@@ -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: 1.1.10

+Version: 1.1.11

 Date: 2020-07-03

 Authors@R: c(

   person(given = "Andrea",

@@ -32,7 +32,6 @@ Imports:

     tidyr,

     purrr,

     rlang,

-    forcats,

     tibble,

     BiocParallel,

     stringr,

@@ -48,7 +47,9 @@ Imports:

     grDevices,

     data.table,

     readxl,

-    tools

+    tools,

+    Rcapture,

+    plotly

 Encoding: UTF-8

 LazyData: false

 Roxygen: list(markdown = TRUE)

@@ -63,7 +64,8 @@ Suggests:

     rmarkdown,

     roxygen2,

     vegan,

-    withr

+    withr,

+    extraDistr

 VignetteBuilder: knitr

 RdMacros: 

     lifecycle

@@ -2,11 +2,15 @@

 export(CIS_grubbs)

 export(CIS_volcano_plot)

+export(HSC_population_plot)

+export(HSC_population_size_estimate)

 export(aggregate_metadata)

 export(aggregate_values_by_key)

 export(annotation_IS_vars)

 export(as_sparse_matrix)

 export(association_file_columns)

+export(available_outlier_tests)

+export(blood_lineages_default)

 export(clinical_relevant_suspicious_genes)

 export(comparison_matrix)

 export(compute_abundance)

@@ -14,9 +18,12 @@ export(compute_near_integrations)

 export(cumulative_count_union)

 export(date_columns_coll)

 export(date_formats)

+export(default_iss_file_prefixes)

+export(default_meta_agg)

 export(default_stats)

 export(generate_Vispa2_launch_AF)

 export(generate_blank_association_file)

+export(import_Vispa2_stats)

 export(import_association_file)

 export(import_parallel_Vispa2Matrices_auto)

 export(import_parallel_Vispa2Matrices_interactive)

@@ -24,6 +31,8 @@ export(import_single_Vispa2Matrix)

 export(known_clinical_oncogenes)

 export(mandatory_IS_vars)

 export(matching_options)

+export(outlier_filter)

+export(outliers_by_pool_fragments)

 export(quantification_types)

 export(realign_after_collisions)

 export(reduced_AF_columns)

@@ -36,6 +45,7 @@ export(unzip_file_system)

 import(BiocParallel)

 import(dplyr)

 import(ggplot2)

+import(htmltools)

 import(lifecycle)

 import(upsetjs)

 importFrom(BiocParallel,MulticoreParam)

@@ -44,6 +54,8 @@ importFrom(BiocParallel,bplapply)

 importFrom(BiocParallel,bpok)

 importFrom(BiocParallel,bpstop)

 importFrom(BiocParallel,bptry)

+importFrom(Rcapture,closedp.0)

+importFrom(Rcapture,closedp.bc)

 importFrom(data.table,fread)

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

 importFrom(data.table,rbindlist)

@@ -60,13 +72,12 @@ importFrom(dplyr,group_by)

 importFrom(dplyr,group_split)

 importFrom(dplyr,inner_join)

 importFrom(dplyr,intersect)

+importFrom(dplyr,left_join)

 importFrom(dplyr,mutate)

 importFrom(dplyr,rename)

 importFrom(dplyr,select)

 importFrom(dplyr,semi_join)

 importFrom(dplyr,slice)

-importFrom(forcats,as_factor)

-importFrom(forcats,fct_inseq)

 importFrom(fs,as_fs_path)

 importFrom(fs,dir_create)

 importFrom(fs,dir_exists)

@@ -91,13 +102,18 @@ importFrom(htmltools,tagList)

 importFrom(htmltools,tags)

 importFrom(lubridate,parse_date_time)

 importFrom(magrittr,`%>%`)

+importFrom(plotly,plot_ly)

 importFrom(psych,describe)

+importFrom(purrr,cross_df)

+importFrom(purrr,detect_index)

 importFrom(purrr,flatten)

+importFrom(purrr,flatten_chr)

 importFrom(purrr,is_empty)

 importFrom(purrr,is_formula)

 importFrom(purrr,is_function)

 importFrom(purrr,map)

 importFrom(purrr,map2)

+importFrom(purrr,map2_chr)

 importFrom(purrr,map2_dfr)

 importFrom(purrr,map2_lgl)

 importFrom(purrr,map_chr)

@@ -108,6 +124,7 @@ importFrom(purrr,pmap)

 importFrom(purrr,pmap_chr)

 importFrom(purrr,pmap_df)

 importFrom(purrr,pmap_dfr)

+importFrom(purrr,pmap_lgl)

 importFrom(purrr,reduce)

 importFrom(purrr,set_names)

 importFrom(purrr,walk)

@@ -126,25 +143,33 @@ importFrom(rlang,.data)

 importFrom(rlang,`:=`)

 importFrom(rlang,abort)

 importFrom(rlang,arg_match)

+importFrom(rlang,as_function)

 importFrom(rlang,call2)

 importFrom(rlang,dots_list)

+importFrom(rlang,enexpr)

 importFrom(rlang,env_bind)

 importFrom(rlang,eval_tidy)

+importFrom(rlang,exec)

 importFrom(rlang,expr)

 importFrom(rlang,fn_fmls_names)

 importFrom(rlang,inform)

+importFrom(rlang,is_formula)

+importFrom(rlang,is_function)

+importFrom(rlang,list2)

 importFrom(rlang,parse_expr)

+importFrom(stats,dt)

 importFrom(stats,median)

 importFrom(stats,na.omit)

 importFrom(stats,p.adjust)

 importFrom(stats,pt)

+importFrom(stats,setNames)

+importFrom(stats,shapiro.test)

 importFrom(stringr,str_detect)

-importFrom(stringr,str_extract)

-importFrom(stringr,str_extract_all)

 importFrom(stringr,str_pad)

 importFrom(stringr,str_replace)

 importFrom(stringr,str_replace_all)

 importFrom(stringr,str_split)

+importFrom(stringr,str_to_upper)

 importFrom(tibble,add_column)

 importFrom(tibble,add_row)

 importFrom(tibble,as_tibble)

@@ -153,12 +178,12 @@ importFrom(tibble,as_tibble_row)

 importFrom(tibble,is_tibble)

 importFrom(tibble,tibble)

 importFrom(tibble,tibble_row)

+importFrom(tibble,tribble)

 importFrom(tidyr,everything)

 importFrom(tidyr,nest)

 importFrom(tidyr,pivot_longer)

 importFrom(tidyr,pivot_wider)

 importFrom(tidyr,separate)

-importFrom(tidyr,unite)

 importFrom(tidyr,unnest)

 importFrom(tools,file_path_sans_ext)

 importFrom(utils,read.csv)

@@ -1,5 +1,35 @@

 \title{ISAnalytics News}

+# ISAnalytics 1.1.11 (2021-05-11)

+

+## NEW FUNCTIONALITY

+

+* `HSC_population_size_estimate` and `HSC_population_plot` allow estimates

+on hematopoietic stem cell population size

+* Importing of Vispa2 stats per pool now has a dedicated function,

+`import_Vispa2_stats`

+* `outlier_filter` and `outliers_by_pool_fragments` offer a mean to filter

+poorly represented samples based on custom outliers tests

+

+## VISIBLE USER CHANGES

+

+* The argument `import_stats` of `aggregate_metadata` is officially deprecated

+in favor of `import_Vispa2_stats`

+* `aggregate_metadata` is now a lot more flexible on what operations can be

+performed on columns via the new argument `aggregating_functions`

+* `import_association_file` allows directly for the import of Vispa2 stats

+and converts time points to months and years where not already present

+* File system alignment of `import_association_file` now produces 3 separate

+columns for paths

+* `separate_quant_matrices` and `comparison_matrix` now do not require 

+mandatory columns other than the quantifications - this allows for separation

+or joining also for aggregated matrices

+

+## FIXES

+

+* Fixed a minor issue in `CIS_volcano_plot` that caused duplication of some

+labels if highlighted genes were provided in input

+

 # ISAnalytics 1.1.10 (2021-04-08)

 ## FIXES

@@ -26,6 +26,7 @@

 #' * Import functions:

 #'   * \code{\link{import_single_Vispa2Matrix}}

 #'   * \code{\link{import_association_file}}

+#'   * \code{\link{import_Vispa2_stats}}

 #'   * \code{\link{import_parallel_Vispa2Matrices_interactive}}

 #'   * \code{\link{import_parallel_Vispa2Matrices_auto}}

 #' * Aggregation functions:

@@ -34,6 +35,9 @@

 #' * Collision removal functions:

 #'   * \code{\link{remove_collisions}}

 #'   * \code{\link{realign_after_collisions}}

+#' * Removal of outliers from raw reads

+#'   * \code{\link{outlier_filter}}

+#'   * \code{\link{outliers_by_pool_fragments}}

 #' * Recalibration functions:

 #'   * \code{\link{compute_near_integrations}}

 #' * Analysis functions:

@@ -45,8 +49,11 @@

 #'   * \code{\link{sample_statistics}}

 #'   * \code{\link{CIS_grubbs}}

 #'   * \code{\link{cumulative_count_union}}

+#' * HSC population size estimate:

+#'   * \code{\link{HSC_population_size_estimate}}

 #' * Plotting functions:

 #'   * \code{\link{CIS_volcano_plot}}

+#'   * \code{\link{HSC_population_plot}}

 #' * Utility functions:

 #'   * \code{\link{generate_blank_association_file}}

 #'   * \code{\link{generate_Vispa2_launch_AF}}

@@ -4,20 +4,28 @@

 #' Performs aggregation on metadata contained in the association file.

 #'

-#' \lifecycle{experimental}

-#' Groups metadata by grouping_keys and returns a summary of info for each

-#' group. For more details on how to use this function:

+#' \lifecycle{maturing}

+#' Groups metadata by the specified grouping keys and returns a

+#' summary of info for each group. For more details on how to use this function:

 #' \code{vignette("Working with aggregate functions", package = "ISAnalytics")}

 #'

 #' @param association_file The imported association file

-#' (via `import_association_file`)

+#' (via link{import_association_file})

 #' @param grouping_keys A character vector of column names to form a group

-#' @param import_stats Should Vispa2 stats files be imported and included?

+#' @param aggregating_functions A data frame containing specifications

+#' of the functions to be applied to columns in the association file during

+#' aggregation. It defaults to \link{default_meta_agg}. The structure of

+#' this data frame should be maintained if the user wishes to change the

+#' defaults.

+#' @param import_stats `r lifecycle::badge("deprecated")` The import

+#' of VISPA2 stats has been moved to its dedicated function,

+#' see \link{import_Vispa2_stats}.

 #' @family Aggregate functions

+#' @importFrom rlang abort inform

 #' @importFrom purrr is_empty

-#' @importFrom tibble is_tibble

+#' @import lifecycle

 #'

-#' @return A tibble

+#' @return An aggregated data frame

 #' @export

 #'

 #' @examples

@@ -30,7 +38,7 @@

 #' association_file <- import_association_file(path_AF, root_correct,

 #'     dates_format = "dmy"

 #' )

-#' aggregated_meta <- aggregate_metadata(association_file, import_stats = FALSE)

+#' aggregated_meta <- aggregate_metadata(association_file)

 #' options(op)

 aggregate_metadata <- function(association_file,

     grouping_keys = c(

@@ -39,88 +47,99 @@ aggregate_metadata <- function(association_file,

         "Tissue",

         "TimePoint"

     ),

-    import_stats = TRUE) {

+    aggregating_functions = default_meta_agg(),

+    import_stats = lifecycle::deprecated()

+    ) {

     # Check parameters

-    stopifnot(tibble::is_tibble(association_file))

-    min_missing <- setdiff(.min_var_set(), colnames(association_file))

-    if (!purrr::is_empty(min_missing)) {

-        stop(paste(c(

-            "Association file is missing some of the mandatory columns:",

-            min_missing

-        ), collapse = "\n"))

-    }

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

     stopifnot(!is.null(grouping_keys))

     stopifnot(is.character(grouping_keys))

-    keys_missing <- setdiff(grouping_keys, colnames(association_file))

+    keys_missing <- grouping_keys[!grouping_keys %in%

+                                      colnames(association_file)]

     if (!purrr::is_empty(keys_missing)) {

-        stop(paste(c(

-            "Some of the grouping keys you provided were not found:",

-            keys_missing

-        ), collapse = "\n"))

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

     }

-    stopifnot(is.logical(import_stats) & length(import_stats) == 1)

-    # Import if true

-    stats <- NULL

-    if (import_stats == TRUE) {

-        stats <- .import_stats_iss(association_file)

-        if (is.null(stats)) {

-            if (getOption("ISAnalytics.verbose") == TRUE) {

-                message(paste("No Vispa2 stats files found for import,

-                    ignoring this step"))

-            }

-        } else {

-            if (getOption("ISAnalytics.widgets") == TRUE) {

-                withCallingHandlers(

-                    {

-                        withRestarts(

-                            {

-                                report <- stats[[2]]

-                                stats <- stats[[1]]

-                                widg <- .iss_import_widget(report)

-                                print(widg)

-                            },

-                            print_err = function(cnd) {

-                                message(.widgets_error())

-                                if (getOption("ISAnalytics.verbose") == TRUE) {

-                                    print(paste0(

-                                        "--- REPORT IMPORT VISPA2",

-                                        "STATS: FILES IMPORTED ---"

-                                    ))

-                                    print(stats[[2]],

-                                        width = Inf,

-                                        n = nrow(stats[[2]])

-                                    )

-                                }

-                            }

-                        )

-                    },

-                    error = function(cnd) {

-                        message(conditionMessage(cnd))

-                        invokeRestart("print_err")

-                    }

-                )

-            } else {

-                if (getOption("ISAnalytics.verbose") == TRUE) {

-                    print(paste0(

-                        "--- REPORT IMPORT VISPA2",

-                        "STATS: FILES IMPORTED ---"

-                    ))

-                    print(stats[[2]],

-                        width = Inf,

-                        n = nrow(stats[[2]])

-                    )

-                }

-                stats <- stats[[1]]

-            }

-        }

+    if (lifecycle::is_present(import_stats)) {

+        lifecycle::deprecate_warn(

+            when = "1.1.11",

+            what = "aggregate_metadata(import_stats)",

+            details = c("Import Vispa2 stats functionality moved",

+                        i = paste("Please use `import_Vispa2_stats()`",

+                                  "or",

+                                  "`import_association_file(import_iss = TRUE)`",

+                                  "instead."))

+        )

+    }

+    aggregated <- .aggregate_meta(association_file = association_file,

+                                  grouping_keys = grouping_keys,

+                                  function_tbl = aggregating_functions)

+    if (is.null(aggregated)) {

+        rlang::inform(paste("No columns in `aggregating_functions$Column`",

+                            "was found in column names of the association",

+                            "file. Nothing to return."))

     }

-    aggregated <- .join_and_aggregate(association_file, stats, grouping_keys)

     aggregated

 }

+

+#' Default metadata aggregation function table

+#'

+#' A default columns-function specifications for \link{aggregate_metadata}

+#'

+#' @details

+#' This data frame contains four columns:

+#'

+#' * `Column`: holds the name of the column in the association file that

+#' should be processed

+#' * `Function`: contains either the name of a function (e.g. mean)

+#' or a purrr-style lambda (e.g. `~ mean(.x, na.rm = TRUE)`). This function

+#' will be applied to the corresponding column specified in `Column`

+#' * `Args`: optional additional arguments to pass to the corresponding

+#' function. This is relevant ONLY if the corresponding `Function` is a

+#' simple function and not a purrr-style lambda.

+#' * `Output_colname`: a `glue` specification that will be used to determine

+#' a unique output column name. See \link[glue]{glue} for more details.

+#'

+#' @importFrom tibble tribble

+#' @return A data frame

+#' @family Aggregate functions

+#' @export

+#'

+#' @examples

+#' default_meta_agg()

+default_meta_agg <- function() {

+    tibble::tribble(

+        ~ Column, ~ Function, ~ Args, ~ Output_colname,

+        "FusionPrimerPCRDate", ~ suppressWarnings(min(.x, na.rm = TRUE)),

+        NA, "{.col}_min",

+        "LinearPCRDate", ~ suppressWarnings(min(.x, na.rm = TRUE)),

+        NA, "{.col}_min",

+        "VCN", ~ suppressWarnings(mean(.x, na.rm = TRUE)),

+        NA, "{.col}_avg",

+        "ng DNA corrected", ~ suppressWarnings(mean(.x, na.rm = TRUE)),

+        NA, "{.col}_avg",

+        "Kapa", ~ suppressWarnings(mean(.x, na.rm = TRUE)),

+        NA, "{.col}_avg",

+        "ng DNA corrected", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "ulForPool", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "BARCODE_MUX", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "TRIMMING_FINAL_LTRLC", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "LV_MAPPED", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "BWA_MAPPED_OVERALL", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum",

+        "ISS_MAPPED_PP", ~ sum(.x, na.rm = TRUE),

+        NA, "{.col}_sum"

+    )

+}

+

 #' Aggregates matrices values based on specified key.

 #'

-#' \lifecycle{experimental}

+#' \lifecycle{maturing}

 #' Performs aggregation on values contained in the integration matrices based

 #' on the key and the specified lambda. For more details on how to use this

 #' function:

@@ -177,12 +196,16 @@ aggregate_metadata <- function(association_file,

 #' See details section.

 #' @param group Other variables to include in the grouping besides `key`,

 #' can be set to NULL

+#' @param join_af_by A character vector representing the joining key

+#' between the matrix and the metadata. Useful to re-aggregate already

+#' aggregated matrices.

 #' @family Aggregate functions

 #'

-#' @importFrom purrr walk

+#' @importFrom purrr walk set_names map_lgl

 #' @importFrom rlang expr eval_tidy abort

 #'

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

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

+#' the specified arguments

 #' @export

 #'

 #' @examples

@@ -219,7 +242,8 @@ aggregate_values_by_key <- function(x,

     group = c(

         mandatory_IS_vars(),

         annotation_IS_vars()

-    )) {

+    ),

+    join_af_by = "CompleteAmplificationID") {

     stopifnot(is.data.frame(x) || is.list(x))

     if (!is.data.frame(x)) {

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

@@ -227,8 +251,13 @@ aggregate_values_by_key <- function(x,

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

                 rlang::abort(.non_ISM_error())

             }

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

-                rlang::abort(.missing_complAmpID_error())

+            if (!all(join_af_by %in% colnames(df))) {

+                rlang::abort(c(x = paste("Missing common columns",

+                                         "to join metadata"),

+                               i = paste("Missing: ",

+                                         paste0(join_af_by[!join_af_by %in%

+                                                               colnames(df)],

+                                                collapse = ", "))))

             }

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

                 rlang::abort(.missing_user_cols_error(

@@ -253,8 +282,13 @@ aggregate_values_by_key <- function(x,

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

             rlang::abort(.non_ISM_error())

         }

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

-            rlang::abort(.missing_complAmpID_error())

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

+            rlang::abort(c(x = paste("Missing common columns",

+                                     "to join metadata"),

+                           i = paste("Missing: ",

+                                     paste0(join_af_by[!join_af_by %in%

+                                                           colnames(x)],

+                                            collapse = ", "))))

         }

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

             rlang::abort(.missing_user_cols_error(

@@ -280,7 +314,7 @@ aggregate_values_by_key <- function(x,

     # Check key

     stopifnot(is.character(key))

     if (!all(key %in% colnames(association_file))) {

-        stop("Key fields are missing from association file")

+        rlang::abort(c(x = "Key fields are missing from association file"))

     }

     # Check lambda

     stopifnot(is.list(lambda))

@@ -288,24 +322,24 @@ aggregate_values_by_key <- function(x,

     stopifnot(is.character(group) | is.null(group))

     if (is.data.frame(x)) {

         if (!all(group %in% c(colnames(association_file), colnames(x)))) {

-            stop(paste("Grouping variables not found"))

+            rlang::abort(paste("Grouping variables not found"))

         }

     } else {

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

             if (!all(group %in% c(colnames(association_file), colnames(df)))) {

-                stop(paste("Grouping variables not found"))

+                rlang::abort(paste("Grouping variables not found"))

             }

         })

     }

     if (is.data.frame(x)) {

         x <- list(x)

         agg_matrix <- .aggregate_lambda(

-            x, association_file, key, value_cols, lambda, group

+            x, association_file, key, value_cols, lambda, group, join_af_by

         )

         return(agg_matrix[[1]])

     }

     agg_matrix <- .aggregate_lambda(

-        x, association_file, key, value_cols, lambda, group

+        x, association_file, key, value_cols, lambda, group, join_af_by

     )

     agg_matrix

 }

@@ -194,14 +194,6 @@ comparison_matrix <- function(x,

     ShsCount = "ShsCount") {

     stopifnot(is.list(x) & !is.data.frame(x))

     stopifnot(all(names(x) %in% quantification_types()))

-    purrr::walk(x, function(m) {

-        mand <- .check_mandatory_vars(m)

-        amp <- .check_complAmpID(m)

-        val <- .check_value_col(m)

-        if (any(c(mand, amp, val) == FALSE)) {

-            stop(.non_ISM_error())

-        }

-    })

     stopifnot(is.character(fragmentEstimate) & length(fragmentEstimate) == 1)

     stopifnot(is.character(seqCount) & length(seqCount) == 1)

     stopifnot(is.character(barcodeCount) & length(barcodeCount) == 1)

@@ -221,8 +213,11 @@ comparison_matrix <- function(x,

         matrix1 %>%

             dplyr::full_join(matrix2, by = commoncols)

     })

-    if (any(is.na(result)) & getOption("ISAnalytics.verbose") == TRUE) {

-        message(.nas_introduced_msg())

+    na_introduced <- purrr::map_lgl(param_names, function(p) {

+        any(is.na(result[[p]]))

+    })

+    if (any(na_introduced) & getOption("ISAnalytics.verbose") == TRUE) {

+        rlang::inform(.nas_introduced_msg())

     }

     result

 }

@@ -248,6 +243,7 @@ comparison_matrix <- function(x,

 #' in input

 #' @param ShsCount Name of the shs count values column

 #' in input

+#' @param key Key columns to perform the joining operation

 #'

 #' @importFrom purrr is_empty map set_names

 #' @importFrom dplyr rename

@@ -278,21 +274,24 @@ comparison_matrix <- function(x,

 #' )

 #' separated_matrix <- separate_quant_matrices(matrices)

 #' options(op)

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

+separate_quant_matrices <- function(

+    x,

+    fragmentEstimate = "fragmentEstimate",

     seqCount = "seqCount",

     barcodeCount = "barcodeCount",

     cellCount = "cellCount",

-    ShsCount = "ShsCount") {

+    ShsCount = "ShsCount",

+    key = c(mandatory_IS_vars(),

+            annotation_IS_vars(),

+            "CompleteAmplificationID")

+    ) {

     stopifnot(is.data.frame(x))

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

-        stop(.non_ISM_error())

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

+        rlang::abort(.missing_user_cols_error(key[!key %in% colnames(x)]))

     }

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

-        stop(.missing_complAmpID_error())

-    }

-    num_cols <- .find_exp_cols(x)

+    num_cols <- .find_exp_cols(x, key)

     if (purrr::is_empty(num_cols)) {

-        stop(.missing_num_cols_error())

+        rlang::abort(.missing_num_cols_error())

     }

     stopifnot(is.character(fragmentEstimate) & length(fragmentEstimate) == 1)

     stopifnot(is.character(seqCount) & length(seqCount) == 1)

@@ -307,24 +306,16 @@ separate_quant_matrices <- function(x, fragmentEstimate = "fragmentEstimate",

     )

     to_copy <- if (any(!num_cols %in% param_col)) {

         if (all(!num_cols %in% param_col)) {

-            stop(.non_quant_cols_error())

+            rlang::abort(.non_quant_cols_error())

         }

         num_cols[!num_cols %in% param_col]

     }

     num_cols <- param_col[param_col %in% num_cols]

-    annot <- if (.is_annotated(x)) {

-        annotation_IS_vars()

-    } else {

-        character(0)

-    }

     if (!purrr::is_empty(to_copy) & getOption("ISAnalytics.verbose") == TRUE) {

-        message(.non_quant_cols_msg(to_copy))

+        rlang::inform(.non_quant_cols_msg(to_copy))

     }

     separated <- purrr::map(num_cols, function(quant) {

-        x[c(

-            mandatory_IS_vars(), annot, "CompleteAmplificationID",

-            to_copy, quant

-        )] %>% dplyr::rename(Value = quant)

+        x[c(key, to_copy, quant)] %>% dplyr::rename(Value = quant)

     }) %>% purrr::set_names(names(num_cols))

     separated

 }

@@ -91,7 +91,10 @@ remove_collisions <- function(x,

         ## Check if it contains the "Value" column. If not find all numeric

         ## columns that are not default columns

         quantifications_cols <- if (.check_value_col(x) == FALSE) {

-            found <- .find_exp_cols(x)

+            found <- .find_exp_cols(x,

+                                    c(mandatory_IS_vars(),

+                                      annotation_IS_vars(),

+                                      "CompleteAmplificationID"))

             if (purrr::is_empty(found)) {

                 stop(.missing_num_cols_error())

             }

@@ -98,6 +98,8 @@ association_file_columns <- function() {

     )

 }

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

+# import

 .af_col_types <- function(mode) {

     if (mode == "fread") {

         types <- list(

@@ -137,9 +139,6 @@ association_file_columns <- function() {

         return(types)

     }

     if (mode == "readr") {

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

-        # date_format <- paste0("%", date_format)

-        # date_format <- paste0(date_format, collapse = "%.")

         types <- list(

             ProjectID = "c", FUSIONID = "c", PoolID = "c", TagSequence = "c",

             SubjectID = "c", VectorType = "c", VectorID = "c",

@@ -180,6 +179,23 @@ association_file_columns <- function() {

     }

 }

+# Internal: used for file system alignment in import_association_file,

+# gives the names of the columns that respectively contain:

+# - the absolute path on disk of the project

+# - the path to the quantification folder

+# - the path to the iss folder

+.path_cols_names <- function() {

+    list(project = "Path", quant = "Path_quant", iss = "Path_iss")

+}

+

+.matrix_annotated_suffixes <- function() {

+    c(".no0.annotated")

+}

+

+.matrix_not_annotated_suffixes <- function() {

+    c("")

+}

+

 #' Names of the columns of the association file to consider for

 #' Vispa2 launch.

 #'

@@ -221,3 +237,8 @@ reduced_AF_columns <- function() {

 .supported_fread_compression_formats <- function() {

     c("gz", "bz2")

 }

+

+

+flag_logics <- function() {

+    c("AND", "OR", "XOR", "NAND", "NOR", "XNOR")

+}

@@ -196,10 +196,13 @@ import_single_Vispa2Matrix <- function(path,

 #' for which the value of the column "ProjectID" is one of the specified

 #' values. If multiple columns are present in the list all filtering

 #' conditions are applied as a logical AND.

+#' @param import_iss Import Vispa2 stats and merge them with the

+#' association file?

 #' @param export_widget_path A path on disk to save produced widgets or NULL

 #' if the user doesn't wish to save the html file

+#' @param ... Additional arguments to pass to \code{\link{import_Vispa2_stats}}

 #' @family Import functions

-#' @return A tibble with the contents of the association file plus a column

+#' @return A tibble with the contents of the association file plus columns

 #' containing the path in the file system for every project and pool if found.

 #' @details The import series of functions is designed to work in combination

 #' with the use of Vispa2 pipeline, please refer to this article for more

@@ -229,7 +232,11 @@ import_single_Vispa2Matrix <- function(path,

 #' @export

 #'

 #' @importFrom purrr map_lgl set_names is_empty

-#' @importFrom rlang inform

+#' @importFrom rlang inform abort dots_list exec

+#' @importFrom htmltools tagList browsable

+#' @importFrom tibble add_column

+#' @import dplyr

+#' @importFrom stringr str_pad

 #' @importFrom magrittr `%>%`

 #' @seealso \code{\link{date_formats}}

 #' @examples

@@ -245,7 +252,9 @@ import_association_file <- function(path,

     root = NULL, tp_padding = 4, dates_format = "ymd",

     separator = "\t",

     filter_for = NULL,

-    export_widget_path = NULL) {

+    import_iss = FALSE,

+    export_widget_path = NULL,

+    ...) {

     # Check parameters

     stopifnot(is.character(path) & length(path) == 1)

     stopifnot((is.character(root) & length(root) == 1) || (is.null(root)))

@@ -257,6 +266,14 @@ import_association_file <- function(path,

         is.integer(tp_padding)) & length(tp_padding) == 1)

     stopifnot(length(dates_format) == 1 & dates_format %in% date_formats())

     stopifnot(is.character(separator) && length(separator) == 1)

+    stopifnot(is.logical(import_iss) && length(import_iss) == 1)

+    if (import_iss & is.null(root)) {

+        rlang::abort(paste(

+            "Can't import Vispa2 stats files without",

+            "file system alignment. Provide the appropriate",

+            "root."

+        ))

+    }

     # Check filter

     stopifnot(is.null(filter_for) ||

         (is.list(filter_for) && !is.null(names(filter_for))))

@@ -292,7 +309,57 @@ import_association_file <- function(path,

         col_probs,

         missing_dates

     )))

-    if (something_to_report) {

+    ## Fix timepoints

+    if (!"TimepointMonths" %in% colnames(as_file)) {

+        as_file <- as_file %>%

+            tibble::add_column(TimepointMonths = NA_real_)

+    }

+    if (!"TimepointYears" %in% colnames(as_file)) {

+        as_file <- as_file %>%

+            tibble::add_column(TimepointYears = NA_real_)

+    }

+    as_file <- as_file %>%

+        dplyr::mutate(

+            TimepointMonths = dplyr::if_else(

+                condition = is.na(.data$TimepointMonths),

+                false = .data$TimepointMonths,

+                true = dplyr::if_else(

+                    condition = as.numeric(.data$TimePoint) == 0,

+                    true = 0,

+                    false = dplyr::if_else(

+                        condition = as.numeric(.data$TimePoint) > 0 &

+                            as.numeric(.data$TimePoint) < 30,

+                        true = ceiling(as.numeric(.data$TimePoint) / 30),

+                        false = round(as.numeric(.data$TimePoint) / 30)

+                    )

+                )

+            ),

+            TimepointYears = dplyr::if_else(

+                condition = is.na(.data$TimepointYears),

+                false = .data$TimepointYears,

+                true = dplyr::if_else(

+                    condition = as.numeric(.data$TimePoint) == 0,

+                    true = 0,

+                    false = dplyr::if_else(

+                        condition = as.numeric(.data$TimePoint) > 0 &

+                            as.numeric(.data$TimePoint) < 360,

+                        true = ceiling(as.numeric(.data$TimePoint) / 360),

+                        false = round(as.numeric(.data$TimePoint) / 360)

+                    )

+                )

+            )

+        ) %>%

+        dplyr::mutate(

+            TimepointMonths = stringr::str_pad(

+                as.character(.data$TimepointMonths),

+                pad = "0", side = "left", width = 2

+            ),

+            TimepointYears = stringr::str_pad(

+                as.character(.data$TimepointYears),

+                pad = "0", side = "left", width = 2

+            ),

+        )

+    widget <- if (something_to_report) {

         summary_report <- .summary_af_import_msg(

             pars_prob = parsing_problems, dates_prob = date_problems,

             cols_prob = col_probs, crit_na = missing_dates,

@@ -305,49 +372,261 @@ import_association_file <- function(path,

             )

         )

         if (getOption("ISAnalytics.widgets") == TRUE) {

-            withCallingHandlers(

-                expr = {

-                    withRestarts(

-                        {

-                            widg <- .checker_widget(

-                                parsing_problems,

-                                date_problems,

-                                checks,

-                                col_probs,

-                                missing_dates

-                            )

-                            print(widg)

-                        },

-                        print_err = function() {

-                            rlang::inform(.widgets_error())

-                            if (getOption("ISAnalytics.verbose") == TRUE) {

-                                rlang::inform(summary_report,

-                                    class = "summary_report"

-                                )

-                            }

-                        }

-                    )

-                },

-                error = function(cnd) {