removed file added by mistake

ms_workflow/03-filtering_aneuploid.R

-# ==========================================================================
-# Setup
-# ==========================================================================
-library("corescf")
-library("data.table")
-library("dplyr")
-library("ComplexHeatmap")
-library("stringr")
-library("ggplot2")
-library("ggridges")
-library("heatmaply")
-library("RColorBrewer")
-
-# ==========================================================================
-# Data
-# ==========================================================================
-dir.create(results_dir, showWarnings = FALSE, recursive = TRUE)
-data_dir <- paste0(Sys.getenv("PRJ_DATA"), "/data")
-results_dir <- paste0(Sys.getenv("PRJ_DATA"), "/aneuploid_cells")
-
-dloup_file <- paste0(
-  data_dir,
-  "/all_C13_mother-group_876-region_chr1_1-5120000_chrY_56320001-57227415-heatmap_copy_number.csv"
-)
-
-dloup <- fread(dloup_file) %>%
-  mutate(node_id = as.character(node_id))
-# colnames(dloup)[1:10]
-
-#
-# metadata
-# --------------------------------------------------------------------------
-metadata <- dloup %>%
-  select(node_id, barcodes, num_cells, num_noisy)
-
-cells <- dloup  %>%
-  select(-c("barcodes", "num_cells", "num_noisy"))
-
-# ==========================================================================
-# Filtering
-# ==========================================================================
-cells_long <- cells %>%
-  gather("segment", "copy_number", -node_id) %>%
-  mutate(chromosome = gsub("(.*):.*", "\\1", segment)) %>%
-  filter(chromosome != "chrY")
-
-# head(cells_long)
- 
-#
-# mean ploidy 
-# --------------------------------------------------------------------------
-aneuploid_cells <- cells_long %>%
-  group_by(node_id, chromosome) %>%
-  arrange(node_id, chromosome) %>%
-  mutate(
-    is_segment_missing = ifelse(copy_number < 0.8, "yes", "no")
-    ) %>% 
-  summarize(
-    mean_ploidy = mean(copy_number, na.rm = TRUE),
-    Frac_intact_chromosome = sum(is_segment_missing == "no", na.rm = TRUE)/n(),
-    is_chromosome_missing = ifelse(Frac_intact_chromosome < 0.1, "yes", "no")
-  ) %>% filter(is_chromosome_missing == "yes")
-  ungroup() %>%
-  group_by(node_id) %>%
-  mutate(
-    mean_ploidy = round(mean_ploidy, 2),
-    is_abnormal = ifelse(mean_ploidy <= 1.75 | mean_ploidy >= 4, "yes", "no"),
-    N_Complete_Karyotype = sum(is_abnormal == "no"),
-    Frac_Complete_Karyotype = sum(is_abnormal == "no") / n()
-  ) %>%
-  filter(is_abnormal  == "yes")
-
-aneuploid_id <- unique(aneuploid_cells$node_id)
-
-#
-# Visualization
-# --------------------------------------------------------------------------
-mat <- cells %>%
-  as.data.frame() %>%
-  column2rownames("node_id") %>%
-  as.matrix()
-
-mat_filt <- mat[aneuploid_id, ]
-
-Heatmap(
-  mat_filt,
-  cluster_columns = FALSE,
-  # col = binary_cols,
-  show_column_names = FALSE
-  # column_split = noisy_lab,
-  # row_split = noisy_lab
-)
-
-# ==========================================================================
-# Reproducibility
-# ==========================================================================
-session::save.session(".03-filtering_aneuploid.dat")
-devtools::session_info()
\ No newline at end of file