Newer
Older
author: Environmental Cheminformatics Group, LCSB, University of Luxembourg
title: "`r paste('Shinyscreen', packageVersion('shinyscreen'))`"
```{r, context='setup', include='false'}
def_datafiles <- shinyscreen:::dtable(File=character(0),
tag=character(0))
def_datatab <- shinyscreen:::dtable("tag"=factor(),
"adduct"=factor(levels=shinyscreen:::DISP_ADDUCTS),
"set"=factor())
## def_state$input$tab$tags <- def_datatab
compl_sets <- eventReactive(rv_state$input$tab$setid,
rv_state$input$tab$setid[,unique(set)])
## Reactive values to support some of the UI elements.
## rv_ui <- reactiveValues(datatab=def_tags)
# Configuration {.tabset}
## Inputs
<details>
<summary>Specify the project directory</summary>
This is where the output files and the state of the analysis will be
saved.
</details>
```{r, echo=FALSE}
actionButton(inputId = "project_b",
label= "Project")
```
Current project directory is `r textOutput("project", inline=T)`
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
Load the config file if needed.
```{r, echo=FALSE}
actionButton(inputId = "conf_file_b",
label= "Load config")
```
<details><summary>Load the compound list(s)</summary>
A compound list is composed of entries describing compounds. This
description is used to search for its spectrum in the data file. The
list is a table in the ***CSV*** format and contains these columns,
* ***ID*** : required column, must be filled; this is a user-defined
ID, uniquely associated with a compound
* ***Name*** : this column can be left blank; if not, it should contain the
names of the compounds
* ***SMILES*** : a _SMILES_ string, describing the structure of the
compound; this entry can be left empty only if one of either
***Formula***, or ***mz*** entries are not
* ***Formula*** : a chemical formula of a compound; this field can be
empty only if one of either ***SMILES***, or ***mz*** entries are
not
* ***mz*** : mass of the ionised compound; this field can be left
empty only if one of either ***SMILES***, or ***Formula*** is not
* ***CAS*** : the CAS number of the compound; it can be left empty
* ***RT*** : retention time of the MS1 peak in minutes, if known; can
be left empty.
Only ***ID*** and one of ***SMILES***, ***Formula*** or ***mz*** must
be filled. When structure, or a formula of a compound is known, it is
also possible to look for various adducts in the sample. Of course,
scanning for completely unknown compounds is also supported by the
***mz*** column. In this case, ***mz*** is the mass of the ion.
It is strongly recommended to quote SMILES, names and formulas in the
CSV file used with Shinyscreen.
</details>
```{r, echo=FALSE}
actionButton(inputId = "comp_list_b",
label= "Compound list(s)")
```
<details><summary>Load compound set list (_setid_ table)</summary>
The compound lists can contain more entries than is necessary. Using
the _setid_ lists, it is possible to create _compound sets_ which
contain only those compounds that will actually be searched for in the
data files. A _setid table_ is a _CSV_ containing at least two
columns,
* ***ID*** : the ID entry from the compound list
* ***set*** : an user-defined set name.
</details>
```{r, echo=FALSE}
actionButton(inputId = "setid_b",
label= "Load the setid table")
```
`r htmlOutput("setids", inline=T)`
## Data files
<details><summary>Load data files</summary>
Shinyscreen currently supports only the **mzML** file format. After
loading the files, set file tags in the file table (column
**tag**). Additionally, specify a set of compounds that is supposed
to be extracted from the file using the **set** column. Finally,
specify the **adduct** in the adduct column. In case of compounds
with unknown structure and formula, the adduct is ignored for obvious
reasons.
</details>
```{r, echo=FALSE}
actionButton(inputId = "datafiles_b",
label= "Load data files.")
```
<details><summary>Assign tags to data files.</summary>
Each tag designates an unique file. Use the table below to assign
tags.
</details>
```{r, echo=FALSE}
rhandsontable::rHandsontableOutput("datafiles")
```
<details><summary>Assign sets to tags.</summary>
For each tag, assign a set and an adduct (if the structure information
exists, otherwise _adduct_ column is ignored).
</details>
```{r, echo=F}
rhandsontable::rHandsontableOutput("datatab")
```
## Extraction
### Spectra extraction based settings
Extract all entries matching the target mass within this error in the
precursor table.
</details>
```{r, echo=F}
shinyscreen::mz_input(input_mz = "ms1_coarse",
input_unit = "ms1_coarse_unit",
def_mz = def_state$conf$tolerance[["ms1 coarse"]],
def_unit = "Da")
The precursor table masses can be of lower accuracy. Once there is a
match within the coarse error, it can be further checked versus the
fine error bounds directly in the mass spectrum.
</details>
```{r, echo=F}
shinyscreen::mz_input(input_mz = "ms1_fine",
input_unit = "ms1_fine_unit",
def_mz = def_state$conf$tolerance[["ms1 fine"]],
def_unit = "ppm")
```
The mz interval over which the intensities are aggregated to generate
a chromatogram.
</details>
```{r, echo=F}
shinyscreen::mz_input(input_mz = "ms1_eic",
input_unit = "ms1_eic_unit",
def_mz = def_state$conf$tolerance[["eic"]],
def_unit = "Da")
```
If the expected retention time has been specified for the compound,
then search for the MS1 signature inside the window defined by this
range.
</details>
```{r, echo=F}
shinyscreen::rt_input(input_rt = "ms1_rt_win",
input_unit = "ms1_rt_win_unit",
def_rt = def_state$conf$tolerance[["rt"]],
def_unit = "min")
```
## Prescreening
Ignore MS1 signal below the threshold.
</details>
```{r, echo=F}
numericInput(inputId = "ms1_int_thresh",
label = NULL,
value = def_state$conf$prescreen$ms1_int_thresh)
```
Ignore MS2 signal below the threshold.
</details>
```{r, echo=F}
numericInput(inputId = "ms2_int_thresh",
label = NULL,
value = def_state$conf$prescreen$ms2_int_thresh)
```
MS1 signal-to-noise ratio.
```{r, echo=F}
numericInput(inputId = "s2n",
label = NULL,
value = def_state$conf$prescreen$s2n)
```
Look for associated MS2 spectrum within this window around the MS1
peak.
</details>
```{r, echo=F}
shinyscreen::rt_input(input_rt = "ret_time_shift_tol",
input_unit = "ret_time_shift_tol_unit",
def_rt = def_state$conf$tolerance[["ret_time_shift_tol"]],
def_unit = "min")
```
<div style= "display: flex; vertical-align:top; ">
<div>
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
<details><summary>Filter summary table</summary>
Selection criteria for filtering entries in the summary table
according to the QA criteria.
* **qa_pass** : entries that passed all checks
* **qa_ms1_exists** : MS1 intensity is above the MS1 threshold
* **qa_ms2_exists** : those entries for which some MS2 spectra have been found
* **qa_ms1_above_noise** : MS1 is intense enough and above the noise level
* **qa_ms2_good_int** : MS2 intensity is above the MS2 threshold
* **qa_ms2_near** : MS2 spectrum is close enough to the MS1 peak
</details>
```{r, echo=F}
checkboxGroupInput("summ_subset",
label=NULL,
choiceNames = shinyscreen:::QA_FLAGS,
choiceValues = shinyscreen:::QA_FLAGS)
```
</div>
<div>
<details><summary>Ordering by columns</summary>
It is possible to order the summary table using columns (keys):
*`r paste(gsub("^-(.+)","\\1",shinyscreen:::DEF_INDEX_SUMM), collapse = ',')`*.
The sequence of columns in the table below describes the
sequence of ordering steps -- the key in the first row sorts the
entire summary table and subsequent keys break the ties.
</details>
```{r, echo=F}
rhandsontable::rHandsontableOutput("order_summ")
```
</div>
</div>
<!-- <details><summary>Order entries</summary> -->
<!-- Sequence of column a -->
<!-- </details> -->
<!-- ```{r, echo=F} -->
<!-- checkboxGroupInput("summ_subset", -->
<!-- label=NULL, -->
<!-- choiceNames = shinyscreen:::QA_FLAGS, -->
<!-- choiceValues = 1:length(shinyscreen:::QA_FLAGS)) -->
<!-- ``` -->
### Logarithmic axis
```{r, echo=F}
checkboxGroupInput("plot_log",
label=NULL,
choiceNames = c("MS1 EIC","MS2 EIC","MS2 Spectrum"),
choiceValues = c(F,F,F))
```
### Global retention time range
```{r, echo=F}
shinyscreen::rt_input(input_rt = "plot_rt_min",
input_unit = "plot_rt_min_unit",
def_rt = NA_real_,
def_unit = "min",
pref = "min:")
shinyscreen::rt_input(input_rt = "plot_rt_max",
input_unit = "plot_rt_max_unit",
def_rt = NA_real_,
def_unit = "min",
pref = "max:")
```
```{r, echo=F}
shiny::textInput(inputId = "rep_aut", label = "Report author", value = def_state$conf$report$author)
shiny::textInput(inputId = "rep_tit", label = "Report title", value = def_state$conf$report$title)
```
# View compound Lists and Sets {.tabset}
## Compound List
```{r, echo=F}
DT::dataTableOutput("comp_table")
```
## Setid Table
```{r, echo=F}
DT::dataTableOutput("setid_table")
```
<details><summary>Extract spectra from data files.</summary>
After Shinyscreen is configured, the compound and setid lists loaded, it
is possible to proceed with extracting the data. This is potentially a
time-intensive step, so some patience might be needed.
Once the data is extracted, it will be possible to quality check the
spectra associated with the compounds specified in the _setid_ list,
to subset that data, look at the plots and publish a report.
</details>
```{r, echo=FALSE}
actionButton(inputId = "extract",
label = "Extract")
```
# Browse Results
ord_nms <- gsub("^-(.+)","\\1",shinyscreen:::DEF_INDEX_SUMM)
ord_asc <- grepl("^-.+",shinyscreen:::DEF_INDEX_SUMM)
ord_asc <- factor(ifelse(ord_asc, "descending", "ascending"),levels = c("ascending","descending"))
def_ord_summ <- shinyscreen:::dtable("Column names"=ord_nms,"Direction"=ord_asc)
```{r, include="false", context='server'}
rf_compound_input_state <- reactive({
sets <- rv_state$conf$compounds$sets
lst <- as.list(rv_state$conf$compounds$lists)
validate(need(length(lst)>0,
message = "Load the compound lists(s) first."))
validate(need(nchar(sets)>0,
message = "Load the setid table first."))
isolate({
state <- rev2list(rv_state)
m <- load_compound_input(state)
## Side effect! This is because my pipeline logic does not
## work nicely with reactive stuff.
rv_state$input$tab$cmpds <- list2rev(m$input$tab$cmpds)
rv_state$input$tab$setid <- m$input$tab$setid
m
})
rf_get_dfiles <- reactive({
input$datafiles_b
if (input$datafiles_b > 0) {
filters <- matrix(c("mzML files", ".mzML",
"All files", "*"),
2, 2, byrow = TRUE)
mzMLs <- tcltk::tk_choose.files(filters=filters)
message("(config) Selected data files: ", paste(mzMLs,collapse = ","))
mzMLs
} else character(0)
})
rf_dfiles_tab <- reactive({
mzMLs <- rf_get_dfiles()
isolate({oldtab <- data.table::as.data.table(rhandsontable::hot_to_r(input$datafiles))})
newf <- setdiff(mzMLs,oldtab$File)
nr <- NROW(oldtab)
tmp <- if (length(newf)>0) shinyscreen:::dtable(File=newf,tag=paste0('F',(nr+1):(nr + length(newf)))) else shinyscreen:::dtable(File=character(),tag=character())
rbind(oldtab,
tmp)
})
rf_tag_tab <- reactive({
state <- rf_compound_input_state()
isolate({oldtab <- rhandsontable::hot_to_r(input$datatab)})
oldt <- oldtab$tag
sets <- compl_sets()
sets <- if (length(sets)==1) sets <- c(sets,"invalid") #Just
#because
#when one
#level,
#rhandsontable
#has issues
#displaying
#it.
otagch <- as.character(oldt)
df_tab <- rhandsontable::hot_to_r(input$datafiles)
tagl <- df_tab$tag
diff <- setdiff(tagl,
otagch)
if (length(diff)!=0) {
## Only change the tag names in the old ones.
pos_tag <- 1:length(tagl)
pos_old <- 1:NROW(oldtab)
pos_mod <- intersect(pos_tag,pos_old)
new_tag <- tagl[pos_mod]
if (NROW(oldtab)>0) oldtab[pos_mod,tag := ..new_tag]
## Now add tags for completely new files, if any.
rest_new <- if (NROW(oldtab) > 0) setdiff(diff,new_tag) else diff
tmp <- shinyscreen:::dtable(tag=factor(rest_new,levels=tagl),
adduct=factor(levels = shinyscreen:::DISP_ADDUCTS),
set=factor(levels = sets))
dt <-data.table::as.data.table(rbind(as.data.frame(oldtab),
as.data.frame(tmp)))
dt[tag %in% df_tab$tag,]
} else oldtab
})
observeEvent(input$project_b,{
wd <- tcltk::tk_choose.dir(default = getwd(),
caption = "Choose project directory")
message("Set project dir to ", wd)
rv_state$conf$project <- wd
})
observeEvent(input$comp_list_b, {
filters <- matrix(c("CSV files", ".csv",
"All files", "*"),
2, 2, byrow = TRUE)
compfiles <- tcltk::tk_choose.files(filters=filters)
message("(config) Selected compound lists: ", paste(compfiles,collapse = ","))
rv_state$conf$compounds$lists <- if (length(compfiles)>0 && nchar(compfiles[[1]])>0) compfiles else "Nothing selected."
})
observeEvent(input$setid_b, {
filters <- matrix(c("CSV files", ".csv",
"All files", "*"),
2, 2, byrow = TRUE)
setids <- tcltk::tk_choose.files(filters=filters)
message("(config) Selected compound sets (setid): ", paste(setids,collapse = ","))
rv_state$conf$compounds$sets <- if (length(setids)>0 && nchar(setids[[1]])>0) setids else "Nothing selected."
})
observeEvent(input$extract,{
tmp <- rev2list(rv_state)
fn_c_state <- file.path(tmp$conf$project,
shinyscreen:::FN_CONF)
yaml::write_yaml(x=tmp$conf,file=fn_c_state)
message("(extract) Config written to ", fn_c_state)
})
```
<!-- Render -->
```{r, include="false", context="server"}
output$project <- renderText(rv_state$conf$project)
output$comp_lists <- renderText({
lsts <- rev2list(rv_state$conf$compounds$lists)
if (length(lsts) > 0 &&
isTruthy(lsts) &&
lsts != "Nothing selected.") {
paste(c("<ul>",
sapply(lsts,
function (x) paste("<li>",x,"</li>")),
"</ul>"))
} else "No compound list selected yet."
})
output$setids <- renderText({
sets <- rv_state$conf$compounds$sets
if (isTruthy(sets) && sets != "Nothing selected.")
paste("selected <em>setid</em> table:",
sets) else "No <em>setid</em> table selected."
})
output$order_summ <- rhandsontable::renderRHandsontable(rhandsontable::rhandsontable(def_ord_summ,
manualRowMove = T))
output$datafiles <- rhandsontable::renderRHandsontable(
{
res <- if (length(rf_get_dfiles())>0) {
rf_dfiles_tab()
} else def_datafiles
rhandsontable::rhandsontable(as.data.frame(res),
width = "50%",
height = "25%",
allowInvalid=F)
})
output$datatab <- rhandsontable::renderRHandsontable(
{
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
df <- rhandsontable::hot_to_r(input$datafiles)
res <- if (NROW(rv_state$input$tab$setid) > 0 &&
NROW(df) > 0) rf_tag_tab() else def_datatab
rhandsontable::rhandsontable(res,stretchH="all",
allowInvalid=F)
})
output$comp_table <- DT::renderDataTable({
state <- rf_compound_input_state()
DT::datatable(state$input$tab$cmpds,
style = 'bootstrap',
class = 'table-condensed',
extensions = 'Scroller',
options = list(scrollX = T,
scrollY = 200,
deferRender = T,
scroller = T))
})
output$setid_table <- DT::renderDataTable({
state <- rf_compound_input_state()
DT::datatable(state$input$tab$setid,
style = 'bootstrap',
class = 'table-condensed',
extensions = 'Scroller',
options = list(scrollX = T,
scrollY = 200,
deferRender = T,
scroller = T))
})
```
```{r, echo=F, context = 'server'}
session$onSessionEnded(function () stopApp())