|
0
|
1
|
|
|
2
|
|
|
3 TOOL_NAME <- "XSeekerPreparator"
|
|
14
|
4 VERSION <- "1.2.2"
|
|
|
5
|
|
|
6 DEBUG_FAST <- FALSE
|
|
|
7 DEBUG_FAST_IGNORE_SLOW_OP <- DEBUG_FAST
|
|
|
8 PROCESS_SMOL_BATCH <- DEBUG_FAST
|
|
|
9 FAST_FEATURE_RATIO <- 10
|
|
0
|
10
|
|
|
11 OUTPUT_SPECIFIC_TOOL <- "XSeeker_Galaxy"
|
|
|
12
|
|
14
|
13 ENRICHED_RDATA_VERSION <- paste("1.2.2", OUTPUT_SPECIFIC_TOOL, sep="-")
|
|
0
|
14 ENRICHED_RDATA_DOC <- sprintf("
|
|
|
15 Welcome to the enriched <Version %s> of the output of CAMERA/xcms.
|
|
|
16 This doc was generated by the tool: %s - Version %s
|
|
|
17 To show the different variables contained in this rdata, type:
|
|
|
18 - `load('this_rdata.rdata', rdata_env <- new.env())`
|
|
|
19 - `names(rdata_env)`
|
|
|
20
|
|
|
21 Sections
|
|
|
22 ######
|
|
|
23
|
|
|
24
|
|
|
25 This tools helpers
|
|
|
26 ------
|
|
|
27 The version number is somewhat special because the evolution of the
|
|
|
28 rdata's format is non-linear.
|
|
|
29 There may be different branches, each evolving separatly.
|
|
|
30 To reflect these branches's diversions, there may be a prepended
|
|
|
31 branch name following this format:
|
|
|
32 major.minor.patch-branch_name
|
|
|
33 Like this, we can process rdata with the same tool, and output
|
|
|
34 rdata formated differently, for each tool.
|
|
|
35
|
|
|
36
|
|
|
37 - enriched_rdata:
|
|
|
38 - Description: flag created by that tool to tell it was enriched.
|
|
|
39 - Retrieval method: enriched_rdata <- TRUE
|
|
|
40
|
|
|
41 - enriched_rdata_version:
|
|
|
42 - Description: A flag created by that tool to tell which version of
|
|
|
43 this tool has enriched the rdata.
|
|
|
44 - Retrieval method: enriched_rdata_version <- sprintf(\"%s\", ENRICHED_RDATA_VERSION)
|
|
|
45
|
|
|
46 - enriched_rdata_doc:
|
|
|
47 - Description: Contains the documentation string.
|
|
|
48
|
|
|
49 Data from original mzxml file
|
|
|
50 ------
|
|
|
51 - tic:
|
|
|
52 - Description: Those are the tic values from the original mzxml
|
|
|
53 file, extracted using xcms 2.
|
|
|
54 - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@tic
|
|
|
55 - xcms version: 2.0
|
|
|
56
|
|
|
57 - mz:
|
|
|
58 - Description: Those are the m/z values from the original mzxml
|
|
|
59 file, extracted using xcms 2.
|
|
|
60 - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$mz
|
|
|
61 - xcms version: 2.0
|
|
|
62
|
|
|
63 - scanindex:
|
|
|
64 - Description: Those are the scanindex values from the original mzxml
|
|
|
65 file, extracted using xcms 2.
|
|
|
66 - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scanindex
|
|
|
67 - xcms version: 2.0
|
|
|
68
|
|
|
69 - scantime:
|
|
|
70 - Description: Those are the scantime values from the original mzxml
|
|
|
71 file, extracted using xcms 2.
|
|
|
72 - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scantime
|
|
|
73 - xcms version: 2.0
|
|
|
74
|
|
|
75 - intensity:
|
|
|
76 - Description: Those are the intensity values from the original mzxml
|
|
|
77 file, extracted using xcms 2.
|
|
|
78 - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$intensity
|
|
|
79 - xcms version: 2.0
|
|
|
80
|
|
|
81 - polarity:
|
|
|
82 - Description: Those are the polarity values from the original mzxml
|
|
|
83 file, extracted using xcms 2.
|
|
|
84 - Retrieval method: as.character(xcms::xcmsRaw('original_file.mzxml')@polarity[[1]])
|
|
|
85 - xcms version: 2.0
|
|
|
86
|
|
|
87 Data taken from incoming rdata
|
|
|
88 ------
|
|
|
89 - variableMetadata:
|
|
|
90 - Description: Unmodified copy of variableMetadata from incoming rdata.
|
|
|
91 - Retrieval method: rdata_file$variableMetadata
|
|
|
92
|
|
|
93 - process_params:
|
|
|
94 - Description: Those are the processing parameters values from the
|
|
|
95 curent rdata. They have been simplified to allow easy access like:
|
|
|
96 for (params in process_params) {
|
|
|
97 if (params[[\"xfunction\"]] == \"annotatediff\") {
|
|
|
98 process_peak_picking_params(params)
|
|
|
99 }
|
|
|
100 }
|
|
|
101 - Retrieval method:
|
|
|
102 ## just he same list, but simplified
|
|
|
103 process_params <- list()
|
|
|
104 for (list_name in names(rdata_file$listOFlistArguments)) {
|
|
|
105 param_list <- list()
|
|
|
106 for (param_name in names(rdata_file$listOFlistArguments[[list_name]])) {
|
|
|
107 param_list[[param_name]] <- rdata_file$listOFlistArguments[[list_name]][[param_name]]
|
|
|
108 }
|
|
|
109 process_params[[length(process_params)+1]] <- param_list
|
|
|
110 }
|
|
|
111 ", ENRICHED_RDATA_VERSION, TOOL_NAME, VERSION, ENRICHED_RDATA_VERSION)
|
|
|
112
|
|
|
113
|
|
|
114
|
|
|
115 get_models <- function(path) {
|
|
|
116 if (is.null(path)) {
|
|
|
117 stop("No models to define the database schema")
|
|
|
118 } else {
|
|
|
119 message(sprintf("Loading models from %s", path))
|
|
|
120 }
|
|
|
121 ## galaxy mangles the "@" to a "__at__"
|
|
|
122 if (substr(path, 1, 9) == "git__at__") {
|
|
|
123 path <- sub("^git__at__", "git@", path, perl=TRUE)
|
|
|
124 }
|
|
|
125 if (
|
|
|
126 substr(path, 1, 4) == "git@"
|
|
|
127 || substr(path, length(path)-4, 4) == ".git"
|
|
|
128 ) {
|
|
|
129 return (get_models_from_git(path))
|
|
|
130 }
|
|
|
131 if (substr(path, 1, 4) == "http") {
|
|
|
132 return (get_models_from_url(path))
|
|
|
133 }
|
|
|
134 return (source(path)$value)
|
|
|
135 }
|
|
|
136
|
|
|
137 get_models_from_git <- function (url, target_file="models.R", rm=TRUE) {
|
|
|
138 tmp <- tempdir()
|
|
|
139 message(sprintf("Cloning %s", url))
|
|
|
140 system2("git", c("clone", url, tmp))
|
|
|
141 result <- search_tree(file.path(tmp, dir), target_file)
|
|
|
142 if (!is.null(result)) {
|
|
|
143 models <- source(result)$value
|
|
|
144 if (rm) {
|
|
|
145 unlink(tmp, recursive=TRUE)
|
|
|
146 }
|
|
|
147 return (models)
|
|
|
148 }
|
|
|
149 if (rm) {
|
|
|
150 unlink(tmp, recursive=TRUE)
|
|
|
151 }
|
|
|
152 stop(sprintf(
|
|
|
153 "Could not find any file named \"%s\" in this repo",
|
|
|
154 target_file
|
|
|
155 ))
|
|
|
156 }
|
|
|
157
|
|
|
158 get_models_from_url <- function (url, target_file="models.R", rm=TRUE) {
|
|
|
159 tmp <- tempdir()
|
|
|
160 message(sprintf("Downloading %s", url))
|
|
|
161 result <- file.path(tmp, target_file)
|
|
|
162 if (download.file(url, destfile=result) == 0) {
|
|
|
163 models <- source(result)$value
|
|
|
164 if (rm) {
|
|
|
165 unlink(tmp, recursive=TRUE)
|
|
|
166 }
|
|
|
167 return (models)
|
|
|
168 }
|
|
|
169 if (rm) {
|
|
|
170 unlink(tmp, recursive=TRUE)
|
|
|
171 }
|
|
|
172 stop("Could not download any file at this adress.")
|
|
|
173 }
|
|
|
174
|
|
|
175 search_tree <- function(path, target) {
|
|
|
176 target <- tolower(target)
|
|
|
177 for (file in list.files(path)) {
|
|
|
178 if (is.dir(file)) {
|
|
|
179 result <- search_tree(file.path(path, file), target)
|
|
|
180 if (!is.null(result)) {
|
|
|
181 return (result)
|
|
|
182 }
|
|
|
183 } else if (tolower(file) == target) {
|
|
|
184 return (file.path(path, file))
|
|
|
185 }
|
|
|
186 }
|
|
|
187 return (NULL)
|
|
|
188 }
|
|
|
189
|
|
|
190 create_database <- function(orm) {
|
|
|
191 orm$recreate_database(no_exists=FALSE)
|
|
|
192 set_database_version(orm, "created")
|
|
|
193 }
|
|
|
194
|
|
|
195 insert_adducts <- function(orm) {
|
|
|
196 message("Creating adducts...")
|
|
|
197 adducts <- list(
|
|
|
198 list("[M-H2O-H]-",1,-1,-48.992020312000001069,1,0,0.5,"H0","H1O3"),
|
|
|
199 list("[M-H-Cl+O]-",1,-1,-19.981214542000000022,2,0,0.5,"O1","H1Cl1"),
|
|
|
200 list("[M-Cl+O]-",1,-1,-18.973389510000000512,3,0,0.5,"O1","Cl1"),
|
|
|
201 list("[M-3H]3-",1,-3,-3.0218293560000000219,4,0,1.0,"H0","H3"),
|
|
|
202 list("[2M-3H]3-",2,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"),
|
|
|
203 list("[3M-3H]3-",3,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"),
|
|
|
204 list("[M-2H]2-",1,-2,-2.0145529039999998666,5,0,1.0,"H0","H2"),
|
|
|
205 list("[2M-2H]2-",2,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"),
|
|
|
206 list("[3M-2H]2-",3,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"),
|
|
|
207 list("[M-H]-",1,-1,-1.0072764519999999333,6,1,1.0,"H0","H1"),
|
|
|
208 list("[2M-H]-",2,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"),
|
|
|
209 list("[3M-H]-",3,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"),
|
|
|
210 list("[M]+",1,1,-0.00054858000000000000945,7,1,1.0,"H0","H0"),
|
|
|
211 list("[M]-",1,-1,0.00054858000000000000945,8,1,1.0,"H0","H0"),
|
|
|
212 list("[M+H]+",1,1,1.0072764519999999333,9,1,1.0,"H1","H0"),
|
|
|
213 list("[2M+H]+",2,1,1.0072764519999999333,9,0,0.5,"H1","H0"),
|
|
|
214 list("[3M+H]+",3,1,1.0072764519999999333,9,0,0.25,"H1","H0"),
|
|
|
215 list("[M+2H]2+",1,2,2.0145529039999998666,10,0,0.75,"H2","H0"),
|
|
|
216 list("[2M+2H]2+",2,2,2.0145529039999998666,10,0,0.5,"H2","H0"),
|
|
|
217 list("[3M+2H]2+",3,2,2.0145529039999998666,10,0,0.25,"H2","H0"),
|
|
|
218 list("[M+3H]3+",1,3,3.0218293560000000219,11,0,0.75,"H3","H0"),
|
|
|
219 list("[2M+3H]3+",2,3,3.0218293560000000219,11,0,0.5,"H3","H0"),
|
|
|
220 list("[3M+3H]3+",3,3,3.0218293560000000219,11,0,0.25,"H3","H0"),
|
|
|
221 list("[M-2H+NH4]-",1,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"),
|
|
|
222 list("[2M-2H+NH4]-",2,-1,16.019272654000001665,12,0,0.0,"N1H4","H2"),
|
|
|
223 list("[3M-2H+NH4]-",3,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"),
|
|
|
224 list("[M+NH4]+",1,1,18.033825558000000199,13,1,1.0,"N1H4","H0"),
|
|
|
225 list("[2M+NH4]+",2,1,18.033825558000000199,13,0,0.5,"N1H4","H0"),
|
|
|
226 list("[3M+NH4]+",3,1,18.033825558000000199,13,0,0.25,"N1H4","H0"),
|
|
|
227 list("[M+H+NH4]2+",1,2,19.041102009999999467,14,0,0.5,"N1H5","H0"),
|
|
|
228 list("[2M+H+NH4]2+",2,2,19.041102009999999467,14,0,0.5,"N1H5","H0"),
|
|
|
229 list("[3M+H+NH4]2+",3,2,19.041102009999999467,14,0,0.25,"N1H5","H0"),
|
|
|
230 list("[M+Na-2H]-",1,-1,20.974668176000001551,15,0,0.75,"Na1","H2"),
|
|
|
231 list("[2M-2H+Na]-",2,-1,20.974668176000001551,15,0,0.25,"Na1","H2"),
|
|
|
232 list("[3M-2H+Na]-",3,-1,20.974668176000001551,15,0,0.25,"Na1","H2"),
|
|
|
233 list("[M+Na]+",1,1,22.989221080000000086,16,1,1.0,"Na1","H0"),
|
|
|
234 list("[2M+Na]+",2,1,22.989221080000000086,16,0,0.5,"Na1","H0"),
|
|
|
235 list("[3M+Na]+",3,1,22.989221080000000086,16,0,0.25,"Na1","H0"),
|
|
|
236 list("[M+H+Na]2+",1,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"),
|
|
|
237 list("[2M+H+Na]2+",2,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"),
|
|
|
238 list("[3M+H+Na]2+",3,2,23.996497531999999353,17,0,0.25,"Na1H1","H0"),
|
|
|
239 list("[M+2H+Na]3+",1,3,25.003773983999998619,18,0,0.25,"H2Na1","H0"),
|
|
|
240 list("[M+CH3OH+H]+",1,1,33.033491200000000276,19,0,0.25,"C1O1H5","H0"),
|
|
|
241 list("[M-H+Cl]2-",1,-2,33.962124838000001148,20,0,1.0,"Cl1","H1"),
|
|
|
242 list("[2M-H+Cl]2-",2,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"),
|
|
|
243 list("[3M-H+Cl]2-",3,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"),
|
|
|
244 list("[M+Cl]-",1,-1,34.969401290000000416,21,1,1.0,"Cl1","H0"),
|
|
|
245 list("[2M+Cl]-",2,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"),
|
|
|
246 list("[3M+Cl]-",3,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"),
|
|
|
247 list("[M+K-2H]-",1,-1,36.948605415999999479,22,0,0.5,"K1","H2"),
|
|
|
248 list("[2M-2H+K]-",2,-1,36.948605415999999479,22,0,0.0,"K1","H2"),
|
|
|
249 list("[3M-2H+K]-",3,-1,36.948605415999999479,22,0,0.0,"K1","H2"),
|
|
|
250 list("[M+K]+",1,1,38.963158319999998013,23,1,1.0,"K1","H0"),
|
|
|
251 list("[2M+K]+",2,1,38.963158319999998013,23,0,0.5,"K1","H0"),
|
|
|
252 list("[3M+K]+",3,1,38.963158319999998013,23,0,0.25,"K1","H0"),
|
|
|
253 list("[M+H+K]2+",1,2,39.970434771999997281,24,0,0.5,"K1H1","H0"),
|
|
|
254 list("[2M+H+K]2+",2,2,39.970434771999997281,24,0,0.5,"K1H1","H0"),
|
|
|
255 list("[3M+H+K]2+",3,2,39.970434771999997281,24,0,0.25,"K1H1","H0"),
|
|
|
256 list("[M+ACN+H]+",1,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"),
|
|
|
257 list("[2M+ACN+H]+",2,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"),
|
|
|
258 list("[M+2Na-H]+",1,1,44.971165708000000902,26,0,0.5,"Na2","H1"),
|
|
|
259 list("[2M+2Na-H]+",2,1,44.971165708000000902,26,0,0.25,"Na2","H1"),
|
|
|
260 list("[3M+2Na-H]+",3,1,44.971165708000000902,26,0,0.25,"Na2","H1"),
|
|
|
261 list("[2M+FA-H]-",2,-1,44.998202851999998586,27,0,0.25,"C1O2H2","H1"),
|
|
|
262 list("[M+FA-H]-",1,-1,44.998202851999998586,27,0,0.5,"C1O2H2","H1"),
|
|
|
263 list("[M+2Na]2+",1,2,45.978442160000000172,28,0,0.5,"Na2","H0"),
|
|
|
264 list("[2M+2Na]2+",2,2,45.978442160000000172,28,0,0.5,"Na2","H0"),
|
|
|
265 list("[3M+2Na]2+",3,2,45.978442160000000172,28,0,0.25,"Na2","H0"),
|
|
|
266 list("[M+H+2Na]3+",1,3,46.985718611999999438,29,0,0.25,"H1Na2","H0"),
|
|
|
267 list("[M+H+FA]+",1,1,47.012755755999997122,30,0,0.25,"C1O2H3","H0"),
|
|
|
268 list("[M+Hac-H]-",1,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"),
|
|
|
269 list("[2M+Hac-H]-",2,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"),
|
|
|
270 list("[M+IsoProp+H]+",1,1,61.064791327999998317,32,0,0.25,"C3H9O1","H0"),
|
|
|
271 list("[M+Na+K]2+",1,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"),
|
|
|
272 list("[2M+Na+K]2+",2,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"),
|
|
|
273 list("[3M+Na+K]2+",3,2,61.9523793999999981,33,0,0.25,"Na1K1","H0"),
|
|
|
274 list("[M+NO3]-",1,-1,61.988366450000000895,34,0,0.5,"N1O3","H0"),
|
|
|
275 list("[M+ACN+Na]+",1,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"),
|
|
|
276 list("[2M+ACN+Na]+",2,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"),
|
|
|
277 list("[M+NH4+FA]+",1,1,64.039304861999994502,36,0,0.25,"N1C1O2H6","H0"),
|
|
|
278 list("[M-2H+Na+FA]-",1,-1,66.980147479999999405,37,0,0.5,"NaC1O2H2","H2"),
|
|
|
279 list("[M+3Na]3+",1,3,68.967663239999993153,38,0,0.25,"Na3","H0"),
|
|
|
280 list("[M+Na+FA]+",1,1,68.99470038399999794,39,0,0.25,"Na1C1O2H2","H0"),
|
|
|
281 list("[M+2Cl]2-",1,-2,69.938802580000000832,40,0,1.0,"Cl2","H0"),
|
|
|
282 list("[2M+2Cl]2-",2,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"),
|
|
|
283 list("[3M+2Cl]2-",3,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"),
|
|
|
284 list("[M+2K-H]+",1,1,76.919040187999996758,41,0,0.5,"K2","H1"),
|
|
|
285 list("[2M+2K-H]+",2,1,76.919040187999996758,41,0,0.25,"K2","H1"),
|
|
|
286 list("[3M+2K-H]+",3,1,76.919040187999996758,41,0,0.25,"K2","H1"),
|
|
|
287 list("[M+2K]2+",1,2,77.926316639999996028,42,0,0.5,"K2","H0"),
|
|
|
288 list("[2M+2K]2+",2,2,77.926316639999996028,42,0,0.5,"K2","H0"),
|
|
|
289 list("[3M+2K]2+",3,2,77.926316639999996028,42,0,0.25,"K2","H0"),
|
|
|
290 list("[M+Br]-",1,-1,78.918886479999997619,43,1,1.0,"Br1","H0"),
|
|
|
291 list("[M+Cl+FA]-",1,-1,80.974880593999998268,44,0,0.5,"Cl1C1O2H2","H0"),
|
|
|
292 list("[M+AcNa-H]-",1,-1,80.995797543999998426,45,0,0.25,"C2H3Na1O2","H1"),
|
|
|
293 list("[M+2ACN+2H]2+",1,2,84.067651115999993292,46,0,0.25,"C4H8N2","H0"),
|
|
|
294 list("[M+K+FA]+",1,1,84.968637623999995868,47,0,0.25,"K1C1O2H2","H0"),
|
|
|
295 list("[M+Cl+Na+FA-H]-",1,-1,102.95682522200000619,48,0,0.5,"Cl1Na1C1O2H2","H1"),
|
|
|
296 list("[2M+3H2O+2H]+",2,1,104.03153939599999944,49,0,0.25,"H8O6","H0"),
|
|
|
297 list("[M+TFA-H]-",1,-1,112.98558742000000165,50,0,0.5,"C2F3O2H1","H1"),
|
|
|
298 list("[M+H+TFA]+",1,1,115.00014032400000019,51,0,0.25,"C2F3O2H2","H0"),
|
|
|
299 list("[M+3ACN+2H]2+",1,2,125.09420022199999778,52,0,0.25,"C6H11N3","H0"),
|
|
|
300 list("[M+NH4+TFA]+",1,1,132.02668943000000468,53,0,0.25,"N1C2F3O2H5","H0"),
|
|
|
301 list("[M+Na+TFA]+",1,1,136.98208495200000811,54,0,0.25,"Na1C2F3O2H1","H0"),
|
|
|
302 list("[M+Cl+TFA]-",1,-1,148.96226516199999423,55,0,0.5,"Cl1C2F3O2H1","H0"),
|
|
|
303 list("[M+K+TFA]+",1,1,152.95602219200000604,56,0,0.25,"K1C2F3O2H1","H0")
|
|
|
304 )
|
|
|
305 dummy_adduct <- orm$adduct()
|
|
|
306 for (adduct in adducts) {
|
|
|
307 i <- 0
|
|
|
308 dummy_adduct$set_name(adduct[[i <- i+1]])
|
|
|
309 dummy_adduct$set_multi(adduct[[i <- i+1]])
|
|
|
310 dummy_adduct$set_charge(adduct[[i <- i+1]])
|
|
|
311 dummy_adduct$set_mass(adduct[[i <- i+1]])
|
|
|
312 dummy_adduct$set_oidscore(adduct[[i <- i+1]])
|
|
|
313 dummy_adduct$set_quasi(adduct[[i <- i+1]])
|
|
|
314 dummy_adduct$set_ips(adduct[[i <- i+1]])
|
|
|
315 dummy_adduct$set_formula_add(adduct[[i <- i+1]])
|
|
|
316 dummy_adduct$set_formula_ded(adduct[[i <- i+1]])
|
|
11
|
317 invisible(dummy_adduct$save())
|
|
0
|
318 dummy_adduct$clear(unset_id=TRUE)
|
|
|
319 }
|
|
|
320 message("Adducts created")
|
|
|
321 }
|
|
|
322
|
|
|
323 insert_base_data <- function(orm, path, archetype=FALSE) {
|
|
|
324 if (archetype) {
|
|
|
325 ## not implemented yet
|
|
|
326 return ()
|
|
|
327 }
|
|
|
328 base_data <- readLines(path)
|
|
|
329 for (sql in strsplit(paste(base_data, collapse=" "), ";")[[1]]) {
|
|
|
330 orm$execute(sql)
|
|
|
331 }
|
|
|
332 set_database_version(orm, "enriched")
|
|
|
333 }
|
|
|
334
|
|
|
335 insert_compounds <- function(orm, compounds_path) {
|
|
|
336 compounds <- read.csv(file=compounds_path, sep="\t")
|
|
|
337 if (is.null(compounds <- translate_compounds(compounds))) {
|
|
|
338 stop("Could not find asked compound's attributes in csv file.")
|
|
|
339 }
|
|
|
340 dummy_compound <- orm$compound()
|
|
|
341 compound_list <- list()
|
|
|
342 for (i in seq_len(nrow(compounds))) {
|
|
|
343 dummy_compound$set_mz(compounds[i, "mz"])
|
|
|
344 dummy_compound$set_name(compounds[i, "name"])
|
|
|
345 dummy_compound$set_common_name(compounds[i, "common_name"])
|
|
|
346 dummy_compound$set_formula(compounds[i, "formula"])
|
|
|
347 compound_list[[length(compound_list)+1]] <- as.list(
|
|
|
348 dummy_compound,
|
|
|
349 c("mz", "name", "common_name", "formula")
|
|
|
350 )
|
|
|
351 dummy_compound$clear(unset_id=TRUE)
|
|
|
352 }
|
|
11
|
353 invisible(dummy_compound$save(bulk=compound_list))
|
|
0
|
354 }
|
|
|
355
|
|
|
356 translate_compounds <- function(compounds) {
|
|
|
357 recognized_headers <- list(
|
|
|
358 c("HMDB_ID", "MzBank", "X.M.H..", "X.M.H...1", "MetName", "ChemFormula", "INChIkey")
|
|
|
359 )
|
|
|
360 header_translators <- list(
|
|
|
361 hmdb_header_translator
|
|
|
362 )
|
|
|
363 for (index in seq_along(recognized_headers)) {
|
|
|
364 headers <- recognized_headers[[index]]
|
|
|
365 if (identical(colnames(compounds), headers)) {
|
|
|
366 return (header_translators[[index]](compounds))
|
|
|
367 }
|
|
|
368 }
|
|
|
369 if (is.null(translator <- guess_translator(colnames(compounds)))) {
|
|
|
370 return (NULL)
|
|
|
371 }
|
|
|
372 return (csv_header_translator(translator, compounds))
|
|
|
373 }
|
|
|
374
|
|
|
375 guess_translator <- function(header) {
|
|
|
376 result <- list(
|
|
11
|
377 # HMDB_ID=NULL,
|
|
0
|
378 mz=NULL,
|
|
|
379 name=NULL,
|
|
|
380 common_name=NULL,
|
|
|
381 formula=NULL,
|
|
|
382 # inchi_key=NULL
|
|
|
383 )
|
|
|
384 asked_cols <- names(result)
|
|
|
385 for (asked_col in asked_cols) {
|
|
|
386 for (col in header) {
|
|
|
387 if ((twisted <- tolower(col)) == asked_col
|
|
|
388 || gsub("-", "_", twisted) == asked_col
|
|
|
389 || gsub(" ", "_", twisted) == asked_col
|
|
|
390 || tolower(gsub("(.)([A-Z])", "\\1_\\2", col)) == asked_col
|
|
|
391 ) {
|
|
|
392 result[[asked_col]] <- col
|
|
|
393 next
|
|
|
394 }
|
|
|
395 }
|
|
|
396 }
|
|
|
397 if (any(mapply(is.null, result))) {
|
|
|
398 return (NULL)
|
|
|
399 }
|
|
|
400 return (result)
|
|
|
401 }
|
|
|
402
|
|
|
403 hmdb_header_translator <- function(compounds) {
|
|
|
404 return (csv_header_translator(
|
|
|
405 list(
|
|
|
406 HMDB_ID="HMDB_ID",
|
|
|
407 mz="MzBank",
|
|
|
408 name="MetName",
|
|
|
409 common_name="MetName",
|
|
|
410 formula="ChemFormula",
|
|
|
411 inchi_key="INChIkey"
|
|
|
412 ), compounds
|
|
|
413 ))
|
|
|
414 }
|
|
|
415
|
|
|
416 csv_header_translator <- function(translation_table, csv) {
|
|
|
417 header_names <- names(translation_table)
|
|
|
418 result <- data.frame(1:nrow(csv))
|
|
|
419 for (i in seq_along(header_names)) {
|
|
|
420 result[, header_names[[i]]] <- csv[, translation_table[[i]]]
|
|
|
421 }
|
|
|
422 result[, "mz"] <- as.numeric(result[, "mz"])
|
|
|
423 return (result)
|
|
|
424 }
|
|
|
425
|
|
|
426 set_database_version <- function(orm, version) {
|
|
|
427 orm$set_tag(
|
|
|
428 version,
|
|
|
429 tag_name="database_version",
|
|
|
430 tag_table_name="XSeeker_tagging_table"
|
|
|
431 )
|
|
|
432 }
|
|
|
433
|
|
|
434 process_rdata <- function(orm, rdata, options) {
|
|
|
435 mzml_tmp_dir <- gather_mzml_files(rdata)
|
|
|
436 samples <- names(rdata$singlefile)
|
|
|
437 if (!is.null(options$samples)) {
|
|
|
438 samples <- samples[options$samples %in% samples]
|
|
|
439 }
|
|
|
440 show_percent <- (
|
|
|
441 is.null(options$`not-show-percent`)
|
|
|
442 || options$`not-show-percent` == FALSE
|
|
|
443 )
|
|
|
444 error <- tryCatch({
|
|
|
445 process_sample_list(
|
|
|
446 orm, rdata, samples,
|
|
|
447 show_percent=show_percent
|
|
|
448 )
|
|
|
449 NULL
|
|
|
450 }, error=function(e) {
|
|
|
451 message(e)
|
|
|
452 e
|
|
|
453 })
|
|
|
454 if (!is.null(mzml_tmp_dir)) {
|
|
|
455 unlink(mzml_tmp_dir, recursive=TRUE)
|
|
|
456 }
|
|
|
457 if (!is.null(error)) {
|
|
|
458 stop(error)
|
|
|
459 }
|
|
|
460 }
|
|
|
461
|
|
|
462 gather_mzml_files <- function(rdata) {
|
|
|
463 if (is.null(rdata$singlefile)) {
|
|
|
464 message("Extracting mxml files")
|
|
|
465 tmp <- tempdir()
|
|
|
466 rdata$singlefile <- utils::unzip(rdata$zipfile, exdir=tmp)
|
|
|
467 names(rdata$singlefile) <- tools::file_path_sans_ext(basename(rdata$singlefile))
|
|
|
468 message("Extracted")
|
|
|
469 return (tmp)
|
|
|
470 } else {
|
|
|
471 message(sprintf("Not a zip file, loading files directly from path: %s", paste(rdata$singlefile, collapse=" ; ")))
|
|
|
472 }
|
|
|
473 return (NULL)
|
|
|
474 }
|
|
|
475
|
|
|
476 process_sample_list <- function(orm, radta, sample_names, show_percent) {
|
|
|
477 file_grouping_var <- find_grouping_var(rdata$variableMetadata)
|
|
|
478 message("Processing samples.")
|
|
|
479 message(sprintf("File grouping variable: %s", file_grouping_var))
|
|
|
480 if(is.null(file_grouping_var)) {
|
|
|
481 stop("Malformed variableMetada.")
|
|
|
482 }
|
|
|
483
|
|
11
|
484 context <- new.env()
|
|
|
485 context$samples <- list()
|
|
|
486 context$peaks <- rdata$xa@xcmsSet@peaks
|
|
|
487 context$groupidx <- rdata$xa@xcmsSet@groupidx
|
|
|
488 xcms_set <- rdata$xa@xcmsSet
|
|
|
489 singlefile <- rdata$singlefile
|
|
0
|
490 process_arg_list <- rdata$listOFlistArguments
|
|
11
|
491 var_meta <- rdata$variableMetadata
|
|
|
492
|
|
0
|
493 process_params <- list()
|
|
12
|
494 if (is.null(process_arg_list)) {
|
|
|
495 histories <- list()
|
|
|
496 for (history in xcms_set@.processHistory) {
|
|
|
497 if (
|
|
|
498 class(history@param) == "CentWaveParam"
|
|
|
499 && history@type == "Peak detection"
|
|
|
500 ) {
|
|
|
501 params <- history@param
|
|
|
502 process_params <- list(list(
|
|
|
503 xfunction="annotatediff",
|
|
|
504 ppm=params@ppm,
|
|
|
505 peakwidth=sprintf("%s - %s", params@peakwidth[[1]], params@peakwidth[[2]]),
|
|
|
506 snthresh=params@snthresh,
|
|
|
507 prefilterStep=params@prefilter[[1]],
|
|
|
508 prefilterLevel=params@prefilter[[2]],
|
|
|
509 mzdiff=params@mzdiff,
|
|
|
510 fitgauss=params@fitgauss,
|
|
|
511 noise=params@noise,
|
|
|
512 mzCenterFun=params@mzCenterFun,
|
|
|
513 integrate=params@integrate,
|
|
|
514 firstBaselineCheck=params@firstBaselineCheck,
|
|
|
515 snthreshIsoROIs=!identical(params@roiScales, numeric(0))
|
|
|
516 ))
|
|
|
517 break
|
|
|
518 }
|
|
0
|
519 }
|
|
12
|
520 } else {
|
|
|
521 for (list_name in names(process_arg_list)) {
|
|
|
522 param_list <- list()
|
|
|
523 for (param_name in names(process_arg_list[[list_name]])) {
|
|
|
524 param_list[[param_name]] <- process_arg_list[[list_name]][[param_name]]
|
|
|
525 }
|
|
|
526 process_params[[length(process_params)+1]] <- param_list
|
|
|
527 }
|
|
0
|
528 }
|
|
12
|
529
|
|
0
|
530 message("Parameters from previous processes extracted.")
|
|
|
531
|
|
|
532
|
|
|
533 indices <- as.numeric(unique(var_meta[, file_grouping_var]))
|
|
|
534 smol_xcms_set <- orm$smol_xcms_set()
|
|
|
535 mz_tab_info <- new.env()
|
|
|
536 g <- xcms::groups(xcms_set)
|
|
|
537 mz_tab_info$group_length <- nrow(g)
|
|
|
538 mz_tab_info$dataset_path <- xcms::filepaths(xcms_set)
|
|
|
539 mz_tab_info$sampnames <- xcms::sampnames(xcms_set)
|
|
|
540 mz_tab_info$sampclass <- xcms::sampclass(xcms_set)
|
|
|
541 mz_tab_info$rtmed <- g[,"rtmed"]
|
|
|
542 mz_tab_info$mzmed <- g[,"mzmed"]
|
|
|
543 mz_tab_info$smallmolecule_abundance_assay <- xcms::groupval(xcms_set, value="into")
|
|
|
544 blogified <- blob::blob(fst::compress_fst(serialize(mz_tab_info, NULL), compression=100))
|
|
11
|
545 rm(mz_tab_info)
|
|
|
546
|
|
|
547 invisible(smol_xcms_set$set_raw(blogified)$save())
|
|
|
548 smol_xcms_set_id <- smol_xcms_set$get_id()
|
|
|
549 rm(smol_xcms_set)
|
|
|
550
|
|
0
|
551 for (no in indices) {
|
|
11
|
552 sample_name <- names(singlefile)[[no]]
|
|
|
553 sample_path <- singlefile[[no]]
|
|
0
|
554 if (
|
|
|
555 is.na(no)
|
|
|
556 || is.null(sample_path)
|
|
|
557 || !(sample_name %in% sample_names)
|
|
|
558 ) {
|
|
|
559 next
|
|
|
560 }
|
|
|
561 env <- new.env()
|
|
11
|
562
|
|
14
|
563 if (!DEBUG_FAST_IGNORE_SLOW_OP) {
|
|
|
564 ms_file <- xcms::xcmsRaw(sample_path)
|
|
|
565 env$tic <- ms_file@tic
|
|
|
566 env$mz <- ms_file@env$mz
|
|
|
567 env$scanindex <- ms_file@scanindex
|
|
|
568 env$scantime <- ms_file@scantime * 60
|
|
|
569 env$intensity <- ms_file@env$intensity
|
|
|
570 env$polarity <- as.character(ms_file@polarity[[1]])
|
|
11
|
571
|
|
14
|
572 ## Again, ms file is huge, so we get rid of it quickly.
|
|
|
573 rm(ms_file)
|
|
|
574
|
|
|
575 }
|
|
0
|
576 env$sample_name <- sample_name
|
|
|
577 env$dataset_path <- sample_path
|
|
|
578 env$process_params <- process_params
|
|
|
579 env$enriched_rdata <- TRUE
|
|
|
580 env$enriched_rdata_version <- ENRICHED_RDATA_VERSION
|
|
|
581 env$tool_name <- TOOL_NAME
|
|
|
582 env$enriched_rdata_doc <- ENRICHED_RDATA_DOC
|
|
14
|
583
|
|
11
|
584 sample <- add_sample_to_database(orm, env, context, smol_xcms_set_id)
|
|
|
585 rm (env)
|
|
|
586 context$samples[no] <- sample$get_id()
|
|
|
587 rm (sample)
|
|
0
|
588 }
|
|
11
|
589 context$clusters <- list()
|
|
|
590 context$show_percent <- show_percent
|
|
|
591 context$cluster_mean_rt_abundance <- list()
|
|
|
592 context$central_feature <- list()
|
|
12
|
593 context$adducts <- list()
|
|
11
|
594 load_variable_metadata(orm, var_meta, context)
|
|
|
595 clusters <- context$clusters
|
|
|
596 rm(context)
|
|
0
|
597 message("Features enrichment")
|
|
11
|
598 complete_features(orm, clusters, show_percent)
|
|
0
|
599 message("Features enrichment done.")
|
|
|
600 return (NULL)
|
|
|
601 }
|
|
|
602
|
|
|
603 find_grouping_var <- function(var_meta) {
|
|
6
|
604 known_colnames = c(
|
|
|
605 "name", "namecustom", "mz", "mzmin", "mzmax",
|
|
|
606 "rt", "rtmin", "rtmax", "npeaks", "isotopes", "adduct", "pcgroup"
|
|
|
607 )
|
|
|
608 col_names <- colnames(var_meta)
|
|
|
609 classes = list()
|
|
|
610 for (name in col_names) {
|
|
|
611 if (!(name %in% known_colnames)) {
|
|
|
612 classes[[length(classes)+1]] = name
|
|
0
|
613 }
|
|
|
614 }
|
|
6
|
615 if (length(classes) > 1) {
|
|
|
616 stop(sprintf("Only one class expected in the variable metadata. Found %d .", length(classes)))
|
|
|
617 }
|
|
7
|
618 if (length(classes) == 0) {
|
|
6
|
619 stop("Could not find any class column in your variableMetadata.")
|
|
|
620 }
|
|
|
621 return (classes[[1]])
|
|
0
|
622 }
|
|
|
623
|
|
11
|
624 add_sample_to_database <- function(orm, env, context, smol_xcms_set_id) {
|
|
0
|
625 message(sprintf("Processing sample %s", env$sample_name))
|
|
|
626 sample <- (
|
|
|
627 orm$sample()
|
|
|
628 $set_name(env$sample_name)
|
|
|
629 $set_path(env$dataset_path)
|
|
|
630 $set_kind("enriched_rdata")
|
|
|
631 $set_polarity(
|
|
|
632 if (is.null(env$polarity) || identical(env$polarity, character(0))) ""
|
|
|
633 else env$polarity
|
|
|
634 )
|
|
|
635 $set_raw(blob::blob(fst::compress_fst(
|
|
|
636 serialize(env, NULL),
|
|
|
637 compression=100
|
|
|
638 )))
|
|
|
639 )
|
|
11
|
640 sample[["smol_xcms_set_id"]] <- smol_xcms_set_id
|
|
|
641 sample$modified__[["smol_xcms_set_id"]] <- smol_xcms_set_id
|
|
|
642 sample <- sample$save()
|
|
0
|
643 load_process_params(orm, sample, env$process_params)
|
|
|
644 message(sprintf("Sample %s inserted.", env$sample_name))
|
|
|
645 return (sample)
|
|
|
646 }
|
|
|
647
|
|
|
648
|
|
11
|
649 load_variable_metadata <- function(orm, var_meta, context) {
|
|
0
|
650 all_clusters <- orm$cluster()$all()
|
|
|
651
|
|
11
|
652 next_feature_id <- get_next_id(orm$feature()$all(), "featureID") + 1
|
|
|
653 next_cluster_id <- 0
|
|
0
|
654 next_pc_group <- get_next_id(all_clusters, "pc_group")
|
|
11
|
655 next_align_group <- get_next_id(all_clusters, "align_group") + 1
|
|
0
|
656 message("Extracting features")
|
|
|
657 invisible(create_features(
|
|
11
|
658 orm, var_meta, context,
|
|
0
|
659 next_feature_id, next_cluster_id,
|
|
|
660 next_pc_group, next_align_group
|
|
|
661 ))
|
|
|
662 message("Extracting features done.")
|
|
|
663 return (NULL)
|
|
|
664 }
|
|
|
665
|
|
|
666 get_next_id <- function(models, attribute) {
|
|
|
667 if ((id <- models$max(attribute)) == Inf || id == -Inf) {
|
|
11
|
668 return (0)
|
|
0
|
669 }
|
|
11
|
670 return (id)
|
|
0
|
671 }
|
|
|
672
|
|
|
673 create_features <- function(
|
|
11
|
674 orm, var_meta, context,
|
|
0
|
675 next_feature_id, next_cluster_id,
|
|
|
676 next_pc_group, next_align_group
|
|
|
677 ) {
|
|
|
678 field_names <- as.list(names(orm$feature()$fields__))
|
|
|
679 field_names[field_names=="id"] <- NULL
|
|
|
680
|
|
|
681 features <- list()
|
|
|
682 dummy_feature <- orm$feature()
|
|
|
683
|
|
|
684 if (show_percent <- context$show_percent) {
|
|
|
685 percent <- -1
|
|
|
686 total <- nrow(var_meta)
|
|
|
687 }
|
|
14
|
688 rows <- seq_len(nrow(var_meta))
|
|
|
689 if (PROCESS_SMOL_BATCH) {
|
|
|
690
|
|
|
691 rows <- rows[1:as.integer(FAST_FEATURE_RATIO/100.0 * length(rows))]
|
|
|
692 }
|
|
|
693 cluster_row <- list()
|
|
|
694 for (row in rows) {
|
|
0
|
695 if (show_percent && (row / total) * 100 > percent) {
|
|
|
696 percent <- percent + 1
|
|
|
697 message("\r", sprintf("\r%d %%", percent), appendLF=FALSE)
|
|
|
698 }
|
|
|
699
|
|
11
|
700 dummy_feature$set_featureID(next_feature_id)
|
|
|
701 next_feature_id <- next_feature_id + 1
|
|
14
|
702
|
|
|
703 curent_var_meta <- var_meta[row, ]
|
|
|
704 set_feature_fields_from_var_meta(dummy_feature, curent_var_meta)
|
|
11
|
705 fake_iso <- dummy_feature$get_iso()
|
|
|
706 iso <- extract_iso(fake_iso)
|
|
|
707 clusterID <- extract_clusterID(fake_iso, next_cluster_id)
|
|
|
708 context$clusterID <- clusterID
|
|
|
709 dummy_feature$set_iso(iso)
|
|
|
710
|
|
0
|
711 peak_list <- context$peaks[context$groupidx[[row]], ]
|
|
10
|
712 if (! ("matrix" %in% class(peak_list))) {
|
|
|
713 peak_list <- matrix(peak_list, nrow=1, ncol=length(peak_list), dimnames=list(c(), names(peak_list)))
|
|
|
714 }
|
|
11
|
715
|
|
|
716 clusterID <- as.character(clusterID)
|
|
|
717 if (is.null(context$central_feature[[clusterID]])) {
|
|
|
718 int_o <- extract_peak_var(peak_list, "into")
|
|
|
719 context$central_feature[[clusterID]] <- (
|
|
|
720 peak_list[peak_list[, "into"] == int_o,]["sample"]
|
|
|
721 )
|
|
|
722 }
|
|
|
723
|
|
14
|
724 if (!DEBUG_FAST_IGNORE_SLOW_OP) {
|
|
|
725 sample_peak_list <- peak_list[as.integer(peak_list[, "sample"]) == context$central_feature[[clusterID]], , drop=FALSE]
|
|
|
726 if (!identical(sample_peak_list, numeric(0)) && !is.null(nrow(sample_peak_list)) && nrow(sample_peak_list) != 0) {
|
|
|
727 if (!is.na(int_o <- extract_peak_var(sample_peak_list, "into"))) {
|
|
|
728 dummy_feature$set_int_o(int_o)
|
|
|
729 }
|
|
|
730 if (!is.na(int_b <- extract_peak_var(sample_peak_list, "intb"))) {
|
|
|
731 dummy_feature$set_int_b(int_b)
|
|
|
732 }
|
|
|
733 if (!is.na(max_o <- extract_peak_var(sample_peak_list, "maxo"))) {
|
|
|
734 dummy_feature$set_max_o(max_o)
|
|
|
735 }
|
|
0
|
736 }
|
|
|
737 }
|
|
14
|
738
|
|
|
739 cluster_row[[row]] <- create_associated_cluster(
|
|
12
|
740 orm,
|
|
14
|
741 context$samples[context$central_feature[[clusterID]]][[1]],
|
|
11
|
742 dummy_feature, clusterID,
|
|
0
|
743 context, curent_var_meta, next_pc_group,
|
|
|
744 next_align_group
|
|
|
745 )
|
|
|
746 next_align_group <- next_align_group + 1
|
|
|
747 features[[length(features)+1]] <- as.list(dummy_feature, field_names)
|
|
|
748 dummy_feature$clear()
|
|
|
749 }
|
|
14
|
750 rm(var_meta)
|
|
|
751 message("")
|
|
0
|
752 message("Saving features")
|
|
11
|
753 invisible(dummy_feature$save(bulk=features))
|
|
14
|
754
|
|
|
755 ## We link manually clusters to the sample they're in.
|
|
|
756 link_cache <- list()
|
|
|
757 for (row in rows) {
|
|
|
758 sample_nos <- unique(context$peaks[context$groupidx[[row]], "sample"])
|
|
|
759 for (sample_id in context$samples[sample_nos]) {
|
|
|
760 cluster_id <- cluster_row[[row]]$get_id()
|
|
|
761 if (is.null(link_cache[[id <- paste(sample_id, cluster_id, sep=";")]])) {
|
|
|
762 link_cache[[id]] <- 1
|
|
|
763 orm$cluster_sample(
|
|
|
764 sample_id=sample_id,
|
|
|
765 cluster_id=cluster_id
|
|
|
766 )$save()
|
|
|
767 }
|
|
|
768 }
|
|
|
769 }
|
|
|
770
|
|
0
|
771 message("Saved.")
|
|
|
772 return (context$clusters)
|
|
|
773 }
|
|
|
774
|
|
|
775 extract_peak_var <- function(peak_list, var_name, selector=max) {
|
|
|
776 value <- peak_list[, var_name]
|
|
|
777 names(value) <- NULL
|
|
|
778 return (selector(value))
|
|
|
779 }
|
|
|
780
|
|
|
781 set_feature_fields_from_var_meta <- function(feature, var_meta) {
|
|
|
782 if (!is.null(mz <- var_meta[["mz"]]) && !is.na(mz)) {
|
|
|
783 feature$set_mz(mz)
|
|
|
784 }
|
|
|
785 if (!is.null(mzmin <- var_meta[["mzmin"]]) && !is.na(mzmin)) {
|
|
|
786 feature$set_mz_min(mzmin)
|
|
|
787 }
|
|
|
788 if (!is.null(mzmax <- var_meta[["mzmax"]]) && !is.na(mzmax)) {
|
|
|
789 feature$set_mz_max(mzmax)
|
|
|
790 }
|
|
|
791 if (!is.null(rt <- var_meta[["rt"]]) && !is.na(rt)) {
|
|
|
792 feature$set_rt(rt)
|
|
|
793 }
|
|
|
794 if (!is.null(rtmin <- var_meta[["rtmin"]]) && !is.na(rtmin)) {
|
|
|
795 feature$set_rt_min(rtmin)
|
|
|
796 }
|
|
|
797 if (!is.null(rtmax <- var_meta[["rtmax"]]) && !is.na(rtmax)) {
|
|
|
798 feature$set_rt_max(rtmax)
|
|
|
799 }
|
|
|
800 if (!is.null(isotopes <- var_meta[["isotopes"]]) && !is.na(isotopes)) {
|
|
|
801 feature$set_iso(isotopes)
|
|
|
802 }
|
|
|
803 return (feature)
|
|
|
804 }
|
|
|
805
|
|
|
806 extract_iso <- function(weird_data) {
|
|
|
807 if (grepl("^\\[\\d+\\]", weird_data)[[1]]) {
|
|
|
808 return (sub("^\\[\\d+\\]", "", weird_data, perl=TRUE))
|
|
|
809 }
|
|
|
810 return (weird_data)
|
|
|
811 }
|
|
|
812
|
|
|
813 extract_clusterID <- function(weird_data, next_cluster_id){
|
|
|
814 if (grepl("^\\[\\d+\\]", weird_data)[[1]]) {
|
|
|
815 clusterID <- stringr::str_extract(weird_data, "^\\[\\d+\\]")
|
|
|
816 clusterID <- as.numeric(stringr::str_extract(clusterID, "\\d+"))
|
|
|
817 } else {
|
|
|
818 clusterID <- 0
|
|
|
819 }
|
|
|
820 return (clusterID + next_cluster_id)
|
|
|
821 }
|
|
|
822
|
|
|
823 create_associated_cluster <- function(
|
|
12
|
824 orm,
|
|
14
|
825 main_sample_id, feature, clusterID,
|
|
0
|
826 context, curent_var_meta, next_pc_group, next_align_group
|
|
|
827 ) {
|
|
11
|
828 clusterID <- as.character(clusterID)
|
|
|
829 if (is.null(cluster <- context$clusters[[clusterID]])) {
|
|
12
|
830 pcgroup <- as.numeric(curent_var_meta[["pcgroup"]])
|
|
|
831 adduct_name <- as.character(curent_var_meta[["adduct"]])
|
|
|
832 annotation <- curent_var_meta[["isotopes"]]
|
|
11
|
833 cluster <- context$clusters[[clusterID]] <- orm$cluster(
|
|
0
|
834 pc_group=pcgroup + next_pc_group,
|
|
12
|
835 # adduct=adduct,
|
|
0
|
836 align_group=next_align_group,
|
|
|
837 # curent_group=curent_group,
|
|
|
838 clusterID=context$clusterID,
|
|
|
839 annotation=annotation
|
|
11
|
840 )
|
|
12
|
841 if (is.null(adduct <- context$adducts[[adduct_name]])) {
|
|
|
842 context$adducts[[adduct_name]] <- orm$adduct()$load_by(name=adduct_name)$first()
|
|
|
843 if (is.null(adduct <- context$adducts[[adduct_name]])) {
|
|
|
844 adduct <- context$adducts[[adduct_name]] <- orm$adduct(name=adduct_name, charge=0)
|
|
|
845 adduct$save()
|
|
|
846 }
|
|
|
847 }
|
|
|
848 cluster$set_adduct(adduct)
|
|
11
|
849 ## Crappy hack to assign sample id to cluster without loading the sample.
|
|
|
850 ## Samples are too big (their sample$env) and slows the process, and eat all the menory
|
|
|
851 ## so we dont't want to load them.
|
|
14
|
852 cluster[["sample_id"]] <- main_sample_id
|
|
|
853 cluster$modified__[["sample_id"]] <- main_sample_id
|
|
0
|
854 } else {
|
|
|
855 if (context$clusterID != 0 && cluster$get_clusterID() == 0) {
|
|
|
856 cluster$set_clusterID(context$clusterID)
|
|
|
857 }
|
|
|
858 }
|
|
|
859 cluster$save()
|
|
|
860 feature$set_cluster(cluster)
|
|
14
|
861 return (cluster)
|
|
0
|
862 }
|
|
|
863
|
|
11
|
864 complete_features <- function(orm, clusters, show_percent) {
|
|
|
865 total <- length(clusters)
|
|
|
866 percent <- -1
|
|
|
867 i <- 0
|
|
|
868 for (cluster in clusters) {
|
|
|
869 i <- i+1
|
|
|
870 if (show_percent && (i / total) * 100 > percent) {
|
|
|
871 percent <- percent + 1
|
|
|
872 message("\r", sprintf("\r%d %%", percent), appendLF=FALSE)
|
|
|
873 }
|
|
0
|
874 features <- orm$feature()$load_by(cluster_id=cluster$get_id())
|
|
|
875 if (features$any()) {
|
|
|
876 if (!is.null(rt <- features$mean("rt"))) {
|
|
|
877 cluster$set_mean_rt(rt)$save()
|
|
|
878 }
|
|
|
879 features_df <- as.data.frame(features)
|
|
|
880 central_feature <- features_df[grepl("^\\[M\\]", features_df[, "iso"]), ]
|
|
|
881 central_feature_into <- central_feature[["int_o"]]
|
|
|
882 if (!identical(central_feature_into, numeric(0)) && central_feature_into != 0) {
|
|
|
883 for (feature in as.vector(features)) {
|
|
|
884 feature$set_abundance(
|
|
|
885 feature$get_int_o() / central_feature_into * 100
|
|
|
886 )$save()
|
|
|
887 }
|
|
|
888 }
|
|
|
889 }
|
|
|
890 }
|
|
|
891 return (NULL)
|
|
|
892 }
|
|
|
893
|
|
|
894 load_process_params <- function(orm, sample, params) {
|
|
|
895 for (param_list in params) {
|
|
|
896 if (is.null(param_list[["xfunction"]])) {
|
|
|
897 next
|
|
|
898 }
|
|
|
899 if (param_list[["xfunction"]] == "annotatediff") {
|
|
|
900 load_process_params_peak_picking(orm, sample, param_list)
|
|
|
901 }
|
|
|
902 }
|
|
|
903 return (sample)
|
|
|
904 }
|
|
|
905
|
|
|
906 load_process_params_peak_picking <- function(orm, sample, peak_picking_params) {
|
|
|
907 return (add_sample_process_parameters(
|
|
|
908 params=peak_picking_params,
|
|
|
909 params_translation=list(
|
|
|
910 ppm="ppm",
|
|
|
911 maxcharge="maxCharge",
|
|
|
912 maxiso="maxIso"
|
|
|
913 ),
|
|
|
914 param_model_generator=orm$peak_picking_parameters,
|
|
|
915 sample_param_setter=sample$set_peak_picking_parameters
|
|
|
916 ))
|
|
|
917 }
|
|
|
918
|
|
|
919 add_sample_process_parameters <- function(
|
|
|
920 params,
|
|
|
921 params_translation,
|
|
|
922 param_model_generator,
|
|
|
923 sample_param_setter
|
|
|
924 ) {
|
|
|
925 model_params <- list()
|
|
|
926 for (rdata_param_name in names(params_translation)) {
|
|
|
927 database_param_name <- params_translation[[rdata_param_name]]
|
|
|
928 if (is.null(rdata_param <- params[[rdata_param_name]])) {
|
|
|
929 next
|
|
|
930 }
|
|
|
931 model_params[[database_param_name]] <- rdata_param
|
|
|
932 }
|
|
|
933 params_models <- do.call(param_model_generator()$load_by, model_params)
|
|
|
934 if (params_models$any()) {
|
|
|
935 params_model <- params_models$first()
|
|
|
936 } else {
|
|
|
937 params_model <- do.call(param_model_generator, model_params)
|
|
|
938 params_model$save()
|
|
|
939 }
|
|
|
940 return (sample_param_setter(params_model)$save())
|
|
|
941 }
|
|
|
942
|
|
|
943
|
|
|
944 library(optparse)
|
|
|
945
|
|
|
946 option_list <- list(
|
|
|
947 optparse::make_option(
|
|
|
948 c("-v", "--version"),
|
|
|
949 action="store_true",
|
|
|
950 help="Display this tool's version and exits"
|
|
|
951 ),
|
|
|
952 optparse::make_option(
|
|
|
953 c("-i", "--input"),
|
|
|
954 type="character",
|
|
|
955 help="The rdata path to import in XSeeker"
|
|
|
956 ),
|
|
|
957 optparse::make_option(
|
|
|
958 c("-s", "--samples"),
|
|
|
959 type="character",
|
|
|
960 help="Samples to visualise in XSeeker"
|
|
|
961 ),
|
|
|
962 optparse::make_option(
|
|
|
963 c("-B", "--archetype"),
|
|
|
964 type="character",
|
|
|
965 help="The name of the base database"
|
|
|
966 ),
|
|
|
967 optparse::make_option(
|
|
|
968 c("-b", "--database"),
|
|
|
969 type="character",
|
|
|
970 help="The base database's path"
|
|
|
971 ),
|
|
|
972 optparse::make_option(
|
|
|
973 c("-c", "--compounds-csv"),
|
|
|
974 type="character",
|
|
|
975 help="The csv containing compounds"
|
|
|
976 ),
|
|
|
977 optparse::make_option(
|
|
|
978 c("-m", "--models"),
|
|
|
979 type="character",
|
|
|
980 help="The path or url (must begin with http[s]:// or git@) to the database's models"
|
|
|
981 ),
|
|
|
982 optparse::make_option(
|
|
|
983 c("-o", "--output"),
|
|
|
984 type="character",
|
|
|
985 help="The path where to output sqlite"
|
|
|
986 ),
|
|
|
987 optparse::make_option(
|
|
|
988 c("-P", "--not-show-percent"),
|
|
|
989 action="store_true",
|
|
|
990 help="Flag not to show the percents",
|
|
|
991 default=FALSE
|
|
|
992 )
|
|
|
993 )
|
|
|
994
|
|
|
995 options(error=function(){traceback(3)})
|
|
|
996
|
|
|
997 parser <- OptionParser(usage="%prog [options] file", option_list=option_list)
|
|
|
998 args <- parse_args(parser, positional_arguments=0)
|
|
|
999
|
|
|
1000 err_code <- 0
|
|
|
1001
|
|
|
1002 if (!is.null(args$options$version)) {
|
|
|
1003 message(sprintf("%s %s", TOOL_NAME, VERSION))
|
|
|
1004 quit()
|
|
|
1005 }
|
|
|
1006
|
|
|
1007 models <- get_models(args$options$models)
|
|
|
1008 orm <- DBModelR::ORM(
|
|
|
1009 connection_params=list(dbname=args$options$output),
|
|
|
1010 dbms="SQLite"
|
|
|
1011 )
|
|
|
1012
|
|
|
1013 invisible(orm$models(models))
|
|
|
1014 invisible(create_database(orm))
|
|
|
1015
|
|
|
1016 message("Database model created")
|
|
|
1017
|
|
|
1018 insert_adducts(orm)
|
|
|
1019
|
|
|
1020 if (!is.null(args$options$database)) {
|
|
|
1021 insert_base_data(orm, args$options$database)
|
|
|
1022 }
|
|
|
1023 message(sprintf("Base data inserted using %s.", args$options$database))
|
|
|
1024
|
|
|
1025 if (!is.null(args$options$archetype)) {
|
|
|
1026 insert_base_data(orm, args$options$archetype, archetype=TRUE)
|
|
|
1027 }
|
|
|
1028 if (!is.null(args$options$`compounds-csv`)) {
|
|
|
1029 insert_compounds(orm, args$options$`compounds-csv`)
|
|
|
1030 }
|
|
|
1031
|
|
|
1032 # if (!is.null(args$options$rdata)) {
|
|
|
1033 # load_rdata_in_base(args$options$rdata, args$options$samples, args$options$`not-show-percent`)
|
|
|
1034 # }
|
|
|
1035
|
|
|
1036
|
|
|
1037 load(args$options$input, rdata <- new.env())
|
|
|
1038
|
|
|
1039 process_rdata(orm, rdata, args$options)
|
|
|
1040
|
|
|
1041 quit(status=err_code)
|
|
|
1042
|
|
|
1043
|
