenames)])
70 pa@grped_df$filename <- basename(pa@fileList[match(pa@grped_df$filename, old_filenames)])
71 }
72
73 if(!all(basename(pa@fileList)==basename(xset@filepaths))){
74 if(!all(names(pa@fileList)==basename(xset@filepaths))){
75 quit(status = 1)
76 }else{
77 xset@filepaths <- unname(pa@fileList)
78 }
79 }
80 99
81 if(is.null(opt$grp_peaklist)){ 100 if(is.null(opt$grp_peaklist)){
82 grp_peaklist = NA 101 grp_peaklist = NA
102
103
83 }else{ 104 }else{
84 grp_peaklist = opt$grp_peaklist 105 grp_peaklist = opt$grp_peaklist
85 } 106 }
86 107
87 print(pa) 108 print('heck')
88 print(pa@fileList) 109 print(pa@fileList)
89 print(xset) 110 print(names(pa@fileList))
90 print(xset@filepaths) 111 print(xset@filepaths)
91 print(opt$ppm) 112 saveRDS(pa, 'test_pa.rds')
92 print(opt$plim)
93 print(convert2RawRT)
94
95
96
97 113
98 pa <- msPurity::frag4feature(pa=pa, xset=xset, ppm=opt$ppm, plim=opt$plim, 114 pa <- msPurity::frag4feature(pa=pa, xset=xset, ppm=opt$ppm, plim=opt$plim,
99 intense=opt$mostIntense, convert2RawRT=convert2RawRT, 115 intense=opt$mostIntense, convert2RawRT=convert2RawRT,
100 db_name='alldata.sqlite', out_dir=opt$out_dir, grp_peaklist=grp_peaklist) 116 db_name='alldata.sqlite', out_dir=opt$out_dir, grp_peaklist=grp_peaklist,
117 create_db=createDB)
101 118
102 save(pa, file=file.path(opt$out_dir, 'frag4feature.RData')) 119 save(pa, file=file.path(opt$out_dir, 'frag4feature.RData'))
103 120
104 print(head(pa@grped_df)) 121 print(head(pa@grped_df))
105 write.table(pa@grped_df, file.path(opt$out_dir, 'frag4feature.tsv'), row.names=FALSE, sep='\t') 122 write.table(pa@grped_df, file.path(opt$out_dir, 'frag4feature.tsv'), row.names=FALSE, sep='\t')