added contam matrices

Author: ed-lau

CHANGES.txt

@@ -1,3 +1,11 @@
+v.0.4.0
+---
+* PYTMT now supports TMT contaminant correction.
+
+v.0.3.5
+---
+* PYTMT now reads the percolator output log file from crux to assign mzML files to Percolator file_idx
+
 v.0.2.8
 ---
 * input changed from specifying percolator directory to percolator file path

contams/WF309595.csv

@@ -0,0 +1,11 @@
+,tru_126,tru_127N,tru_127C,tru_128N,tru_128C,tru_129N,tru_129C,tru_130N,tru_130C,tru_131N
+obs_126,1.000,0.000,0.008,0.000,0.000,0.000,0.000,0.000,0.000,0.000
+ obs_127N,0.000,1.000,0.000,0.012,0.000,0.000,0.000,0.000,0.000,0.000
+ obs_127C,0.074,0.000,1.000,0.000,0.013,0.000,0.003,0.000,0.000,0.000
+ obs_128N,0.000,0.072,0.000,1.000,0.000,0.016,0.000,0.000,0.000,0.000
+ obs_128C,0.000,0.000,0.066,0.000,1.000,0.000,0.027,0.000,0.000,0.000
+ obs_129N,0.000,0.000,0.000,0.063,0.000,1.000,0.000,0.022,0.000,0.000
+ obs_129C,0.000,0.000,0.000,0.000,0.057,0.000,1.000,0.000,0.031,0.000
+ obs_130N,0.000,0.000,0.000,0.000,0.000,0.054,0.000,1.000,0.000,0.087
+ obs_130C,0.000,0.000,0.000,0.000,0.001,0.000,0.048,0.000,1.000,0.000
+ obs_131N,0.000,0.000,0.000,0.000,0.000,0.013,0.000,0.046,0.000,1.000

contams/XB318561.csv

@@ -0,0 +1,11 @@
+,tru_126,tru_127N,tru_127C,tru_128N,tru_128C,tru_129N,tru_129C,tru_130N,tru_130C,tru_131N
+obs_126,1.000,0.000,0.074,0.000,0.000,0.000,0.000,0.000,0.000,0.000
+ obs_127N,0.000,1.000,0.000,0.078,0.000,0.001,0.000,0.000,0.000,0.000
+ obs_127C,0.008,0.000,1.000,0.000,0.069,0.000,0.001,0.000,0.000,0.000
+ obs_128N,0.000,0.012,0.000,1.000,0.000,0.063,0.000,0.000,0.000,0.000
+ obs_128C,0.000,0.000,0.015,0.000,1.000,0.000,0.062,0.000,0.002,0.000
+ obs_129N,0.000,0.000,0.000,0.015,0.000,1.000,0.000,0.057,0.000,0.001
+ obs_129C,0.000,0.000,0.000,0.000,0.026,0.000,1.000,0.000,0.048,0.000
+ obs_130N,0.000,0.000,0.000,0.000,0.000,0.022,0.000,1.000,0.000,0.046
+ obs_130C,0.000,0.000,0.000,0.000,0.000,0.000,0.031,0.000,1.000,0.000
+ obs_131N,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.087,0.000,1.000

pytmt/main.py

@@ -14,6 +14,7 @@
 from pytmt.get_spec import Mzml
 from pytmt import tmt_reporters
 from pytmt import quantify_spec
+from pytmt import correct_matrix
 
 def quant(args):
     """
@@ -162,7 +163,7 @@ def quant(args):
                 idx, pathname = pattern[0]
                 dirname, filename = os.path.split(pathname)
                 mzml_files[int(idx)] = re.sub('\.pep\.xml', '', filename)
-                #TODO: will probably have to account for .pin or other input to Percolator
+                # TODO: will probably have to account for .pin or other input to Percolator
 
     # If the log file does not exist, assign index naively based on sort
     else:
@@ -279,10 +280,18 @@ def quant(args):
     for reporter in reporters:
         output_df_columns.append('m' + str(reporter))
 
-    output_df_columns.append('spectrum_int')
 
+
+    output_df_columns.append('spectrum_int')
     output_df = pd.DataFrame(output_list, columns=output_df_columns)
 
+    # Correct for contamination
+    if args.contam is not None:
+        output_df = correct_matrix.correct_matrix(output_df=output_df,
+                                                  contam=args.contam,
+                                                  nnls=args.nnls,
+                                                  )
+
     # Final output, merging the input and output tables
     final_df = pd.merge(id_df, output_df, how='left')
 
@@ -306,13 +315,22 @@ def main():
     import argparse
 
     parser = argparse.ArgumentParser(description='pytmt returns ms2 tmt quantification values'
-                                                 'from Percolator (Crux or Standalone) output')
+                                                 'from Percolator output and perform contamination'
+                                                 'correction')
 
-    parser.add_argument('mzml', help='path to folder containing mzml files')
+    parser.add_argument('mzml',
+                        help='path to folder containing mzml files',
+                        )
 
-    parser.add_argument('id', help='path to percolator target psms output file')
+    parser.add_argument('id',
+                        help='path to percolator target psms output file',
+                        )
 
-    parser.add_argument('-u', '--unique', action='store_true', help='quantify unique peptides only')
+    parser.add_argument('-u',
+                        '--unique',
+                        action='store_true',
+                        help='quantify unique peptides only',
+                        )
 
     parser.add_argument('-q', '--qvalue',
                         help='quantify peptides with q value below this threshold [default: 1.0]',
@@ -332,10 +350,21 @@ def main():
     parser.add_argument('-o', '--out', help='name of the output directory [default: tmt_out]',
                         default='tmt_out')
 
-
     parser.add_argument('-v', '--version', action='version',
                         version='%(prog)s {version}'.format(version=__version__))
 
+    parser.add_argument('-c', '--contam',
+                        help='Path to contaminant matrix csv file.'
+                             ' Leave blank to get tmt output without correction',
+                        metavar='CONTAM',
+                        type=argparse.FileType('r'),
+                        )
+
+    parser.add_argument('-n', '--nnls',
+                        action='store_true',
+                        help='uses non-negative least square for contamination correction',
+                        )
+
     parser.set_defaults(func=quant)
 
 

requirements.txt

@@ -1,3 +1,4 @@
 pandas>=1.0.4
 pymzml==2.4.6
-tqdm>=4.46.0
+tqdm>=4.46.0
+scipy>=1.0.0