1. ISAnalytics
  2. R
  3. exported-vars.R
Browse code

[FIX] Fixed code for tidyselect warnings, minor adjustments

Giulia Pais authored on 30/11/2022 16:11:17
Showing 1 changed files
R/exported-vars.R
History View file @ 9b7eb4a
... ... 
@@ -172,8 +172,10 @@
172 172 
         dplyr::left_join(.types_mapping(), by = "types")
173 173 
     if (mode == "fread") {
174 174 
         specs_mappings <- specs_mappings %>%
175 
-            dplyr::select(.data$names, .data$fread) %>%
176 
-            dplyr::group_by(.data$fread)
175 
+            dplyr::select(
176 
+                dplyr::all_of(c("names", "fread"))
177 
+            ) %>%
178 
+            dplyr::group_by(dplyr::across(dplyr::all_of("fread")))
177 179 
         types <- specs_mappings %>%
178 180 
             dplyr::group_keys() %>%
179 181 
             dplyr::pull(.data$fread)
... ... 
@@ -195,8 +197,8 @@
195 197 
         dplyr::left_join(.types_mapping(), by = "types")
196 198 
     if (mode == "fread") {
197 199 
         specs_mappings <- specs_mappings %>%
198 
-            dplyr::select(.data$names, .data$fread) %>%
199 
-            dplyr::group_by(.data$fread)
200 
+            dplyr::select(dplyr::all_of(c("names", "fread"))) %>%
201 
+            dplyr::group_by(dplyr::across(dplyr::all_of("fread")))
200 202 
         types <- specs_mappings %>%
201 203 
             dplyr::group_keys() %>%
202 204 
             dplyr::pull(.data$fread)
... ... 
@@ -218,8 +220,8 @@
218 220 
         dplyr::left_join(.types_mapping(), by = "types")
219 221 
     if (mode == "fread") {
220 222 
         specs_mappings <- specs_mappings %>%
221 
-            dplyr::select(.data$names, .data$fread) %>%
222 
-            dplyr::group_by(.data$fread)
223 
+            dplyr::select(dplyr::all_of(c("names", "fread"))) %>%
224 
+            dplyr::group_by(dplyr::across(dplyr::all_of("fread")))
223 225 
         types <- specs_mappings %>%
224 226 
             dplyr::group_keys() %>%
225 227 
             dplyr::pull(.data$fread)
... ... 
@@ -299,7 +301,7 @@ reduced_AF_columns <- function() {
299 301 
         vars_df = association_file_columns(TRUE),
300 302 
         duplicate_politic = politics
301 303 
     ) %>%
302 
-        dplyr::select(.data$names, .data$tag)
304 
+        dplyr::select(dplyr::all_of(c("names", "tag")))
303 305 
     data.table::setDT(tag_cols)
304 306 
     return(tag_cols)
305 307 
 }
Browse code

[HOTFIX] Condensed vignettes due to Bioconductor package size issues

Giulia Pais authored on 21/04/2022 09:37:58
Showing 1 changed files
R/exported-vars.R
History View file @ 2b4a9a7
... ... 
@@ -370,7 +370,7 @@ refGene_table_cols <- function() {
370 370 
 #' @description
371 371 
 #' Contains all information associated with critical tags used in the dynamic
372 372 
 #' vars system. To know more see
373 
-#' `vignette("setup_workflow", package="ISAnalytics")`.
373 
+#' `vignette("workflow_start", package="ISAnalytics")`.
374 374 
 #'
375 375 
 #' @return A data frame
376 376 
 #' @export
Browse code

[UPDATE] Final partial update for 1.5.4 - finished documentation, ready to merge

Giulia Pais authored on 20/04/2022 15:58:57
Showing 1 changed files
R/exported-vars.R
History View file @ 5970a6c
... ... 
@@ -5,227 +5,231 @@
5 5 
 # Internal: default mandatory IS vars and associated column types.
6 6 
 # The combination of these fields defines a unique integration site.
7 7 
 .default_mandatory_IS_vars <- function() {
8 
-  tibble::tribble(
9 
-    ~ names, ~ types, ~ transform, ~ flag, ~ tag,
10 
-    "chr", "char", NULL, "required", "chromosome",
11 
-    "integration_locus", "int", NULL, "required", "locus",
12 
-    "strand", "char", NULL, "required", "is_strand"
13 
-  )
8 
+    tibble::tribble(
9 
+        ~names, ~types, ~transform, ~flag, ~tag,
10 
+        "chr", "char", NULL, "required", "chromosome",
11 
+        "integration_locus", "int", NULL, "required", "locus",
12 
+        "strand", "char", NULL, "required", "is_strand"
13 
+    )
14 14 
 }
15 15
16 16 
 # Internal: default genomic annotation IS vars and associated column types.
17 17 
 .default_annotation_IS_vars <- function() {
18 
-  tibble::tribble(
19 
-    ~ names, ~ types, ~ transform, ~ flag, ~ tag,
20 
-    "GeneName", "char", NULL, "required", "gene_symbol",
21 
-    "GeneStrand", "char", NULL, "required", "gene_strand"
22 
-  )
18 
+    tibble::tribble(
19 
+        ~names, ~types, ~transform, ~flag, ~tag,
20 
+        "GeneName", "char", NULL, "required", "gene_symbol",
21 
+        "GeneStrand", "char", NULL, "required", "gene_strand"
22 
+    )
23 23 
 }
24 24
25 25 
 # Internal: default association file columns and types
26 26 
 .default_af_cols <- function() {
27 
-  tibble::tribble(
28 
-    ~ names, ~ types, ~ transform, ~ flag, ~ tag,
29 
-    "ProjectID", "char", NULL, "required", "project_id",
30 
-    "FUSIONID", "char", NULL, "optional", "fusion_id",
31 
-    "PoolID", "char", NULL, "required", "pool_id",
32 
-    "TagSequence", "char", NULL, "required", "tag_seq",
33 
-    "SubjectID", "char", NULL, "required", "subject",
34 
-    "VectorType", "char", NULL, "optional", NA_character_,
35 
-    "VectorID", "char", NULL, "required", "vector_id",
36 
-    "ExperimentID", "char", NULL, "optional", NA_character_,
37 
-    "Tissue", "char", NULL, "required", "tissue",
38 
-    "TimePoint", "char", ~ stringr::str_pad(.x, 4, side = "left", pad = "0"),
39 
-    "required", "tp_days",
40 
-    "DNAFragmentation", "char", NULL, "optional", NA_character_,
41 
-    "PCRMethod", "char", NULL, "required", "pcr_method",
42 
-    "TagIDextended", "char", NULL, "optional", NA_character_,
43 
-    "Keywords","char", NULL, "optional", NA_character_,
44 
-    "CellMarker", "char", NULL, "required", "cell_marker",
45 
-    "TagID", "char", NULL, "required", "tag_id",
46 
-    "NGSProvider", "char", NULL, "optional", NA_character_,
47 
-    "NGSTechnology", "char", NULL, "required", "ngs_tech",
48 
-    "ConverrtedFilesDir", "char", NULL, "optional", NA_character_,
49 
-    "ConverrtedFilesName", "char", NULL, "optional", NA_character_,
50 
-    "SourceFileFolder", "char", NULL, "optional", NA_character_,
51 
-    "SourceFileNameR1", "char", NULL, "optional", NA_character_,
52 
-    "SourceFileNameR2", "char", NULL, "optional", NA_character_,
53 
-    "DNAnumber", "char", NULL, "required", "dna_num",
54 
-    "ReplicateNumber", "int", NULL, "required", "pcr_replicate",
55 
-    "DNAextractionDate", "date", NULL, "optional", NA_character_,
56 
-    "DNAngUsed", "numeric", NULL, "required", NA_character_,
57 
-    "LinearPCRID", "char", NULL, "optional", NA_character_,
58 
-    "LinearPCRDate", "date", NULL, "optional", NA_character_,
59 
-    "SonicationDate", "date", NULL, "optional", NA_character_,
60 
-    "LigationDate", "date", NULL, "optional", NA_character_,
61 
-    "1stExpoPCRID", "char", NULL, "optional", NA_character_,
62 
-    "1stExpoPCRDate", "date", NULL, "optional", NA_character_,
63 
-    "2ndExpoID", "char", NULL, "optional", NA_character_,
64 
-    "2ndExpoDate", "date", NULL, "optional", NA_character_,
65 
-    "FusionPrimerPCRID", "char", NULL, "optional", NA_character_,
66 
-    "FusionPrimerPCRDate", "date", NULL, "optional", NA_character_,
67 
-    "PoolDate", "date", NULL, "optional", NA_character_,
68 
-    "SequencingDate", "date", NULL, "required", NA_character_,
69 
-    "VCN", "numeric", NULL, "required", "vcn",
70 
-    "Genome", "char", NULL, "required", "genome",
71 
-    "SequencingRound", "int", NULL, "optional", NA_character_,
72 
-    "Genotype", "char", NULL, "optional", NA_character_,
73 
-    "TestGroup", "char", NULL, "optional", NA_character_,
74 
-    "MOI", "char", NULL, "optional", NA_character_,
75 
-    "Engraftment", "numeric", NULL, "optional", NA_character_,
76 
-    "Transduction", "numeric", NULL, "optional", NA_character_,
77 
-    "Notes", "char", NULL, "optional", NA_character_,
78 
-    "AddedField1", "char", NULL, "optional", NA_character_,
79 
-    "AddedField2", "char", NULL, "optional", NA_character_,
80 
-    "AddedField3", "char", NULL, "optional", NA_character_,
81 
-    "AddedField4", "char", NULL, "optional", NA_character_,
82 
-    "concatenatePoolIDSeqRun", "char", NULL,"required", "vispa_concatenate",
83 
-    "AddedField6_RelativeBloodPercentage", "char", NULL, "optional",
84 
-    NA_character_,
85 
-    "AddedField7_PurityTestFeasibility", "char", NULL, "optional",
86 
-    NA_character_,
87 
-    "AddedField8_FacsSeparationPurity", "char", NULL, "optional", NA_character_,
88 
-    "Kapa", "numeric", NULL, "required", NA_character_,
89 
-    "ulForPool", "numeric", NULL, "required", NA_character_,
90 
-    "CompleteAmplificationID", "char", NULL, "required", "pcr_repl_id",
91 
-    "UniqueID", "char", NULL, "required", NA_character_,
92 
-    "StudyTestID", "char", NULL, "optional", NA_character_,
93 
-    "StudyTestGroup", "char", NULL, "optional", NA_character_,
94 
-    "MouseID", "char", NULL, "optional", NA_character_,
95 
-    "Tigroup", "char", NULL, "optional", NA_character_,
96 
-    "Tisource", "char", NULL, "optional", NA_character_,
97 
-    "PathToFolderProjectID", "char", NULL, "required", "proj_folder",
98 
-    "SamplesNameCheck", "char", NULL, "optional", NA_character_,
99 
-    "TimepointDays", "char", NULL, "optional", NA_character_,
100 
-    "TimepointMonths", "char", NULL, "optional", NA_character_,
101 
-    "TimepointYears", "char", NULL, "optional", NA_character_,
102 
-    "ng DNA corrected", "numeric", NULL, "optional", NA_character_
103 
-  )
27 
+    tibble::tribble(
28 
+        ~names, ~types, ~transform, ~flag, ~tag,
29 
+        "ProjectID", "char", NULL, "required", "project_id",
30 
+        "FUSIONID", "char", NULL, "optional", "fusion_id",
31 
+        "PoolID", "char", NULL, "required", "pool_id",
32 
+        "TagSequence", "char", NULL, "required", "tag_seq",
33 
+        "SubjectID", "char", NULL, "required", "subject",
34 
+        "VectorType", "char", NULL, "optional", NA_character_,
35 
+        "VectorID", "char", NULL, "required", "vector_id",
36 
+        "ExperimentID", "char", NULL, "optional", NA_character_,
37 
+        "Tissue", "char", NULL, "required", "tissue",
38 
+        "TimePoint", "char", ~ stringr::str_pad(.x, 4, side = "left", pad = "0"),
39 
+        "required", "tp_days",
40 
+        "DNAFragmentation", "char", NULL, "optional", NA_character_,
41 
+        "PCRMethod", "char", NULL, "required", "pcr_method",
42 
+        "TagIDextended", "char", NULL, "optional", NA_character_,
43 
+        "Keywords", "char", NULL, "optional", NA_character_,
44 
+        "CellMarker", "char", NULL, "required", "cell_marker",
45 
+        "TagID", "char", NULL, "required", "tag_id",
46 
+        "NGSProvider", "char", NULL, "optional", NA_character_,
47 
+        "NGSTechnology", "char", NULL, "required", "ngs_tech",
48 
+        "ConverrtedFilesDir", "char", NULL, "optional", NA_character_,
49 
+        "ConverrtedFilesName", "char", NULL, "optional", NA_character_,
50 
+        "SourceFileFolder", "char", NULL, "optional", NA_character_,
51 
+        "SourceFileNameR1", "char", NULL, "optional", NA_character_,
52 
+        "SourceFileNameR2", "char", NULL, "optional", NA_character_,
53 
+        "DNAnumber", "char", NULL, "required", "dna_num",
54 
+        "ReplicateNumber", "int", NULL, "required", "pcr_replicate",
55 
+        "DNAextractionDate", "date", NULL, "optional", NA_character_,
56 
+        "DNAngUsed", "numeric", NULL, "required", NA_character_,
57 
+        "LinearPCRID", "char", NULL, "optional", NA_character_,
58 
+        "LinearPCRDate", "date", NULL, "optional", NA_character_,
59 
+        "SonicationDate", "date", NULL, "optional", NA_character_,
60 
+        "LigationDate", "date", NULL, "optional", NA_character_,
61 
+        "1stExpoPCRID", "char", NULL, "optional", NA_character_,
62 
+        "1stExpoPCRDate", "date", NULL, "optional", NA_character_,
63 
+        "2ndExpoID", "char", NULL, "optional", NA_character_,
64 
+        "2ndExpoDate", "date", NULL, "optional", NA_character_,
65 
+        "FusionPrimerPCRID", "char", NULL, "optional", NA_character_,
66 
+        "FusionPrimerPCRDate", "date", NULL, "optional", NA_character_,
67 
+        "PoolDate", "date", NULL, "optional", NA_character_,
68 
+        "SequencingDate", "date", NULL, "required", NA_character_,
69 
+        "VCN", "numeric", NULL, "required", "vcn",
70 
+        "Genome", "char", NULL, "required", "genome",
71 
+        "SequencingRound", "int", NULL, "optional", NA_character_,
72 
+        "Genotype", "char", NULL, "optional", NA_character_,
73 
+        "TestGroup", "char", NULL, "optional", NA_character_,
74 
+        "MOI", "char", NULL, "optional", NA_character_,
75 
+        "Engraftment", "numeric", NULL, "optional", NA_character_,
76 
+        "Transduction", "numeric", NULL, "optional", NA_character_,
77 
+        "Notes", "char", NULL, "optional", NA_character_,
78 
+        "AddedField1", "char", NULL, "optional", NA_character_,
79 
+        "AddedField2", "char", NULL, "optional", NA_character_,
80 
+        "AddedField3", "char", NULL, "optional", NA_character_,
81 
+        "AddedField4", "char", NULL, "optional", NA_character_,
82 
+        "concatenatePoolIDSeqRun", "char", NULL, "required",
83 
+        "vispa_concatenate",
84 
+        "AddedField6_RelativeBloodPercentage", "char", NULL, "optional",
85 
+        NA_character_,
86 
+        "AddedField7_PurityTestFeasibility", "char", NULL, "optional",
87 
+        NA_character_,
88 
+        "AddedField8_FacsSeparationPurity", "char", NULL, "optional",
89 
+        NA_character_,
90 
+        "Kapa", "numeric", NULL, "required", NA_character_,
91 
+        "ulForPool", "numeric", NULL, "required", NA_character_,
92 
+        "CompleteAmplificationID", "char", NULL, "required", "pcr_repl_id",
93 
+        "UniqueID", "char", NULL, "required", NA_character_,
94 
+        "StudyTestID", "char", NULL, "optional", NA_character_,
95 
+        "StudyTestGroup", "char", NULL, "optional", NA_character_,
96 
+        "MouseID", "char", NULL, "optional", NA_character_,
97 
+        "Tigroup", "char", NULL, "optional", NA_character_,
98 
+        "Tisource", "char", NULL, "optional", NA_character_,
99 
+        "PathToFolderProjectID", "char", NULL, "required", "proj_folder",
100 
+        "SamplesNameCheck", "char", NULL, "optional", NA_character_,
101 
+        "TimepointDays", "char", NULL, "optional", NA_character_,
102 
+        "TimepointMonths", "char", NULL, "optional", NA_character_,
103 
+        "TimepointYears", "char", NULL, "optional", NA_character_,
104 
+        "ng DNA corrected", "numeric", NULL, "optional", NA_character_
105 
+    )
104 106 
 }
105 107
106 108 
 # Internal: default columns and types of vispa2 stats cols
107 109 
 .default_iss_stats_specs <- function() {
108 
-  tibble::tribble(
109 
-    ~ names, ~ types, ~ transform, ~ flag, ~ tag,
110 
-    "RUN_NAME", "char", NULL, "required", NA_character_,
111 
-    "POOL", "char", NULL, "required", "vispa_concatenate",
112 
-    "TAG", "char", ~ stringr::str_replace_all(.x, pattern = "\\.",
113 
-                                              replacement = ""), "required",
114 
-    "tag_seq",
115 
-    "RAW_READS", "int", NULL, "optional", NA_character_,
116 
-    "QUALITY_PASSED", "int", NULL, "optional", NA_character_,
117 
-    "PHIX_MAPPING", "int", NULL, "optional", NA_character_,
118 
-    "PLASMID_MAPPED_BYPOOL", "int", NULL, "optional", NA_character_,
119 
-    "BARCODE_MUX", "int", NULL, "required", NA_character_,
120 
-    "LTR_IDENTIFIED", "int", NULL, "optional", NA_character_,
121 
-    "TRIMMING_FINAL_LTRLC", "int", NULL, "optional", NA_character_,
122 
-    "LV_MAPPED", "int", NULL, "optional", NA_character_,
123 
-    "BWA_MAPPED_OVERALL", "int", NULL, "optional", NA_character_,
124 
-    "ISS_MAPPED_OVERALL", "int", NULL, "optional", NA_character_,
125 
-    "ISS_MAPPED_PP", "int", NULL, "optional", NA_character_
126 
-  )
110 
+    tibble::tribble(
111 
+        ~names, ~types, ~transform, ~flag, ~tag,
112 
+        "RUN_NAME", "char", NULL, "required", NA_character_,
113 
+        "POOL", "char", NULL, "required", "vispa_concatenate",
114 
+        "TAG", "char", ~ stringr::str_replace_all(.x,
115 
+            pattern = "\\.",
116 
+            replacement = ""
117 
+        ), "required",
118 
+        "tag_seq",
119 
+        "RAW_READS", "int", NULL, "optional", NA_character_,
120 
+        "QUALITY_PASSED", "int", NULL, "optional", NA_character_,
121 
+        "PHIX_MAPPING", "int", NULL, "optional", NA_character_,
122 
+        "PLASMID_MAPPED_BYPOOL", "int", NULL, "optional", NA_character_,
123 
+        "BARCODE_MUX", "int", NULL, "required", NA_character_,
124 
+        "LTR_IDENTIFIED", "int", NULL, "optional", NA_character_,
125 
+        "TRIMMING_FINAL_LTRLC", "int", NULL, "optional", NA_character_,
126 
+        "LV_MAPPED", "int", NULL, "optional", NA_character_,
127 
+        "BWA_MAPPED_OVERALL", "int", NULL, "optional", NA_character_,
128 
+        "ISS_MAPPED_OVERALL", "int", NULL, "optional", NA_character_,
129 
+        "ISS_MAPPED_PP", "int", NULL, "optional", NA_character_
130 
+    )
127 131 
 }
128 132
129 133 
 # Mappings between input format and formats requested by external parsing
130 134 
 # functions
131 135 
 .types_mapping <- function() {
132 
-  tibble::tribble(
133 
-    ~ types, ~ mapping, ~ fread,
134 
-    "char", "c", "character",
135 
-    "int", "i", "integer",
136 
-    "logi", "l", "logical",
137 
-    "numeric", "d", "numeric",
138 
-    "factor", "f", "factor",
139 
-    "date", "c", "charcter",
140 
-    "ymd", "c", "character",
141 
-    "ydm", "c", "character",
142 
-    "mdy", "c", "character",
143 
-    "myd", "c", "character",
144 
-    "dmy", "c", "character",
145 
-    "yq", "c", "character",
146 
-    "ym", "c", "character",
147 
-    "my", "c", "character",
148 
-    "ymd_hms", "c", "character",
149 
-    "ymd_hm", "c", "character",
150 
-    "ymd_h", "c", "character",
151 
-    "dmy_hms", "c", "character",
152 
-    "dmy_hm", "c", "character",
153 
-    "dmy_h", "c", "character",
154 
-    "mdy_hms", "c", "character",
155 
-    "mdy_hm", "c", "character",
156 
-    "mdy_h", "c", "character",
157 
-    "ydm_hms", "c", "character",
158 
-    "ydm_hm", "c", "character",
159 
-    "ydm_h", "c", "character"
160 
-  )
136 
+    tibble::tribble(
137 
+        ~types, ~mapping, ~fread,
138 
+        "char", "c", "character",
139 
+        "int", "i", "integer",
140 
+        "logi", "l", "logical",
141 
+        "numeric", "d", "numeric",
142 
+        "factor", "f", "factor",
143 
+        "date", "c", "charcter",
144 
+        "ymd", "c", "character",
145 
+        "ydm", "c", "character",
146 
+        "mdy", "c", "character",
147 
+        "myd", "c", "character",
148 
+        "dmy", "c", "character",
149 
+        "yq", "c", "character",
150 
+        "ym", "c", "character",
151 
+        "my", "c", "character",
152 
+        "ymd_hms", "c", "character",
153 
+        "ymd_hm", "c", "character",
154 
+        "ymd_h", "c", "character",
155 
+        "dmy_hms", "c", "character",
156 
+        "dmy_hm", "c", "character",
157 
+        "dmy_h", "c", "character",
158 
+        "mdy_hms", "c", "character",
159 
+        "mdy_hm", "c", "character",
160 
+        "mdy_h", "c", "character",
161 
+        "ydm_hms", "c", "character",
162 
+        "ydm_hm", "c", "character",
163 
+        "ydm_h", "c", "character"
164 
+    )
161 165 
 }
162 166
163 167 
 # Internal: associates column types with column names for a more precise
164 168 
 # import
165 169 
 .mandatory_IS_types <- function(mode) {
166 
-  specs <- mandatory_IS_vars(include_types = TRUE)
167 
-  specs_mappings <- specs %>%
168 
-    dplyr::left_join(.types_mapping(), by = "types")
169 
-  if (mode == "fread") {
170 
-    specs_mappings <- specs_mappings %>%
171 
-      dplyr::select(.data$names, .data$fread) %>%
172 
-      dplyr::group_by(.data$fread)
173 
-    types <- specs_mappings %>%
174 
-      dplyr::group_keys() %>%
175 
-      dplyr::pull(.data$fread)
176 
-    specs_mappings <- specs_mappings %>%
177 
-      dplyr::group_split(.keep = FALSE)
178 
-    names(specs_mappings) <- types
179 
-    types <- purrr::map(specs_mappings, ~ .x$names)
170 
+    specs <- mandatory_IS_vars(include_types = TRUE)
171 
+    specs_mappings <- specs %>%
172 
+        dplyr::left_join(.types_mapping(), by = "types")
173 
+    if (mode == "fread") {
174 
+        specs_mappings <- specs_mappings %>%
175 
+            dplyr::select(.data$names, .data$fread) %>%
176 
+            dplyr::group_by(.data$fread)
177 
+        types <- specs_mappings %>%
178 
+            dplyr::group_keys() %>%
179 
+            dplyr::pull(.data$fread)
180 
+        specs_mappings <- specs_mappings %>%
181 
+            dplyr::group_split(.keep = FALSE)
182 
+        names(specs_mappings) <- types
183 
+        types <- purrr::map(specs_mappings, ~ .x$names)
184 
+        return(types)
185 
+    }
186 
+    types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
180 187 
     return(types)
181 
-  }
182 
-  types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
183 
-  return(types)
184 188 
 }
185 189
186 190 
 # Internal: associates column types with column names for a more precise
187 191 
 # import
188 192 
 .annotation_IS_types <- function(mode) {
189 
-  specs <- annotation_IS_vars(include_types = TRUE)
190 
-  specs_mappings <- specs %>%
191 
-    dplyr::left_join(.types_mapping(), by = "types")
192 
-  if (mode == "fread") {
193 
-    specs_mappings <- specs_mappings %>%
194 
-      dplyr::select(.data$names, .data$fread) %>%
195 
-      dplyr::group_by(.data$fread)
196 
-    types <- specs_mappings %>%
197 
-      dplyr::group_keys() %>%
198 
-      dplyr::pull(.data$fread)
199 
-    specs_mappings <- specs_mappings %>%
200 
-      dplyr::group_split(.keep = FALSE)
201 
-    names(specs_mappings) <- types
202 
-    types <- purrr::map(specs_mappings, ~ .x$names)
193 
+    specs <- annotation_IS_vars(include_types = TRUE)
194 
+    specs_mappings <- specs %>%
195 
+        dplyr::left_join(.types_mapping(), by = "types")
196 
+    if (mode == "fread") {
197 
+        specs_mappings <- specs_mappings %>%
198 
+            dplyr::select(.data$names, .data$fread) %>%
199 
+            dplyr::group_by(.data$fread)
200 
+        types <- specs_mappings %>%
201 
+            dplyr::group_keys() %>%
202 
+            dplyr::pull(.data$fread)
203 
+        specs_mappings <- specs_mappings %>%
204 
+            dplyr::group_split(.keep = FALSE)
205 
+        names(specs_mappings) <- types
206 
+        types <- purrr::map(specs_mappings, ~ .x$names)
207 
+        return(types)
208 
+    }
209 
+    types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
203 210 
     return(types)
204 
-  }
205 
-  types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
206 
-  return(types)
207 211 
 }
208 212
209 213 
 # Internal: associates column types with column names for a more precise
210 214 
 # import
211 215 
 .af_col_types <- function(mode) {
212 
-  specs <- association_file_columns(include_types = TRUE)
213 
-  specs_mappings <- specs %>%
214 
-    dplyr::left_join(.types_mapping(), by = "types")
215 
-  if (mode == "fread") {
216 
-    specs_mappings <- specs_mappings %>%
217 
-      dplyr::select(.data$names, .data$fread) %>%
218 
-      dplyr::group_by(.data$fread)
219 
-    types <- specs_mappings %>%
220 
-      dplyr::group_keys() %>%
221 
-      dplyr::pull(.data$fread)
222 
-    specs_mappings <- specs_mappings %>%
223 
-      dplyr::group_split(.keep = FALSE)
224 
-    names(specs_mappings) <- types
225 
-    types <- purrr::map(specs_mappings, ~ .x$names)
226 
-    return(types)
227 
-  }
228 
-  types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
216 
+    specs <- association_file_columns(include_types = TRUE)
217 
+    specs_mappings <- specs %>%
218 
+        dplyr::left_join(.types_mapping(), by = "types")
219 
+    if (mode == "fread") {
220 
+        specs_mappings <- specs_mappings %>%
221 
+            dplyr::select(.data$names, .data$fread) %>%
222 
+            dplyr::group_by(.data$fread)
223 
+        types <- specs_mappings %>%
224 
+            dplyr::group_keys() %>%
225 
+            dplyr::pull(.data$fread)
226 
+        specs_mappings <- specs_mappings %>%
227 
+            dplyr::group_split(.keep = FALSE)
228 
+        names(specs_mappings) <- types
229 
+        types <- purrr::map(specs_mappings, ~ .x$names)
230 
+        return(types)
231 
+    }
232 
+    types <- as.list(setNames(specs_mappings$mapping, specs_mappings$names))
229 233 
 }
230 234
231 235
... ... 
@@ -266,36 +270,38 @@
266 270 
 #' @examples
267 271 
 #' reduced_AF_columns()
268 272 
 reduced_AF_columns <- function() {
269 
-  required <- list(
270 
-    tag_id = "char",
271 
-    tissue = "char",
272 
-    subject = "char",
273 
-    tp_days = c("char", "numeric", "integer"),
274 
-    fusion_id = "char",
275 
-    pcr_repl_id = "char",
276 
-    cell_marker = "char",
277 
-    project_id = "char",
278 
-    vector_id = "char",
279 
-    pool_id = "char"
280 
-  )
281 
-  politics <- list(
282 
-    tag_id = "error",
283 
-    tissue = "error",
284 
-    subject = "error",
285 
-    tp_days = "first",
286 
-    fusion_id = "error",
287 
-    pcr_repl_id = "error",
288 
-    cell_marker = "error",
289 
-    project_id = "error",
290 
-    vector_id = "error",
291 
-    pool_id = "error"
292 
-  )
293 
-  tag_cols <- .check_required_cols(required_tags = required,
294 
-                                   vars_df = association_file_columns(TRUE),
295 
-                                   duplicate_politic = politics) %>%
296 
-    dplyr::select(.data$names, .data$tag)
297 
-  data.table::setDT(tag_cols)
298 
-  return(tag_cols)
273 
+    required <- list(
274 
+        tag_id = "char",
275 
+        tissue = "char",
276 
+        subject = "char",
277 
+        tp_days = c("char", "numeric", "integer"),
278 
+        fusion_id = "char",
279 
+        pcr_repl_id = "char",
280 
+        cell_marker = "char",
281 
+        project_id = "char",
282 
+        vector_id = "char",
283 
+        pool_id = "char"
284 
+    )
285 
+    politics <- list(
286 
+        tag_id = "error",
287 
+        tissue = "error",
288 
+        subject = "error",
289 
+        tp_days = "first",
290 
+        fusion_id = "error",
291 
+        pcr_repl_id = "error",
292 
+        cell_marker = "error",
293 
+        project_id = "error",
294 
+        vector_id = "error",
295 
+        pool_id = "error"
296 
+    )
297 
+    tag_cols <- .check_required_cols(
298 
+        required_tags = required,
299 
+        vars_df = association_file_columns(TRUE),
300 
+        duplicate_politic = politics
301 
+    ) %>%
302 
+        dplyr::select(.data$names, .data$tag)
303 
+    data.table::setDT(tag_cols)
304 
+    return(tag_cols)
299 305 
 }
300 306
301 307 
 # Names of the columns of iss stats considered for aggregation
... ... 
@@ -359,107 +365,168 @@ refGene_table_cols <- function() {
359 365 
 }
360 366
361 367
362 
-#' Title
368 
+#' All available tags for dynamic vars look-up tables.
363 369 
 #'
364 
-#' @return
370 
+#' @description
371 
+#' Contains all information associated with critical tags used in the dynamic
372 
+#' vars system. To know more see
373 
+#' `vignette("setup_workflow", package="ISAnalytics")`.
374 
+#'
375 
+#' @return A data frame
365 376 
 #' @export
366 377 
 #'
367 378 
 #' @examples
379 
+#' available_tags()
368 380 
 available_tags <- function() {
369 
-  data.table::data.table(
370 
-    tag = c("chromosome", "locus", "is_strand", "gene_symbol", "gene_strand",
371 
-            "project_id", "fusion_id", "tag_seq", "subject", "vector_id",
381 
+    data.table::data.table(
382 
+        tag = c(
383 
+            "chromosome", "locus", "is_strand", "gene_symbol", "gene_strand",
384 
+            "project_id", "pool_id", "fusion_id", "tag_seq", "subject",
385 
+            "vector_id",
372 386 
             "tissue", "tp_days", "pcr_method", "cell_marker", "tag_id",
373 387 
             "ngs_tech", "dna_num", "pcr_replicate", "vcn", "vispa_concatenate",
374 388 
             "pcr_repl_id", "proj_folder", "genome",
375 
-            "vispa_concatenate", "tag_seq"),
376 
-    needed_in = list(c("top_targeted_genes",
377 
-                       "CIS_grubbs",
378 
-                       "compute_near_integrations"),
379 
-                     c("top_targeted_genes",
380 
-                       "CIS_grubbs",
381 
-                       "compute_near_integrations"),
382 
-                     c("CIS_grubbs",
383 
-                       "compute_near_integrations"),
384 
-                     c("top_targeted_genes",
385 
-                       "CIS_grubbs",
386 
-                       "compute_near_integrations",
387 
-                       "CIS_volcano_plot"),
388 
-                     c("top_targeted_genes",
389 
-                       "CIS_grubbs"),
390 
-                     c("generate_default_folder_structure",
391 
-                       "import_Vispa2_stats", "remove_collisions",
392 
-                       "generate_Vispa2_launch_AF", "import_association_file",
393 
-                       "import_parallel_Vispa2Matrices"),
394 
-                     c("generate_Vispa2_launch_AF"),
395 
-                     c("generate_default_folder_structure",
396 
-                       "import_association_file", "import_Vispa2_stats"),
397 
-                     c("import_association_file",
398 
-                       "HSC_population_size_estimate"),
399 
-                     c("generate_Vispa2_launch_AF"),
400 
-                     c("generate_Vispa2_launch_AF", "import_association_file",
401 
-                       "HSC_population_size_estimate"),
402 
-                     c("generate_Vispa2_launch_AF", "import_association_file"),
403 
-                     c(),
404 
-                     c("generate_Vispa2_launch_AF", "import_association_file",
405 
-                       "HSC_population_size_estimate"),
406 
-                     c("generate_Vispa2_launch_AF"),
407 
-                     c(),
408 
-                     c(),
409 
-                     c("import_association_file", "remove_collisions"),
410 
-                     c(),
411 
-                     c("import_association_file", "generate_Vispa2_launch_AF",
412 
-                       "generate_default_folder_structure",
413 
-                       "import_Vispa2_stats", "import_parallel_Vispa2Matrices"),
414 
-                     c("pcr_id_column", "generate_Vispa2_launch_AF",
415 
-                       "import_association_file", "import_Vispa2_stats"),
416 
-                     c("import_association_file"),
417 
-                     c(),
418 
-                     c("import_association_file", "generate_Vispa2_launch_AF",
419 
-                       "generate_default_folder_structure",
420 
-                       "import_Vispa2_stats", "import_parallel_Vispa2Matrices"),
421 
-                     c("generate_default_folder_structure",
422 
-                       "import_association_file", "import_Vispa2_stats")
423 
-                     ),
424 
-    description = c(paste("Number of the chromosome"),
425 
-                    paste("The locus at which the integration occurs"),
426 
-                    paste("The DNA strand in which the integration occurs"),
427 
-                    paste("The symbol of the gene"),
428 
-                    paste("The strand of the gene"),
429 
-                    paste("Unique identifier of a project"),
430 
-                    paste("Identification code/number of the",
431 
-                          "barcoded (SLiM-)PCR product included in the",
432 
-                          "sequencing library"),
433 
-                    paste("The barcode tag sequence"),
434 
-                    paste("Unique identifier of a study subject",
435 
-                          "(usually a patient)"),
436 
-                    paste("Unique identifier of the vector used"),
437 
-                    paste("The biological tissue the sample belongs to"),
438 
-                    paste("The time point expressed in days"),
439 
-                    paste("The PCR method used"),
440 
-                    paste("Cell marker associated with isolated",
441 
-                          "cells carrying the IS"),
442 
-                    paste("Unique identifier of the barcode tag, as specified",
443 
-                          "in VISPA2 requirements"),
444 
-                    paste("Technology used for next generation sequencing"),
445 
-                    paste("Identification code/number of the DNA extraction",
446 
-                          "from a specific biological sample"),
447 
-                    paste("Number of the PCR replicate"),
448 
-                    paste("Vector copy number"),
449 
-                    paste("Unique identifier of a pool as specified in VISPA2"),
450 
-                    paste("Unique identifier of the pcr replicate, used as",
451 
-                          "key to join data and metadata"),
452 
-                    paste("Path on disk containing the standard VISPA2 folder",
453 
-                          "structure of the project"),
454 
-                    paste("The reference genome (e.g. “hg19”)"),
455 
-                    paste("Unique identifier of a pool as specified in VISPA2"),
456 
-                    paste("The barcode tag sequence")
457 
-                    ),
458 
-    dyn_vars_tbl = c("mand_vars", "mand_vars", "mand_vars",
459 
-                     "annot_vars", "annot_vars",
460 
-                     "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
461 
-                     "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
462 
-                     "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
463 
-                     "af_vars", "af_vars", "af_vars", "iss_vars", "iss_vars")
464 
-  )
389 
+            "vispa_concatenate", "tag_seq"
390 
+        ),
391 
+        needed_in = list(
392 
+            c(
393 
+                "top_targeted_genes",
394 
+                "CIS_grubbs",
395 
+                "compute_near_integrations"
396 
+            ),
397 
+            c(
398 
+                "top_targeted_genes",
399 
+                "CIS_grubbs",
400 
+                "compute_near_integrations"
401 
+            ),
402 
+            c(
403 
+                "CIS_grubbs",
404 
+                "compute_near_integrations"
405 
+            ),
406 
+            c(
407 
+                "top_targeted_genes",
408 
+                "CIS_grubbs",
409 
+                "compute_near_integrations",
410 
+                "CIS_volcano_plot"
411 
+            ),
412 
+            c(
413 
+                "top_targeted_genes",
414 
+                "CIS_grubbs"
415 
+            ),
416 
+            c(
417 
+                "generate_default_folder_structure",
418 
+                "import_Vispa2_stats", "remove_collisions",
419 
+                "generate_Vispa2_launch_AF", "import_association_file",
420 
+                "import_parallel_Vispa2Matrices"
421 
+            ),
422 
+            c(
423 
+                "generate_Vispa2_launch_AF", "remove_collisions",
424 
+                "import_association_file"
425 
+            ),
426 
+            c("generate_Vispa2_launch_AF"),
427 
+            c(
428 
+                "generate_default_folder_structure",
429 
+                "import_association_file", "import_Vispa2_stats"
430 
+            ),
431 
+            c(
432 
+                "import_association_file",
433 
+                "HSC_population_size_estimate"
434 
+            ),
435 
+            c("generate_Vispa2_launch_AF"),
436 
+            c(
437 
+                "generate_Vispa2_launch_AF", "import_association_file",
438 
+                "HSC_population_size_estimate"
439 
+            ),
440 
+            c("generate_Vispa2_launch_AF", "import_association_file"),
441 
+            c(),
442 
+            c(
443 
+                "generate_Vispa2_launch_AF", "import_association_file",
444 
+                "HSC_population_size_estimate"
445 
+            ),
446 
+            c("generate_Vispa2_launch_AF"),
447 
+            c(),
448 
+            c(),
449 
+            c("import_association_file", "remove_collisions"),
450 
+            c(),
451 
+            c(
452 
+                "import_association_file", "generate_Vispa2_launch_AF",
453 
+                "generate_default_folder_structure",
454 
+                "import_Vispa2_stats", "import_parallel_Vispa2Matrices"
455 
+            ),
456 
+            c(
457 
+                "pcr_id_column", "generate_Vispa2_launch_AF",
458 
+                "import_association_file", "import_Vispa2_stats"
459 
+            ),
460 
+            c("import_association_file"),
461 
+            c(),
462 
+            c(
463 
+                "import_association_file", "generate_Vispa2_launch_AF",
464 
+                "generate_default_folder_structure",
465 
+                "import_Vispa2_stats", "import_parallel_Vispa2Matrices"
466 
+            ),
467 
+            c(
468 
+                "generate_default_folder_structure",
469 
+                "import_association_file", "import_Vispa2_stats"
470 
+            )
471 
+        ),
472 
+        description = c(
473 
+            paste("Number of the chromosome"),
474 
+            paste("The locus at which the integration occurs"),
475 
+            paste("The DNA strand in which the integration occurs"),
476 
+            paste("The symbol of the gene"),
477 
+            paste("The strand of the gene"),
478 
+            paste("Unique identifier of a project"),
479 
+            paste("Unique identifier of a sequencing pool"),
480 
+            paste(
481 
+                "Identification code/number of the",
482 
+                "barcoded (SLiM-)PCR product included in the",
483 
+                "sequencing library"
484 
+            ),
485 
+            paste("The barcode tag sequence"),
486 
+            paste(
487 
+                "Unique identifier of a study subject",
488 
+                "(usually a patient)"
489 
+            ),
490 
+            paste("Unique identifier of the vector used"),
491 
+            paste("The biological tissue the sample belongs to"),
492 
+            paste("The time point expressed in days"),
493 
+            paste("The PCR method used"),
494 
+            paste(
495 
+                "Cell marker associated with isolated",
496 
+                "cells carrying the IS"
497 
+            ),
498 
+            paste(
499 
+                "Unique identifier of the barcode tag, as specified",
500 
+                "in VISPA2 requirements"
501 
+            ),
502 
+            paste("Technology used for next generation sequencing"),
503 
+            paste(
504 
+                "Identification code/number of the DNA extraction",
505 
+                "from a specific biological sample"
506 
+            ),
507 
+            paste("Number of the PCR replicate"),
508 
+            paste("Vector copy number"),
509 
+            paste("Unique identifier of a pool as specified in VISPA2"),
510 
+            paste(
511 
+                "Unique identifier of the pcr replicate, used as",
512 
+                "key to join data and metadata"
513 
+            ),
514 
+            paste(
515 
+                "Path on disk containing the standard VISPA2 folder",
516 
+                "structure of the project"
517 
+            ),
518 
+            paste("The reference genome (e.g. 'hg19')"),
519 
+            paste("Unique identifier of a pool as specified in VISPA2"),
520 
+            paste("The barcode tag sequence")
521 
+        ),
522 
+        dyn_vars_tbl = c(
523 
+            "mand_vars", "mand_vars", "mand_vars",
524 
+            "annot_vars", "annot_vars",
525 
+            "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
526 
+            "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
527 
+            "af_vars", "af_vars", "af_vars", "af_vars", "af_vars",
528 
+            "af_vars", "af_vars", "af_vars", "af_vars",
529 
+            "iss_vars", "iss_vars"
530 
+        )
531 
+    )
465 532 
 }
Browse code

[UPDATE] Partial update 1.5.4 - fixed all functions, increased package coverage, documentation still to fix

Giulia Pais authored on 15/04/2022 16:47:59
Showing 1 changed files
R/exported-vars.R
History View file @ 743f4ae
... ... 
@@ -27,12 +27,12 @@
27 27 
   tibble::tribble(
28 28 
     ~ names, ~ types, ~ transform, ~ flag, ~ tag,
29 29 
     "ProjectID", "char", NULL, "required", "project_id",
30 
-    "FUSIONID", "char", NULL, "optional", NA_character_,
30 
+    "FUSIONID", "char", NULL, "optional", "fusion_id",
31 31 
     "PoolID", "char", NULL, "required", "pool_id",
32 32 
     "TagSequence", "char", NULL, "required", "tag_seq",
33 33 
     "SubjectID", "char", NULL, "required", "subject",
34 34 
     "VectorType", "char", NULL, "optional", NA_character_,
35 
-    "VectorID", "char", NULL, "required", NA_character_,
35 
+    "VectorID", "char", NULL, "required", "vector_id",
36 36 
     "ExperimentID", "char", NULL, "optional", NA_character_,
37 37 
     "Tissue", "char", NULL, "required", "tissue",
38 38 
     "TimePoint", "char", ~ stringr::str_pad(.x, 4, side = "left", pad = "0"),
... ... 
@@ -42,7 +42,7 @@
42 42 
     "TagIDextended", "char", NULL, "optional", NA_character_,
43 43 
     "Keywords","char", NULL, "optional", NA_character_,
44 44 
     "CellMarker", "char", NULL, "required", "cell_marker",
45 
-    "TagID", "char", NULL, "required", NA_character_,
45 
+    "TagID", "char", NULL, "required", "tag_id",
46 46 
     "NGSProvider", "char", NULL, "optional", NA_character_,
47 47 
     "NGSTechnology", "char", NULL, "required", "ngs_tech",
48 48 
     "ConverrtedFilesDir", "char", NULL, "optional", NA_character_,
... ... 
@@ -266,11 +266,36 @@
266 266 
 #' @examples
267 267 
 #' reduced_AF_columns()
268 268 
 reduced_AF_columns <- function() {
269 
-    c(
270 
-        "TagID", "Tissue", "SubjectID", "TimePoint", "FUSIONID",
271 
-        "CompleteAmplificationID", "CellMarker", "ProjectID", "VectorID",
272 
-        "PoolID"
273 
-    )
269 
+  required <- list(
270 
+    tag_id = "char",
271 
+    tissue = "char",
272 
+    subject = "char",
273 
+    tp_days = c("char", "numeric", "integer"),
274 
+    fusion_id = "char",
275 
+    pcr_repl_id = "char",
276 
+    cell_marker = "char",
277 
+    project_id = "char",
278 
+    vector_id = "char",
279 
+    pool_id = "char"
280 
+  )
281 
+  politics <- list(
282 
+    tag_id = "error",
283 
+    tissue = "error",
284 
+    subject = "error",
285 
+    tp_days = "first",
286 
+    fusion_id = "error",
287 
+    pcr_repl_id = "error",
288 
+    cell_marker = "error",
289 
+    project_id = "error",
290 
+    vector_id = "error",
291 
+    pool_id = "error"
292 
+  )
293 
+  tag_cols <- .check_required_cols(required_tags = required,
294 
+                                   vars_df = association_file_columns(TRUE),
295 
+                                   duplicate_politic = politics) %>%
296 
+    dplyr::select(.data$names, .data$tag)
297 
+  data.table::setDT(tag_cols)
298 
+  return(tag_cols)
274 299 
 }
275 300
276 301 
 # Names of the columns of iss stats considered for aggregation
... ... 
@@ -334,20 +359,107 @@ refGene_table_cols <- function() {
334 359 
 }
335 360
336 361
337 
-available_column_tags <- function() {
338 
-    list(
339 
-        critical = list(af = c(
340 
-            "project_id", "pool_id", "tag_seq", "subject", "tissue",
341 
-            "cell_marker", "pcr_replicate", "vispa_concatenate",
342 
-            "pcr_repl_id", "proj_folder"
343 
-        ),
344