Restruct DIA-NN step 3,4,5

bin/diann_convert.py

@@ -50,9 +50,9 @@ def convert(ctx, diann_report, exp_design):
     out_triqler.loc[:, "searchScore"] = 1 - report['PEP']
 
     out_msstats = out_msstats[out_msstats["Intensity"] != 0]
-    out_msstats.to_csv('./out_msstats.csv', sep=',', index=False)
+    out_msstats.to_csv(os.path.basename(exp_design) + '_out_msstats.csv', sep=',', index=False)
     out_triqler = out_triqler[out_triqler["intensity"] != 0]
-    out_triqler.to_csv('./out_triqler.tsv', sep='\t', index=False)
+    out_triqler.to_csv(os.path.basename(exp_design) + '_out_triqler.tsv', sep='\t', index=False)
 
 def query_expdesign_value(reference, f_table, s_table):
     query_reference = f_table[f_table["run"] == reference]

bin/msstats_plfq.R

@@ -212,16 +212,21 @@ if (l == 1) {
     #write all comparisons into one CSV file
     write.table(test.MSstats$ComparisonResult, file=paste0(args[8],"_comparisons.csv"), quote=FALSE, sep='\t', row.names = FALSE)
 
-    groupComparisonPlots(data=test.MSstats$ComparisonResult, type="ComparisonPlot",
-                        width=12, height=12,dot.size = 2)
-
-    test.MSstats$Volcano <- test.MSstats$ComparisonResult[!is.na(test.MSstats$ComparisonResult$pvalue),]
-    groupComparisonPlots(data=test.MSstats$Volcano, type="VolcanoPlot",
+    valid_comp_data <- test.MSstats$ComparisonResult[!is.na(test.MSstats$ComparisonResult$pvalue), ]
+    if (nrow(valid_comp_data[!duplicated(valid_comp_data$Protein),]) < 2) {
+        warning("Warning: No valid Protein Comparison, Skip groupComparisonPlots step!")
+    } else {
+        groupComparisonPlots(data=test.MSstats$ComparisonResult, type="ComparisonPlot",
                         width=12, height=12,dot.size = 2)
 
-    # Otherwise it fails since the behaviour is undefined
-    if (nrow(contrast_mat) > 1) {
-        groupComparisonPlots(data=test.MSstats$ComparisonResult, type="Heatmap",
+        groupComparisonPlots(data=valid_comp_data, type="VolcanoPlot",
                             width=12, height=12,dot.size = 2)
+
+        # Otherwise it fails since the behaviour is undefined
+        if (nrow(contrast_mat) > 1) {
+            groupComparisonPlots(data=test.MSstats$ComparisonResult, type="Heatmap",
+                                width=12, height=12,dot.size = 2)
+        }
     }
+
 }

bin/msstats_tmt.R

@@ -242,4 +242,27 @@ if (l == 1) {
 
     #TODO allow manual input (e.g. proteins of interest)
     write.table(test.MSstatsTMT$ComparisonResult, file=paste0("msstatsiso_results.csv"), quote=FALSE, sep='\t', row.names = FALSE)
+
+    valid_comp_data <- test.MSstatsTMT$ComparisonResult[!is.na(test.MSstatsTMT$ComparisonResult$pvalue), ]
+
+    if (nrow(valid_comp_data[!duplicated(valid_comp_data$Protein),]) < 2) {
+        warning("Warning: No enough valid Protein Comparison, Skip groupComparisonPlots step!")
+    } else {
+        require(MSstats)
+        # BUG groupComparisonPlots function: re-run OpenMStoMSstatsTMTFormat
+        quant <- OpenMStoMSstatsTMTFormat(data, useUniquePeptide=useUniquePeptide, rmPSM_withfewMea_withinRun=rmPSM_withfewMea_withinRun,
+            rmProtein_with1Feature=rmProtein_with1Feature
+        )
+        groupComparisonPlots(data=test.MSstatsTMT$ComparisonResult, type="ComparisonPlot", width=12, height=12, dot.size = 2)
+
+        groupComparisonPlots(data=valid_comp_data, type="VolcanoPlot",
+                            width=12, height=12, dot.size = 2)
+
+        # Otherwise it fails since the behavior is undefined
+        if (nrow(contrast_mat) > 1) {
+            groupComparisonPlots(data=test.MSstatsTMT$ComparisonResult, type="Heatmap",
+                                width=12, height=12, dot.size = 2)
+        }
+    }
+
 }

bin/prepare_diann_parameters.py

@@ -22,9 +22,6 @@ def generate_cfg(ctx, enzyme, fix_mod, var_mod, precursor_tolerence, precursor_t
     cut = enzyme_cut(enzyme)
     unimod_database = UnimodDatabase()
     fix_ptm, var_ptm = convert_mod(unimod_database, fix_mod, var_mod)
-    mass_acc, mass_acc_ms1 = mass_tolerence(precursor_tolerence, precursor_tolerence_unit, fragment_tolerence, fragment_tolerence_unit)
-    mass_acc = " --mass-acc " + str(mass_acc)
-    mass_acc_ms1 = " --mass-acc-ms1 " + str(mass_acc_ms1)
 
     var_ptm_str = " --var-mod "
     fix_ptm_str = " --fixed-mod "
@@ -36,11 +33,7 @@ def generate_cfg(ctx, enzyme, fix_mod, var_mod, precursor_tolerence, precursor_t
         diann_var_ptm += (var_ptm_str + mod)
 
     with open("diann_config.cfg", "w") as f:
-        f.write("--dir ./mzMLs --cut " + cut + diann_fix_ptm + diann_var_ptm + mass_acc + mass_acc_ms1 +
-                " --matrices --report-lib-info")
-
-    with open("library_config.cfg", "w") as f:
-        f.write("--cut " + cut + diann_fix_ptm + diann_var_ptm + " --gen-spec-lib --smart-profiling")
+        f.write("--cut " + cut + diann_fix_ptm + diann_var_ptm)
 
 def convert_mod(unimod_database, fix_mod, var_mod):
     pattern = re.compile("\((.*?)\)")
@@ -110,23 +103,6 @@ def enzyme_cut(enzyme):
         cut = "--cut"
     return cut
 
-def mass_tolerence(prec, precursor_tolerence_unit, frag, fragment_tolerence_unit):
-    if precursor_tolerence_unit == "ppm":
-        ms1_tolerence = prec
-    else:
-        # Default 10 ppm
-        print("Warning: " + precursor_tolerence_unit + " unit not supported for DIA-NN. Default 10 ppm")
-        ms1_tolerence = 10
-
-    if fragment_tolerence_unit == "ppm":
-        ms2_tolerence = frag
-    else:
-        # Default 20 ppm
-        ms2_tolerence = 20
-        print("Warning: " + fragment_tolerence_unit + " unit not supported for DIA-NN. Default 20 ppm")
-
-    return ms1_tolerence, ms2_tolerence
-
 cli.add_command(generate_cfg)
 
 if __name__ == "__main__":

conf/modules.config

@@ -235,6 +235,11 @@ process {
     // DIA-NN
     withName: '.*:DIA:.*' {
         ext.when = { !params.enable_conda }
+        publishDir  = [
+            path: { "${params.outdir}/${task.process.tokenize(':')[-1].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
     }
 
 }

modules/local/librarygeneration/main.nf → modules/local/assemble_empirical_library/main.nf

@@ -1,20 +1,20 @@
-process LIBRARYGENERATION {
-    label 'process_high'
+process ASSEMBLE_EMPIRICAL_LIBRARY {
+    label 'process_low'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://containers.biocontainers.pro/s3/SingImgsRepo/diann/v1.8.1_cv1/diann_v1.8.1_cv1.img' :
         'biocontainers/diann:v1.8.1_cv1' }"
 
     input:
-    tuple file(mzml), file(fasta)
-    file(library_config)
+    path(mzMLs)
+    path("quant/*")
+    path(lib)
+    path(diann_config)
 
     output:
-    path "*_lib.tsv", emit: lib_splib
+    path "empirical_library.tsv", emit: empirical_library
+    path "assemble_empirical_library.log", emit: log
     path "versions.yml", emit: version
-    path "report.log.txt", emit: log
-    path "*.tsv.speclib", emit: speclib
-    path "*.predicted.speclib", emit: predict_speclib
 
     when:
     task.ext.when == null || task.ext.when
@@ -24,29 +24,37 @@ process LIBRARYGENERATION {
 
     min_pr_mz = params.min_pr_mz ? "--min-pr-mz $params.min_pr_mz":""
     max_pr_mz = params.max_pr_mz ? "--max-pr-mz $params.max_pr_mz":""
-    min_fr_mz = params.min_fr_mz ? "--min_fr_mz $params.min_fr_mz":""
-    max_fr_mz = params.max_fr_mz ? "--max_fr_mz $params.max_fr_mz":""
+    min_fr_mz = params.min_fr_mz ? "--min-fr-mz $params.min_fr_mz":""
+    max_fr_mz = params.max_fr_mz ? "--max-fr-mz $params.max_fr_mz":""
+
+    mass_acc = params.mass_acc_automatic ? "--quick-mass-acc --individual-mass-acc" : "--mass-acc $params.mass_acc_ms2 --mass-acc-ms1 $params.mass_acc_ms1"
+    scan_window = params.scan_window_automatic ? "--individual-windows" : "--window $params.scan_window"
 
     """
-    diann   `cat library_config.cfg` \\
-            --fasta ${fasta} \\
-            --fasta-search \\
-            --f ${mzml} \\
-            --out-lib ${mzml.baseName}_lib.tsv \\
+    diann   "echo \$(cat ${diann_config})" \\
+            --f ${(mzMLs as List).join(' --f ')} \\
+            --lib ${lib} \\
             ${min_pr_mz} \\
             ${max_pr_mz} \\
             ${min_fr_mz} \\
             ${max_fr_mz} \\
+            --threads ${task.cpus} \\
+            --out-lib empirical_library.tsv \\
             --missed-cleavages $params.allowed_missed_cleavages \\
             --min-pep-len $params.min_peptide_length \\
             --max-pep-len $params.max_peptide_length \\
             --min-pr-charge $params.min_precursor_charge \\
             --max-pr-charge $params.max_precursor_charge \\
             --var-mods $params.max_mods \\
-            --threads ${task.cpus} \\
-            --predictor \\
             --verbose $params.diann_debug \\
-            |& tee diann.log
+            --rt-profiling \\
+            --temp ./quant/ \\
+            --use-quant \\
+            ${mass_acc} \\
+            ${scan_window} \\
+            --gen-spec-lib \\
+            $args \\
+            |& tee assemble_empirical_library.log
 
 
     cat <<-END_VERSIONS > versions.yml

modules/local/diannsearch/meta.yml → modules/local/assemble_empirical_library/meta.yml

@@ -1,8 +1,7 @@
-name: diannsearch
-description: A module for DIA library free analysis based on DIA-NN.
+name: assemble_empirical_library
+description: A module for assemble empirical library analysis based on DIA-NN.
 keywords:
   - DIA-NN
-  - library free
   - DIA
 tools:
   - DIA-NN:
@@ -11,34 +10,30 @@ tools:
       homepage: https://github.com/vdemichev/DiaNN
       documentation: https://github.com/vdemichev/DiaNN
 input:
+  - mzMLs:
+      type: file
+      description: Spectra file in mzML format
+      pattern: "*.mzML"
+  - quant:
+      type: file
+      description: The .quant files containing IDs and quantification information
   - lib:
       type: file
       description: Spectra library file
       pattern: "*.tsv"
-  - spectra:
-      type: dir
-      description: The directory for spectra files
-  - searchdb:
-      type: file
-      description: Fasta sequence file
-      pattern: "*.{fasta,fa}"
-  - cfg:
+  - diann_config:
       type: dir
       description: Specifies a file to load options/commands from.
       pattern: "*.cfg"
 output:
-  - report:
-      type: file
-      description: Main report file. A text table containing precursor and protein IDs, as well as plenty of associated information. Most column names are self-explanatory.
-      pattern: "diann_report.tsv"
-  - report_stat:
+  - empirical_library:
       type: file
-      description: Contains a number of QC metrics which can be used for data filtering, e.g. to exclude failed runs, or as a readout for method optimization.
-      pattern: "diann_report.stats.tsv"
+      description: An empirical spectral library from the .quant files.
+      pattern: "empirical_library.tsv"
   - log:
       type: file
       description: DIA-NN log file
-      pattern: "diann_report.log.txt"
+      pattern: "assemble_empirical_library.log"
   - version:
       type: file
       description: File containing software version

modules/local/diann_preliminary_analysis/main.nf

@@ -1,17 +1,17 @@
 process DIANN_PRELIMINARY_ANALYSIS {
+    tag "$meta.id"
     label 'process_high'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://containers.biocontainers.pro/s3/SingImgsRepo/diann/v1.8.1_cv1/diann_v1.8.1_cv1.img' :
         'biocontainers/diann:v1.8.1_cv1' }"
 
     input:
-    tuple file(mzML), file(predict_tsv), file(diann_config)
+    tuple val(meta), file(mzML), file(predict_tsv), file(diann_config)
 
     output:
     path "*.quant", emit: diann_quant
-    path "${mzML.baseName}_lib.tsv", emit: lib
-    path "*.log.txt", emit: log
+    tuple val(meta), path("*_diann.log"), emit: log
     path "versions.yml", emit: version
 
     when:
@@ -24,11 +24,12 @@ process DIANN_PRELIMINARY_ANALYSIS {
     min_fr_mz = params.min_fr_mz ? "--min-fr-mz $params.min_fr_mz" : ""
     max_fr_mz = params.max_fr_mz ? "--max-fr-mz $params.max_fr_mz" : ""
 
-    quick_mass_acc = params.quick_mass_acc ? "--quick-mass-acc" : ""
+    mass_acc = params.mass_acc_automatic ? "--quick-mass-acc --individual-mass-acc" : "--mass-acc $params.mass_acc_ms2 --mass-acc-ms1 $params.mass_acc_ms1"
+    scan_window = params.scan_window_automatic ? "--individual-windows" : "--window $params.scan_window"
     time_corr_only = params.time_corr_only ? "--time-corr-only" : ""
 
     """
-    diann   `cat diann_config.cfg` \\
+    diann   "echo \$(cat ${diann_config})" \\
             --lib ${predict_tsv} \\
             --f ${mzML} \\
             ${min_pr_mz} \\
@@ -43,16 +44,14 @@ process DIANN_PRELIMINARY_ANALYSIS {
             --max-pr-charge $params.max_precursor_charge \\
             --var-mods $params.max_mods \\
             --verbose $params.diann_debug \\
-            --window $params.scan_window \\
-            --gen-spec-lib \\
-            --out-lib ${mzML.baseName}_lib.tsv \\
+            ${scan_window} \\
             --temp ./ \\
             --min-corr $params.min_corr \\
             --corr-diff $params.corr_diff \\
-            ${quick_mass_acc} \\
+            ${mass_acc} \\
             ${time_corr_only} \\
             $args \\
-            |& tee diann.log
+            |& tee ${mzML.baseName}_diann.log
 
 
     cat <<-END_VERSIONS > versions.yml

modules/local/diann_preliminary_analysis/meta.yml

@@ -10,6 +10,9 @@ tools:
       homepage: https://github.com/vdemichev/DiaNN
       documentation: https://github.com/vdemichev/DiaNN
 input:
+  - meta:
+      type: map
+      description: Groovy Map containing sample information
   - predict_tsv:
       type: file
       description: Silico-predicted spectral library by deep leaning predictor in DIA-NN
@@ -27,14 +30,10 @@ output:
       type: file
       description: Quantification file from DIA-NN
       pattern: "*.quant"
-  - lib:
-      type: file
-      description: Spectral library file
-      pattern: "*.tsv"
   - log:
       type: file
       description: DIA-NN log file
-      pattern: "diann_report.log.txt"
+      pattern: "*_diann.log"
   - version:
       type: file
       description: File containing software version

modules/local/diannconvert/main.nf

@@ -1,4 +1,5 @@
 process DIANNCONVERT {
+    tag "$exp_design.Name"
     label 'process_low'
 
     conda (params.enable_conda ? "conda-forge::pandas_schema bioconda::sdrf-pipelines=0.0.21" : null)
@@ -13,8 +14,8 @@ process DIANNCONVERT {
     path(exp_design)
 
     output:
-    path "out_msstats.csv", emit: out_msstats
-    path "out_triqler.tsv", emit: out_triqler
+    path "*out_msstats.csv", emit: out_msstats
+    path "*out_triqler.tsv", emit: out_triqler
     path "versions.yml", emit: version
 
     script: