From 988a1c2f0c66d2264995c16703f98740b760a9a2 Mon Sep 17 00:00:00 2001
From: Adrian Nievergelt <nieverge@pigino-pc-6.mpi-cbg.de>
Date: Thu, 5 Dec 2019 18:14:16 +0100
Subject: [PATCH] added MOTL multiplyer scripts for general use

---
 subtomogramAveraging/csv_2Xshifts_apn.py | 45 +++++++++++++++++
 subtomogramAveraging/multiplyMOTL.py     | 62 ++++++++++++++++++++++++
 2 files changed, 107 insertions(+)
 create mode 100755 subtomogramAveraging/csv_2Xshifts_apn.py
 create mode 100755 subtomogramAveraging/multiplyMOTL.py

diff --git a/subtomogramAveraging/csv_2Xshifts_apn.py b/subtomogramAveraging/csv_2Xshifts_apn.py
new file mode 100755
index 0000000..17e7ac8
--- /dev/null
+++ b/subtomogramAveraging/csv_2Xshifts_apn.py
@@ -0,0 +1,45 @@
+'''
+31-07-2017
+
+Pigino Lab, MPI-CBG
+
+Edits the csv file, doubling the x,y,z values,
+deletes last semicolon from each line, and then replaces
+all the semicolons with comma
+'''
+
+import fileinput
+import sys
+import codecs
+import os
+
+with fileinput.input(inplace=True) as f:
+    with fileinput.input(inplace=True) as f1:
+
+        
+            #Skips the first line in the csv file
+            next(f)
+
+            print("CCC,reserved,reserved,pIndex,wedgeWT,NA,NA,NA,NA,NA,xOffset,yOffset,zOffset,NA,NA,reserved,EulerZ(1),EulerZ(3),EulerX(2),reserved,CREATED WITH PEET Version 1.9.1 04/01/2014")
+            for line in f:
+
+                #removes ; from the end of all lines where it appears
+                #leaves all other lines unchanged
+                line = line.rstrip('\n');
+                #if line.endswith(';'):
+                #line = line[:-1]
+
+                #array that stores the index value of all the semicolons in the line
+                sc_pos_array = [i for i,x in enumerate(line) if x == ',']
+                
+                #Multiplies and replaces x,y,z values by 2* the value 
+                line = line[0:sc_pos_array[9]+1] + str(2 * float(line[sc_pos_array[9]+1 : sc_pos_array[10]])) + "," + str(2 * float(line[sc_pos_array[10]+1 : sc_pos_array[11]])) + "," + str(2 * float(line[sc_pos_array[11]+1 : sc_pos_array[12]])) + line[sc_pos_array[12]:]
+
+                #finally, replace all the semicolons with comma
+                #line = line.replace(';',',')      
+                
+
+                print(line)
+
+        
+        
diff --git a/subtomogramAveraging/multiplyMOTL.py b/subtomogramAveraging/multiplyMOTL.py
new file mode 100755
index 0000000..0c8b77f
--- /dev/null
+++ b/subtomogramAveraging/multiplyMOTL.py
@@ -0,0 +1,62 @@
+#!/usr/bin/python
+
+# APN - 2019-05-06
+
+import os,sys
+import argparse
+import matplotlib.pyplot as plt
+import csv
+
+parser = argparse.ArgumentParser(description = "Takes a PEET motif list (MOTL) file and duplicates the motif descriptor lines a specified number of times.")
+
+# parser.add_argument("-f", "--file", help="create overlay for a single file",
+parser.add_argument('-i', '--input', nargs='?', default='.', help='Input file to process')
+parser.add_argument('-o', '--output', nargs='?', default='.', help='Output file to write to. If no argument is provided, a _mult suffix will be added to the original file name')
+parser.add_argument('-n', '--number', nargs='?', type=int, default='4', help='How many times to duplicate data lines')
+parser.add_argument('-H', '--headerLines', nargs='?', type=int, default='1', help='Number of header lines in file')
+parser.add_argument('-it', '--ignoreTail', nargs='?', type=int, default=0, help='Ignores the given number of columns at the end of the file when parsing')
+parser.add_argument('-g', '--graph', action='store_true', help='Store a graph of the corrected and uncorrected line intensities for debug purposes.')
+
+
+args = parser.parse_args()
+
+
+def row_count(filename):
+  with open(filename) as in_file:
+    return sum(1 for _ in in_file)
+
+if args.input == '.':
+  print("Missing input file");
+  print(parser.print_help())
+  sys.exit()
+
+if args.output == '.':
+  inPath = os.path.splitext(args.input)
+  args.output = inPath[0] + "_mult" + inPath[1]
+
+if args.number < 1:
+  print("Data line duplication argument must be at least 1.")
+  sys.exit()
+
+args.ignoreTail = abs(args.ignoreTail)
+
+
+with open(args.input, 'r') as csvInFile, open(args.output, 'w') as csvOutFile:
+  csvReader = csv.reader(csvInFile, delimiter=',', quotechar='#')
+  csvWriter = csv.writer(csvOutFile, delimiter=',', quotechar='#')
+
+  lastLineNumber = row_count(args.input)
+
+  for row in csvReader:
+
+    if csvReader.line_num <= args.headerLines or csvReader.line_num == lastLineNumber:
+      # PEET column descriptor line or last line, don't duplicate
+      if csvReader.line_num <= args.headerLines:
+        csvWriter.writerow(row)
+      else:
+        csvWriter.writerow(row[:len(row)-args.ignoreTail])
+    else:
+      # Data line, write as many times as requested
+      for i in range(args.number):
+        csvWriter.writerow(row[:len(row)-args.ignoreTail])
+    
-- 
GitLab