@@ -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: 1.3.5

+Version: 1.3.6

 Date: 2020-07-03

 Authors@R: c(

   person(given = "Andrea",

@@ -39,6 +39,7 @@ export(mandatory_IS_vars)

 export(matching_options)

 export(outlier_filter)

 export(outliers_by_pool_fragments)

+export(purity_filter)

 export(quantification_types)

 export(realign_after_collisions)

 export(reduced_AF_columns)

@@ -2,6 +2,16 @@

 title: "NEWS"

 output: github_document

 ---

+# ISAnalytics 1.3.6 (2021-10-05)

+

+## NEW

+

+* Added new feature `purity_filter()`

+

+## FIXES

+

+* Fixed small issue in printing information in reports

+

 # ISAnalytics 1.3.5 (2021-09-21)

 ## MAJOR CHANGES

@@ -1,6 +1,16 @@

 NEWS

 ================

+# ISAnalytics 1.3.6 (2021-10-05)

+

+## NEW

+

+-   Added new feature `purity_filter()`

+

+## FIXES

+

+-   Fixed small issue in printing information in reports

+

 # ISAnalytics 1.3.5 (2021-09-21)

 ## MAJOR CHANGES

@@ -1462,6 +1462,255 @@ is_sharing <- function(...,

 }

+#' Filter integration sites based on purity.

+#'

+#' @description

+#' \lifecycle{experimental}

+#' Filter that targets possible contamination between cell lines based on

+#' a numeric quantification (likely abundance or sequence count).

+#'

+#' @details

+#' ## Setting input arguments

+#'

+#' The input matrix can be re-aggregated with the provided `group_key`

+#' argument. This key contains the names of the columns to group on

+#' (besides the columns holding genomic coordinates of the integration

+#' sites) and must be contained in at least one of `x` or `lineages`

+#' data frames. If the key is not found only in `x`, then a join operation

+#' with the `lineages` data frame is performed on the common column(s)

+#' `join_on`.

+#'

+#' ## Group selection

+#' It is possible for the user to specify on which groups the logic of the

+#' filter should be applied to. For example: if we have

+#' `group_key = c("HematoLineage")` and we set

+#' `selected_groups = c("CD34", "Myeloid","Lymphoid")`

+#' it means that a single integration will be evaluated for the filter only

+#' for groups that have the values of "CD34", "Myeloid" and "Lymphoid" in

+#' the "HematoLineage" column.

+#' If the same integration is present in other groups it is

+#' kept as it is. `selected_groups` can be set to `NULL` if we want

+#' the logic to apply to every group present in the data frame,

+#' it can be set as a simple character vector as the example above if

+#' the group key has length 1 (and there is no need to filter on time point).

+#' If the group key is longer than 1 then the filter is applied only on the

+#' first element of the key.

+#'

+#' If a more refined selection on groups is needed, a data frame can

+#' be provided instead:

+#'

+#' ```

+#' group_key = c("CellMarker", "Tissue")

+#' selected_groups = tibble::tribble(

+#' ~ CellMarker, ~ Tissue,

+#' "CD34", "BM",

+#' "CD14", "BM",

+#' "CD14", "PB"

+#' )

+#' ```

+#'

+#' Columns in the data frame should be the same as group key (plus,

+#' eventually, the time point column). In this example only those groups

+#' identified by the rows in the provided data frame are processed.

+#'

+#' @family Analysis functions

+#'

+#' @param x An aggregated integration matrix, obtained via

+#' `aggregate_values_by_key()`

+#' @param lineages A data frame containing cell lineages information

+#' @param aggregation_key The key used for aggregating `x`

+#' @param group_key A character vector of column names for re-aggregation.

+#' Column names must be either in `x` or in `lineages`. See details.

+#' @param selected_groups Either NULL, a character vector or a

+#' data frame for group selection. See details.

+#' @param join_on Common columns to perform a join operation on

+#' @param min_value A minimum value to filter the input matrix. Integrations

+#' with a value strictly lower than `min_value` are excluded (dropped) from

+#' the output.

+#' @param impurity_threshold The ratio threshold for impurity in groups

+#' @param by_timepoint Should filtering be applied on each time point? If

+#' `FALSE`, all time points are merged together

+#' @param timepoint_column Column in `x` containing the time point

+#' @param value_column Column in `x` containing the numeric

+#' quantification of interest

+#'

+#' @return A data frame

+#' @export

+#'

+#' @examples

+#' data("integration_matrices", package = "ISAnalytics")

+#' data("association_file", package = "ISAnalytics")

+#' aggreg <- aggregate_values_by_key(

+#'     x = rlang::current_env()$integration_matrices,

+#'     association_file = rlang::current_env()$association_file,

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

+#' )

+#' filtered_by_purity <- purity_filter(x = aggreg,

+#' value_column = "seqCount_sum")

+#' head(filtered_by_purity)

+purity_filter <- function(x,

+                          lineages = blood_lineages_default(),

+                          aggregation_key = c("SubjectID", "CellMarker",

+                                              "Tissue", "TimePoint"),

+                          group_key = c("CellMarker", "Tissue"),

+                          selected_groups = NULL,

+                          join_on = "CellMarker",

+                          min_value = 3,

+                          impurity_threshold = 10,

+                          by_timepoint = TRUE,

+                          timepoint_column = "TimePoint",

+                          value_column = "seqCount_sum") {

+    ## Checks

+    #### - Base

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

+    stopifnot(is.character(aggregation_key))

+    stopifnot(is.character(group_key))

+    stopifnot(is.logical(by_timepoint))

+    stopifnot(is.numeric(min_value) || is.integer(min_value))

+    stopifnot(is.numeric(impurity_threshold) || is.integer(impurity_threshold))

+    stopifnot(is.character(value_column))

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

+                  is.data.frame(selected_groups))

+    #### - Keys

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

+        rlang::abort(.missing_user_cols_error(

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

+            ))

+    }

+    if (!value_column[1] %in% colnames(x)) {

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

+    }

+    to_join <- if (all(group_key %in% colnames(x))) {

+        ### If the groups rely only on attributes not related to lineages

+        ### and are contained in the input matrix

+        FALSE

+    } else {

+        ### If lineages info is needed

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

+        if (!all(group_key %in% unique(c(colnames(x), colnames(lineages))))) {

+            missing_cols <- group_key[!group_key %in% unique(c(colnames(x),

+                                               colnames(lineages)))]

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

+        }

+        if (!(all(join_on %in% colnames(x)) &

+              all(join_on %in% colnames(lineages)))

+            ) {

+            missing_common <- c("Missing common column(s) to join on",

+                                i = paste("The column(s) provided in argument",

+                                          "`join_on` is missing from one or",

+                                          "both data frames, aborting"))

+           rlang::abort(missing_common)

+        }

+        TRUE

+    }

+    if (by_timepoint) {

+       stopifnot(is.character(timepoint_column))

+        timepoint_column <- timepoint_column[1]

+        if (!timepoint_column %in% colnames(x)) {

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

+        }

+        group_key <- union(group_key, timepoint_column)

+    }

+    ## Pre-processing

+    #### - Join if needed

+    if (to_join) {

+        x <- x %>%

+            dplyr::left_join(lineages, by = join_on)

+    }

+    #### - Group and sum

+    is_vars <- if (.is_annotated(x)) {

+        c(mandatory_IS_vars(), annotation_IS_vars())

+    } else {

+        mandatory_IS_vars()

+    }

+    grouped <- x %>%

+        dplyr::group_by(dplyr::across(dplyr::all_of(c(is_vars, group_key)))) %>%

+        dplyr::summarise(Value = sum(.data[[value_column]]),

+                         .groups = "drop")

+    #### - value filter

+    filtered_value <- threshold_filter(x = grouped,

+                                 threshold = min_value,

+                                 cols_to_compare = "Value",

+                                 comparators = ">=")

+    #### - Separating IS 1: group filtering

+    pre_filt <- list()

+    if (is.null(selected_groups) || purrr::is_empty(selected_groups)) {

+        pre_filt[["process"]] <- filtered_value

+        pre_filt[["keep"]] <- filtered_value[0, ]

+    } else if (is.character(selected_groups)) {

+        pre_filt[["process"]] <- filtered_value %>%

+            dplyr::filter(.data[[group_key[1]]] %in% selected_groups)

+        pre_filt[["keep"]] <- filtered_value %>%

+            dplyr::filter(!.data[[group_key[1]]] %in% selected_groups)

+    } else {

+        ok_cols <- colnames(selected_groups)[colnames(selected_groups) %in%

+                                                 group_key]

+        selected_groups <- selected_groups %>%

+            dplyr::select(dplyr::all_of(ok_cols)) %>%

+            dplyr::distinct()

+        if (ncol(selected_groups) == 0 ||

+            nrow(selected_groups) == 0) {

+            pre_filt[["process"]] <- filtered_value

+            pre_filt[["keep"]] <- filtered_value[0, ]

+        } else {

+            pre_filt[["process"]] <- dplyr::inner_join(filtered_value,

+                                                       selected_groups,

+                                                       by = ok_cols)

+            pre_filt[["keep"]] <- dplyr::anti_join(filtered_value,

+                                                   selected_groups,

+                                                   by = ok_cols)

+        }

+    }

+    if (nrow(pre_filt$process) == 0) {

+        if (getOption("ISAnalytics.verbose")) {

+            rlang::inform("No iss to process, done")

+        }

+        return(filtered_value)

+    }

+    #### - Separating IS 2: iss that are shared between groups are going to be

+    #### processed, unique iss are kept as they are

+    vars_to_group <- if (by_timepoint) {

+        c(is_vars, timepoint_column)

+    } else {

+        is_vars

+    }

+    by_is <- pre_filt$process %>%

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

+        dplyr::summarise(n = n(), .groups = "drop")

+    to_process <- by_is %>%

+        dplyr::filter(.data$n > 1) %>%

+        dplyr::select(-.data$n) %>%

+        dplyr::inner_join(pre_filt$process, by = vars_to_group)

+    if (nrow(to_process) == 0) {

+        ## If there are no shared iss there is nothing to process,

+        ## return just the filtered matrix

+        return(filtered_value)

+    }

+    to_keep <- by_is %>%

+        dplyr::filter(.data$n == 1) %>%

+        dplyr::select(-.data$n) %>%

+        dplyr::inner_join(pre_filt$process, by = vars_to_group)

+    #### - Process groups

+    .filter_by_purity <- function(group) {

+        max_val <- max(group$Value)

+        processed <- group %>%

+            dplyr::mutate(remove = (max_val / .data$Value) >

+                              impurity_threshold) %>%

+            dplyr::filter(remove == FALSE) %>%

+            dplyr::select(-.data$remove)

+        processed

+    }

+    processed_iss <- to_process %>%

+        dplyr::group_by(dplyr::across(vars_to_group)) %>%

+        dplyr::group_modify(~ .filter_by_purity(.x)) %>%

+        dplyr::ungroup()

+    #### - Re-compose matrix

+    final <- processed_iss %>%

+        dplyr::bind_rows(to_keep) %>%

+        dplyr::bind_rows(pre_filt$keep)

+    final

+}

+

 #' A set of pre-defined functions for `sample_statistics`.

 #'

 #' @return A named list of functions/purrr-style lambdas

@@ -137,6 +137,16 @@ options("ISAnalytics.reports" = TRUE)

 Show more

 </summary>

+# ISAnalytics 1.3.6 (2021-10-05)

+

+## NEW

+

+-   Added new feature `purity_filter()`

+

+## FIXES

+

+-   Fixed small issue in printing information in reports

+

 # ISAnalytics 1.3.5 (2021-09-21)

 ## MAJOR CHANGES

@@ -129,16 +129,16 @@ logic <- if (length(params$key) > 1) {

         combined <- rbind(base_flag, c(flag_logic, ""))

         paste(

             "* Key length > 1, flagging formula used: ",

-            paste(combined, collapse = " ")

+            paste0(combined, collapse = " ")

         )

     } else {

         base_flag <- paste0(

-            "(tdist_", key, " < ", params$outlier_thresh,

-            " & zscore_", key, " < 0)"

+            "(tdist_", params$key, " < ", params$outlier_thresh,

+            " & zscore_", params$key, " < 0)"

         )

         paste(

             "* Flagging formula used: ",

-            paste(base_flag)

+            paste0(base_flag)

         )

     }

 log2 <- if (params$log2_req) {

@@ -80,6 +80,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

@@ -81,29 +81,29 @@ For more details on how this files were generated use the help

 The default values are included in this package and

 it can be accessed by doing:\if{html}{\out{<div class="r">}}\preformatted{head(known_clinical_oncogenes())

-#> # A tibble: 5 × 2

-#>   GeneName KnownClonalExpansion

-#>   <chr>    <lgl>               

-#> 1 MECOM    TRUE                

-#> 2 CCND2    TRUE                

-#> 3 TAL1     TRUE                

-#> 4 LMO2     TRUE                

-#> 5 HMGA2    TRUE

-}\if{html}{\out{</div>}}

+}\if{html}{\out{</div>}}\preformatted{## # A tibble: 5 × 2

+##   GeneName KnownClonalExpansion

+##   <chr>    <lgl>               

+## 1 MECOM    TRUE                

+## 2 CCND2    TRUE                

+## 3 TAL1     TRUE                

+## 4 LMO2     TRUE                

+## 5 HMGA2    TRUE

+}

 If the user wants to change this parameter the input data frame must

 preserve the column structure. The same goes for the \code{suspicious_genes}

 parameter (DOIReference column is optional):\if{html}{\out{<div class="r">}}\preformatted{head(clinical_relevant_suspicious_genes())

-#> # A tibble: 6 × 3

-#>   GeneName ClinicalRelevance DOIReference                                

-#>   <chr>    <lgl>             <chr>                                       

-#> 1 DNMT3A   TRUE              https://doi.org/10.1182/blood-2018-01-829937

-#> 2 TET2     TRUE              https://doi.org/10.1182/blood-2018-01-829937

-#> 3 ASXL1    TRUE              https://doi.org/10.1182/blood-2018-01-829937

-#> 4 JAK2     TRUE              https://doi.org/10.1182/blood-2018-01-829937

-#> 5 CBL      TRUE              https://doi.org/10.1182/blood-2018-01-829937

-#> 6 TP53     TRUE              https://doi.org/10.1182/blood-2018-01-829937

-}\if{html}{\out{</div>}}

+}\if{html}{\out{</div>}}\preformatted{## # A tibble: 6 × 3

+##   GeneName ClinicalRelevance DOIReference                                

+##   <chr>    <lgl>             <chr>                                       

+## 1 DNMT3A   TRUE              https://doi.org/10.1182/blood-2018-01-829937

+## 2 TET2     TRUE              https://doi.org/10.1182/blood-2018-01-829937

+## 3 ASXL1    TRUE              https://doi.org/10.1182/blood-2018-01-829937

+## 4 JAK2     TRUE              https://doi.org/10.1182/blood-2018-01-829937

+## 5 CBL      TRUE              https://doi.org/10.1182/blood-2018-01-829937

+## 6 TP53     TRUE              https://doi.org/10.1182/blood-2018-01-829937

+}

 }

 }

 \examples{

@@ -70,6 +70,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

@@ -62,6 +62,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

@@ -91,6 +91,7 @@ Other Analysis functions:

 \code{\link{compute_abundance}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

@@ -57,6 +57,7 @@ Other Analysis functions:

 \code{\link{compute_abundance}()},

 \code{\link{cumulative_count_union}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

@@ -95,6 +95,7 @@ Other Analysis functions:

 \code{\link{compute_abundance}()},

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

new file mode 100644

@@ -0,0 +1,128 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/analysis-functions.R

+\name{purity_filter}

+\alias{purity_filter}

+\title{Filter integration sites based on purity.}

+\usage{

+purity_filter(

+  x,

+  lineages = blood_lineages_default(),

+  aggregation_key = c("SubjectID", "CellMarker", "Tissue", "TimePoint"),

+  group_key = c("CellMarker", "Tissue"),

+  selected_groups = NULL,

+  join_on = "CellMarker",

+  min_value = 3,

+  impurity_threshold = 10,

+  by_timepoint = TRUE,

+  timepoint_column = "TimePoint",

+  value_column = "seqCount_sum"

+)

+}

+\arguments{

+\item{x}{An aggregated integration matrix, obtained via

+\code{aggregate_values_by_key()}}

+

+\item{lineages}{A data frame containing cell lineages information}

+

+\item{aggregation_key}{The key used for aggregating \code{x}}

+

+\item{group_key}{A character vector of column names for re-aggregation.

+Column names must be either in \code{x} or in \code{lineages}. See details.}

+

+\item{selected_groups}{Either NULL, a character vector or a

+data frame for group selection. See details.}

+

+\item{join_on}{Common columns to perform a join operation on}

+

+\item{min_value}{A minimum value to filter the input matrix. Integrations

+with a value strictly lower than \code{min_value} are excluded (dropped) from

+the output.}

+

+\item{impurity_threshold}{The ratio threshold for impurity in groups}

+

+\item{by_timepoint}{Should filtering be applied on each time point? If

+\code{FALSE}, all time points are merged together}

+

+\item{timepoint_column}{Column in \code{x} containing the time point}

+

+\item{value_column}{Column in \code{x} containing the numeric

+quantification of interest}

+}

+\value{

+A data frame

+}

+\description{

+\lifecycle{experimental}

+Filter that targets possible contamination between cell lines based on

+a numeric quantification (likely abundance or sequence count).

+}

+\details{

+\subsection{Setting input arguments}{

+

+The input matrix can be re-aggregated with the provided \code{group_key}

+argument. This key contains the names of the columns to group on

+(besides the columns holding genomic coordinates of the integration

+sites) and must be contained in at least one of \code{x} or \code{lineages}

+data frames. If the key is not found only in \code{x}, then a join operation

+with the \code{lineages} data frame is performed on the common column(s)

+\code{join_on}.

+}

+

+\subsection{Group selection}{

+

+It is possible for the user to specify on which groups the logic of the

+filter should be applied to. For example: if we have

+\code{group_key = c("HematoLineage")} and we set

+\code{selected_groups = c("CD34", "Myeloid","Lymphoid")}

+it means that a single integration will be evaluated for the filter only

+for groups that have the values of "CD34", "Myeloid" and "Lymphoid" in

+the "HematoLineage" column.

+If the same integration is present in other groups it is

+kept as it is. \code{selected_groups} can be set to \code{NULL} if we want

+the logic to apply to every group present in the data frame,

+it can be set as a simple character vector as the example above if

+the group key has length 1 (and there is no need to filter on time point).

+If the group key is longer than 1 then the filter is applied only on the

+first element of the key.

+

+If a more refined selection on groups is needed, a data frame can

+be provided instead:\preformatted{group_key = c("CellMarker", "Tissue")

+selected_groups = tibble::tribble(

+~ CellMarker, ~ Tissue,

+"CD34", "BM",

+"CD14", "BM",

+"CD14", "PB"

+)

+}

+

+Columns in the data frame should be the same as group key (plus,

+eventually, the time point column). In this example only those groups

+identified by the rows in the provided data frame are processed.

+}

+}

+\examples{

+data("integration_matrices", package = "ISAnalytics")

+data("association_file", package = "ISAnalytics")

+aggreg <- aggregate_values_by_key(

+    x = rlang::current_env()$integration_matrices,

+    association_file = rlang::current_env()$association_file,

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

+)

+filtered_by_purity <- purity_filter(x = aggreg,

+value_column = "seqCount_sum")

+head(filtered_by_purity)

+}

+\seealso{

+Other Analysis functions: 

+\code{\link{CIS_grubbs}()},

+\code{\link{comparison_matrix}()},

+\code{\link{compute_abundance}()},

+\code{\link{cumulative_count_union}()},

+\code{\link{cumulative_is}()},

+\code{\link{is_sharing}()},

+\code{\link{sample_statistics}()},

+\code{\link{separate_quant_matrices}()},

+\code{\link{threshold_filter}()},

+\code{\link{top_integrations}()}

+}

+\concept{Analysis functions}

@@ -78,6 +78,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()},

 \code{\link{top_integrations}()}

@@ -62,6 +62,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{threshold_filter}()},

 \code{\link{top_integrations}()}

@@ -78,8 +78,7 @@ It is also possible to filter different data frames with different

 sets of conditions. Besides having the possibility of defining the

 other parameters as simple vector, which has the same results as

 operating on an unnamed list, the user can define the parameters as

-named lists containing vectors. For example:\if{html}{\out{<div class="r">}}\preformatted{

-example_df <- tibble::tibble(a = c(20, 30, 40),

+named lists containing vectors. For example:\if{html}{\out{<div class="r">}}\preformatted{example_df <- tibble::tibble(a = c(20, 30, 40),

                              b = c(40, 50, 60),

                              c = c("a", "b", "c"),

                              d = c(3L, 4L, 5L))

@@ -87,31 +86,30 @@ example_list <- list(first = example_df,

                      second = example_df,

                      third = example_df)

 print(example_list)

-#> $first

-#> # A tibble: 3 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    20    40 a         3

-#> 2    30    50 b         4

-#> 3    40    60 c         5

-#> 

-#> $second

-#> # A tibble: 3 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    20    40 a         3

-#> 2    30    50 b         4

-#> 3    40    60 c         5

-#> 

-#> $third

-#> # A tibble: 3 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    20    40 a         3

-#> 2    30    50 b         4

-#> 3    40    60 c         5

-

-filtered <- threshold_filter(example_list,

+}\if{html}{\out{</div>}}\preformatted{## $first

+## # A tibble: 3 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    20    40 a         3

+## 2    30    50 b         4

+## 3    40    60 c         5

+## 

+## $second

+## # A tibble: 3 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    20    40 a         3

+## 2    30    50 b         4

+## 3    40    60 c         5

+## 

+## $third

+## # A tibble: 3 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    20    40 a         3

+## 2    30    50 b         4

+## 3    40    60 c         5

+}\if{html}{\out{<div class="r">}}\preformatted{filtered <- threshold_filter(example_list,

 threshold = list(first = c(20, 60),

 third = c(25)),

 cols_to_compare = list(first = c("a", "b"),

@@ -119,27 +117,27 @@ third = c("a")),

 comparators = list(first = c(">", "<"),

 third = c(">=")))

 print(filtered)

-#> $first

-#> # A tibble: 1 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    30    50 b         4

-#> 

-#> $second

-#> # A tibble: 3 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    20    40 a         3

-#> 2    30    50 b         4

-#> 3    40    60 c         5

-#> 

-#> $third

-#> # A tibble: 2 × 4

-#>       a     b c         d

-#>   <dbl> <dbl> <chr> <int>

-#> 1    30    50 b         4

-#> 2    40    60 c         5

-}\if{html}{\out{</div>}}

+}\if{html}{\out{</div>}}\preformatted{## $first

+## # A tibble: 1 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    30    50 b         4

+## 

+## $second

+## # A tibble: 3 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    20    40 a         3

+## 2    30    50 b         4

+## 3    40    60 c         5

+## 

+## $third

+## # A tibble: 2 × 4

+##       a     b c         d

+##   <dbl> <dbl> <chr> <int>

+## 1    30    50 b         4

+## 2    40    60 c         5

+}

 The above signature will roughly be translated as:

 \itemize{

@@ -213,6 +211,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{top_integrations}()}

@@ -78,6 +78,7 @@ Other Analysis functions:

 \code{\link{cumulative_count_union}()},

 \code{\link{cumulative_is}()},

 \code{\link{is_sharing}()},

+\code{\link{purity_filter}()},

 \code{\link{sample_statistics}()},

 \code{\link{separate_quant_matrices}()},

 \code{\link{threshold_filter}()}

@@ -108,6 +108,7 @@ test_that(paste(func_name, "reads type NEW standard"), {

 })

 test_that(paste(func_name, "reads type NEW different params"), {

+    skip_on_os("windows")

     tf <- withr::local_tempfile(fileext = ".tsv")

     readr::write_tsv(sample_df, tf)

     expected_summary_msg <- .summary_ism_import_msg(

new file mode 100644

@@ -0,0 +1,328 @@

+library(ISAnalytics)

+func_name <- "purity_filter"

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

+# Global vars

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

+

+df <- tibble::tibble(chr = c('1', '1', '1', '1', '1', '1', '1', '1', '1', '1',

+                             '1', '1', '1', '1', '1', '1', '1', '1', '1', '1',

+                             '1', '1', '1', '1', '1', '1', '1', '1', '1', '1',

+                             '1', '1', '1', '1', '1', '1', '1', '1', '1', '1'),

+                     integration_locus = c(121249, 251227, 645551, 732938,

+                                           775536, 846681, 1029785, 1036835,

+                                           121249, 251227, 645551, 732938,

+                                           775536, 846681, 1029785, 1036835,

+                                           121249, 251227, 645551, 732938,

+                                           775536, 846681, 1029785, 1036835,

+                                           121249, 251227, 645551, 732938,

+                                           775536, 846681, 1029785, 1036835,

+                                           121249, 251227, 645551, 732938,

+                                           775536, 846681, 1029785, 1036835),

+                     strand = c('+', '+', '+', '+', '+', '+', '-', '+', '+',

+                                '+', '+', '+', '+', '+', '-', '+', '+', '+',

+                                '+', '+', '+', '+', '-', '+', '+', '+', '+',

+                                '+', '+', '+', '-', '+', '+', '+', '+', '+',

+                                '+', '+', '-', '+'),

+                     GeneName = c('LOC729737', 'LOC100132287', 'LOC100133331',

+                                  'LOC100288069', 'LINC01128', 'LOC100130417',

+                                  'C1orf159', 'C1orf159', 'LOC729737',

+                                  'LOC100132287', 'LOC100133331',

+                                  'LOC100288069', 'LINC01128', 'LOC100130417',

+                                  'C1orf159', 'C1orf159', 'LOC729737',

+                                  'LOC100132287', 'LOC100133331',

+                                  'LOC100288069', 'LINC01128', 'LOC100130417',

+                                  'C1orf159', 'C1orf159', 'LOC729737',

+                                  'LOC100132287', 'LOC100133331',

+                                  'LOC100288069', 'LINC01128', 'LOC100130417',

+                                  'C1orf159', 'C1orf159', 'LOC729737',

+                                  'LOC100132287', 'LOC100133331',

+                                  'LOC100288069', 'LINC01128', 'LOC100130417',

+                                  'C1orf159', 'C1orf159'),

+                     GeneStrand = c('-', '+', '-', '-', '+', '-', '-', '-',

+                                    '-', '+', '-', '-', '+', '-', '-', '-',

+                                    '-', '+', '-', '-', '+', '-', '-', '-',

+                                    '-', '+', '-', '-', '+', '-', '-', '-',

+                                    '-', '+', '-', '-', '+', '-', '-', '-'),

+                     CellMarker = c('CD13', 'CD13', 'CD13', 'CD13', 'CD13',

+                                    'CD13', 'CD13', 'CD13', 'CD14', 'CD14',

+                                    'CD14', 'CD14', 'CD14', 'CD14', 'CD14',

+                                    'CD14', 'CD19', 'CD19', 'CD19', 'CD19',

+                                    'CD19', 'CD19', 'CD19', 'CD19', 'CD3',

+                                    'CD3', 'CD3', 'CD3', 'CD3', 'CD3', 'CD3',

+                                    'CD3', 'CD34', 'CD34', 'CD34', 'CD34',

+                                    'CD34', 'CD34', 'CD34', 'CD34'),

+                     Tissue = c('BM', 'BM', 'BM', 'BM', 'BM', 'BM', 'BM',

+                                'BM', 'PB', 'PB', 'PB', 'PB', 'PB', 'PB',

+                                'PB', 'PB', 'PB', 'PB', 'PB', 'PB', 'PB',

+                                'PB', 'PB', 'PB', 'PB', 'PB', 'PB', 'PB',

+                                'PB', 'PB', 'PB', 'PB', 'BM', 'BM', 'BM',

+                                'BM', 'BM', 'BM', 'BM', 'BM'),

+                     TimePoint = c('01', '01', '01', '01', '01', '01', '01',

+                                   '01', '01', '01', '01', '01', '01', '01',

+                                   '01', '01', '01', '01', '01', '01', '01',

+                                   '01', '01', '01', '01', '01', '01', '01',

+                                   '01', '01', '01', '01', '01', '01', '01',

+                                   '01', '01', '01', '01', '01'),

+                     Value = c(1, 1, 1, 1000, 1, 10, 3, 3, 1, 1000, 1000, 500,

+                               1, 12, 30, 1000, 1, 1, 500, 1, 10, 14, 30, 90,

+                               1, 1, 1, 1, 10, 9, 30, 90, 1000, 1, 1, 300,

+                               10, 8, 1000, 3))

+

+expected_output_sc <- tibble::tibble(chr = c('1', '1', '1', '1', '1', '1', '1',

+                                             '1', '1', '1', '1', '1', '1', '1',

+                                             '1', '1', '1', '1', '1'),

+                                     integration_locus = c(121249, 251227,

+                                                           645551, 645551,

+                                                           732938, 732938,

+                                                           732938, 775536,

+                                                           775536, 775536,

+                                                           775536, 775536,

+                                                           846681, 846681,

+                                                           846681, 846681,

+                                                           846681, 1029785,

+                                                           1036835),

+                                     strand = c('+', '+', '+', '+', '+', '+',

+                                                '+', '+', '+', '+', '+', '+',

+                                                '+', '+', '+', '+', '+', '-',

+                                                '+'),

+                                     GeneName = c('LOC729737', 'LOC100132287',

+                                                  'LOC100133331',

+                                                  'LOC100133331',

+                                                  'LOC100288069',

+                                                  'LOC100288069',

+                                                  'LOC100288069',

+                                                  'LINC01128',

+                                                  'LINC01128',

+                                                  'LINC01128',

+                                                  'LINC01128', 'LINC01128',

+                                                  'LOC100130417',

+                                                  'LOC100130417',

+                                                  'LOC100130417',

+                                                  'LOC100130417',

+                                                  'LOC100130417', 'C1orf159',

+                                                  'C1orf159'),

+                                     GeneStrand = c('-', '+', '-', '-', '-',

+                                                    '-', '-', '+', '+', '+',

+                                                    '+', '+', '-', '-', '-',

+                                                    '-', '-', '-', '-'),

+                                     TimePoint = c('01', '01', '01', '01',

+                                                   '01', '01', '01', '01',

+                                                   '01', '01', '01', '01',

+                                                   '01', '01', '01', '01',

+                                                   '01', '01', '01'),

+                                     CellMarker = c('CD34', 'CD14', 'CD14',

+                                                    'CD19', 'CD13', 'CD14',

+                                                    'CD34', 'CD13', 'CD14',

+                                                    'CD19', 'CD3', 'CD34',

+                                                    'CD13', 'CD14', 'CD19',

+                                                    'CD3', 'CD34', 'CD34',

+                                                    'CD14'),

+                                     Tissue = c('BM', 'PB', 'PB', 'PB', 'BM',

+                                                'PB', 'BM', 'BM', 'PB', 'PB',

+                                                'PB', 'BM', 'BM', 'PB', 'PB',

+                                                'PB', 'BM', 'BM', 'PB'),

+                                     Value = c(1000, 1000, 1000, 500, 1000,

+                                               500, 300, 1, 1, 10, 10, 10, 10,

+                                               12, 14, 9, 8, 1000, 1000))

+expected_output_ab <- tibble::tibble(chr = c('1', '1', '1', '1', '1', '1', '1',

+                                             '1', '1', '1', '1', '1', '1', '1',

+                                             '1', '1', '1', '1'),

+                     integration_locus = c(121249, 251227, 645551, 645551,