# global knitting options for code rendering knitr::opts_chunk$set(collapse = TRUE, comment = "#>") # change to TRUE to enable global knitting options for automatic saving of all plots as .png and .pdf if (FALSE) { knitr::opts_chunk$set( dev = c("png", "pdf"), fig.keep = "all", dev.args = list(pdf = list(encoding = "WinAnsi", useDingbats = FALSE)), fig.path = file.path("fig_output", paste0(gsub("\\.[Rr]md", "", knitr::current_input()), "_")) ) }
This is an example of a data processing pipeline for bulk Elemental Analyser Isotope Ratio Mass Spectrometry (EA-IRMS) carbon isotope measurements. It can be downloaded as a template (or just to see the plain-text code) by following the Source
link above. Knitting for stand-alone data analysis works best to HTML
rather than the website rendering you see here. To make this formatting change simply delete line #6 in the template file (the line that says rmarkdown::html_vignette:
).
Note that all code chunks that contain a critical step towards the final data (i.e. do more than visualization or a data summary) are marked with (*)
in the header to make it easier to follow all key steps during interactive use.
This example was run using isoreader version r packageVersion("isoreader")
and isoprocessor version r packageVersion("isoprocessor")
. If you want to reproduce the example, please make sure that you have these or newer versions of both packages installed:
# restart your R session (this command only works in RStudio) .rs.restartR() # installs the development tools package if not yet installed if(!requireNamespace("devtools", quietly = TRUE)) install.packages("devtools") # installs the newest version of isoreader and isoprocessor devtools::install_github("isoverse/isoreader") devtools::install_github("isoverse/isoprocessor")
library(tidyverse) # general data wrangling and plotting library(isoreader) # reading the raw data files library(isoprocessor) # processing the data
# set file path(s) to data files, folders or rds collections # can be multiple folders or mix of folders and files, using example data set here data_path <- iso_get_processor_example("ea_irms_example_carbon.cf.rds") # read files iso_files_raw <- # path to data files data_path %>% # read data files in parallel for fast read iso_read_continuous_flow() %>% # filter out files with read errors (e.g. from aborted analysis) iso_filter_files_with_problems()
# process peak table iso_files_w_peak_table <- iso_files_raw %>% # set peak table from vendor data table iso_set_peak_table_automatically_from_vendor_data_table() %>% # convert units from mV to V for amplitudes and area iso_convert_peak_table_units(V = mV, Vs = mVs)
# process file information iso_files_w_file_info <- iso_files_w_peak_table %>% # rename key file info columns iso_rename_file_info( id1 = `Identifier 1`, id2 = `Identifier 2`, prep = Preparation, seq_nr = Row, analysis = Analysis ) %>% # parse text info into numbers iso_parse_file_info(number = c(seq_nr, analysis)) %>% # process specific sequence file information iso_mutate_file_info( # what is the type of each analysis? type = case_when( id1 == "empty" ~ "empty", id1 == "blank" ~ "blank", prep == "lin.std" ~ "linearity", prep == "drift.std" ~ "drift", id1 == "pugel" ~ "scale1", id1 == "EDTA2" ~ "scale2", TRUE ~ "sample" ), # what is the mass of the sample? mass = parse_number(id2) %>% iso_double_with_units("ug"), # what folder are the data files in? (usually folder = sequence) folder = basename(dirname(file_path)) ) %>% # focus only on the relevant file info, discarding the rest iso_select_file_info(folder, analysis, seq_nr, file_datetime, id1, id2, type, mass)
# filter out files we don't want to process futher iso_files_without_empty <- iso_files_w_file_info %>% # filter out emptys at the beginning of the run iso_filter_files(type != "empty")
# identify peaks peak_map <- tibble::tribble( ~compound, ~ref_nr, ~rt, # peak map data (row-by-row) "CO2 analyte", NA, 300, "CO2 ref", 1, 415, "CO2 ref", 2, 465 ) peak_map %>% knitr::kable(digits = 0) iso_files_w_mapped_peaks <- iso_files_without_empty %>% iso_map_peaks(peak_map) # show first few rows of the peak mappings summary (unmapped peaks = N2) iso_files_w_mapped_peaks %>% iso_summarize_peak_mappings() %>% head(10) %>% knitr::kable() # assign final collection of iso_files to a simpler name iso_files <- iso_files_w_mapped_peaks
# display file information iso_files %>% iso_get_file_info() %>% iso_make_units_explicit() %>% knitr::kable()
# plot the chromatograms iso_files %>% # select a few analyses to show iso_filter_files(analysis %in% c(19642, 19656, 19681)) %>% # introduce a label column for coloring the lines iso_mutate_file_info(label = sprintf("#%d: %s (%s)", analysis, id1, type)) %>% # generate plot iso_plot_continuous_flow_data( # select data and aesthetics data = c(44), color = label, panel = NULL, # peak labels for the analyte peak peak_label = iso_format(id1, rt, d13C, signif = 3), peak_label_options = list(size = 3, nudge_x = 50), peak_label_filter = compound == "CO2 analyte" )
Visualize the reference peaks. It looks like the sample at seq_nr=66
has an abnormously high r46/44
difference between the two reference peaks (>0.5 permil). However, it is stable for r45/44
so will likely be okay for d13C. Nevertheless, we'll flag it as potentially problematic to keep an eye on the sample in the final data.
iso_files %>% # get all peaks iso_get_peak_table(include_file_info = c(seq_nr, analysis, type), quiet = TRUE) %>% # focus on reference peaks only and add reference info filter(!is.na(ref_nr)) %>% mutate(ref_info = paste0(ref_nr, ifelse(is_ref == 1, "*", ""))) %>% # visualize iso_plot_ref_peaks( # specify the ratios to visualize x = seq_nr, ratio = c(`r45/44`, `r46/44`), fill = ref_info, panel_scales = "fixed" ) %>% # mark ranges & outliers iso_mark_x_range(condition = type == "sample", fill = "peru", alpha = 0.2) %>% iso_mark_value_range(plus_minus_value = 0.25) %>% iso_mark_outliers(plus_minus_value = 0.25, label = iso_format(seq_nr)) + # add labels labs(x = "Sequence #", fill = "Reference\npeak") iso_files <- iso_files %>% iso_mutate_file_info(note = ifelse(seq_nr == 66, "ref peaks deviate > 0.5 permil in r46/44", ""))
peak_table <- iso_files %>% # whole peak table iso_get_peak_table(include_file_info = everything()) %>% # focus on analyte peak only filter(compound == "CO2 analyte") %>% # calculate 13C mean, sd and deviation from mean within each type iso_mutate_peak_table( group_by = type, d13C_mean = mean(d13C), d13C_sd = sd(d13C), d13C_dev = d13C - d13C_mean )
peak_table %>% # visualize with convenience function iso_plot_data iso_plot_data( # choose x and y (multiple y possible) x = seq_nr, y = c(area44, d13C), # choose other aesthetics color = type, size = 3, # add label (optionally, for interactive plot) label = c(info = sprintf("%s (%d)", id1, analysis)), # decide what geoms to include points = TRUE )
# optinally, use an interactive plot to explore your data # - make sure you install the plotly library --> install.packages("plotly") # - switch to eval=TRUE in the options of this chunk to include in knit # - this should work for all plots in this example processing file library(plotly) ggplotly(dynamicTicks = TRUE)
Examine the variation in each of the standards.
peak_table %>% # everything but the sample filter(type != "sample") %>% # generate plot iso_plot_data(x = mass, y = d13C, color = type, size = 3, points = TRUE, panel = type ~ .) %>% # mark +/- 1, 2, 3 std. deviation value ranges iso_mark_value_range(plus_minus_sd = c(1,2,3)) %>% # mark outliers (those outside the 3 sigma range) iso_mark_outliers(plus_minus_sd = 3, label = analysis)
Analysis #19691 is more than 3 standard deviations outside the scale2 standard mean and therefore explicitly flagged as an is_outlier.
# mark outlier peak_table <- peak_table %>% iso_mutate_peak_table(is_outlier = analysis %in% c(19691))
# this information is often maintained in a csv or Excel file instead # but generated here from scratch for demonstration purposes standards <- tibble::tribble( ~id1, ~true_d13C, ~true_percent_C, "acn1", -29.53, 71.09, "act1", -29.53, 71.09, "pugel", -12.6, 44.02, "EDTA2", -40.38, 41.09 ) %>% mutate( # add units true_d13C = iso_double_with_units(true_d13C, "permil") ) # printout standards table standards %>% iso_make_units_explicit() %>% knitr::kable(digits = 2) # add standards peak_table_w_standards <- peak_table %>% iso_add_standards(stds = standards, match_by = "id1") %>% iso_mutate_peak_table(mass_C = mass * true_percent_C/100)
Look at changes in the drift standard over the course of the run:
peak_table_w_standards %>% filter(type == "drift") %>% iso_plot_data( # alternatively could use x = seq_nr, or x = analysis x = file_datetime, y = d13C, size = area44, points = TRUE, date_breaks = "2 hours", # add some potential calibration model lines geom_smooth(method = "lm", color = "red", se = FALSE), geom_smooth(method = "loess", color = "blue", se = FALSE) ) %>% # mark the total value range iso_mark_value_range()
This looks like random scatter rather than any systematic drift but let's check with a linear regression to confirm:
calib_drift <- peak_table_w_standards %>% # prepare for calibration iso_prepare_for_calibration() %>% # run different calibrations iso_generate_calibration( # provide a calibration name calibration = "drift", # provide different regression models to test if there is any # systematic pattern in d13C_dev (deviation from the mean) model = c( lm(d13C_dev ~ 1), lm(d13C_dev ~ file_datetime), loess(d13C_dev ~ file_datetime, span = 0.5) ), # specify which data points to use in the calibration use_in_calib = is_std_peak & type == "drift" & !is_outlier ) %>% # remove problematic calibrations if there are any iso_remove_problematic_calibrations() # visualize residuals calib_drift %>% iso_plot_residuals(x = file_datetime, date_breaks = "3 hours")
Although a local polynomial (loess
) correction would improve the overall variation in the residuals, this improvement is minor (<0.01 permil) and it is not clear that this correction addresses any systemic trend. Therefore, no drift correction is applied.
Look at the response of the linearity standard and the range the samples are in:
peak_table_w_standards %>% filter(type %in% c("linearity", "sample")) %>% iso_plot_data( x = area44, y = d13C, panel = type ~ ., color = type, points = TRUE, # add a trendline to the linearity panel highlighting the variation geom_smooth(data = function(df) filter(df, type == "linearity"), method = "lm") )
The linearity standard shows a systematic area-dependent effect on the measured isotopic composition that is likely to have a small effect on the sample isotopic compositions. In runs that include two isotopically different standards (2 point scale calibration) both across the entire linearity range, isotopic offset, discrimination, and linearity can all be evaluated in one joint multi-variate regression. However, this run included only one linearity standard which can be used to correct for linearity prior to offset and discrimination corrections.
# run a set of regressions to evaluate linearity calib_linearity <- peak_table_w_standards %>% # prepare for calibration iso_prepare_for_calibration() %>% # run different calibrations iso_generate_calibration( calibration = "lin", # again evaluating different regression models of the deviation from the mean model = c( lm(d13C_dev ~ 1), lm(d13C_dev ~ area44), lm(d13C_dev ~ sqrt(area44)), lm(d13C_dev ~ I(1/area44)) ), use_in_calib = is_std_peak & type == "linearity" & !is_outlier ) %>% # remove problematic calibrations if there are any iso_remove_problematic_calibrations()
# visualizing residuals calib_linearity %>% iso_plot_residuals(x = area44)
# show calibration coefficients calib_linearity %>% iso_plot_calibration_parameters()
It is clear that there is a small (~0.02 permil improvement in the residual) but significant (p < 0.05) linearity effect that could be reasonably corrected with any of the assessed area dependences. However, we will use the ~ area44
correction because it explains more of the variation in the signal range that the samples fall into (~ 100-250 Vs) as can be seen in the residuals plot.
# apply calibration calib_linearity_applied <- calib_linearity %>% # decide which calibration to apply filter(lin_calib == "lm(d13C_dev ~ area44)") %>% # apply calibration indication what should be calcculated iso_apply_calibration(predict = d13C_dev) %>% # evaluate calibration range across area44 iso_evaluate_calibration_range(area44) # show linearity correction range calib_linearity_applied %>% iso_get_calibration_range() %>% knitr::kable(d = 2) # fetch peak table from applied calibration peak_table_lin_corr <- calib_linearity_applied %>% iso_get_calibration_data() %>% # calculate the corrected d13C value mutate(d13C_lin_corr = d13C - d13C_dev_pred)
Check the improvement in standard deviation of the linearity standard:
peak_table_lin_corr %>% filter(type == "linearity") %>% iso_plot_data( area44, c(d13C, d13C_lin_corr), color = variable, panel = NULL, points = TRUE ) %>% # show standard deviation range iso_mark_value_range(mean = FALSE, plus_minus_sd = 1)
Look at the linearity corrected isotopic measurement of the two discrimnation standardds relative to their known isotopic value:
peak_table_lin_corr %>% filter(type %in% c("scale1", "scale2")) %>% iso_plot_data( x = true_d13C, y = d13C_lin_corr, color = id1, points = TRUE, # add 1:1 slope for a visual check on scaling and offset geom_abline(slope = 1, intercept = 0) )
Evaluate regression models for isotopic scale contraction (discrimination) and offset:
# run a set of regressions to evaluate linearity calib_scale <- peak_table_lin_corr %>% # prepare for calibration iso_prepare_for_calibration() %>% # run different calibrations iso_generate_calibration( calibration = "scale", model = lm(d13C_lin_corr ~ true_d13C), use_in_calib = is_std_peak & type %in% c("scale1", "scale2") & !is_outlier ) %>% # remove problematic calibrations if there are any iso_remove_problematic_calibrations()
# visualizing residuals calib_scale %>% iso_plot_residuals(x = true_d13C, shape = id1, size = area44, trendlines = FALSE)
# show calibration coefficients calib_scale %>% iso_plot_calibration_parameters() + theme_bw() # reset theme for horizontal x axis labels
# apply calibration calib_scale_applied <- calib_scale %>% # decide which calibration to apply filter(scale_calib == "lm(d13C_lin_corr ~ true_d13C)") %>% # apply calibration indicating what should be calculated iso_apply_calibration(predict = true_d13C) %>% # evaluate calibration range iso_evaluate_calibration_range(true_d13C_pred) # show scale range calib_scale_applied %>% iso_get_calibration_range() %>% knitr::kable(d = 2) # get calibrated data peak_table_lin_scale_corr <- calib_scale_applied %>% iso_get_calibration_data()
# check the overal calibration results by visualizing # all analytes with known isotopic composition peak_table_lin_scale_corr %>% filter(!is.na(true_d13C)) %>% iso_plot_data( x = c(`known d13C` = true_d13C), y = c(`measured d13C` = true_d13C_pred), color = id1, size = area44, points = TRUE, shape = is_outlier, # add the expected 1:1 line geom_abline(slope = 1, intercept = 0) )
Check how well signal intensity varies with the amount of carbon for all standards
# visualize the linearity standard's signal intensity vs. amount of carbon peak_table_lin_scale_corr %>% filter(!is.na(mass_C)) %>% iso_plot_data( x = mass_C, y = area44, color = type, points = TRUE, # add overall linear regression fit to visualize geom_smooth(method = "lm", mapping = aes(color = NULL)) )
Calibrate the amount of C using the linearity standard
# run a set of regressions to evaluate linearity calib_mass_C <- peak_table_lin_scale_corr %>% # prepare for calibration iso_prepare_for_calibration() %>% # run different calibrations iso_generate_calibration( calibration = "mass", model = lm(mass_C ~ area44), use_in_calib = is_std_peak & type == "linearity" & !is_outlier ) %>% # remove problematic calibrations if there are any iso_remove_problematic_calibrations()
# visualizing residuals calib_mass_C %>% iso_plot_residuals(x = area44, color = type, trendlines = FALSE)
# show calibration coefficients calib_mass_C %>% iso_plot_calibration_parameters() + theme_bw() # reset theme for horizontal x axis labels
# apply calibration calib_mass_C_applied <- calib_mass_C %>% # decide which calibration to apply filter(mass_calib == "lm(mass_C ~ area44)") %>% # apply calibration to predict mass_C (creating new mass_C_pred column) # since it's a single step calibration, also calculate the error iso_apply_calibration(predict = mass_C, calculate_error = TRUE) %>% # evaluate calibration range for the mass_C_pred column iso_evaluate_calibration_range(mass_C_pred) # show scale range calib_mass_C_applied %>% iso_get_calibration_range() %>% knitr::kable(d = 2) # get calibrated data peak_table_lin_scale_mass_corr <- calib_mass_C_applied %>% iso_get_calibration_data() %>% iso_mutate_peak_table( # calcuilate % C and propagate error (adjust if there is also error in mass) percent_C = 100 * mass_C_pred / mass, percent_C_se = 100 * mass_C_pred_se / mass )
# check the overal calibration results by visualizing # all analytes with known %C peak_table_lin_scale_mass_corr %>% filter(!is.na(true_percent_C)) %>% iso_plot_data( x = c(`known %C` = true_percent_C), # define 2 y values to panel y = c(`measured %C` = percent_C, `measured - known %C` = percent_C - true_percent_C), # include regression error bars to highlight variation beyond the estimated y_error = c(percent_C_se, percent_C_se), color = type, size = area44, points = TRUE, # add the expected 1:1 line geom_abline(slope = 1, intercept = 0) )
It looks like there is quite some variation around the known value --> check if there is temporal drift affecting the measured %C:
peak_table_lin_scale_mass_corr %>% filter(type == "drift") %>% iso_plot_data( x = file_datetime, y = c(`measured %C` = percent_C), size = area44, points = TRUE, # add some potential regression models geom_smooth(method = "lm", color = "red", se = FALSE), geom_smooth(method = "loess", color = "blue", se = FALSE) )
It does NOT look like there is a systematic drift so will not apply a correction.
For this run, use the linearity standard for a very conservative accuracy and precision standard.
peak_table_lin_scale_mass_corr %>% filter(type == "linearity") %>% group_by(id1, true_d13C) %>% iso_summarize_data_table(true_d13C_pred) %>% mutate( accuracy = abs(`true_d13C_pred mean` - true_d13C), precision = `true_d13C_pred sd` ) %>% select(id1, n, accuracy, precision) %>% iso_make_units_explicit() %>% knitr::kable(d = 3)
Check the precision for all standards but keep in mind that the linearity
standard was used for calibration. The drift
standard provides the most conservative accuracy and precision estimate:
peak_table_lin_scale_mass_corr %>% filter(!is.na(true_percent_C)) %>% group_by(type, true_percent_C) %>% iso_summarize_data_table(percent_C) %>% mutate( accuracy = abs(`percent_C mean` - true_percent_C), precision = `percent_C sd` ) %>% select(type, n, accuracy, precision) %>% iso_make_units_explicit() %>% knitr::kable(d = 3)
peak_table_lin_scale_mass_corr %>% filter(type == "sample") %>% iso_plot_data( x = id1, y = c(true_d13C_pred, percent_C), shape = str_extract(id1, "^\\w+"), color = iso_format(area = lin_in_range, d13C = scale_in_range), points = TRUE ) %>% iso_mark_calibration_range(calibration = "scale") + labs(shape = "data groups", color = "in calibration ranges")
Final data processing and visualization usually depends on the type of data and the metadata available for contextualization (e.g. core depth, source organism, age, etc.). The relevant metadata can be added easily with iso_add_file_info()
during the initial data load / file info procesing. Alternatively, just call iso_add_file_info()
again at this later point or use dplyr's left_join
directly.
# @user: add final data processing and plot(s) data_summary <- tibble()
# export the calibrations with all information and data to Excel peak_table_lin_scale_mass_corr %>% iso_export_calibration_to_excel( filepath = format(Sys.Date(), "%Y%m%d_ea_irms_example_carbon_export.xlsx"), # include data summary as an additional useful tab `data summary` = data_summary )
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.