## ----install_package, eval = FALSE-------------------------------------------- # install.packages("BiocManager") # BiocManager::install("RmzTabM") ## ----load_package------------------------------------------------------------- library(RmzTabM) ## ----load_required_package---------------------------------------------------- #| message: FALSE #' required packages library(SummarizedExperiment) ## ----load_se------------------------------------------------------------------ #' Load the Metabonaut preprocessing result data(se) se ## ----coldata_se, results = "asis"--------------------------------------------- library(pander) pandoc.table(colData(se) |> as.data.frame(), style = "rmarkdown", split.table = Inf) ## ----rowdata_se, results = "asis"--------------------------------------------- pandoc.table(rowData(se) |> as.data.frame() |> head(), style = "rmarkdown", split.table = Inf) ## ----assayname_se------------------------------------------------------------- assayNames(se) ## ----species_and_tissue_se---------------------------------------------------- colData(se)$species colData(se)$tissue ## ----polarity_se-------------------------------------------------------------- colData(se)$polarity ## ----sampleCols_se------------------------------------------------------------ colData(se)$sample_name #' define mapping of `colData()` column names to mzTab-M sample fields scols <- sampleCols(sample = "sample_name", species = "species", tissue = "tissue", sample_type = "sample_type") ## ----msRunCols_assayCols_se--------------------------------------------------- #' Define columns for MS run and assays mscols <- msRunCols(location = "derived_spectra_data_file", instrument_ref = "instrument", scan_polarity = "polarity") acols <- assayCols(assay = "derived_spectra_data_file") ## ----derived_spectra_data_file_se--------------------------------------------- colData(se)$derived_spectra_data_file ## ----study_variable_group_se-------------------------------------------------- #' technical variable: the sample matrix colData(se)$blood_sample_type #' phenotype of study samples or QC for QC samples colData(se)$phenotype #' age of study participants; NA for QC samples colData(se)$age ## ----mztabm_mtd--------------------------------------------------------------- mzt <- MzTabM(se, id = "MTBLS8735", sampleCols = scols, msRunCols = mscols, assayCols = acols, groups = c("age", "phenotype", "blood_sample_type")) mzt ## ----rowdata_se_smf, results = "asis"----------------------------------------- pandoc.table(rowData(se) |> as.data.frame() |> head(), style = "rmarkdown", split.table = Inf) ## ----feature_id_se------------------------------------------------------------ rowData(se)$feature_id <- rownames(se) ## ----smfCols------------------------------------------------------------------ smf_cols <- smfCols(exp_mass_to_charge = "mzmed", retention_time_in_seconds = "rtmed", feature_id = "feature_id") ## ----mztabm_mtd_smf----------------------------------------------------------- #' Create a MTD+SMF mzTab-M object from the SummarizedExperiment mzt <- MzTabM(se, id = "MTBLS8735", sampleCols = scols, msRunCols = mscols, assayCols = acols, groups = c("age", "phenotype", "blood_sample_type"), smfCols. = smf_cols, assayName = "raw_filled") mzt ## ----mtd_head, results = "asis"----------------------------------------------- pandoc.table(mtd(mzt) |> head(), style = "rmarkdown", split.table = Inf, justify = "ll") ## ----smf_head, results = "asis"----------------------------------------------- pandoc.table(smf(mzt) |> head(), style = "rmarkdown", split.table = Inf) ## ----getmtdcv----------------------------------------------------------------- getMtdCv(mzt) ## ----setmtdcv----------------------------------------------------------------- mzt <- setMtdCv(mzt, label = c("BTO", "NCBITaxon"), full_name = c("The BRENDA Tissue Ontology (BTO)", "NCBI organismal classification"), version = c("2021-10-26", "2025-12-03"), uri = c("https://www.ebi.ac.uk/ols4/ontologies/bto", "https://www.ebi.ac.uk/ols4/ontologies/ncbitaxon")) ## ----setSW-------------------------------------------------------------------- mzt <- setMtdField(mzt, "software", "[MS, MS:1001582, xcms, 4.10.0]") getMtdField(mzt, "software") ## ----setinstrument------------------------------------------------------------ #' Adding MS instrument information. mzt <- setMtdInstrument( mzt, name = "[MS, MS:1002584, AB Sciex TripleTOF 5600+, ]", source = "[MS, MS:1000073, ESI, ]", analyzer = c(`analyzer[1]` = "[MS, MS:1003763, quadrupole time-of-flight instrument, ]"), detector = "[,,null,null]") ## ----setcontact--------------------------------------------------------------- mzt <- setMtdContact( mzt, name = c("Johannes Rainer", "Philippine Louail"), affiliation= c("Institute for Biomedicine, Eurac Research, Bolzano, Italy", "Institute for Biomedicine, Eurac Research, Bolzano, Italy"), email = c("johannes.rainer@eurac.edu", "philippine.louail@eurac.edu"), orcid = c("0000-0002-6977-7147", "0009-0007-5429-6846")) ## ----writemztabm-------------------------------------------------------------- writeMzTabM(mzt, path = file.path(tempdir(), "MTBLS8735_mtd_smf.mzTab")) ## ----readmztabm--------------------------------------------------------------- mzt_r <- readMzTabM(file.path(tempdir(), "MTBLS8735_mtd_smf.mzTab")) mzt_r ## ----make_se------------------------------------------------------------------ se_r <- makeSummarizedExperimentFromMzTabM( mzt_r, rowIdCol = "opt_global_feature_id", smfCols. = smf_cols, assayName = "raw_filled" ) se_r ## ----experiment, results = "asis"--------------------------------------------- #' Define a simple data.frame of the measured samples of an experiment exp <- data.frame( sample_name = c("S1_T1", "S1_T2", "S2_T1", "S2_T2", "S3_T1", "S3_T2"), sample_id = c("S1", "S1", "S2", "S2", "S3", "S3"), timepoint = c("0h", "6h", "0h", "6h", "0h", "6h"), genotype = c("WT", "WT", "KO", "KO", "KO", "KO"), operator = c("BB", "BB", "BB", "BB", "FB", "FB"), file_name = c("s1-t1.mzML", "s1-t2.mzML", "s2-t1.mzML", "s2-t2.mzML", "s3-t1.mzML", "s3-t2.mzML") ) pandoc.table(exp, style = "rmarkdown", split.table = Inf) ## ----mtdskeleton-------------------------------------------------------------- mtd <- mtdSkeleton( id = "EXP_001", software = "[MS, MS:1001582, xcms, 4.1.0]" ) ## ----mtd_base_show, results = "asis"------------------------------------------ pandoc.table(mtd, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_title_description------------------------------------------------ mtd <- rbind( mtd, c("title", "Experiment 1 preprocessed data"), c("description", "The preprocessed data of the experiment 1.") ) ## ----mtd_build_instrument----------------------------------------------------- instr <- mtdFields( name = "[MS, MS:1000449, LTQ Orbitrap,]", source = "[MS, MS:1000073, ESI,]", `analyzer[1]` = "[MS, MS:1000291, linear ion trap,]", detector = "[MS, MS:1000253, electron multiplier,]", field_prefix = "instrument" ) ## ----mtd_show_instrument, results = "asis"------------------------------------ pandoc.table(instr, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_instrument------------------------------------------------------- mtd <- rbind(mtd, instr) ## ----mtd_build_sample--------------------------------------------------------- mtd_s <- mtdSample( sample = unique(exp$sample_id), species = "[NCBITaxon, NCBITaxon:9606, Homo sapiens, ]", tissue = "[BTO, BTO:0000759, liver, ]", cell_type = "[CL, CL:0000182, hepatocyte, ]", c("[,,Extraction date, 2011-12-21]", "[,,Extraction date, 2011-12-22]", "[,,Extraction date, 2011-12-23]") ) ## ----mtd_show_sample, results = "asis"---------------------------------------- pandoc.table(mtd_s, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_build_cv, results = "asis"------------------------------------------- add_cv <- mtdFields( label = c("BTO", "NCBITaxon"), full_name = c("The BRENDA Tissue Ontology (BTO)", "NCBI organismal classification"), version = c("2021-10-26", "2025-12-03"), uri = c("https://www.ebi.ac.uk/ols4/ontologies/bto", "https://www.ebi.ac.uk/ols4/ontologies/ncbitaxon"), field_prefix = "cv") pandoc.table(add_cv, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_cv--------------------------------------------------------------- add_cv[, 1L] <- sub("1", "4", add_cv[, 1L]) add_cv[, 1L] <- sub("2", "5", add_cv[, 1L]) mtd <- rbind(mtd, add_cv) ## ----mtd_add_sample----------------------------------------------------------- mtd <- rbind(mtd, mtd_s) ## ----mtd_build_msrun---------------------------------------------------------- mtd_msr <- mtdMsRun( location = exp$file_name, format = "[MS, MS:1000584, mzML file, ]", id_format = "[MS, MS:1000530, mzML unique identifier, ]", scan_polarity = "positive") ## ----mtd_show_msrun, results = "asis"----------------------------------------- pandoc.table(mtd_msr, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_msrun------------------------------------------------------------ mtd <- rbind(mtd, mtd_msr) ## ----mtd_build_assay---------------------------------------------------------- mtd_a <- mtdAssay( assay = exp$sample_name, sample_ref = c("sample[1]", "sample[1]", "sample[2]", "sample[2]", "sample[3]", "sample[3]"), ms_run_ref = paste0("ms_run[", seq_len(nrow(exp)), "]") ) ## ----mtd_show_assay, results = "asis"----------------------------------------- pandoc.table(mtd_a, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_assay------------------------------------------------------------ mtd <- rbind(mtd, mtd_a) ## ----mtd_build_studyVar------------------------------------------------------- mtd_svar <- mtdStudyVariables( exp, groups = c("timepoint", "genotype", "operator"), group_unit = c("[, , hours, ]", "", "")) ## ----mtd_show_studyVar, results = "asis"-------------------------------------- pandoc.table(mtd_svar, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----mtd_add_studyVar--------------------------------------------------------- mtd <- rbind(mtd, mtd_svar) ## ----mtdsort------------------------------------------------------------------ mtd <- mtdSort(mtd) ## ----mtd_final_show, results = "asis"----------------------------------------- pandoc.table(mtd, style = "rmarkdown", split.table = Inf, justify = "ll") ## ----abundances--------------------------------------------------------------- abundances <- cbind(c(200.1, 1232.1, 54.3, 399.1, 599.8, 23.1, NA), c(260.2, 39.5, 177.4, 599.5, 5344.1, 332.1, 43.0), c(256.1, 904.2, 56.9, 533.1, 489.9, 3231.22, 23.4), c(232.1, 43.3, 201.4, 434.2, 5154.1, 43.4, 324.3), c(264.2, 1102.4, 43.5, 514.5, 583.1, 432.3, 43.3), c(246.2, 52.1, 187.2, 508.3, 601.5, 432.2, 34.5)) colnames(abundances) <- exp$sample_name rownames(abundances) <- c("FT01", "FT02", "FT03", "FT04", "FT05", "FT06", "FT07") ## ----feature_info------------------------------------------------------------- feature_info <- data.frame( mzmed = c(195.088, 127.1, 299.2, 181.07, 218.077, 343.123, 148.06), rtmed = c(25.6, 128.4, 67.2, 127.3, 25.7, 167.2, 76.34), rtmin = c(23.1, 125.1, 65.1, 122.3, 23.3, 162.3, 71.3), rtmax = c(26.9, 130.3, 69.1, 134.2, 26.8, 172.1, 81.2), adduct = c("[M+H]+", NA, NA, "[M+Na]+", "[M+Na]+", "[M+H]+", "[M+H]+"), charge = c(1L, NA, NA, 1L, 1L, 1L, 1L) ) rownames(feature_info) <- rownames(abundances) ## ----smfCreate---------------------------------------------------------------- smf <- smfCreate( x = abundances, exp_mass_to_charge = feature_info$mzmed, retention_time_in_seconds = feature_info$rtmed, retention_time_in_seconds_start = feature_info$rtmin, retention_time_in_seconds_end = feature_info$rtmax, charge = feature_info$charge, adduct_ion = feature_info$adduct, feature_id = rownames(feature_info)) ## ----smf_show, results = "asis"----------------------------------------------- pandoc.table(smf, style = "rmarkdown", split.table = Inf) ## ----annotation--------------------------------------------------------------- anns <- data.frame( id = c("HMDB:HMDB0001847", "HMDB:HMDB0000122|HMDB:HMDB0000169", "HMDB:HMDB0000258", "HMDB:HMDB0060475"), formula = c("C8H10N4O2", "C6H12O6|C6H12O6", "C12H22O11", "C5H9NO4"), neutral_mass = c(194.0804, "180.0634|180.0634", 342.1162, 147.0531), name = c("caffeine", "glucose|mannose", "sucrose", "DL-glutamate"), adduct = c("[M+H]1+", "[M+Na]1+", "[M+H]1+", "[M+H]1+"), uri = c("http://www.hmdb.ca/metabolites/HMDB0001847", "http://www.hmdb.ca/metabolites/HMDB0000122|http://www.hmdb.ca/metabolites/HMDB0000169", "http://www.hmdb.ca/metabolites/HMDB0000258", "http://www.hmdb.ca/metabolites/HMDB0060475"), note = c("manual curation") ) ## ----sml_filter--------------------------------------------------------------- abundances_sml <- abundances[c(1, 4, 6, 7), ] ## ----smlCreate, results = "asis"---------------------------------------------- sml <- smlCreate(x = abundances_sml, database_identifier = anns$id, chemical_formula = anns$formula, theoretical_neutral_mass = anns$neutral_mass, adduct_ions = anns$adduct, uri = anns$uri, note = anns$note) pandoc.table(sml, style = "rmarkdown", split.table = Inf) ## ----smf_id_refs-------------------------------------------------------------- sml$SMF_ID_REFS = c("1|5", "4", "6", "7") ## ----sml_add_study_var, results = "asis"-------------------------------------- sml <- smlAddStudyVariableColumns(sml, mtd) pandoc.table(sml, style = "rmarkdown", split.table = Inf) ## ----sme_df------------------------------------------------------------------- ev_df <- data.frame( evidence_input_id = c("ms_run[1]:mass=700.5255;rt=20ยท5", "ms_run[2]:mass=452.2782;rt=35.1", "ms_run[3]:mass=882.6210;rt=40.0"), exp_mass_to_charge = c(700.5255, 452.2782, 882.6210), charge = c(1, 1, 1), theoretical_mass_to_charge = c(700.5281, 452.2777, 882.6224), spectra_ref = c("ms_run[1]:index=7646", "ms_run[2]:index=7640", "ms_run[3]:index=7671|ms_run[3]:index=7725"), identification_method = "[, , LipidDataAnalyzer, 2.11.1]", ms_level = "[MS, MS:1000511, ms level, 2]") ## ----smeCreate---------------------------------------------------------------- sme <- smeCreate( evidence_input_id = ev_df$evidence_input_id, exp_mass_to_charge = ev_df$exp_mass_to_charge, charge = ev_df$charge, theoretical_mass_to_charge = ev_df$theoretical_mass_to_charge, spectra_ref = ev_df$spectra_ref, identification_method = ev_df$identification_method, ms_level = ev_df$ms_level, mtd = mtd ) pandoc.table(sme, style = "rmarkdown", split.table = Inf) ## ----sessionInfo-------------------------------------------------------------- sessionInfo()