| Previous changeset 15:05ff1c55db84 (2015-03-20) Next changeset 18:cc2f31d1bac0 (2015-03-26) |
|
Commit message:
restored pdfread module |
|
modified:
GCMS/combine_output.py GCMS/combine_output.xml rankfilter_GCMS/rankfilter.py |
|
added:
rankfilter_GCMS/pdfread.py |
| b |
| diff -r 05ff1c55db84 -r 94b62c8be01e GCMS/combine_output.py --- a/GCMS/combine_output.py Fri Mar 20 17:11:04 2015 +0100 +++ b/GCMS/combine_output.py Thu Mar 26 09:27:51 2015 +0100 |
| [ |
| @@ -5,7 +5,6 @@ ''' import csv -import re import sys import math import pprint @@ -81,13 +80,15 @@ # The ID in the RankFilter output contains the following 5 fields: rf_id = rankfilter['ID'].split('-') try: + if 'Formula' not in rankfilter: + raise Exception("Error: old Rankfilter format detected (the selected Rankfilter data does not contain the column 'Formula'). Solution: rerun Rankfilter again.") hit = [rf_id[0], # Centrotype rf_id[1], # cent.Factor rf_id[2], # scan nr rf_id[3], # R.T. (umin) rf_id[4], # nr. Peaks + rankfilter['R.T.'], # Appending other fields - rankfilter['R.T.'], rankfilter['Name'], rankfilter['Formula'], rankfilter['Library'].strip(), |
| b |
| diff -r 05ff1c55db84 -r 94b62c8be01e GCMS/combine_output.xml --- a/GCMS/combine_output.xml Fri Mar 20 17:11:04 2015 +0100 +++ b/GCMS/combine_output.xml Thu Mar 26 09:27:51 2015 +0100 |
| b |
| @@ -15,13 +15,13 @@ <data format="tabular" label="${tool.name} (Multi) on ${on_string}" name="out_multi" /> </outputs> <help> -Performs a combination of output files from the 'RankFilter' and 'Lookup RI for CAS' tools into two tab-separated files. +Performs a combination of given 'RankFilter' and 'Lookup RI for CAS' files into two tab-separated files. -Merges data from both input dictionaries based on the Centrotype field. +This combination is a merge of the given files based on the Centrotype field. In the 'RIQC-RankFilter output' the centrotype is found in the 'ID' field (first part before the "-"). In the 'RIQC-Lookup RI for CAS output' the centrotype is found in the 'Centrotype' field. -The files produced are contain either all hits for a compound on a single line (Single) or on separate lines +The files produced contain either all hits for a compound on a single line (Single) or on separate lines (Multi). .. class:: infomark |
| b |
| diff -r 05ff1c55db84 -r 94b62c8be01e rankfilter_GCMS/pdfread.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rankfilter_GCMS/pdfread.py Thu Mar 26 09:27:51 2015 +0100 |
| [ |
| b'@@ -0,0 +1,203 @@\n+"""\n+Copyright (C) 2011 by Velitchka Mihaleva, Wageningen University \n+\n+Permission is hereby granted, free of charge, to any person obtaining a copy\n+of this software and associated documentation files (the "Software"), to deal\n+in the Software without restriction, including without limitation the rights\n+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell\n+copies of the Software, and to permit persons to whom the Software is\n+furnished to do so, subject to the following conditions:\n+\n+The above copyright notice and this permission notice shall be included in\n+all copies or substantial portions of the Software.\n+\n+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\n+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\n+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN\n+THE SOFTWARE.\n+"""\n+\n+import sys\n+import csv\n+\n+def getPDF(filename, print_progress):\n+ \'\'\'\n+ Parses NIST PDF file\n+ @param filename: PDF file to parse\n+ \'\'\'\n+ NistInput = {}\n+ NistInput_missed = {}\n+ nist_input = open(filename, \'r\').read()\n+\n+ hitid = []\n+ rt = []\n+ name = []\n+ forward = []\n+ cas = []\n+ reverse = []\n+ prob = []\n+ lib_id = []\n+ nist_id = []\n+ missed_compounds = []\n+ id_missed_compounds = []\n+ formula = []\n+\n+ hit_list = nist_input.split(\'** Search Report Page 1 of 1 **\')\n+ hit_list.pop(0)\n+ #number_hits = range(10)\n+ line_id = 0\n+ for line in hit_list:\n+ line = line.strip().translate(None, \'\\r\')\n+ if line != \'\':\n+ hits = line.replace(\'\\n\', \' \').replace(\'\\x0c\', \'\').replace(\'^L\', \'\').split(\'Hit\') #solution? : if we wouldn\'t replace the \\n by \' \' but by some special sign, then reading formula would be simpler! \n+ #strange....code seems fine actually...debug! See test/data/download.pdf \n+ # strange thing is that it looks like the new line does not end up in the text file, eventhough it looks like there is a new line in the pdf...perhaps a bug in the pdf2text command in linux?\n+ spec_id = hits.pop(0).split(\' \')[1]\n+ j = 0\n+ for hh in hits:\n+ cell = hh.split(\';\')\n+ if print_progress == True:\n+ print \'Processing line: \', line_id, \' with length: \', len(cell), \':\\n\\t\', cell\n+ line_id += 1\n+ if len(cell) == 7: # the compound has CAS number\n+ if len(cell[1].split(\':\')) == 2:\n+ forward.append((cell[1].split(\':\')[1]).strip())\n+ # indication that the name contains the ":". Should join the cells of name_tmp from 1 till end\n+ if len(cell[0].split(\':\')) > 2:\n+ name_tmp = \':\'.join(cell[0].split(\':\')[1:])\n+ else:\n+ name_tmp = cell[0].split(\':\')[1]\n+ \n+ name.append(name_tmp.replace(" ", " ").strip())\n+ name_tmp = name_tmp.strip().split(\' \')\n+ if name_tmp:\n+ # if the name ends with a word that starts with C, F or H, then assume this last word is a formula:\n+ if name_tmp[-1][0] == \'C\' or name_tmp[-1][0] == \'F\' or name_tmp[-1][0] == \'H\':\n+ formule = (name_tmp[-1])\n+ else:\n+ formule = (\'not_def\')\n+ else:\n+ '..b'hat starts with C, F or H, then assume this last word is a formula:\n+ if name_tmp[-1][0] == \'C\' or name_tmp[-1][0] == \'F\' or name_tmp[-1][0] == \'H\':\n+ formule = (name_tmp[-1])\n+ else:\n+ formule = (\'not_def\')\n+ else:\n+ formule = (\'not_def\')\n+ formula.append(formule.replace(" ", " "))\n+ reverse.append((cell[2].split(\':\')[1]).strip())\n+ prob.append(cell[3].split(\' \')[2].replace(\'%\', \'\'))\n+ cas.append(\'undef\')\n+ lib_id.append((cell[4].split(\':\')[1]).strip())\n+ nist_id.append(cell[5].split(\':\')[1].replace(\'.\', \'\').strip())\n+ j = j + 1\n+\n+ else:\n+ missed_compounds.append(hh)\n+ id_missed_compounds.append(spec_id)\n+\n+ else: # Missing columns, report and quit\n+ missed_compounds.append(hh)\n+ id_missed_compounds.append(spec_id)\n+\n+ for _ in range(j):\n+ hitid.append(str(spec_id.replace(" ", " ")))\n+ #NB: this is the RT as found in the "id" generated by e.g. msclust, so NOT the RT of the library hit:\n+ rt.append(str(float(spec_id.split(\'-\')[3]) / 1e+06))\n+\n+ NistInput[\'ID\'] = hitid\n+ NistInput[\'R.T.\'] = rt\n+ NistInput[\'Name\'] = name\n+ NistInput[\'CAS\'] = cas\n+ NistInput[\'Formula\'] = formula\n+ NistInput[\'Forward\'] = forward\n+ NistInput[\'Reverse\'] = reverse\n+ NistInput[\'Probability\'] = prob\n+ NistInput[\'Library\'] = lib_id\n+ NistInput[\'Library ID\'] = nist_id\n+ NistInput_missed[\'Missed Compounds\'] = missed_compounds\n+ NistInput_missed[\'ID missed Compounds\'] = id_missed_compounds\n+\n+ return NistInput, NistInput_missed\n+\n+\n+def convert_pdftotext2tabular(filename, output_file, error_file, print_progress):\n+ \'\'\'\n+ Converts NIST PDF file to tabular format\n+ @param filename: PDF file to parse\n+ @param output_file: output file for the hits\n+ @param error_file: output file for failed hits\n+ \'\'\'\n+ [HitList, HitList_missed] = getPDF(filename, print_progress)\n+ # save Hitlist as tab seperate file\n+ Hitlist_as_text = "\\t".join(HitList.keys()) + "\\n"\n+ Hitlist_array_of_array = ([HitList[row] for row in HitList.keys()])\n+ Hitlist_as_text += str("\\n".join(["\\t".join(e) for e in zip(*Hitlist_array_of_array)]))\n+ output_fh = open(output_file, \'wb\')\n+ output_fh.write(Hitlist_as_text)\n+ output_fh.close()\n+\n+ out_missed_pdf = open(error_file, \'wb\')\n+ for x, y in zip(HitList_missed[\'Missed Compounds\'], HitList_missed[\'ID missed Compounds\']):\n+ out_missed_pdf.write("Line with incorrect format or unexpected number of fields:\\n")\n+ out_missed_pdf.write(\'%s\\n\' % \'\\t\'.join([y, x]))\n+ out_missed_pdf.close()\n+\n+\n+\n+\n+\n+def read_tabular_old(filename):\n+ \'\'\'\n+ Function to read tabular format (created by convert_pdftotext2tabular)\n+ and output a dict with header of columns as key and value is columns of tabular as list\n+ @param filename: tabular file to read\n+ \'\'\'\n+ input_fh = None\n+ try:\n+ input_fh = open(filename, \'r\')\n+ except IOError, error:\n+ raise error\n+ colnames = input_fh.readline().strip().split(\'\\t\')\n+ cells = []\n+ for line in input_fh.readlines():\n+ cells.append(line.strip().split(\'\\t\'))\n+ #transform from row oriented structure to column oriented structure\n+ cells = zip(*cells)\n+ #store the list of list in form of final output\n+ RankFilterGC_format = {}\n+ for colnumber in range(len(colnames)):\n+ RankFilterGC_format[colnames[colnumber]] = cells[colnumber]\n+ return RankFilterGC_format\n+\n+\n+if __name__ == \'__main__\':\n+ convert_pdftotext2tabular(sys.argv[1], sys.argv[2], sys.argv[3], True)\n' |
| b |
| diff -r 05ff1c55db84 -r 94b62c8be01e rankfilter_GCMS/rankfilter.py --- a/rankfilter_GCMS/rankfilter.py Fri Mar 20 17:11:04 2015 +0100 +++ b/rankfilter_GCMS/rankfilter.py Thu Mar 26 09:27:51 2015 +0100 |
| [ |
| @@ -142,6 +142,8 @@ # Convert 'Name' data to list in order to be indexed # library_data['Name']=list(library_data['Name']) + # tries to match on CAS first. If this is not possible (cas is 'undef' + # or not found) then tries to match on name: for hit_cas, hit_name in zip(hit_list['CAS'], hit_list['Name']): index = 0 if hit_cas != 'undef': |