Mercurial > repos > tomnl > create_msp

comparison create_sqlite_db.R @ 4:7ae48818a229 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 97c9122c9af9ddca3a2498185ce8c7919c0df03a
author tomnl
date Tue, 08 May 2018 05:28:37 -0400
parents 4b417094bf71
children 278a7e7a84cf
comparison
equal deleted inserted replaced
3:3ecba7815437 4:7ae48818a229
55 make_option("--cores", default=4), 55 make_option("--cores", default=4),
56 make_option("--mzML_files", type="character"), 56 make_option("--mzML_files", type="character"),
57 make_option("--galaxy_names", type="character"), 57 make_option("--galaxy_names", type="character"),
58 make_option("--grp_peaklist", type="character"), 58 make_option("--grp_peaklist", type="character"),
59 make_option("--db_name", type="character", default='lcms_data.sqlite'), 59 make_option("--db_name", type="character", default='lcms_data.sqlite'),
60 make_option("--raw_rt_columns", action="store_true") 60 make_option("--raw_rt_columns", action="store_true"),
61 make_option("--metfrag_result", type="character"),
62 make_option("--sirius_csifingerid_result", type="character"),
63 make_option("--probmetab_result", type="character")
61 ) 64 )
65
62 66
63 # store options 67 # store options
64 opt<- parse_args(OptionParser(option_list=option_list)) 68 opt<- parse_args(OptionParser(option_list=option_list))
65 69
66 loadRData <- function(rdata_path, name){ 70 loadRData <- function(rdata_path, name){
73 print(opt$xset) 77 print(opt$xset)
74 print(opt$xcms_camera_option) 78 print(opt$xcms_camera_option)
75 # Requires 79 # Requires
76 pa <- loadRData(opt$pa, 'pa') 80 pa <- loadRData(opt$pa, 'pa')
77 81
78 print('TESTETSTESTETE') 82
79 print(pa@fileList) 83 print(pa@fileList)
80 84
81 85
82 if (opt$xcms_camera_option=='xcms'){ 86 if (opt$xcms_camera_option=='xcms'){
83 xset <- loadRData(opt$xset, 'xset') 87 xset <- loadRData(opt$xset, 'xset')
124 px <- msPurity::purityX(xset, saveEIC = TRUE, 128 px <- msPurity::purityX(xset, saveEIC = TRUE,
125 cores=opt$cores, sqlitePth=db_pth, 129 cores=opt$cores, sqlitePth=db_pth,
126 rtrawColumns = rtrawColumns) 130 rtrawColumns = rtrawColumns)
127 } 131 }
128 132
129
130
131 con <- DBI::dbConnect(RSQLite::SQLite(), db_pth) 133 con <- DBI::dbConnect(RSQLite::SQLite(), db_pth)
134
135 add_extra_table_elucidation <- function(name, pth){
136
137 if (!is.null(pth)){
138
139 print(pth)
140 df <- read.table(pth, header = TRUE, sep='\t', stringsAsFactors = FALSE, comment.char = "")
141 # bug for repeating headers
142 df <- df[!df$UID=='UID',]
143
144 # get peakid, an scan id
145 df_ids <- stringr::str_split_fixed(df$UID, '-', 3)
146 colnames(df_ids) <- c('grp_id', 'file_id', 'peak_id')
147 df <- cbind(df_ids, df)
148 # export to database
149
150
151 DBI::dbWriteTable(con, name=name, value=df, row.names=FALSE)
152
153 }
154
155 }
156
157
158 add_probmetab <- function(pth){
159 if (!is.null(pth)){
160
161 df <- read.table(pth, header = TRUE, sep='\t', stringsAsFactors = FALSE, comment.char = "")
162 df$grp_id <- 1:nrow(df)
163 start <- T
164 for (i in 1:nrow(df)){
165
166 x <- df[i,]
167
168
169 if(is.na(x$proba) | x$proba =='NA'){
170
171 next
172 }
173
174 mpc <- stringr::str_split(x$mpc, ';')
175 proba <- stringr::str_split(x$proba, ';')
176
177 for (j in 1:length(mpc[[1]])){
178
179 row <- c(x$grp_id, x$propmz, mpc[[1]][j], proba[[1]][j])
180
181 if (start){
182 df_out <- data.frame(t(row), stringsAsFactors=F)
183 start <- F
184 }else{
185 df_out <- data.frame(rbind(df_out, row), stringsAsFactors=F)
186 }
187 print(df_out)
188
189 }
190
191 }
192
193 colnames(df_out) <- c('grp_id', 'propmz', 'mpc', 'proba')
194 DBI::dbWriteTable(con, name='probmetab_results', value=df_out, row.names=FALSE)
195
196 }
197
198
199 }
200
201 add_extra_table_elucidation('metfrag_results', opt$metfrag_result)
202 add_extra_table_elucidation('sirius_csifingerid_results', opt$sirius_csifingerid_result)
203 add_probmetab(opt$probmetab_result)
204
205
206
132 207
133 cmd <- paste('SELECT cpg.grpid, cpg.mz, cpg.mzmin, cpg.mzmax, cpg.rt, cpg.rtmin, cpg.rtmax, c_peaks.cid, ', 208 cmd <- paste('SELECT cpg.grpid, cpg.mz, cpg.mzmin, cpg.mzmax, cpg.rt, cpg.rtmin, cpg.rtmax, c_peaks.cid, ',
134 'c_peaks.mzmin AS c_peak_mzmin, c_peaks.mzmax AS c_peak_mzmax, ', 209 'c_peaks.mzmin AS c_peak_mzmin, c_peaks.mzmax AS c_peak_mzmax, ',
135 'c_peaks.rtmin AS c_peak_rtmin, c_peaks.rtmax AS c_peak_rtmax, s_peak_meta.*, fileinfo.filename, fileinfo.nm_save ', 210 'c_peaks.rtmin AS c_peak_rtmin, c_peaks.rtmax AS c_peak_rtmax, s_peak_meta.*, fileinfo.filename, fileinfo.nm_save ',
136 'FROM c_peak_groups AS cpg ', 211 'FROM c_peak_groups AS cpg ',