Cleanup params

bin/chunked_ms2rescore.py

@@ -16,7 +16,7 @@ def argparse_setup():
     parser.add_argument("-spectra", help="Corresponding mzML file or .d path for PSMs file", required=True, type=str)
 
     parser.add_argument("-model", help="Model for MS2PIP", default="HCD", type=str)
-    parser.add_argument("-model_dir", help="Directory to store/find MS2PIP model", default="/mnt/data/ms2pip-model", type=str)
+    parser.add_argument("-model_dir", help="Directory to store/find MS2PIP model", default="./ms2pip-model", type=str)
     parser.add_argument("-ms2_tolerance", help="The MS2/fragment tolerance", default=0.02, type=float)
     parser.add_argument("-spectrum_id_pattern", help="The spectrum ID pattern to correspond PSMs to spectra", default="(.*)", type=str)
     parser.add_argument("-processes", help="Number of processes / threads to use", default=8, type=int)

bin/ms2rescore_check_or_download_model.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python
+
+import argparse
+import logging
+
+from ms2pip.constants import MODELS
+from ms2pip._utils.xgb_models import validate_requested_xgb_model
+
+
+def argparse_setup():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-ms2pip_model", help="Model for MS2PIP", default="HCD", type=str)
+    parser.add_argument("-model_dir", help="Directory to store/find MS2PIP model", default="./ms2pip-model", type=str)
+
+    return parser.parse_args()
+
+if __name__ == "__main__":
+    args = argparse_setup()
+    logging.basicConfig(level=logging.INFO)
+
+    ms2pip_model = args.ms2pip_model
+    model_dir = args.model_dir
+
+    # Validate / download requested model
+    if ms2pip_model in MODELS.keys():
+        print(f"Checking {ms2pip_model} model")
+        if "xgboost_model_files" in MODELS[ms2pip_model].keys():
+            validate_requested_xgb_model(
+                MODELS[ms2pip_model]["xgboost_model_files"],
+                MODELS[ms2pip_model]["model_hash"],
+                model_dir,
+            )
+

main.nf

@@ -2,43 +2,6 @@
 // Nextflow pipeline for peptide identification with multiple search engines and post-processing tools
 //
 
-// default python image
-params.python_image = 'ghcr.io/medbioinf/pipeline-of-identification:latest'
-params.oktoberfest_image = 'medbioinf/oktoberfest'
-
-// parameters set by the command line
-params.raw_files = ''
-params.mzml_files = ''    // may contain globs
-params.fasta = ''
-params.fasta_target_decoy = ''
-params.precursor_tol_ppm = 10
-params.fragment_tol_da = 0.02
-params.is_timstof = false
-params.entrapment_fold = 0
-params.use_only_rank1_psms = true
-
-// keep the (converted) mzML files
-params.keep_mzmls = true
-
-// should the search engines be executed?
-params.execute_comet = true
-params.execute_maxquant = true
-params.execute_msamanda = true
-params.execute_msfragger = true
-params.execute_msgfplus = true
-params.execute_sage = true
-params.execute_xtandem = true
-
-// default parameter files
-params.outdir = './'
-params.comet_params_file = "${baseDir}/config/comet.params"
-params.maxquant_params_file = "${baseDir}/config/mqpar.xml"
-params.msamanda_config_file = "${baseDir}/config/msamanda_settings.xml"
-params.msfragger_config_file = "${baseDir}/config/closed_fragger.params"
-params.msgfplus_params_file = "${baseDir}/config/MSGFPlus_Params.txt"
-params.sage_config_file = "${baseDir}/config/sage_config.json"
-params.xtandem_config_file = "${baseDir}/config/xtandem_input.xml"
-
 // including modules
 include {create_entrapment_database} from "./src/preprocess/create_entrapment_database.nf"
 include {create_decoy_database} from "./src/preprocess/create_decoy_database.nf"

nextflow.config

@@ -1,9 +1,205 @@
-workflow.output.mode = "copy"
+// Global default params, used in configs
+params {
+  // input / output parameters
+  outdir = './'
+  raw_files = './msms-files/*.raw'
+  mzml_files = ''
+  fasta = ''
+  fasta_target_decoy = ''
+  entrapment_fold = 0
+  keep_mzmls = true
+  tdf2mzml_threads = 8
+  decoy_database_threads = 4
+  fdrbench_mem_gb = 16
+
+  // search specific parameters
+  precursor_tol_ppm = 10
+  fragment_tol_da = 0.02
+  is_timstof = false
+  use_only_rank1_psms = true
+  convert_psm_tsv_mem = '32.GB'
+  enhance_psm_tsv_mem = '8.GB'
+
+  execute_comet = true
+  comet_params_file = "${baseDir}/config/comet.params"
+  comet_threads = 16
+  comet_mem = '8.GB'
+  comet_psm_id_pattern = '(.*)'
+  comet_spectrum_id_pattern = '.*scan=(\\d+)$'
+  comet_scan_id_pattern = '^(?P<scan_id>\\d+)$'
+
+  execute_maxquant = true
+  maxquant_params_file = "${baseDir}/config/mqpar.xml"
+  maxquant_threads = 4
+  maxquant_mem = "32.GB"
+  maxquant_psm_id_pattern = ""
+  maxquant_spectrum_id_pattern = ""
+  maxquant_scan_id_pattern = ""
+
+  execute_msamanda = true
+  msamanda_config_file = "${baseDir}/config/msamanda_settings.xml"
+  msamanda_threads = 16
+  msamanda_mem = '64.GB'
+  msamanda_psm_id_pattern = '(.*)'
+  msamanda_spectrum_id_pattern = '(.*)'
+  msamanda_scan_id_pattern = '.*scan=(?P<scan_id>\\d+)$'
+
+  execute_msfragger = true
+  msfragger_config_file = "${baseDir}/config/closed_fragger.params"
+  msfragger_threads = 16
+  msfragger_mem_gb = 16
+  msfragger_db_split = 0
+  msfragger_calibrate = 2
+  msfragger_psm_id_pattern = '(.*)'
+  msfragger_spectrum_id_pattern = '(.*)'
+  msfragger_scan_id_pattern = '.*scan=(?P<scan_id>\\d+)$'
+
+  execute_msgfplus = true
+  msgfplus_params_file = "${baseDir}/config/MSGFPlus_Params.txt"
+  msgfplus_threads = 6
+  msgfplus_mem_gb = 16
+  msgfplus_tasks = 0
+  msgfplus_instrument = 1 // 0: Low-res LCQ/LTQ, 1: Orbitrap/FTICR/Lumos, 2: TOF, 3: Q-Exactive
+  msgfplus_split_input = 10000     // split input mzMLs into chunks of this size, 0 to disable
+  msgfplus_merge_mem_gb = 16       // memory for merging PSMs, used in merge_psms process
+  msgfplus_split_fasta = 0         // split the fasta into this many chunks, 0 to disable
+  msgfplus_psm_id_pattern = '(.*)'
+  msgfplus_spectrum_id_pattern = '(.*)'
+  msgfplus_scan_id_pattern = '.*scan=(?P<scan_id>\\d+)$'
+
+  execute_sage = true
+  sage_config_file = "${baseDir}/config/sage_config.json"
+  sage_threads = 16
+  sage_mem = '128.GB'
+  sage_prefilter = 'false'
+  sage_prefilter_chunk_size = 0
+  sage_psm_id_pattern = '(.*)'
+  sage_spectrum_id_pattern = '(.*)'
+  sage_scan_id_pattern = '.*scan=(?P<scan_id>\\d+)$'
+
+  execute_xtandem = true
+  xtandem_config_file = "${baseDir}/config/xtandem_input.xml"  
+  xtandem_threads = 16
+  xtandem_mem = '128.GB'
+  xtandem_psm_id_pattern = '(.*)'
+  xtandem_spectrum_id_pattern = '(.*)'
+  xtandem_scan_id_pattern = '.*scan=(?P<scan_id>\\d+)$'
+
+  // parameters for ms2rescore
+  ms2rescore_threads = 4
+  ms2rescore_mem = '64.GB'
+  ms2rescore_model = 'HCD'
+  ms2rescore_chunk_size = 100000
+  ms2pip_model_dir = './ms2pip-model'
+
+  // parameters for oktoberfest
+  oktoberfest_memory = '64.GB'
+  oktoberfest_to_pin_memory = '4.GB'
+  oktoberfest_intensity_model = 'Prosit_2020_intensity_HCD'
+  oktoberfest_irt_model = 'Prosit_2019_irt'
+  oktoberfest_forks = 1 // have some mercy with the koina servers
+
+  // number of threads used by percolator
+  percolator_threads = 4
+  percolator_mem = '4.GB'
+}
+
+manifest {
+  name = 'mpc-bioinformatics/McQuaC'
+  contributors = [
+    [
+      name: 'Julian Uszkoreit',
+      affiliation: 'Ruhr University Bochum, Medical Bioinformatics',
+      github: '@julianu',
+      contribution: ['author', 'maintainer', 'contributor'],
+      orcid: '0000-0001-7522-4007',
+    ],
+    [
+      name: 'Dirk Winkelhardt',
+      affiliation: 'Ruhr University Bochum, Medical Bioinformatics',
+      github: '@di-hardt',
+      contribution: ['author', 'maintainer', 'contributor'],
+      orcid: '0000-0001-8770-2221',
+    ],
+  ]
+  homePage = 'https://github.com/medbioinf/pipeline-of-identification'
+  description = """A pipeline for the identification of peptides from mass spectrometry data, integrating multiple search engines and post-processing tools."""
+  mainScript = 'main.nf'
+  defaultBranch = 'main'
+  nextflowVersion = '!>=24.10.6'
+  version = '0.1.0'
+}
 
 profiles {
-    docker {
-        docker.enabled = true
-        docker.runOptions = "--user=root"
-        docker.fixOwnership = true
+  docker {
+    docker.enabled = true
+    docker.runOptions = "--user=root"
+    docker.fixOwnership = true
+
+    process {
+      withLabel: python_image {
+        container = 'ghcr.io/medbioinf/mspepid:latest'
+      }
+
+      withLabel: comet_image {
+        container = 'quay.io/medbioinf/comet-ms:v2024.01.0'
+      }
+
+      withLabel: maxquant_image {
+        container = 'quay.io/medbioinf/maxquant:2.6.3.0'
+      }
+
+      withLabel: msamanda_image {
+        container = 'quay.io/medbioinf/msamanda:3.0.22.071'
+      }
+
+      withLabel: msfragger_image {
+        container = 'medbioinf/msfragger'
+      }
+
+      withLabel: msgfplus_image {
+        container = 'quay.io/medbioinf/msgfplus:v2024.03.26'
+      }
+
+      withLabel: mzidmerger_image {
+        container = 'quay.io/medbioinf/mzid-merger:1.4.26'
+      }
+
+      withLabel: sage_image {
+        container = 'quay.io/medbioinf/sage:v0.15.0-beta.1'
+      }
+
+      withLabel: xtandem_image {
+        container = 'quay.io/medbioinf/xtandem:2017.2.1.4'
+      }
+
+      withLabel: percolator_image {
+        container = 'ghcr.io/percolator/percolator:branch-3-08'
+      }
+
+      withLabel: msconvert_image {
+        container = 'proteowizard/pwiz-skyline-i-agree-to-the-vendor-licenses:3.0.25073-842baef'
+      }
+
+      withLabel: tdf2mzml_image {
+        container = 'quay.io/medbioinf/tdf2mzml:0.4'
+      }
+
+      withLabel: oktoberfest_image {
+        container = 'medbioinf/oktoberfest'
+      }
+
+      withLabel: openms_image {
+        container = 'quay.io/medbioinf/openms:3.4.1'
+      }
+
+      withLabel: fdrbench_image {
+        container = 'quay.io/medbioinf/fdrbench-nightly:146f77'
+      }
     }
-}
+  }
+}
+
+plugins {
+  id 'nf-schema@2.5.0'
+}