Library metadata is displayed in hover window + kludge bug fix

DESCRIPTION

@@ -21,5 +21,5 @@ Imports:
     V8 (>= 1.5)
 Remotes:
     ropensci/plotly@efe5535d40200b12e87301f5fd2b5805d0dd38ce
-Suggests: testthat, roxygen2
+Suggests: testthat, roxygen2, bit64
 RoxygenNote: 6.0.1

R/create_server.R

@@ -212,7 +212,15 @@ createAcquacottaServer <- function(config = createConfig()) {
             # This string is used by event_data to register user interactions with the plot
             # This string is used by shinyjs to reset a click event, so that the user can click on the same plot element twice
             source = config$plotly_id_lib_source,
-            marker = list(line = list(color = 'rgb(0,0,0)', width = line_width))
+            marker = list(line = list(color = 'rgb(0,0,0)', width = line_width)),
+            # Hovertext showing metadata for library
+            text = ~paste(
+              'Lane: ', Lane,
+              '</br>Study: ', Study,
+              '</br>Barcode: ', Barcode,
+              '</br>Group ID: ', `Group ID`,
+              '</br>External Name: ', `External Name`
+            )
           ) %>%
           add_bars(
             y = ~ Value,

R/list_reports.R

@@ -16,11 +16,6 @@ listRunReports <- function(base_dir) {
                    file = file,
                    name = name)
 
-  # This is temporary code to exclude the TSV files in the base directory from eariler app version
-  valid_dir <- list.dirs(path = full_path, full.names = TRUE)
-  valid_dir <- valid_dir[2:length(valid_dir)]
-  dt <- dt[dt$dir_path %in% valid_dir, ]
-
   # If two or more TSV files share the same name, their parent folder name is prepanded to remove ambiguity
   dup_name <- duplicated(dt$name) | duplicated(dt$name, fromLast = TRUE)
   unambiguous_name <- paste(

R/utility.R

@@ -95,6 +95,16 @@ fixSeqWareTSV <- function(t.df, valid.dt) {
     paste(result.dt$Library, result.dt$Lane, result.dt$Barcode, sep = "_")
   )
 
+  # Add any missing columns as all NA (Columns from the valid.dt starting with # are ignored, as it is a flag to split column)
+  missing.columns <- setdiff(valid.dt$app.name, colnames(result.dt))
+  remove.flag.columns <- grepl('^[^#]', missing.columns) # Columns that do not start with flag
+  missing.columns <- missing.columns[remove.flag.columns]
+
+  if(!identical(missing.columns, character(0))) {
+    # https://stackoverflow.com/questions/11745169/dynamic-column-names-in-data-table
+    result.dt[, (missing.columns) := NA]
+  }
+
   return(result.dt)
 }
 
@@ -164,6 +174,16 @@ readSeqWareTSV <- function(path) {
     set(dt, j = "Run Name", value = factor(rep(path, nrow(dt))))
 
   }, warning = function(w) {
+    # This is a crutch to fix a bug in data.table. If fread causes a warning, it is caught, but the function is left in a failed state.
+    # The next valid call to fread will fail again, as the function has to reset itself. The next valid call will work fine.
+    # I am manually making a valid call to fread to reset it
+    # Issue is at https://github.com/Rdatatable/data.table/issues/2904
+    tryCatch({
+      fread("echo bug, fix")
+    }, warning = function(w) {
+      # Squash the warning message produced by resetting fread
+    })
+
     stop(conditionMessage(w))
   })
 }

config/column_naming.csv

@@ -8,6 +8,8 @@ Insert Mean (SD),#Split_Mean_SD,NA,
 Insert Mean,Insert Mean,Numeric,
 Insert Stddev,Insert Stddev,Numeric,
 Read Length,#Split_Read1_Read2,NA,
+R1 Length,R1 Length,Numeric,
+R2 Length,R2 Length,Numeric,
 PF Reads,PF Reads,Numeric,
 PF Yield,PF Yield,Numeric,
 Map Percent,Map Percent,Numeric,

tests/testthat/test_list_reports.R

@@ -1,6 +1,3 @@
-library(testthat)
-library(acquacotta)
-
 context("Loading Run Report files")
 
 test_that("Loading of clean data", {

tests/testthat/test_utility.R

@@ -0,0 +1,13 @@
+context("Reading Run Report")
+
+test_that("Loading of valid data", {
+  expect_error(readSeqWareTSV("./test_utility_data/180406_valid.tsv"), NA)
+})
+
+test_that("Loading of invalid data is handled gracefully", {
+  expect_error(readSeqWareTSV("./test_utility_data/180406_invalid.tsv"))
+
+  # fread() cleaned up bug does not happen
+  # https://github.com/Rdatatable/data.table/issues/2904
+  expect_error(readSeqWareTSV("./test_utility_data/180406_valid.tsv"), NA)
+})

tests/testthat/test_utility_data/180406_invalid.tsv

@@ -0,0 +1,28 @@
+Lane	Barcode	Group ID	External Name	Library	Insert Mean	Insert Stddev	Read Length	PF Reads	PF Yield	Map Percent	R1 Mismatch Percent	R2 Mismatch Percent	R1 Indel Percent	R2 Indel Percent	R1 Soft Clip Percent	R2 Soft Clip Percent	Reads/SP	Percent Mapped on Target	Estimated Yield (collapsed)	Coverage (collapsed)	Target Size (bp)	Number of Targets	Target File
+1	CTCCGATCGTCC	na	na	Lib1	381.15	171.79	151, 151	216418826	32679172611	92.17	0.4	1.03	0.06	0.06	1.06	2.38	1.2	100	24729302364	7.88	3137161171	93	T1
+1	ATCTAGCCGGCC	na	na	Lib2	363.78	159.04	151, 151	252302380	38097555690	91.75	0.4	1.02	0.06	0.06	1.1	2.46	1.21	100	28285158676	9.02	3137161171	93	T2
+1	TCGGGAAGGTCC	na	na	Lib3	369.18	162.14	151, 151	236526798	35715462763	92.15	0.4	0.97	0.06	0.06	1.01	2.23	1.2	100	26935365729	8.59	3137161171	93	T3
+1	GCCTCGAAGTCC	na	na	Lib4	375.03	168.3	151, 151	243644668	36790256463	92.41	0.41	0.98	0.06	0.06	1.14	2.3	1.2	100	27834574154	8.87	3137161171	93	T4
+2	ATCTAGCCGGCC	na	na	Lib5	372.56	166.46	151, 151	254039950	38359982266	91.77	0.36	1.01	0.06	0.06	1.07	2.28	1.2	100	28787340464	9.18	3137161171	93	T5
+2	TCGGGAAGGTCC	na	na	Lib6	379.52	170.98	151, 151	238841060	36064868521	92.18	0.37	0.98	0.06	0.06	1.02	2.14	1.19	100	27455453152	8.75	3137161171	93	T6
+2	GCCTCGAAGTCC	na	na	Lib7	384.88	176.13	151, 151	247411212	37358963614	92.42	0.37	0.98	0.06	0.06	1.08	2.25	1.19	100	28522068554	9.09	3137161171	93	T7
+2	CTCCGATCGTCC	na	na	Lib8	391.5	178.75	151, 151	221182532	33398484860	92.19	0.36	1.02	0.06	0.06	1	2.32	1.19	100	25508277420	8.13	3137161171	93	T8
+3	GCCTCGAAGTCC	na	na	Lib9	395.1	185.66	151, 151	254121044	38372177283	92.38	0.36	0.97	0.06	0.06	1.09	2.29	1.2	100	28941215516	9.23	3137161171	93	T9
+3	TCGGGAAGGTCC	na	na	Lib10	388.72	178.51	151, 151	244101080	36859194245	92.13	0.35	0.95	0.06	0.06	0.98	2.16	1.21	100	27729094422	8.84	3137161171	93	T10
+3	CTCCGATCGTCC	na	na	Lib11	401.92	188.53	151, 151	227552300	34360273237	92.14	0.35	1.03	0.06	0.06	1.04	2.36	1.2	100	25912070735	8.26	3137161171	93	T11
+3	ATCTAGCCGGCC	na	na	Lib12	380.29	174.51	151, 151	259420556	39172393171	91.73	0.36	0.99	0.06	0.06	1.11	2.36	1.22	100	29024773825	9.25	3137161171	93	T12
+4	ATCTAGCCGGCC	na	na	Lib13	382.18	174.56	151, 151	258522006	39036759398	91.78	0.33	0.94	0.06	0.06	1.1	2.29	1.22	100	28821734974	9.19	3137161171	93	T13
+4	GCCTCGAAGTCC	na	na	Lib14	396.34	185.94	151, 151	253040936	38209062060	92.42	0.33	0.92	0.06	0.06	1.06	2.23	1.21	100	28719305274	9.15	3137161171	93	T14
+4	TCGGGAAGGTCC	na	na	Lib15	389.41	178.05	151, 151	243227188	
+36727286387	92.19	0.32	0.89	0.06	0.06	0.97	2.11	1.21	100	27532330327	8.78	3137161171	93	T15
+4	CTCCGATCGTCC	na	na	Lib16	404.6	189.15	151, 151	226971682	34272611454	92.19	0.32	0.97	0.06	0.06	0.98	2.3	1.21	100	25755587119	8.21	3137161171	93	T16
+5	ATCTAGCCGGCC	na	na	Lib17	377.45	175.64	151, 151	262110344	39578617505	91.74	0.35	0.94	0.06	0.06	1.18	2.29	1.26	100	28295604657	9.02	3137161171	93	T17
+5	GCCTCGAAGTCC	na	na	Lib18	390.52	186.33	151, 151	255439380	38571326444	92.41	0.35	0.93	0.06	0.06	1.11	2.3	1.24	100	28176385193	8.98	3137161171	93	T18
+5	TCGGGAAGGTCC	na	na	Lib19	384.09	178.29	151, 151	246301176	37191373174	92.13	0.35	0.91	0.06	0.06	1.01	2.15	1.25	100	27067104926	8.63	3137161171	93	T19
+5	CTCCGATCGTCC	na	na	Lib20	399.6	189.24	151, 151	229297100	34623839979	92.16	0.34	0.99	0.06	0.06	1.05	2.34	1.24	100	25315289382	8.07	3137161171	93	T20
+6	CTCCGATCGTCC	na	na	Lib21	399.79	187.64	151, 151	226406380	34187224251	92.14	0.36	1.03	0.06	0.06	1.01	2.31	1.21	100	25502118885	8.13	3137161171	93	T21
+6	ATCTAGCCGGCC	na	na	Lib22	377.95	173.58	151, 151	258628142	39052848619	91.74	0.36	1	0.06	0.06	1.11	2.36	1.23	100	28547020088	9.1	3137161171	93	T22
+6	TCGGGAAGGTCC	na	na	Lib23	386.48	178.16	151, 151	243040660	36699058535	92.14	0.36	0.96	0.06	0.06	1.03	2.13	1.22	100	27264861066	8.69	3137161171	93	T23
+6	GCCTCGAAGTCC	na	na	Lib24	393.02	184.94	151, 151	252419606	38115229911	92.38	0.36	0.99	0.06	0.06	1.09	2.33	1.22	100	28401642000	9.05	3137161171	93	T24
+7	AAGCGTACGTCC	na	na	Lib25	301.12	149.43	151, 151	988749818	149301208938	91.18	0.39	0.93	0.07	0.06	3.01	4.04	1.25	100	105042282719	33.48	3137161171	93	T25
+8	TTTAGTCAGTCC	na	na	Lib26	308.09	155.88	151, 151	1000300318	151045251998	92.15	0.4	0.87	0.06	0.06	2.13	3.11	1.24	100	109434035708	34.88	3137161171	93	T26

tests/testthat/test_utility_data/180406_valid.tsv

@@ -0,0 +1,27 @@
+Lane	Barcode	Group ID	External Name	Library	Insert Mean	Insert Stddev	Read Length	PF Reads	PF Yield	Map Percent	R1 Mismatch Percent	R2 Mismatch Percent	R1 Indel Percent	R2 Indel Percent	R1 Soft Clip Percent	R2 Soft Clip Percent	Reads/SP	Percent Mapped on Target	Estimated Yield (collapsed)	Coverage (collapsed)	Target Size (bp)	Number of Targets	Target File
+1	CTCCGATCGTCC	na	na	Lib1	381.15	171.79	151, 151	216418826	32679172611	92.17	0.4	1.03	0.06	0.06	1.06	2.38	1.2	100	24729302364	7.88	3137161171	93	T1
+1	ATCTAGCCGGCC	na	na	Lib2	363.78	159.04	151, 151	252302380	38097555690	91.75	0.4	1.02	0.06	0.06	1.1	2.46	1.21	100	28285158676	9.02	3137161171	93	T2
+1	TCGGGAAGGTCC	na	na	Lib3	369.18	162.14	151, 151	236526798	35715462763	92.15	0.4	0.97	0.06	0.06	1.01	2.23	1.2	100	26935365729	8.59	3137161171	93	T3
+1	GCCTCGAAGTCC	na	na	Lib4	375.03	168.3	151, 151	243644668	36790256463	92.41	0.41	0.98	0.06	0.06	1.14	2.3	1.2	100	27834574154	8.87	3137161171	93	T4
+2	ATCTAGCCGGCC	na	na	Lib5	372.56	166.46	151, 151	254039950	38359982266	91.77	0.36	1.01	0.06	0.06	1.07	2.28	1.2	100	28787340464	9.18	3137161171	93	T5
+2	TCGGGAAGGTCC	na	na	Lib6	379.52	170.98	151, 151	238841060	36064868521	92.18	0.37	0.98	0.06	0.06	1.02	2.14	1.19	100	27455453152	8.75	3137161171	93	T6
+2	GCCTCGAAGTCC	na	na	Lib7	384.88	176.13	151, 151	247411212	37358963614	92.42	0.37	0.98	0.06	0.06	1.08	2.25	1.19	100	28522068554	9.09	3137161171	93	T7
+2	CTCCGATCGTCC	na	na	Lib8	391.5	178.75	151, 151	221182532	33398484860	92.19	0.36	1.02	0.06	0.06	1	2.32	1.19	100	25508277420	8.13	3137161171	93	T8
+3	GCCTCGAAGTCC	na	na	Lib9	395.1	185.66	151, 151	254121044	38372177283	92.38	0.36	0.97	0.06	0.06	1.09	2.29	1.2	100	28941215516	9.23	3137161171	93	T9
+3	TCGGGAAGGTCC	na	na	Lib10	388.72	178.51	151, 151	244101080	36859194245	92.13	0.35	0.95	0.06	0.06	0.98	2.16	1.21	100	27729094422	8.84	3137161171	93	T10
+3	CTCCGATCGTCC	na	na	Lib11	401.92	188.53	151, 151	227552300	34360273237	92.14	0.35	1.03	0.06	0.06	1.04	2.36	1.2	100	25912070735	8.26	3137161171	93	T11
+3	ATCTAGCCGGCC	na	na	Lib12	380.29	174.51	151, 151	259420556	39172393171	91.73	0.36	0.99	0.06	0.06	1.11	2.36	1.22	100	29024773825	9.25	3137161171	93	T12
+4	ATCTAGCCGGCC	na	na	Lib13	382.18	174.56	151, 151	258522006	39036759398	91.78	0.33	0.94	0.06	0.06	1.1	2.29	1.22	100	28821734974	9.19	3137161171	93	T13
+4	GCCTCGAAGTCC	na	na	Lib14	396.34	185.94	151, 151	253040936	38209062060	92.42	0.33	0.92	0.06	0.06	1.06	2.23	1.21	100	28719305274	9.15	3137161171	93	T14
+4	TCGGGAAGGTCC	na	na	Lib15	389.41	178.05	151, 151	243227188	36727286387	92.19	0.32	0.89	0.06	0.06	0.97	2.11	1.21	100	27532330327	8.78	3137161171	93	T15
+4	CTCCGATCGTCC	na	na	Lib16	404.6	189.15	151, 151	226971682	34272611454	92.19	0.32	0.97	0.06	0.06	0.98	2.3	1.21	100	25755587119	8.21	3137161171	93	T16
+5	ATCTAGCCGGCC	na	na	Lib17	377.45	175.64	151, 151	262110344	39578617505	91.74	0.35	0.94	0.06	0.06	1.18	2.29	1.26	100	28295604657	9.02	3137161171	93	T17
+5	GCCTCGAAGTCC	na	na	Lib18	390.52	186.33	151, 151	255439380	38571326444	92.41	0.35	0.93	0.06	0.06	1.11	2.3	1.24	100	28176385193	8.98	3137161171	93	T18
+5	TCGGGAAGGTCC	na	na	Lib19	384.09	178.29	151, 151	246301176	37191373174	92.13	0.35	0.91	0.06	0.06	1.01	2.15	1.25	100	27067104926	8.63	3137161171	93	T19
+5	CTCCGATCGTCC	na	na	Lib20	399.6	189.24	151, 151	229297100	34623839979	92.16	0.34	0.99	0.06	0.06	1.05	2.34	1.24	100	25315289382	8.07	3137161171	93	T20
+6	CTCCGATCGTCC	na	na	Lib21	399.79	187.64	151, 151	226406380	34187224251	92.14	0.36	1.03	0.06	0.06	1.01	2.31	1.21	100	25502118885	8.13	3137161171	93	T21
+6	ATCTAGCCGGCC	na	na	Lib22	377.95	173.58	151, 151	258628142	39052848619	91.74	0.36	1	0.06	0.06	1.11	2.36	1.23	100	28547020088	9.1	3137161171	93	T22
+6	TCGGGAAGGTCC	na	na	Lib23	386.48	178.16	151, 151	243040660	36699058535	92.14	0.36	0.96	0.06	0.06	1.03	2.13	1.22	100	27264861066	8.69	3137161171	93	T23
+6	GCCTCGAAGTCC	na	na	Lib24	393.02	184.94	151, 151	252419606	38115229911	92.38	0.36	0.99	0.06	0.06	1.09	2.33	1.22	100	28401642000	9.05	3137161171	93	T24
+7	AAGCGTACGTCC	na	na	Lib25	301.12	149.43	151, 151	988749818	149301208938	91.18	0.39	0.93	0.07	0.06	3.01	4.04	1.25	100	105042282719	33.48	3137161171	93	T25
+8	TTTAGTCAGTCC	na	na	Lib26	308.09	155.88	151, 151	1000300318	151045251998	92.15	0.4	0.87	0.06	0.06	2.13	3.11	1.24	100	109434035708	34.88	3137161171	93	T26