Merge pull request #761 from reid-wagner/add_fragpipe

Add FragPipe

tools/fragpipe/.shed.yml

@@ -0,0 +1,11 @@
+owner: galaxyp
+name: fragpipe
+categories:
+- Proteomics
+description: Data analysis for mass spectrometry-based proteomics.
+homepage_url: https://fragpipe.nesvilab.org/
+long_description: |
+  FragPipe is a suite of computational tools enabling comprehensive analysis of mass spectrometry-based proteomics data.
+  FragPipe uses MSFragger - an ultrafast proteomic search engine suitable for both conventional and “open” (wide precursor mass tolerance) peptide identification.
+remote_repository_url: https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/fragpipe
+type: unrestricted

tools/fragpipe/fragpipe

@@ -0,0 +1,65 @@
+#!/bin/bash
+
+# Modified version of the Bioconda wrapper of the script for command-line FragPipe, calling a local link to fragpipe instead of the version in $CONDA_PREFIX.
+# Ensures the user agrees to MSFragger and IonQuant academic licenses.
+
+license_agreement_text='
+Please accept the academic license.
+
+FragPipe uses tools that are available freely for academic research and educational purposes only.
+
+Please provide license keys for MSFragger and IonQuant with the --msfragger_key and --ionquant_key flags. By passing these, you verify that you have read the ACADEMIC licenses for the MSFragger and IonQuant tools. You may obtain these keys by agreeing to the terms at http://msfragger-upgrader.nesvilab.org/upgrader/ and https://msfragger.arsci.com/ionquant/.'
+
+declare -a fragpipe_args
+
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        --msfragger_key)
+            shift
+            msfragger_key=$1
+            ;;
+        --ionquant_key)
+            shift
+            ionquant_key=$1
+            ;;
+        --workflow)
+            fragpipe_args+=("$1")
+            shift
+            workflow_file="$1"
+            fragpipe_args+=("$1")
+            ;;
+        *)
+            fragpipe_args+=("$1")
+            ;;
+    esac
+    shift
+done
+
+if [[ ! -z "$workflow_file" ]]; then
+    # Because the DIA-NN license is incompatible with bioconda, we remove the feature.
+    grep 'diann.run-dia-nn=true' "$workflow_file" >/dev/null
+    if [[ $? -eq 0 ]]; then
+        echo "Error: DIA-NN is disabled in the FragPipe bioconda package."
+        exit 1
+    fi
+fi
+
+if [[ -z $msfragger_key || -z $ionquant_key ]]; then
+    echo "$license_agreement_text"
+    exit 1
+else
+    msfragger --key $msfragger_key --help | grep 'License key verified' >/dev/null 2>&1
+    if [[ $? -ne 0 ]]; then
+        echo "Error: Invalid MSFragger license key"
+        echo "$license_agreement_text"
+        exit 1
+    fi
+    ionquant --key $ionquant_key --help | grep 'License key verified' >/dev/null 2>&1
+    if [[ $? -ne 0 ]]; then
+        echo "Error: Invalid IonQuant license key"
+        echo "$license_agreement_text"
+        exit 1
+    fi
+fi
+
+sh fragpipe_local/bin/fragpipe "${fragpipe_args[@]}"

tools/fragpipe/genericize_db.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python3
+#
+# Prefixes sequence headers in the input FASTA file that are not formatted according to the UniProt, NCBI, or ENSEMBL formats with '>generic|' to avoid being misinterpreted by Philosopher.
+#
+
+import re
+import sys
+
+input_db_file = sys.argv[1]
+output_db_file = sys.argv[2]
+
+
+def sub_header(line):
+    return re.sub(r'^>(?!sp\||tr\||db\||AP_|NP_|YP_|XP_|WP_|ENSP|UniRef|nxp|generic)', '>generic|', line)
+
+
+with open(input_db_file) as in_file, open(output_db_file, 'w') as out_file:
+    for line in in_file:
+        out_file.write(sub_header(line))