v0.17.0 spike-in logic started

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: qSIP2
 Title: qSIP Analysis
-Version: 0.16.15
+Version: 0.17.0
 Authors@R: 
     person("Jeff", "Kimbrel", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0001-7213-9392"))

NAMESPACE

@@ -34,6 +34,9 @@ export(infer_source_data)
 export(is_qsip_data)
 export(is_qsip_data_list)
 export(is_qsip_filtered)
+export(jgi_feature_df)
+export(jgi_sample_df)
+export(jgi_source_df)
 export(multi_qsip_wrapper)
 export(multi_qsip_wrapper_launcher)
 export(n_resamples)

NEWS.md

@@ -1,3 +1,7 @@
+# qSIP2 0.17.0
+
+* New functions to work with JGI spike-ins
+
 # qSIP2 0.16
 
 * Added new vignettes

R/jgi_feature_df.R

@@ -0,0 +1,13 @@
+#' Make a feature dataframe from a JGI coverage file
+#'
+#' @export
+
+jgi_feature_df <- function(coverage_file) {
+  readr::read_csv(coverage_file, show_col_types = F) |>
+    tidyr::pivot_longer(
+      cols = c(dplyr::everything(), -Feature),
+      names_to = "sample_id",
+      values_to = "COVERAGE"
+    ) |>
+    dplyr::rename("feature_id" = "Feature")
+}

R/jgi_sample_df.R

@@ -0,0 +1,25 @@
+#' Make a sample dataframe from JGI proposal file
+#'
+#' @export
+
+jgi_sample_df <- function(file_path, skip = 27) {
+  readr::read_lines(proposal_file,
+    skip = skip
+  ) |>
+    tibble::enframe() |>
+    dplyr::filter(stringr::str_detect(value, "^\\d+\\.\\d+")) |>
+    tidyr::separate(value, sep = "\t", into = c("Fraction", "Fraction_eluted_volume (uL)", "Fraction_density (g/mL)", "Eluted_DNA_concentration (ng/uL)", "Run_date", "Library_name", "Fastq_name", "Sequencing_project_ID", "Sequins_added (pg)", "Mix_type", "Raw_reads_count", "Filtered_reads_count")) |>
+    tidyr::separate(Fraction, sep = " ", into = c("Fraction", "sample_id")) |>
+    tidyr::separate(Fraction, sep = "\\.", into = c("SOURCE", "Fraction")) |>
+    dplyr::select(sample_id,
+      SOURCE,
+      gradient_pos = Fraction,
+      gradient_pos_density = `Fraction_density (g/mL)`,
+      eluted_volume_ul = `Fraction_eluted_volume (uL)`,
+      eluted_conc_ng_ul = `Eluted_DNA_concentration (ng/uL)`,
+      sequins_pg = `Sequins_added (pg)`,
+      MIX = Mix_type
+    ) |>
+    dplyr::left_join(sources, by = "SOURCE") |>
+    dplyr::select(-SOURCE)
+}

R/jgi_source_df.R

@@ -0,0 +1,15 @@
+#' Make a source dataframe from JGI proposal file
+#'
+#' @export
+
+jgi_source_df <- function(file_path, skip = 27) {
+  readr::read_lines(file_path,
+    skip = skip
+  ) |>
+    tibble::enframe() |>
+    dplyr::filter(stringr::str_detect(value, "^\\d+\\. ")) |>
+    tidyr::separate(value, sep = "\t", into = c("Source_sample", "Source_sample_ID", "Sample_group", "Group ID", "Isotope_label", "SIP_combined_assembly_AP_ID")) |>
+    tidyr::separate(Source_sample, sep = " ", into = c("SOURCE", "SOURCE_ID")) |>
+    dplyr::mutate(SOURCE = stringr::str_remove(SOURCE, "\\.")) |>
+    dplyr::select(SOURCE, source_mat_id = SOURCE_ID, isotope = Isotope_label)
+}

_pkgdown.yml

@@ -62,6 +62,12 @@ reference:
   - plot_EAF_values
   - plot_growth_values
 
+- title: Spike-In Controls
+  contents:
+  - jgi_source_df
+  - jgi_sample_df
+  - jgi_feature_df
+
 - title: Datasets
   contents:
   - example_source_df

data-raw/example_qsip_data.R

@@ -118,6 +118,22 @@ isotope_palette = c(
   "16O" = "#037bcf", "18O" = "#ff0000"
 )
 
+# JGI
+jgi_mixes <- readxl::read_excel("/Users/kimbrel1/Library/CloudStorage/OneDrive-LLNL/Documents/Soils_SFA/analysis/qSIP_refactor/JGI_spike_ins/JGI_mixes.xlsx") |>
+  tidyr::pivot_longer(
+    cols = tidyr::ends_with("stoichiometry"),
+    names_to = "MIX",
+    values_to = "STOICHIOMETRY"
+  ) |>
+  tidyr::drop_na(STOICHIOMETRY) |>
+  dplyr::mutate(
+    MIX = stringr::str_remove(MIX, "_stoichiometry"),
+    MIX = stringr::str_remove(MIX, "MIX_")
+  ) |>
+  dplyr::mutate(RATIO = STOICHIOMETRY / sum(STOICHIOMETRY), .by = MIX) |>
+  dplyr::rename(feature_id = ID) |>
+  dplyr::arrange(MIX)
+
 # save
 usethis::use_data(example_source_df, overwrite = TRUE)
 usethis::use_data(example_sample_df, overwrite = TRUE)
@@ -135,3 +151,4 @@ usethis::use_data(example_qsip_growth_t0, overwrite = TRUE)
 usethis::use_data(example_group_dataframe, overwrite = TRUE)
 
 usethis::use_data(isotope_palette, overwrite = TRUE, internal = TRUE)
+usethis::use_data(jgi_mixes, overwrite = TRUE, internal = TRUE)