new file mode 100644

@@ -0,0 +1,48 @@

+on:

+  push:

+    branches:

+      - RELEASE_3_12

+      - master

+

+name: pkgdown

+

+jobs:

+  pkgdown:

+    runs-on: macOS-latest

+    env:

+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}

+    steps:

+      - uses: actions/checkout@v2

+

+      - uses: r-lib/actions/setup-r@v1

+

+      - uses: r-lib/actions/setup-pandoc@v1

+

+      - name: Query dependencies

+        run: |

+          install.packages('remotes')

+          saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)

+          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")

+        shell: Rscript {0}

+

+      - name: Cache R packages

+        uses: actions/cache@v2

+        with:

+          path: ${{ env.R_LIBS_USER }}

+          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}

+          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-

+

+      - name: Install dependencies

+        run: |

+          remotes::install_deps(dependencies = TRUE)

+          install.packages("pkgdown", type = "binary")

+        shell: Rscript {0}

+

+      - name: Install package

+        run: R CMD INSTALL .

+

+      - name: Deploy package

+        run: |

+          git config --local user.email "actions@github.com"

+          git config --local user.name "GitHub Actions"

+          Rscript -e 'pkgdown::deploy_to_branch(new_process = FALSE)'

@@ -1,6 +1,6 @@

 Package: ISAnalytics

 Title: Analyze gene therapy vector insertion sites data identified from genomics next generation sequencing reads for clonal tracking studies

-Version: 1.1.9

+Version: 1.1.10

 Date: 2020-07-03

 Authors@R: c(

   person(given = "Andrea",

@@ -45,7 +45,10 @@ Imports:

     stats,

     upsetjs,

     psych,

-    grDevices

+    grDevices,

+    data.table,

+    readxl,

+    tools

 Encoding: UTF-8

 LazyData: false

 Roxygen: list(markdown = TRUE)

@@ -59,7 +62,9 @@ Suggests:

     sessioninfo,

     rmarkdown,

     roxygen2,

-    vegan

+    vegan,

+    withr

 VignetteBuilder: knitr

 RdMacros: 

     lifecycle

+Config/testthat/edition: 3

@@ -37,7 +37,6 @@ import(BiocParallel)

 import(dplyr)

 import(ggplot2)

 import(lifecycle)

-import(lubridate)

 import(upsetjs)

 importFrom(BiocParallel,MulticoreParam)

 importFrom(BiocParallel,SnowParam)

@@ -45,13 +44,15 @@ importFrom(BiocParallel,bplapply)

 importFrom(BiocParallel,bpok)

 importFrom(BiocParallel,bpstop)

 importFrom(BiocParallel,bptry)

+importFrom(data.table,fread)

+importFrom(data.table,melt.data.table)

+importFrom(data.table,rbindlist)

+importFrom(data.table,setDT)

 importFrom(dplyr,across)

 importFrom(dplyr,all_of)

 importFrom(dplyr,arrange)

 importFrom(dplyr,bind_cols)

 importFrom(dplyr,bind_rows)

-importFrom(dplyr,contains)

-importFrom(dplyr,desc)

 importFrom(dplyr,distinct)

 importFrom(dplyr,filter)

 importFrom(dplyr,full_join)

@@ -64,7 +65,6 @@ importFrom(dplyr,rename)

 importFrom(dplyr,select)

 importFrom(dplyr,semi_join)

 importFrom(dplyr,slice)

-importFrom(dplyr,slice_head)

 importFrom(forcats,as_factor)

 importFrom(forcats,fct_inseq)

 importFrom(fs,as_fs_path)

@@ -75,6 +75,7 @@ importFrom(fs,file_exists)

 importFrom(fs,is_dir)

 importFrom(fs,path)

 importFrom(fs,path_dir)

+importFrom(fs,path_ext)

 importFrom(fs,path_wd)

 importFrom(ggrepel,geom_label_repel)

 importFrom(grDevices,colorRamp)

@@ -88,6 +89,7 @@ importFrom(htmltools,h4)

 importFrom(htmltools,save_html)

 importFrom(htmltools,tagList)

 importFrom(htmltools,tags)

+importFrom(lubridate,parse_date_time)

 importFrom(magrittr,`%>%`)

 importFrom(psych,describe)

 importFrom(purrr,flatten)

@@ -98,6 +100,7 @@ importFrom(purrr,map)

 importFrom(purrr,map2)

 importFrom(purrr,map2_dfr)

 importFrom(purrr,map2_lgl)

+importFrom(purrr,map_chr)

 importFrom(purrr,map_dbl)

 importFrom(purrr,map_dfr)

 importFrom(purrr,map_lgl)

@@ -113,14 +116,23 @@ importFrom(reactable,colDef)

 importFrom(reactable,colFormat)

 importFrom(reactable,reactable)

 importFrom(reactable,reactableTheme)

+importFrom(readr,cols)

 importFrom(readr,parse_factor)

+importFrom(readr,problems)

+importFrom(readr,read_delim)

 importFrom(readr,write_tsv)

+importFrom(readxl,read_excel)

 importFrom(rlang,.data)

 importFrom(rlang,`:=`)

+importFrom(rlang,abort)

 importFrom(rlang,arg_match)

+importFrom(rlang,call2)

+importFrom(rlang,dots_list)

 importFrom(rlang,env_bind)

 importFrom(rlang,eval_tidy)

 importFrom(rlang,expr)

+importFrom(rlang,fn_fmls_names)

+importFrom(rlang,inform)

 importFrom(rlang,parse_expr)

 importFrom(stats,median)

 importFrom(stats,na.omit)

@@ -148,6 +160,7 @@ importFrom(tidyr,pivot_wider)

 importFrom(tidyr,separate)

 importFrom(tidyr,unite)

 importFrom(tidyr,unnest)

+importFrom(tools,file_path_sans_ext)

 importFrom(utils,read.csv)

 importFrom(utils,read.delim)

 importFrom(utils,tail)

@@ -1,5 +1,50 @@

 \title{ISAnalytics News}

+# ISAnalytics 1.1.10 (2021-04-08)

+

+## FIXES

+

+* Fixed issue in `compute_near_integrations`: when provided recalibration

+map export path as a folder now the function works correctly and produces

+an automatically generated file name

+* Fixed issue in `aggregate_metadata`: now paths to folder that contains

+Vispa2 stats is looked up correctly. Also, VISPA2 stats columns are aggregated

+if found in the input data frame independently from the parameter 

+`import_stats`.

+

+## IMPROVEMENTS

+

+* `compute_abundance` can now take as input aggregated matrices and has

+additional parameters to offer more flexibility to the user. Major updates

+and improvements also on documentation and reproducible examples.

+* Major improvements in function `import_single_Vispa2Matrix`: import is 

+now preferentially carried out using `data.table::fread` greatly speeding up 

+the process - where not possible `readr::read_delim` is used instead

+* Major improvements in function `import_association_file`: greatly improved

+parsing precision (each column has a dedicated type), import report now 

+signals parsing problems and their location and signals also

+problems in parsing dates.

+Report also includes potential problems in column names and signals missing

+data in important columns. Added also the possibility to give various file 

+formats in input including `*.xls(x)` formats.

+* Function `top_integrations` can now take additional parameters to compute

+top n genes for each specified group

+* Removed faceting parameters in `CIS_volcano_plot` due to poor precision

+(easier to add faceting manually) and added parameters to return the 

+data frame that generated the plot as an additional result. Also, it is 

+now possible to specify a vector of gene names to highlight even if they're

+not above the annotation threshold.

+

+## MINOR

+

+* ISAnalytics website has improved graphic theme and has an additional button

+on the right that leads to the devel (or release) version of the website

+* Updated vignettes

+

+## FOR DEVS ONLY

+

+* Complete rework of test suite to be compliant to testthat v.3

+

 # ISAnalytics 1.1.9 (2021-02-17)

 ## FIXES

@@ -21,7 +21,7 @@

 #' @export

 #'

 #' @examples

-#' op <- options("ISAnalytics.widgets" = FALSE)

+#' op <- options("ISAnalytics.widgets" = FALSE, "ISAnalytics.verbose" = FALSE)

 #' path_AF <- system.file("extdata", "ex_association_file.tsv",

 #'     package = "ISAnalytics"

 #' )

@@ -180,13 +180,13 @@ aggregate_metadata <- function(association_file,

 #' @family Aggregate functions

 #'

 #' @importFrom purrr walk

-#' @importFrom rlang expr eval_tidy

+#' @importFrom rlang expr eval_tidy abort

 #'

 #' @return A list of tibbles or a single tibble according to input

 #' @export

 #'

 #' @examples

-#' op <- options("ISAnalytics.widgets" = FALSE)

+#' op <- options("ISAnalytics.widgets" = FALSE, "ISAnalytics.verbose" = FALSE)

 #' path_AF <- system.file("extdata", "ex_association_file.tsv",

 #'     package = "ISAnalytics"

 #' )

@@ -201,12 +201,12 @@ aggregate_metadata <- function(association_file,

 #'     matrix_type = "annotated", workers = 2, matching_opt = "ANY"

 #' )

 #' agg <- aggregate_values_by_key(

-#'     x = matrices$seqCount,

-#'     association_file = association_file

+#'     x = matrices,

+#'     association_file = association_file,

+#'     value_cols = c("fragmentEstimate", "seqCount")

 #' )

 #' options(op)

-aggregate_values_by_key <- function(

-    x,

+aggregate_values_by_key <- function(x,

     association_file,

     value_cols = "Value",

     key = c(

@@ -225,39 +225,55 @@ aggregate_values_by_key <- function(

         purrr::walk(x, function(df) {

             stopifnot(is.data.frame(df))

             if (.check_mandatory_vars(df) == FALSE) {

-                stop(.non_ISM_error())

+                rlang::abort(.non_ISM_error())

             }

             if (.check_complAmpID(df) == FALSE) {

-                stop(.missing_complAmpID_error())

+                rlang::abort(.missing_complAmpID_error())

             }

             if (!all(value_cols %in% colnames(df))) {

-                stop(.missing_user_cols_error())

+                rlang::abort(.missing_user_cols_error(

+                    value_cols[!value_cols %in% colnames(df)]

+                ))

             }

-            purrr::walk(value_cols, function(col) {

-                expr <- rlang::expr(`$`(df, !!col))

-                if (!is.numeric(rlang::eval_tidy(expr)) &&

-                    !is.integer(rlang::eval_tidy(expr))) {

-                    stop(.non_num_user_cols_error())

+            is_numeric_col <- purrr::map_lgl(value_cols, function(col) {

+                if (!is.double(df[[col]]) &&

+                    !is.integer(df[[col]])) {

+                    FALSE

+                } else {

+                    TRUE

                 }

-            })

+            }) %>% purrr::set_names(value_cols)

+            if (any(!is_numeric_col)) {

+                rlang::abort(.non_num_user_cols_error(

+                    names(is_numeric_col)[!is_numeric_col]

+                ))

+            }

         })

     } else {

         if (.check_mandatory_vars(x) == FALSE) {

-            stop(.non_ISM_error())

+            rlang::abort(.non_ISM_error())

         }

         if (.check_complAmpID(x) == FALSE) {

-            stop(.missing_complAmpID_error())

+            rlang::abort(.missing_complAmpID_error())

         }

         if (!all(value_cols %in% colnames(x))) {

-            stop(.missing_user_cols_error())

+            rlang::abort(.missing_user_cols_error(

+                value_cols[!value_cols %in% colnames(x)]

+            ))

         }

-        purrr::walk(value_cols, function(col) {

-            expr <- rlang::expr(`$`(x, !!col))

-            if (!is.numeric(rlang::eval_tidy(expr)) &&

-                !is.integer(rlang::eval_tidy(expr))) {

-                stop(.non_num_user_cols_error())

+        is_numeric_col <- purrr::map_lgl(value_cols, function(col) {

+            if (!is.double(x[[col]]) &&

+                !is.integer(x[[col]])) {

+                FALSE

+            } else {

+                TRUE

             }

-        })

+        }) %>% purrr::set_names(value_cols)

+        if (any(!is_numeric_col)) {

+            rlang::abort(.non_num_user_cols_error(

+                names(is_numeric_col)[!is_numeric_col]

+            ))

+        }

     }

     # Check association file

     stopifnot(is.data.frame(association_file))

@@ -1,11 +1,12 @@

 #------------------------------------------------------------------------------#

 # Analysis functions

 #------------------------------------------------------------------------------#

-#' Computes the abundance of every integration in the sample.

+

+#' Computes the abundance for every integration event in the input data frame.

 #'

 #' \lifecycle{maturing}

-#' Abundance is obtained for every row by calculating the ratio

-#' between the single value and the total value for the sample.

+#' Abundance is obtained for every integration event by calculating the ratio

+#' between the single value and the total value for the given group.

 #'

 #' @details Abundance will be computed upon the user selected columns

 #' in the `columns` parameter. For each column a corresponding

@@ -13,19 +14,28 @@

 #' column) will be produced.

 #'

 #' @param x An integration matrix - aka a data frame that includes

-#' the `mandatory_IS_vars()` as columns

+#' the `mandatory_IS_vars()` as columns. The matrix can either be aggregated

+#' (via `aggregate_values_by_key()`) or not.

 #' @param columns A character vector of column names to process,

 #' must be numeric or integer columns

 #' @param percentage Add abundance as percentage?

+#' @param key The key to group by when calculating totals

+#' @param keep_totals A value between `TRUE`, `FALSE` or `df`. If `TRUE`,

+#' the intermediate totals for each group will be kept in the output

+#' data frame as a dedicated column with a trailing "_tot". If `FALSE`,

+#' totals won't be included in the output data frame. If `df`, the totals

+#' are returned to the user as a separate data frame, together with the

+#' abundance data frame.

 #'

 #' @family Analysis functions

 #'

 #' @importFrom magrittr `%>%`

-#' @importFrom tibble is_tibble

 #' @import dplyr

 #' @importFrom rlang .data eval_tidy parse_expr

+#' @importFrom purrr map_lgl

 #' @importFrom stringr str_replace

-#' @return An integration matrix

+#' @return Either a single data frame with computed abundance values or

+#' a list of 2 data frames (abundance_df, quant_totals)

 #' @export

 #'

 #' @examples

@@ -33,54 +43,79 @@

 #'     package = "ISAnalytics"

 #' )

 #' matrix <- import_single_Vispa2Matrix(path)

-#' abundance <- compute_abundance(matrix)

-compute_abundance <- function(x, columns = "Value", percentage = TRUE) {

+#'

+#' # Simple integration matrix - grouping by CompleteAmplificationID

+#' abundance1 <- compute_abundance(matrix)

+#' abundance1

+#'

+#' # Keeping totals as a separate data frame

+#' abundance2 <- compute_abundance(matrix, keep_totals = "df")

+#' abundance2

+compute_abundance <- function(x,

+    columns = "Value",

+    percentage = TRUE,

+    key = "CompleteAmplificationID",

+    keep_totals = FALSE) {

     ## Check parameters

-    stopifnot(tibble::is_tibble(x))

+    stopifnot(is.data.frame(x))

     stopifnot(is.character(columns))

+    stopifnot(is.character(key))

     if (.check_mandatory_vars(x) == FALSE) {

         stop(.non_ISM_error())

     }

-    if (.check_complAmpID(x) == FALSE) {

-        stop(.missing_complAmpID_error())

-    }

     stopifnot(is.logical(percentage) & length(percentage) == 1)

-    if (!all(columns %in% colnames(x))) {

-        stop(.missing_user_cols_error())

+    if (!all(columns %in% colnames(x)) | !all(key %in% colnames(x))) {

+        missing_cols <- c(

+            columns[!columns %in% colnames(x)],

+            key[!key %in% colnames(x)]

+        )

+        rlang::abort(.missing_user_cols_error(missing_cols))

     }

-    purrr::walk(columns, function(col) {

+    non_num_cols <- purrr::map_lgl(columns, function(col) {

         expr <- rlang::expr(`$`(x, !!col))

-        if (!is.numeric(rlang::eval_tidy(expr)) &

-            !is.numeric(rlang::eval_tidy(expr))) {

-            stop(.non_num_user_cols_error())

+        if (is.numeric(rlang::eval_tidy(expr)) |

+            is.integer(rlang::eval_tidy(expr))) {

+            return(FALSE)

+        } else {

+            return(TRUE)

         }

     })

+    if (any(non_num_cols)) {

+        stop(.non_num_user_cols_error(columns[non_num_cols]))

+    }

+    stopifnot(is.logical(keep_totals) || keep_totals == "df")

     ## Computation

+    ### Computes totals for each group defined by key

     totals <- x %>%

-        dplyr::group_by(.data$CompleteAmplificationID) %>%

+        dplyr::group_by(dplyr::across(dplyr::all_of(key))) %>%

         dplyr::summarise(

             dplyr::across(dplyr::all_of(columns),

                 sum,

-                .names = "{.col}_sum"

+                .names = "{.col}_tot"

             ),

             .groups = "drop"

         )

+    ### Computes abundance as value (for each col) / total of the corresponding

+    ### group (defined by key)

     abundance_df <- x %>%

-        dplyr::left_join(totals, by = "CompleteAmplificationID") %>%

+        dplyr::left_join(totals, by = key) %>%

         dplyr::mutate(dplyr::across(dplyr::all_of(columns),

             list(ab = ~ .x / rlang::eval_tidy(

                 rlang::parse_expr(

                     paste(

                         dplyr::cur_column(),

-                        "sum",

+                        "tot",

                         sep = "_"

                     )

                 )

             )),

             .names = "{.col}_RelAbundance"

         )) %>%

-        dplyr::select(-c(dplyr::all_of(paste(columns, "sum", sep = "_")))) %>%

         dplyr::distinct()

+    if (keep_totals == FALSE || keep_totals == "df") {

+        abundance_df <- abundance_df %>%

+            dplyr::select(-c(dplyr::all_of(paste(columns, "tot", sep = "_"))))

+    }

     if (percentage == TRUE) {

         abundance_df <- abundance_df %>%

             dplyr::mutate(

@@ -93,7 +128,11 @@ compute_abundance <- function(x, columns = "Value", percentage = TRUE) {

                 dplyr::contains("PercAbundance")

             )

     }

-    abundance_df

+    if (keep_totals == "df") {

+        return(list(abundance_df = abundance_df, quant_totals = totals))

+    } else {

+        return(abundance_df)

+    }

 }

@@ -139,9 +178,11 @@ compute_abundance <- function(x, columns = "Value", percentage = TRUE) {

 #' root_pth <- system.file("extdata", "fs.zip", package = "ISAnalytics")

 #' root <- unzip_file_system(root_pth, "fs")

 #' matrices <- import_parallel_Vispa2Matrices_auto(

-#'     path, root,

-#'     c("fragmentEstimate", "seqCount"), "annotated", 2, NULL, "ANY",

-#'     dates_format = "dmy"

+#'     association_file = path, root = root,

+#'     quantification_type = c("fragmentEstimate", "seqCount"),

+#'     matrix_type = "annotated", workers = 2, patterns = NULL,

+#'     matching_opt = "ANY",

+#'     dates_format = "dmy", multi_quant_matrix = FALSE

 #' )

 #' total_matrix <- comparison_matrix(matrices)

 #' options(op)

@@ -225,13 +266,17 @@ comparison_matrix <- function(x,

 #' )

 #' root_pth <- system.file("extdata", "fs.zip", package = "ISAnalytics")

 #' root <- unzip_file_system(root_pth, "fs")

-#' matrices <- import_parallel_Vispa2Matrices_auto(

-#'     path, root,

-#'     c("fragmentEstimate", "seqCount"), "annotated", 2, NULL, "ANY",

+#' association_file <- import_association_file(

+#'     path = path, root = root,

 #'     dates_format = "dmy"

 #' )

-#' total_matrix <- comparison_matrix(matrices)

-#' separated_matrix <- separate_quant_matrices(total_matrix)

+#' matrices <- import_parallel_Vispa2Matrices_auto(

+#'     association_file = association_file,

+#'     quantification_type = c("seqCount", "fragmentEstimate"),

+#'     matrix_type = "annotated", workers = 2, patterns = NULL,

+#'     matching_opt = "ANY"

+#' )

+#' separated_matrix <- separate_quant_matrices(matrices)

 #' options(op)

 separate_quant_matrices <- function(x, fragmentEstimate = "fragmentEstimate",

     seqCount = "seqCount",

@@ -446,33 +491,40 @@ threshold_filter <- function(x,

 }

-#' Sorts and keeps the top n integration sites in a data frame.

+#' Sorts and keeps the top n integration sites based on the values

+#' in a given column.

 #'

 #' \lifecycle{experimental}

 #' The input data frame will be sorted by the highest values in

 #' the columns specified and the top n rows will be returned as output.

 #' The user can choose to keep additional columns in the output

 #' by passing a vector of column names or passing 2 "shortcuts":

-#' * `keep` = "everything" keeps all columns in the original data frame

-#' * `keep` = "nothing" only keeps the mandatory columns

+#' * `keep = "everything"` keeps all columns in the original data frame

+#' * `keep = "nothing"` only keeps the mandatory columns

 #' (`mandatory_IS_vars()`) plus the columns in the `columns` parameter.

 #'

 #' @param x An integration matrix (data frame containing

 #' `mandatory_IS_vars()`)

-#' @param n How many rows should the output have? Must be numeric

+#' @param n How many integrations should be sliced (in total or

+#'  for each group)? Must be numeric

 #' or integer and greater than 0

 #' @param columns Columns to use for the sorting. If more than a column

 #' is supplied primary ordering is done on the first column,

 #' secondary ordering on all other columns

 #' @param keep Names of the columns to keep besides `mandatory_IS_vars()`

 #' and `columns`

+#' @param key Either `NULL` or a character vector of column names to group

+#' by. If not `NULL` the input will be grouped and the top fraction will

+#' be extracted from each group.

 #'

 #' @family Analysis functions

 #'

-#' @importFrom dplyr arrange across all_of desc slice_head select

+#' @import dplyr

 #' @importFrom magrittr `%>%`

+#' @importFrom rlang abort

 #'

-#' @return A data frame with `n` rows

+#' @return Either a data frame with at most n rows or

+#' a data frames with at most n*(number of groups) rows.

 #' @export

 #'

 #' @examples

@@ -490,21 +542,40 @@ threshold_filter <- function(x,

 #'     columns = c("Value", "Value2"),

 #'     keep = "nothing"

 #' )

-top_integrations <- function(x, n = 50, columns = "RelAbundance",

-    keep = "everything") {

+#' top_key <- top_integrations(smpl,

+#'     n = 3,

+#'     columns = "Value",

+#'     keep = "Value2",

+#'     key = "CompleteAmplificationID"

+#' )

+top_integrations <- function(x, n = 50,

+    columns = "fragmentEstimate_sum_RelAbundance",

+    keep = "everything", key = NULL) {

     stopifnot(is.data.frame(x))

     stopifnot(is.numeric(n) & length(n) == 1 & n > 0)

     stopifnot(is.character(keep))

     stopifnot(is.character(columns))

+    stopifnot(is.null(key) || is.character(key))

     if (!.check_mandatory_vars(x)) {

-        stop(.non_ISM_error())

+        rlang::abort(.non_ISM_error())

     }

     if (!all(columns %in% colnames(x))) {

-        stop(.missing_user_cols_error())

+        rlang::abort(.missing_user_cols_error(

+            columns[!columns %in% colnames(x)]

+        ))

     }

     if (!(all(keep == "everything") || all(keep == "nothing"))) {

         if (any(!keep %in% colnames(x))) {

-            stop(.missing_user_cols_error())

+            rlang::abort(.missing_user_cols_error(

+                keep[!keep %in% colnames(x)]

+            ))

+        }

+    }

+    if (!is.null(key)) {

+        if (!all(key %in% colnames(x))) {

+            rlang::abort(.missing_user_cols_error(

+                key[!key %in% colnames(x)]

+            ))

         }

     }

     essential_cols <- c(mandatory_IS_vars(), columns)

@@ -515,6 +586,18 @@ top_integrations <- function(x, n = 50, columns = "RelAbundance",

     } else {

         keep[!keep %in% essential_cols]

     }

+    if (!is.null(key)) {

+        result <- x %>%

+            dplyr::group_by(dplyr::across(dplyr::all_of(key))) %>%

+            dplyr::arrange(dplyr::across(

+                dplyr::all_of(columns),

+                dplyr::desc

+            ), .by_group = TRUE) %>%

+            dplyr::slice_head(n = n) %>%

+            dplyr::select(dplyr::all_of(c(key, essential_cols, to_keep))) %>%

+            dplyr::ungroup()

+        return(result)

+    }

     result <- x %>%

         dplyr::arrange(dplyr::across(

             dplyr::all_of(columns),

@@ -602,7 +685,7 @@ top_integrations <- function(x, n = 50, columns = "RelAbundance",

 #'     association_file = association_file, root = NULL,

 #'     quantification_type = c("seqCount", "fragmentEstimate"),

 #'     matrix_type = "annotated", workers = 2, patterns = NULL,

-#'     matching_opt = "ANY"

+#'     matching_opt = "ANY", multi_quant_matrix = FALSE

 #' )

 #'

 #' stats <- sample_statistics(matrices$seqCount, association_file)

@@ -719,6 +802,7 @@ sample_statistics <- function(x, metadata,

 #' @importFrom rlang .data

 #' @importFrom magrittr `%>%`

 #' @importFrom stats median pt p.adjust

+#' @importFrom utils read.csv

 #'

 #' @return A data frame

 #' @export

@@ -742,7 +826,7 @@ sample_statistics <- function(x, metadata,

 #'     dates_format = "dmy"

 #' )

 #'

-#' cis <- CIS_grubbs(matrices$seqCount)

+#' cis <- CIS_grubbs(matrices)

 #'

 #' options(op)

 CIS_grubbs <- function(x,

@@ -776,28 +860,34 @@ CIS_grubbs <- function(x,

     # Try to import annotation file

     if (ext == "tsv") {

-        refgenes <- read.csv(

+        refgenes <- utils::read.csv(

             file = genomic_annotation_file,

             header = TRUE, fill = TRUE, sep = "\t",

             check.names = FALSE,

             na.strings = c("NONE", "NA", "NULL", "NaN", "")

         )

         refgenes <- tibble::as_tibble(refgenes) %>%

-            dplyr::mutate(chrom = stringr::str_replace_all(.data$chrom,

-                                                           "chr", ""))

+            dplyr::mutate(chrom = stringr::str_replace_all(

+                .data$chrom,

+                "chr", ""

+            ))

     } else if (ext == "csv") {

-        refgenes <- read.csv(

+        refgenes <- utils::read.csv(

             file = genomic_annotation_file,

             header = TRUE, fill = TRUE,

             check.names = FALSE,

             na.strings = c("NONE", "NA", "NULL", "NaN", "")

         )

         refgenes <- tibble::as_tibble(refgenes) %>%

-            dplyr::mutate(chrom = stringr::str_replace_all(.data$chrom,

-                                                           "chr", ""))

+            dplyr::mutate(chrom = stringr::str_replace_all(

+                .data$chrom,

+                "chr", ""

+            ))

     } else {

-        stop(paste("The genomic annotation file must be either in",

-                   ".tsv or .csv format (compressed or not)"))

+        stop(paste(

+            "The genomic annotation file must be either in",

+            ".tsv or .csv format (compressed or not)"

+        ))

     }

     # Check annotation file format

@@ -832,7 +922,8 @@ CIS_grubbs <- function(x,

                 stats::median(.data$integration_locus),

             distinct_orientations = dplyr::n_distinct(.data$strand),

             describe = list(tibble::as_tibble(

-                psych::describe(.data$integration_locus))),

+                psych::describe(.data$integration_locus)

+            )),

             .groups = "drop"

         ) %>%

         tidyr::unnest(.data$describe, keep_empty = TRUE, names_sep = "_")

@@ -1028,7 +1119,7 @@ CIS_grubbs <- function(x,

 #'     association_file = association_file, root = NULL,

 #'     quantification_type = c("seqCount", "fragmentEstimate"),

 #'     matrix_type = "annotated", workers = 2, patterns = NULL,

-#'     matching_opt = "ANY"

+#'     matching_opt = "ANY", multi_quant_matrix = FALSE

 #' )

 #'

 #' #### EXTERNAL AGGREGATION

@@ -60,8 +60,11 @@

 #'     dates_format = "dmy"

 #' )

 #' matrices <- import_parallel_Vispa2Matrices_auto(

-#'     association_file, NULL,

-#'     c("fragmentEstimate", "seqCount"), "annotated", 2, NULL, "ANY"

+#'     association_file = association_file, root = NULL,

+#'     quantification_type = c("fragmentEstimate", "seqCount"),

+#'     matrix_type = "annotated", workers = 2,

+#'     patterns = NULL, matching_opt = "ANY",

+#'     multi_quant_matrix = FALSE

 #' )

 #' matrices <- remove_collisions(matrices, association_file)

 #' options(op)

@@ -406,8 +409,11 @@ remove_collisions <- function(x,

 #'     dates_format = "dmy"

 #' )

 #' matrices <- import_parallel_Vispa2Matrices_auto(

-#'     association_file, NULL,

-#'     c("fragmentEstimate", "seqCount"), "annotated", 2, NULL, "ANY"

+#'     association_file = association_file, root = NULL,

+#'     quantification_type = c("fragmentEstimate", "seqCount"),

+#'     matrix_type = "annotated", workers = 2,

+#'     patterns = NULL, matching_opt = "ANY",

+#'     multi_quant_matrix = FALSE

 #' )

 #' sc_matrix <- remove_collisions(matrices$seqCount, association_file)

 #' others <- matrices[!names(matrices) %in% "seqCount"]

@@ -1,3 +1,7 @@

+#------------------------------------------------------------------------------#

+# Exported/Internal variables

+#------------------------------------------------------------------------------#

+

 #' Names of mandatory variables for an integration matrix.

 #'

 #' Contains the names of the columns that need to be present in order for a

@@ -12,6 +16,25 @@ mandatory_IS_vars <- function() {

     c("chr", "integration_locus", "strand")

 }

+# Internal: associates column types with column names for a more precise

+# import

+.mandatory_IS_types <- function(mode) {

+    if (mode == "fread") {

+        return(list(

+            character = c("chr", "strand"),

+            integer = "integration_locus"

+        ))

+    } else {

+        return(

+            list(

+                chr = "c",

+                integration_locus = "i",

+                strand = "c"

+            )

+        )

+    }

+}

+

 #' Names of the annotation variables for an integration matrix.

 #'

 #' Contains the names of the columns that are present if the integration matrix

@@ -26,6 +49,19 @@ annotation_IS_vars <- function() {

     c("GeneName", "GeneStrand")

 }

+# Internal: associates column types with column names for a more precise

+# import

+.annotation_IS_types <- function(mode) {

+    if (mode == "fread") {

+        return(list(character = c("GeneName", "GeneStrand")))

+    } else {

+        return(list(

+            GeneName = "c",

+            GeneStrand = "c"

+        ))

+    }

+}

+

 #' Names of the columns in the association file.

 #'

 #' All the names of the columns present in the association file.

@@ -55,10 +91,95 @@ association_file_columns <- function() {

         "Kapa", "ulForPool", "CompleteAmplificationID", "UniqueID",

         "StudyTestID",

         "StudyTestGroup", "MouseID", "Tigroup", "Tisource",

-        "PathToFolderProjectID"

+        "PathToFolderProjectID",

+        "SamplesNameCheck",

+        "TimepointDays", "TimepointMonths",

+        "TimepointYears", "ng DNA corrected"

     )

 }

+.af_col_types <- function(mode) {

+    if (mode == "fread") {

+        types <- list(

+            character = c(

+                "ProjectID", "FUSIONID", "PoolID", "TagSequence",

+                "SubjectID", "VectorType", "VectorID", "ExperimentID",

+                "Tissue", "TimePoint", "DNAFragmentation",

+                "PCRMethod", "TagIDextended", "Keywords",

+                "CellMarker", "TagID", "NGSProvider", "NGSTechnology",

+                "ConverrtedFilesDir", "ConverrtedFilesName",

+                "SourceFileFolder", "SourceFileNameR1",

+                "SourceFileNameR2", "DNAnumber", "LinearPCRID",

+                "1stExpoPCRID", "2ndExpoID", "FusionPrimerPCRID",

+                "Genome", "Genotype", "Notes", "AddedField1",

+                "AddedField2", "AddedField3", "AddedField4",

+                "concatenatePoolIDSeqRun", "CompleteAmplificationID",

+                "UniqueID", "StudyTestID", "Tigroup", "Tisource",

+                "PathToFolderProjectID", "SamplesNameCheck",

+                "DNAextractionDate", "LinearPCRDate",

+                "SonicationDate", "LigationDate",

+                "FusionPrimerPCRDate", "PoolDate", "SequencingDate",

+                "MOI", "AddedField6_RelativeBloodPercentage",

+                "TestGroup"

+            ),

+            double = c(

+                "DNAngUsed", "VCN", "Engraftment", "Transduction",

+                "AddedField7_PurityTestFeasibility",

+                "AddedField8_FacsSeparationPurity", "Kapa",

+                "ulForPool", "TimepointMonths", "TimepointYears",

+                "ng DNA corrected"

+            ),

+            integer = c(

+                "ReplicateNumber", "SequencingRound",

+                "StudyTestGroup", "MouseID", "TimepointDays"

+            )

+        )

+        return(types)

+    }

+    if (mode == "readr") {

+        # date_format <- unlist(strsplit(date_format))