1 #!/bin/env python
2 #
3 # File: RDKitDrawMoleculesAndDataTable.py
4 # Author: Manish Sud <msud@san.rr.com>
5 #
6 # Copyright (C) 2024 Manish Sud. All rights reserved.
7 #
8 # The functionality available in this script is implemented using RDKit, an
9 # open source toolkit for cheminformatics developed by Greg Landrum.
10 #
11 # This file is part of MayaChemTools.
12 #
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
14 # the terms of the GNU Lesser General Public License as published by the Free
15 # Software Foundation; either version 3 of the License, or (at your option) any
16 # later version.
17 #
18 # MayaChemTools is distributed in the hope that it will be useful, but without
19 # any warranty; without even the implied warranty of merchantability of fitness
20 # for a particular purpose. See the GNU Lesser General Public License for more
21 # details.
22 #
23 # You should have received a copy of the GNU Lesser General Public License
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
26 # Boston, MA, 02111-1307, USA.
27 #
28
29 from __future__ import print_function
30
31 # Add local python path to the global path and import standard library modules...
32 import os
33 import sys; sys.path.insert(0, os.path.join(os.path.dirname(sys.argv[0]), "..", "lib", "Python"))
34 import time
35 import re
36 import random
37
38 # RDKit imports...
39 try:
40 from rdkit import rdBase
41 from rdkit import Chem
42 from rdkit.Chem import AllChem
43 except ImportError as ErrMsg:
44 sys.stderr.write("\nFailed to import RDKit module/package: %s\n" % ErrMsg)
45 sys.stderr.write("Check/update your RDKit environment and try again.\n\n")
46 sys.exit(1)
47
48 # MayaChemTools imports...
49 try:
50 from docopt import docopt
51 import MiscUtil
52 import RDKitUtil
53 except ImportError as ErrMsg:
54 sys.stderr.write("\nFailed to import MayaChemTools module/package: %s\n" % ErrMsg)
55 sys.stderr.write("Check/update your MayaChemTools environment and try again.\n\n")
56 sys.exit(1)
57
58 ScriptName = os.path.basename(sys.argv[0])
59 Options = {}
60 OptionsInfo = {}
61
62 def main():
63 """Start execution of the script."""
64
65 MiscUtil.PrintInfo("\n%s (RDKit v%s; MayaChemTools v%s; %s): Starting...\n" % (ScriptName, rdBase.rdkitVersion, MiscUtil.GetMayaChemToolsVersion(), time.asctime()))
66
67 (WallClockTime, ProcessorTime) = MiscUtil.GetWallClockAndProcessorTime()
68
69 # Retrieve command line arguments and options...
70 RetrieveOptions()
71
72 # Process and validate command line arguments and options...
73 ProcessOptions()
74
75 # Perform actions required by the script...
76 GenerateMoleculesAndDataTable()
77
78 MiscUtil.PrintInfo("\n%s: Done...\n" % ScriptName)
79 MiscUtil.PrintInfo("Total time: %s" % MiscUtil.GetFormattedElapsedTime(WallClockTime, ProcessorTime))
80
81 def GenerateMoleculesAndDataTable():
82 """Generate a HTML table containing molecules and alphanumerical data."""
83
84 # Retrieve data...
85 ValidMols = RetrieveMoleculesAndData()
86
87 # Setup data type map...
88 DataMap = IdentifyStructureAndNumericalData(ValidMols)
89
90 # Validate data labels used to specify highlighting data...
91 ValidateSpecifiedDataLabels(DataMap)
92
93 # Validate show molecule name option...
94 ValidateShowMolNameOption(DataMap)
95
96 # Compute 2D coordinates before alignment...
97 if OptionsInfo["Compute2DCoords"]:
98 MiscUtil.PrintInfo("\nComputing 2D coordinates for primary structure data...")
99 for Mol in ValidMols:
100 AllChem.Compute2DCoords(Mol)
101
102 # Perform alignment to a common template for primary molecular structure data...
103 PerformAlignment(ValidMols)
104
105 # Write out a HTML file...
106 WriteHTMLTableFile(ValidMols, DataMap)
107
108 def WriteHTMLTableFile(ValidMols, DataMap):
109 """Write out a HTML table file."""
110
111 Outfile = OptionsInfo["Outfile"]
112
113 Writer = open(Outfile, "w")
114 if Writer is None:
115 MiscUtil.PrintError("Failed to setup a writer for output fie %s " % Outfile)
116
117 MiscUtil.PrintInfo("\nGenerating file %s..." % Outfile)
118
119 WriteHTMLPageHeader(Writer, DataMap)
120 WriteHTMLPageTitle(Writer)
121
122 WriteHTMLTableHeader(Writer)
123 WriteHTMLTableRows(Writer, ValidMols, DataMap)
124 WriteHTMLTableEnd(Writer)
125
126 WriteHTMLPageFooter(Writer)
127 WriteHTMLPageEnd(Writer)
128
129 if Writer is not None:
130 Writer.close()
131
132 def WriteHTMLTableRows(Writer, ValidMols, DataMap):
133 """Write out HTML table rows."""
134
135 WriteTableHeaderRow(Writer, ValidMols, DataMap)
136 WriteTableDataRows(Writer, ValidMols, DataMap)
137 WriteTableFooterRow(Writer, ValidMols, DataMap)
138
139 def WriteTableDataRows(Writer, ValidMols, DataMap):
140 """Write out table data row."""
141
142 Writer.write(""" <tbody>\n""")
143
144 MolCount = 0
145 for Mol in ValidMols:
146 MolCount += 1
147 Writer.write(""" <tr>\n""")
148
149 if OptionsInfo["CounterCol"]:
150 Writer.write(""" <td></td>\n""")
151
152 SetupPrimaryStructureTableData(Writer, Mol)
153
154 if OptionsInfo["ShowMolName"]:
155 MolName = RDKitUtil.GetMolName(Mol, MolCount)
156 WrappedMolName = MiscUtil.WrapText(MolName, "<br/>", OptionsInfo["WrapTextWidth"])
157 Writer.write(""" <td>%s</td>\n""" % WrappedMolName)
158
159 # Set up rest of the data..
160 AvailableDataLabelsMap = Mol.GetPropsAsDict(includePrivate = False, includeComputed = False)
161 for DataLabel in DataMap["DataLabels"]:
162 if not DataLabel in AvailableDataLabelsMap:
163 Writer.write(""" <td></td>\n""")
164 continue
165
166 # Check for empty value...
167 DataValue = "%s" % AvailableDataLabelsMap[DataLabel]
168 DataValue = DataValue.strip()
169 if MiscUtil.IsEmpty(DataValue):
170 Writer.write(""" <td></td>\n""")
171 continue
172
173 if DataMap["StructureDataMap"][DataLabel]:
174 SetupNonPrimaryStructureTableData(Writer, DataLabel, DataValue, DataMap)
175 else:
176 SetupAlphanumericTableData(Writer, DataLabel, DataValue, DataMap)
177
178 Writer.write(""" </tr>\n""")
179
180 Writer.write(""" </tbody>\n""")
181
182 def SetupPrimaryStructureTableData(Writer, Mol):
183 """Set up an inline SVG image for primary structure data for a table cell."""
184
185 HightlightAtomList = SetupAtomListToHighlight(Mol, "Structure")
186 SVGImageTag = SetupMolInLineSVGImageTag(Mol, HightlightAtomList)
187
188 Writer.write(""" <td bgcolor="white"><%s></td>\n""" % SVGImageTag)
189
190 def SetupNonPrimaryStructureTableData(Writer, DataLabel, DataValue, DataMap):
191 """Set up an inline SVG image for non primary structure data cell."""
192
193 WrappedDataValue = DataValue
194 if OptionsInfo["WrapText"]:
195 WrappedDataValue = MiscUtil.WrapText(DataValue, "<br/>", OptionsInfo["WrapTextWidth"])
196
197 if DataMap["SMILESDataMap"][DataLabel]:
198 Mol = Chem.MolFromSmiles(DataValue, sanitize = False)
199 Mol.UpdatePropertyCache(strict = False)
200 else:
201 MiscUtil.PrintWarning("\nIgnoring uknown structure data column type with column label %s: %s\n" % (DataLabel, DataValue))
202 Writer.write(""" <td>%s</td>\n""" % WrappedDataValue)
203 return
204
205 if Mol is None:
206 MiscUtil.PrintWarning("\nSMILES parsing failed for data label %s: %s\n" % (DataLabel, DataValue))
207 Writer.write(""" <td>%s</td>\n""" % WrappedDataValue)
208 return
209 elif not Mol.GetNumHeavyAtoms():
210 Writer.write(""" <td>%s</td>\n""" % WrappedDataValue)
211 return
212 elif AllChem.Compute2DCoords(Mol) < 0:
213 Writer.write(""" <td>%s</td>\n""" % WrappedDataValue)
214 return
215
216 HightlightAtomList = SetupAtomListToHighlight(Mol, DataLabel)
217 SVGImageTag = SetupMolInLineSVGImageTag(Mol, HightlightAtomList)
218
219 Writer.write(""" <td bgcolor="white"><%s></td>\n""" % SVGImageTag)
220
221 def SetupAlphanumericTableData(Writer, DataLabel, DataValue, DataMap):
222 """Set up alphanumeric data."""
223
224 BackgroundColor, BackgroundColorType = GetAlphanumeircValueHighlightBackgroundColor(DataLabel, DataValue, DataMap)
225 SetupAlphanumericTableDataValue(Writer, DataValue, BackgroundColor, BackgroundColorType)
226
227 def WriteTableHeaderRow(Writer, ValidMols, DataMap):
228 """Write out table header row."""
229
230 TableHeaderStyle = OptionsInfo["TableHeaderStyle"]
231 if TableHeaderStyle is None:
232 Writer.write(""" <thead>\n""")
233 Writer.write(""" <tr>\n""")
234 elif re.match("^(thead|table)", TableHeaderStyle):
235 Writer.write(""" <thead class="%s">\n""" % TableHeaderStyle)
236 Writer.write(""" <tr>\n""")
237 else:
238 Writer.write(""" <thead>\n""")
239 Writer.write(""" <tr bgcolor="%s"\n""" % TableHeaderStyle)
240
241 if OptionsInfo["CounterCol"]:
242 Writer.write(""" <th></th>\n""")
243 Writer.write(""" <th>Structure</th>\n""")
244 if OptionsInfo["ShowMolName"]:
245 Writer.write(""" <th>%s</th>\n""" % OptionsInfo["ShowMolNameDataLabel"])
246
247 # Write out rest of the column headers...
248 for DataLabel in DataMap["DataLabels"]:
249 Writer.write(""" <th>%s</th>\n""" % DataLabel)
250
251 Writer.write(""" </tr>\n""")
252 Writer.write(""" </thead>\n""")
253
254 def WriteTableFooterRow(Writer, ValidMols, DataMap):
255 """Write out table footer row."""
256
257 if not OptionsInfo["TableFooter"]:
258 return
259
260 Writer.write(""" <tfoot>\n""")
261 Writer.write(""" <tr>\n""")
262
263 if OptionsInfo["CounterCol"]:
264 Writer.write(""" <td></td>\n""")
265 Writer.write(""" <td>Structure</td>\n""")
266 if OptionsInfo["ShowMolName"]:
267 Writer.write(""" <td>%s</td>\n""" % OptionsInfo["ShowMolNameDataLabel"])
268
269 # Write out rest of the column headers...
270 for DataLabel in DataMap["DataLabels"]:
271 Writer.write(""" <td>%s</td>\n""" % DataLabel)
272
273 Writer.write(""" </tr>\n""")
274 Writer.write(""" </tfoot>\n""")
275
276 def WriteHTMLPageHeader(Writer, DataMap):
277 """Write out HTML page header."""
278
279 # Collect column indices containing counter and structure data to disable
280 # sorting and searching. In addition, set up a list to exclude counter and
281 # primary structure columns from column visibility pulldown along with
282 # any other columns...
283 #
284 if OptionsInfo["CounterCol"]:
285 StrColIndicesList = ["0", "1"]
286 ColVisibilityExcludeColIndicesList = ["0", "1"]
287 ColIndexOffset = 2
288 FreezeLeftColumns = "2"
289 else:
290 StrColIndicesList = ["0"]
291 ColVisibilityExcludeColIndicesList = ["0"]
292 ColIndexOffset = 1
293 FreezeLeftColumns = "1"
294
295 if OptionsInfo["ShowMolName"]:
296 ColIndexOffset += 1
297
298 MaxColVisColCount = OptionsInfo["ColVisibilityCtrlMax"]
299 MaxDataColVisColCount = MaxColVisColCount - len(ColVisibilityExcludeColIndicesList)
300 MaxDataColVisColCount = MaxColVisColCount
301
302 DataColVisibilityExclude = False
303 ColCount = len(DataMap["DataLabels"])
304 if OptionsInfo["ColVisibility"]:
305 if ColCount > MaxDataColVisColCount:
306 DataColVisibilityExclude = True
307 MiscUtil.PrintWarning("The number of data columns, %d, is more than %d. Only first %d data columns will be available in column visibility pulldown." % (ColCount, MaxColVisColCount, MaxColVisColCount))
308
309 DisplayButtons = False
310 if OptionsInfo["ColVisibility"]:
311 if ColCount > 0 or OptionsInfo["ShowMolName"]:
312 DisplayButtons = True
313
314 FreezeCols = False
315 if (OptionsInfo["FreezeCols"] and OptionsInfo["ScrollX"]):
316 FreezeCols = True
317
318 for Index, DataLabel in enumerate(DataMap["DataLabels"]):
319 if DataMap["StructureDataMap"][DataLabel]:
320 StrColIndex = Index + ColIndexOffset
321 StrColIndicesList.append("%s" % StrColIndex)
322
323 if OptionsInfo["ColVisibility"]:
324 if Index >= MaxDataColVisColCount:
325 ColIndex = Index + ColIndexOffset
326 ColVisibilityExcludeColIndicesList.append("%s" %ColIndex)
327
328 StrColIndices = MiscUtil.JoinWords(StrColIndicesList, ", ")
329 ColVisibilityExcludeColIndices = MiscUtil.JoinWords(ColVisibilityExcludeColIndicesList, ", ")
330
331 Paging = "true" if OptionsInfo["Paging"] else "false"
332 PageLength = "%d" % OptionsInfo["PageLength"]
333 PagingType = "\"%s\"" % OptionsInfo["PagingType"]
334
335 ScrollX = "true" if OptionsInfo["ScrollX"] else "false"
336
337 ScrollY = ""
338 if OptionsInfo["ScrollY"]:
339 if re.search("vh$", OptionsInfo["ScrollYSize"]):
340 ScrollY = "\"%s\"" % OptionsInfo["ScrollYSize"]
341 else:
342 ScrollY = "%s" % OptionsInfo["ScrollYSize"]
343
344 RegexSearch = "true" if OptionsInfo["RegexSearch"] else "false"
345
346 # Start HTML header...
347 Title = "Molecules and data table" if OptionsInfo["Header"] is None else OptionsInfo["Header"]
348
349 Writer.write("""\
350 <!doctype html>
351 <html lang="en">
352 <head>
353 <title>%s</title>
354 <meta charset="utf-8">
355 <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
356 <link rel="stylesheet" type="text/css" href="https://maxcdn.bootstrapcdn.com/bootstrap/4.0.0/css/bootstrap.min.css">
357 <link rel="stylesheet" type="text/css" href="https://cdn.datatables.net/1.10.16/css/dataTables.bootstrap4.min.css">
358
359 """ % (Title))
360
361 if (FreezeCols):
362 Writer.write("""\
363 <link rel="stylesheet" type="text/css" href="https://cdn.datatables.net/fixedcolumns/3.2.4/css/fixedColumns.bootstrap4.min.css">
364 """)
365
366 if (OptionsInfo["KeysNavigation"]):
367 Writer.write("""\
368 <link rel="stylesheet" type="text/css" href="https://cdn.datatables.net/keytable/2.3.2/css/keyTable.bootstrap4.min.css">
369 """)
370
371 Writer.write("""\
372
373 <script type="text/javascript" language="javascript" src="https://code.jquery.com/jquery-1.12.4.js"></script>
374 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/1.10.16/js/jquery.dataTables.min.js"></script>
375 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/1.10.16/js/dataTables.bootstrap4.min.js"></script>
376
377 """)
378
379 if DisplayButtons:
380 Writer.write("""\
381 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/buttons/1.5.1/js/dataTables.buttons.min.js"></script>
382 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/buttons/1.5.1/js/buttons.bootstrap4.min.js"></script>
383 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/buttons/1.5.1/js/buttons.colVis.min.js"></script>
384
385 """)
386
387 if (FreezeCols):
388 Writer.write("""\
389 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/fixedcolumns/3.2.4/js/dataTables.fixedColumns.min.js"></script>
390 """)
391
392 if (OptionsInfo["KeysNavigation"]):
393 Writer.write("""\
394 <script type="text/javascript" language="javascript" src="https://cdn.datatables.net/keytable/2.3.2/js/dataTables.keyTable.min.js"></script>
395 """)
396
397 # Intialize table using Bootstrap, DataTables and JQuery frameworks...
398 Writer.write("""\
399
400 <script type="text/javascript" class="init">
401
402 $(document).ready(function() {
403 var MolsAndDataTable = $('#MolsAndDataTable').DataTable( {
404 "columnDefs": [
405 {
406 "orderable": false,
407 "searchable": false,
408 "targets": [%s]
409 },
410 """ % (StrColIndices))
411
412 if OptionsInfo["ColVisibility"]:
413 Writer.write("""\
414 {
415 "className": "noColVisCtrl",
416 "targets": [%s]
417 }
418 """ % (ColVisibilityExcludeColIndices))
419
420 Writer.write("""\
421 ],
422 """)
423
424 # Setup column visibility control pulldown by excluding counter column
425 # and primary structure column from the list...
426 #
427 if OptionsInfo["ColVisibility"]:
428 # Set up dom for button display...
429 if OptionsInfo["Paging"]:
430 Writer.write("""\
431 "dom": "<'row'<'col'l><'col'B><'col'f>>" +
432 "<'row'<'col-sm-12'tr>>" +
433 "<'row'<'col-sm-5'i><'col-sm-7'p>>",
434 """)
435 else:
436 Writer.write("""\
437 "dom": "<'row'<'col-sm-6'B><'col-sm-6'f>>" +
438 "<'row'<'col-sm-12'tr>>" +
439 "<'row'<'col-sm-5'i><'col-sm-7'p>>",
440 """)
441 # Set up buttons...
442 Writer.write("""\
443 "buttons": [
444 {
445 "extend": "colvis",
446 "text": "Column visibility",
447 "className": "btn btn-outline-light text-dark",
448 "columns": ":not(.noColVisCtrl)",
449 """)
450 if not DataColVisibilityExclude:
451 Writer.write("""\
452 "prefixButtons": [ "colvisRestore" ],
453 """)
454
455 Writer.write("""\
456 "columnText": function ( dt, colIndex, colLabel ) {
457 return (colIndex + 1) + ": " + colLabel;
458 },
459 }
460 ],
461 """)
462
463 # Write out rest of the variables for DataTables...
464 if FreezeCols:
465 Writer.write("""\
466 "fixedColumns": {
467 "leftColumns": %s
468 },
469 """ % (FreezeLeftColumns))
470
471 if (OptionsInfo["KeysNavigation"]):
472 Writer.write("""\
473 "keys": true,
474 """)
475
476 Writer.write("""\
477 "pageLength": %s,
478 "lengthMenu": [ [10, 15, 25, 50, 100, 500, 1000, -1], [10, 15, 25, 50, 100, 500, 1000, "All"] ],
479 "paging": %s,
480 "pagingType": %s,
481 "scrollX": %s,
482 "scrollY": %s,
483 "scrollCollapse": true,
484 "order": [],
485 "search" : {"regex" : %s},
486 } );
487 """ % (PageLength, Paging, PagingType, ScrollX, ScrollY, RegexSearch))
488
489 if OptionsInfo["CounterCol"]:
490 Writer.write("""\
491 MolsAndDataTable.on( 'order.dt search.dt', function () {
492 MolsAndDataTable.column(0, {search:'applied', order:'applied'}).nodes().each( function (cell, rowIndex) {
493 cell.innerHTML = rowIndex + 1;
494 } );
495 } ).draw();
496 """)
497
498 # End of Javacscript code...
499 Writer.write("""\
500 } );
501
502 </script>
503 """)
504
505 # Finish up HTML header...
506 Writer.write("""\
507
508 </head>
509 <body>
510 <div class="container-fluid">
511 <br/>
512 """)
513
514 def WriteHTMLPageEnd(Writer):
515 """Write out HTML page end."""
516
517 Writer.write("""\
518 </div>
519 </body>
520 </html>
521 """)
522
523 def WriteHTMLPageTitle(Writer):
524 """Write out HTML page title."""
525
526 if OptionsInfo["Header"] is None:
527 return
528
529 Writer.write(""" <%s class="text-center">%s</%s>\n""" % (OptionsInfo["HeaderStyle"], OptionsInfo["Header"], OptionsInfo["HeaderStyle"]))
530
531 def WriteHTMLPageFooter(Writer):
532 """Write out HTML page footer."""
533
534 if OptionsInfo["Footer"] is None:
535 return
536
537 Writer.write(""" <br/>\n <p class="%s">%s</p>\n""" % (OptionsInfo["FooterClass"], OptionsInfo["Footer"]))
538
539 def WriteHTMLTableHeader(Writer):
540 """Write out HTML table header."""
541
542 if OptionsInfo["TableStyle"] is None:
543 Writer.write("""\n <table id="MolsAndDataTable" cellspacing="0" width="100%">\n""")
544 else:
545 Writer.write(""" <table id="MolsAndDataTable" class="%s" cellspacing="0" width="100%s">\n""" % (OptionsInfo["TableStyle"], "%"))
546
547 def WriteHTMLTableEnd(Writer):
548 """Write out HTML table end."""
549
550 Writer.write(""" </table>\n\n""")
551
552 def RetrieveMoleculesAndData():
553 """Retrieve molecules and data from input file."""
554
555 MiscUtil.PrintInfo("\nReading file %s..." % OptionsInfo["Infile"])
556
557 if MiscUtil.CheckFileExt(OptionsInfo["Infile"] ,"smi csv tsv txt"):
558 # Check for the presence of SMILES column name in title line...
559 Infile = open(OptionsInfo["Infile"], "r")
560 if Infile is None:
561 MiscUtil.PrintError("Couldn't open file %s..." % OptionsInfo["Infile"])
562 Line = Infile.readline()
563 Infile.close()
564
565 if not re.search("SMILES", Line, re.I):
566 MiscUtil.PrintError("The input file, %s, must contain a title line containing a column name with SMILES in its name." % OptionsInfo["Infile"])
567
568 if MiscUtil.CheckFileExt(OptionsInfo["Infile"],"sdf sd smi"):
569 ValidMols, MolCount, ValidMolCount = RDKitUtil.ReadAndValidateMolecules(OptionsInfo["Infile"], **OptionsInfo["InfileParams"])
570 else:
571 ValidMols, MolCount, ValidMolCount = RetrieveMoleculesFromTextFile(OptionsInfo["Infile"])
572
573 MiscUtil.PrintInfo("Total number of molecules: %d" % MolCount)
574 MiscUtil.PrintInfo("Number of valid molecules: %d" % ValidMolCount)
575 MiscUtil.PrintInfo("Number of ignored molecules: %d" % (MolCount - ValidMolCount))
576
577 return ValidMols
578
579 def RetrieveMoleculesFromTextFile(Infile):
580 """Retrieve molecules from a CSV/TSV text file."""
581
582 # Read and parse text lines...
583 Delimiter = "," if MiscUtil.CheckFileExt(Infile ,"csv") else "\t"
584 QuoteChar = '"'
585 IgnoreHeaderLine = False
586 TextLinesWords = MiscUtil.GetTextLinesWords(Infile, Delimiter, QuoteChar, IgnoreHeaderLine)
587
588 # Process column names...
589 ColNames = TextLinesWords[0]
590 ColCount = len(ColNames)
591
592 MolColIndex = None
593 MolDataColIndices = []
594
595 FirstSMILES = True
596 for ColIndex in range(0, ColCount):
597 if re.search("SMILES", ColNames[ColIndex], re.I) and FirstSMILES:
598 MolColIndex = ColIndex
599 FirstSMILES = False
600 continue
601
602 MolDataColIndices.append(ColIndex)
603
604 if MolColIndex is None:
605 MiscUtil.PrintError("The input file, %s, must contain a title line containing a column name with SMILES in its name." % Infile)
606
607 ValidMols = []
608 MolCount = 0
609
610 Sanitize = OptionsInfo["InfileParams"]["Sanitize"]
611
612 # Process data lines...
613 for LineIndex in range(1, len(TextLinesWords)):
614 MolCount += 1
615 LineWords = TextLinesWords[LineIndex]
616 if len(LineWords) != ColCount:
617 MiscUtil.PrintWarning("Ignoring text line number %d: Number of columns, %d, must match number of columns, %d, in title line.\nLine: %s" % (MolCount, len(LineWords), ColCount, Delimiter.join(LineWords)))
618 continue
619
620 # Process molecule column...
621 MolSMILES = LineWords[MolColIndex]
622 Mol = Chem.MolFromSmiles(MolSMILES, sanitize = Sanitize)
623 if Mol is None:
624 MiscUtil.PrintWarning("Ignoring text line number %d: SMILES parsing failed\nLine: %s" % (MolCount, Delimiter.join(LineWords)))
625 continue
626
627 # Process molecule data columns...
628 for ColIndex in MolDataColIndices:
629 Name = ColNames[ColIndex]
630 Value = LineWords[ColIndex]
631 Mol.SetProp(Name, Value)
632
633 ValidMols.append(Mol)
634
635 ValidMolCount = len(ValidMols)
636
637 return (ValidMols, MolCount, ValidMolCount)
638
639 def IdentifyStructureAndNumericalData(ValidMols):
640 """Identify structure and alphanumerical data."""
641
642 DataMap = {}
643 DataMap["DataLabels"] = []
644 DataMap["DataLabelsMap"] = {}
645 DataMap["CanonicalDataLabelsMap"] = {}
646
647 DataMap["StructureDataMap"] = {}
648 DataMap["SMILESDataMap"] = {}
649
650 # Retrieve all possible data labels...
651 if MiscUtil.CheckFileExt(OptionsInfo["Infile"] ,"smi csv tsv txt"):
652 # First molecule contains all possible data fields...
653 Mol = ValidMols[0]
654 ProcessMolDataLabels(ValidMols[0], DataMap)
655 else:
656 # Go over all molecules to identify unique data labels...
657 MiscUtil.PrintInfo("\nRetrieving unique data labels for data in file %s..." % OptionsInfo["Infile"])
658 for Mol in ValidMols:
659 ProcessMolDataLabels(Mol, DataMap)
660
661 return DataMap
662
663 def ProcessMolDataLabels(Mol, DataMap):
664 """Process data label to identify and track its type."""
665
666 for DataLabel in Mol.GetPropNames(includePrivate = False, includeComputed = False):
667 if DataLabel in DataMap["DataLabelsMap"]:
668 continue
669
670 # Track labels...
671 DataMap["DataLabels"].append(DataLabel)
672 DataMap["DataLabelsMap"][DataLabel] = DataLabel
673 DataMap["CanonicalDataLabelsMap"][DataLabel.lower()] = DataLabel
674
675 DataMap["StructureDataMap"][DataLabel] = False
676 DataMap["SMILESDataMap"][DataLabel] = False
677
678 if re.search("SMILES", DataLabel, re.I):
679 DataMap["StructureDataMap"][DataLabel] = True
680 DataMap["SMILESDataMap"][DataLabel] = True
681
682 def ValidateShowMolNameOption(DataMap):
683 """Validate show molecule name option."""
684
685 if not OptionsInfo["ShowMolName"]:
686 return
687
688 if not MiscUtil.CheckFileExt(OptionsInfo["Infile"],"sdf sd smi"):
689 OptionsInfo["ShowMolName"] = False
690 return
691
692 CanonicalDataLabel = OptionsInfo["ShowMolNameDataLabel"].lower()
693 if CanonicalDataLabel in DataMap["CanonicalDataLabelsMap"]:
694 OptionsInfo["ShowMolName"] = False
695 if not OptionsInfo["ShowMolNameAuto"]:
696 MiscUtil.PrintWarning("Ignoring \"--showMolName\" option: Data label \"Name\" corresponding to molecule name is already present in input file.")
697
698 def ValidateSpecifiedDataLabels(DataMap):
699 """Validate data labels used to specify highlighting data."""
700
701 ValidateSpecifiedDataLabelsForHighlightSMARTS(DataMap)
702
703 ValidateSpecifiedDataLabelsForHighlightValues(DataMap)
704 ValidateSpecifiedDataLabelsForHighlightRanges(DataMap)
705 ValidateSpecifiedDataLabelsForHighlightClasses(DataMap)
706
707 def ValidateSpecifiedDataLabelsForHighlightSMARTS(DataMap):
708 """Validate data labels used to specify highlighting SMARTS option."""
709
710 if OptionsInfo["HighlightSMARTSAllMode"]:
711 return
712
713 for DataLabel in OptionsInfo["HighlightSMARTSDataLabels"]:
714 if re.match("^Structure$", DataLabel, re.I):
715 continue
716
717 CanonicalDataLabel = DataLabel.lower()
718 if not CanonicalDataLabel in DataMap["CanonicalDataLabelsMap"]:
719 MiscUtil.PrintError("The data label specified, %s, using option \"--highlightSMARTS\" doesn't exist in input file." % DataLabel)
720
721 Label = DataMap["CanonicalDataLabelsMap"][CanonicalDataLabel]
722 if not DataMap["StructureDataMap"][Label]:
723 MiscUtil.PrintError("The data label specified, %s, using option \"--highlightSMARTS\" doesn't correspond to structure data: Valid structure data labels: SMILES in data label." % DataLabel)
724
725 def ValidateSpecifiedDataLabelsForHighlightValues(DataMap):
726 """Validate data labels used to specify highlighting values option."""
727
728 ValidateDataLabels("--highlightValues", DataMap, OptionsInfo["HighlightValuesLabels"])
729
730 def ValidateSpecifiedDataLabelsForHighlightRanges(DataMap):
731 """Validate data labels used to specify highlighting ranges option."""
732
733 ValidateDataLabels("--highlightRanges", DataMap, OptionsInfo["HighlightRangesLabels"])
734
735 def ValidateSpecifiedDataLabelsForHighlightClasses(DataMap):
736 """Validate data labels used to specify highlighting classes option."""
737
738 if OptionsInfo["HighlightClassesRules"] is None:
739 return
740
741 ValidDataLabelsList = []
742 NotValidDataLabelsList = []
743 for Label in OptionsInfo["HighlightClassesLabels"]:
744 ValidCanonicalLabel = None
745
746 for LabelSynonym in OptionsInfo["HighlightClassesSynonymsMap"][Label]:
747 CanonicalLabel = LabelSynonym.lower()
748
749 # Is this label already in use...
750 if CanonicalLabel in OptionsInfo["HighlightValuesCanonicalLabelsMap"]:
751 MiscUtil.PrintInfo("")
752 MiscUtil.PrintWarning("The data label, %s, for class, %s , in option \"--highlightValuesClasses\" has already been used in \"--highlightValues\" option. It'll be ignored during highlighting." % (LabelSynonym, OptionsInfo["HighlightClasses"]))
753 continue
754
755 if CanonicalLabel in OptionsInfo["HighlightRangesCanonicalLabelsMap"]:
756 MiscUtil.PrintInfo("")
757 MiscUtil.PrintWarning("The data label, %s, for class, %s , in option \"--highlightValuesClasses\" has already been used in \"--highlightValuesRanges\" option. It'll be ignored during highlighting." % (LabelSynonym, OptionsInfo["HighlightClasses"]))
758 continue
759
760 # Is this label present in input file...
761 if CanonicalLabel in DataMap["CanonicalDataLabelsMap"]:
762 ValidCanonicalLabel = CanonicalLabel
763 break
764
765 if ValidCanonicalLabel is None:
766 MiscUtil.PrintWarning("The data label or its synonyms - %s - for class, %s , in option \"--highlightValuesClasses\" either don't exist in input file or have already been used for highlighting in option \"--highlightValuesClasses\" or \"--highlightValuesRanges\". It'll be ignored during highlighting." % (MiscUtil.JoinWords(OptionsInfo["HighlightClassesSynonymsMap"][Label], ", "), OptionsInfo["HighlightClasses"]))
767 NotValidDataLabelsList.append(Label)
768 continue
769
770 # Track label...
771 OptionsInfo["HighlightClassesCanonicalLabelsMap"][ValidCanonicalLabel] = Label
772 ValidDataLabelsList.append(DataMap["CanonicalDataLabelsMap"][ValidCanonicalLabel])
773
774 ValidDataLabelsCount = len(ValidDataLabelsList)
775 NotValidDataLabelsCount = len(NotValidDataLabelsList)
776 DataLabelsCount = len(OptionsInfo["HighlightClassesLabels"])
777
778 if ValidDataLabelsCount == 0:
779 MiscUtil.PrintInfo("")
780 MiscUtil.PrintWarning("The data labels and their synonyms for class, %s , in option \"--highlightValuesClasses\" either don't exists in input file or have already been used for highlighting in option \"--highlightValuesClasses\" or \"--highlightValuesRanges\". No class highlighting will be performed. Missing data labels: %s" % (OptionsInfo["HighlightClasses"], MiscUtil.JoinWords(OptionsInfo["HighlightClassesLabels"], ", ")))
781 elif ValidDataLabelsCount < DataLabelsCount:
782 MiscUtil.PrintInfo("")
783 MiscUtil.PrintWarning("The class, %s, based highlighting specified using \"--highlightValuesClasses\" option will be performed using only, %d, out of, %d, data labels: %s\nThe rest of the data label(s) - %s - either don't exist in the input file or have aready been used for highlighting in option \"--highlightValuesClasses\" or \"--highlightValuesRanges\"." % (OptionsInfo["HighlightClasses"], ValidDataLabelsCount, DataLabelsCount, MiscUtil.JoinWords(ValidDataLabelsList, ", "), MiscUtil.JoinWords(NotValidDataLabelsList, ", ") ))
784
785 def ValidateDataLabels(OptionName, DataMap, DataLabels):
786 """Validate data labels."""
787
788 for DataLabel in DataLabels:
789 if re.match("^Structure$", DataLabel, re.I):
790 MiscUtil.PrintError("The data label specified, %s, using option \"-%s\" must not correspond to structure data. Structure label is not allowed." % (DataLabel, OptionName))
791
792 CanonicalDataLabel = DataLabel.lower()
793 if not CanonicalDataLabel in DataMap["CanonicalDataLabelsMap"]:
794 MiscUtil.PrintError("The data label specified, %s, using option \"%s\" doesn't exist in input file." % (DataLabel, OptionName))
795
796 Label = DataMap["CanonicalDataLabelsMap"][CanonicalDataLabel]
797 if DataMap["StructureDataMap"][Label]:
798 MiscUtil.PrintError("The data label specified, %s, using option \"%s\" must not correspond to structure data: Valid structure data labels contain \"SMILES\" in their name.." % (DataLabel, OptionName))
799
800 def SetupMolInLineSVGImageTag(Mol, HightlightAtomList):
801 """Setup a inline SVG image tag for molecule."""
802
803 SVGText = RDKitUtil.GetInlineSVGForMolecule(Mol, OptionsInfo["MolImageWidth"], OptionsInfo["MolImageHeight"], AtomListToHighlight = HightlightAtomList, Base64Encoded = OptionsInfo["MolImageEncoded"])
804
805 if OptionsInfo["MolImageEncoded"]:
806 SVGInlineImageTag = "img src=\"data:image/svg+xml;base64,\n%s\"" % SVGText
807 else:
808 SVGInlineImageTag = "img src=\"data:image/svg+xml;charset=UTF-8,\n%s\"" % SVGText
809
810 return SVGInlineImageTag
811
812 def SetupAtomListToHighlight(Mol, DataLabel):
813 """Set up atom list to highlight using specified SMARTS patterns."""
814
815 HighlightAtomList = None
816 if OptionsInfo["HighlightSMARTS"] is None:
817 return HighlightAtomList
818
819 if OptionsInfo["HighlightSMARTSAllMode"]:
820 PatternMol = OptionsInfo["HighlightSMARTSPatternMol"]
821 else:
822 CanonicalDataLabel = DataLabel.lower()
823 if not CanonicalDataLabel in OptionsInfo["HighlightSMARTSCanonicalDataLabelsMap"]:
824 return HighlightAtomList
825
826 Label = OptionsInfo["HighlightSMARTSCanonicalDataLabelsMap"][CanonicalDataLabel]
827 PatternMol = OptionsInfo["HighlightSMARTSPatternMolsMap"][Label]
828
829 # Get matched atom lists and flatten it...
830 MatchedAtomsLists = Mol.GetSubstructMatches(PatternMol)
831 MatchedAtoms = [ Atom for AtomsList in MatchedAtomsLists for Atom in AtomsList]
832
833 if len(MatchedAtoms):
834 HighlightAtomList = MatchedAtoms
835
836 return HighlightAtomList
837
838 def GetAlphanumeircValueHighlightBackgroundColor(DataLabel, DataValue, DataMap):
839 """Get background highlight color for a value."""
840
841 BackgroundColor = None
842 BackgroundColorType = None
843
844 CanonicalDataLabel =DataLabel.lower()
845 if CanonicalDataLabel in OptionsInfo["HighlightValuesCanonicalLabelsMap"]:
846 return GetBackgroundColorUsingHighlightValuesMode(DataLabel, DataValue, DataMap)
847 elif CanonicalDataLabel in OptionsInfo["HighlightRangesCanonicalLabelsMap"]:
848 return GetBackgroundColorUsingHighlightRangesMode(DataLabel, DataValue, DataMap)
849 elif CanonicalDataLabel in OptionsInfo["HighlightClassesCanonicalLabelsMap"]:
850 return GetBackgroundColorUsingHighlightClassesMode(DataLabel, DataValue, DataMap)
851 elif OptionsInfo["HighlightClassesRandom"]:
852 return GetBackgroundColorUsingRandomMode(DataLabel, DataValue, DataMap)
853
854 return (BackgroundColor, BackgroundColorType)
855
856 def GetBackgroundColorUsingHighlightValuesMode(DataLabel, DataValue, DataMap):
857 """Get background highlight color for a value."""
858
859 BackgroundColor = None
860 BackgroundColorType = None
861
862 CanonicalDataLabel =DataLabel.lower()
863 if not CanonicalDataLabel in OptionsInfo["HighlightValuesCanonicalLabelsMap"]:
864 return (BackgroundColor, BackgroundColorType)
865
866 Label = OptionsInfo["HighlightValuesCanonicalLabelsMap"][CanonicalDataLabel]
867 DataType = OptionsInfo["HighlightValuesTypesMap"][Label]
868 Criterion = OptionsInfo["HighlightValuesCriteriaMap"][Label]
869 CriterionValue = OptionsInfo["HighlightValuesCriteriaValuesMap"][Label]
870
871 return GetBackgroundColorForHighlightingValue(DataLabel, DataValue, DataType, Criterion, CriterionValue)
872
873 def GetBackgroundColorUsingHighlightClassesMode(DataLabel, DataValue, DataMap):
874 """Get background highlight color for a value."""
875
876 BackgroundColor = None
877 BackgroundColorType = None
878
879 CanonicalDataLabel =DataLabel.lower()
880 if not CanonicalDataLabel in OptionsInfo["HighlightClassesCanonicalLabelsMap"]:
881 return (BackgroundColor, BackgroundColorType)
882
883 Label = OptionsInfo["HighlightClassesCanonicalLabelsMap"][CanonicalDataLabel]
884 DataType = OptionsInfo["HighlightClassesTypesMap"][Label]
885 Criterion = OptionsInfo["HighlightClassesCriteriaMap"][Label]
886 CriterionValue = OptionsInfo["HighlightClassesCriteriaValuesMap"][Label]
887
888 return GetBackgroundColorForHighlightingValue(DataLabel, DataValue, DataType, Criterion, CriterionValue)
889
890 def GetBackgroundColorForHighlightingValue(DataLabel, DataValue, DataType, Criterion, CriterionValue):
891 """Get background color for highlighting a value."""
892
893 ValueOkay = False
894 if re.match("^numeric$", DataType, re.I):
895 if not MiscUtil.IsNumber(DataValue):
896 MiscUtil.PrintWarning("Ignoring data value, %s, for data label, %s, during numeric highlighting: It must be a number" % (DataValue, DataLabel))
897 return (BackgroundColor, BackgroundColorType)
898
899 DataValue = float(DataValue)
900 if re.match("^gt$", Criterion, re.I):
901 ValueOkay = True if DataValue > CriterionValue else False
902 elif re.match("^lt$", Criterion, re.I):
903 ValueOkay = True if DataValue < CriterionValue else False
904 elif re.match("^ge$", Criterion, re.I):
905 ValueOkay = True if DataValue >= CriterionValue else False
906 elif re.match("^le$", Criterion, re.I):
907 ValueOkay = True if DataValue <= CriterionValue else False
908 elif re.match("^eq$", Criterion, re.I):
909 ValueOkay = True if DataValue == CriterionValue else False
910 elif re.match("^ne$", Criterion, re.I):
911 ValueOkay = True if DataValue != CriterionValue else False
912 else:
913 return (BackgroundColor, BackgroundColorType)
914 elif re.match("^text$", DataType, re.I):
915 DataValue = "%s" % DataValue
916 if re.match("^gt$", Criterion, re.I):
917 ValueOkay = True if DataValue > CriterionValue else False
918 elif re.match("^lt$", Criterion, re.I):
919 ValueOkay = True if DataValue < CriterionValue else False
920 elif re.match("^ge$", Criterion, re.I):
921 ValueOkay = True if DataValue >= CriterionValue else False
922 elif re.match("^le$", Criterion, re.I):
923 ValueOkay = True if DataValue <= CriterionValue else False
924 elif re.match("^eq$", Criterion, re.I):
925 ValueOkay = True if DataValue == CriterionValue else False
926 elif re.match("^ne$", Criterion, re.I):
927 ValueOkay = True if DataValue != CriterionValue else False
928 else:
929 return (BackgroundColor, BackgroundColorType)
930 elif re.match("^regex$", DataType, re.I):
931 DataValue = "%s" % DataValue
932 if re.match("^eq$", Criterion, re.I):
933 ValueOkay = True if re.search("%s" % CriterionValue, DataValue, re.I) else False
934 elif re.match("^ne$", Criterion, re.I):
935 ValueOkay = False if re.search("%s" % CriterionValue, DataValue, re.I) else True
936 else:
937 return (BackgroundColor, BackgroundColorType)
938
939 BackgroundColor = OptionsInfo["HighlightColorsList"][0] if ValueOkay else OptionsInfo["HighlightColorsList"][1]
940 BackgroundColorType = OptionsInfo["HighlightColorsType"]
941
942 return (BackgroundColor, BackgroundColorType)
943
944 def GetBackgroundColorUsingHighlightRangesMode(DataLabel, DataValue, DataMap):
945 """Get background highlight color for value range."""
946
947 BackgroundColor = None
948 BackgroundColorType = None
949
950 CanonicalDataLabel =DataLabel.lower()
951 if not CanonicalDataLabel in OptionsInfo["HighlightRangesCanonicalLabelsMap"]:
952 return (BackgroundColor, BackgroundColorType)
953
954 Label = OptionsInfo["HighlightRangesCanonicalLabelsMap"][CanonicalDataLabel]
955 DataType = OptionsInfo["HighlightRangesTypesMap"][Label]
956 CriterionLower = OptionsInfo["HighlightRangesCriteriaLowerMap"][Label]
957 CriterionLowerValue = OptionsInfo["HighlightRangesCriteriaLowerValuesMap"][Label]
958 CriterionUpper = OptionsInfo["HighlightRangesCriteriaUpperMap"][Label]
959 CriterionUpperValue = OptionsInfo["HighlightRangesCriteriaUpperValuesMap"][Label]
960
961 if re.match("^numeric$", DataType, re.I):
962 if not MiscUtil.IsNumber(DataValue):
963 MiscUtil.PrintWarning("Ignoring data value, %s, for data label, %s, during numeric highlighting: It must be a number" % (DataValue, DataLabel))
964 return (BackgroundColor, BackgroundColorType)
965
966 DataValue = float(DataValue)
967 ColorIndex = 1
968
969 if DataValue < CriterionLowerValue and re.match("^lt$", CriterionLower, re.I):
970 ColorIndex = 0
971 elif DataValue <= CriterionLowerValue and re.match("^le$", CriterionLower, re.I):
972 ColorIndex = 0
973 elif DataValue > CriterionUpperValue and re.match("^gt$", CriterionUpper, re.I):
974 ColorIndex = 2
975 elif DataValue >= CriterionUpperValue and re.match("^ge$", CriterionUpper, re.I):
976 ColorIndex = 2
977 elif re.match("^text$", DataType, re.I):
978 DataValue = "%s" % DataValue
979 ColorIndex = 1
980
981 if DataValue < CriterionLowerValue and re.match("^lt$", CriterionLower, re.I):
982 ColorIndex = 0
983 elif DataValue <= CriterionLowerValue and re.match("^le$", CriterionLower, re.I):
984 ColorIndex = 0
985 elif DataValue > CriterionUpperValue and re.match("^gt$", CriterionUpper, re.I):
986 ColorIndex = 2
987 elif DataValue >= CriterionUpperValue and re.match("^ge$", CriterionUpper, re.I):
988 ColorIndex = 2
989 else:
990 return (BackgroundColor, BackgroundColorType)
991
992 BackgroundColor = OptionsInfo["HighlightColorsRangesList"][ColorIndex]
993 BackgroundColorType = OptionsInfo["HighlightColorsRangesType"]
994
995 return (BackgroundColor, BackgroundColorType)
996
997 def GetBackgroundColorUsingRandomMode(DataLabel, DataValue, DataMap):
998 """Get a random background highlight color for a value."""
999
1000 BackgroundColor = random.choice(OptionsInfo["HighlightColorsRandomList"])
1001 BackgroundColorType = OptionsInfo["HighlightColorsRandomType"]
1002
1003 return (BackgroundColor, BackgroundColorType)
1004
1005 def SetupAlphanumericTableDataValue(Writer, DataValue, BackgroundColor, BackgroundColorType):
1006 """Set up alphanumeric data value for a table cell."""
1007
1008 WrappedDataValue = "%s" % DataValue
1009
1010 # Look for new lines...
1011 Delim = "<br/>"
1012 if re.search("(\r\n|\r|\n)", WrappedDataValue):
1013 WrappedDataValue = re.sub("(\r\n|\r|\n)", "<br/>", DataValue)
1014
1015 # Wrap text...
1016 if OptionsInfo["WrapText"] and len(WrappedDataValue) > OptionsInfo["WrapTextWidth"]:
1017 WrappedDataLines = []
1018 for DataLine in WrappedDataValue.split("<br/>"):
1019 WrappedDataLine = MiscUtil.WrapText(DataLine, "<br/>", OptionsInfo["WrapTextWidth"])
1020 WrappedDataLines.append(WrappedDataLine)
1021
1022 WrappedDataValue = "<br/>".join(WrappedDataLines)
1023
1024 # Highlight value...
1025 if BackgroundColor is not None:
1026 ColorTypeTag = GetBackgroundColorTypeTagForTableValue(BackgroundColor, BackgroundColorType)
1027 Writer.write(""" <td %s = "%s">%s</td>\n""" % (ColorTypeTag, BackgroundColor, WrappedDataValue))
1028 else:
1029 Writer.write(""" <td>%s</td>\n""" % WrappedDataValue)
1030
1031 def GetBackgroundColorTypeTagForTableValue(Color, ColorType):
1032 """Setup color type tage for setting background of a table value."""
1033
1034 ColorTypeTag = "class" if re.match("^colorclass", ColorType, re.I) else "bgcolor"
1035
1036 return ColorTypeTag
1037
1038 def PerformAlignment(ValidMols):
1039 """Perform alignment to a common template specified by a SMARTS pattern."""
1040
1041 if OptionsInfo["AlignmentSMARTSPattern"] is None:
1042 return
1043
1044 MiscUtil.PrintInfo("\nPerforming alignment for primary structure data...")
1045
1046 PatternMol = Chem.MolFromSmarts(OptionsInfo["AlignmentSMARTSPattern"])
1047 AllChem.Compute2DCoords(PatternMol)
1048
1049 MatchedValidMols = [ValidMol for ValidMol in ValidMols if ValidMol.HasSubstructMatch(PatternMol)]
1050 for ValidMol in MatchedValidMols:
1051 AllChem.GenerateDepictionMatching2DStructure(ValidMol, PatternMol)
1052
1053 def ProcessHighlightSMARTSOption():
1054 """Process highlight SMARTS option."""
1055
1056 OptionsInfo["HighlightSMARTS"] = None
1057 OptionsInfo["HighlightSMARTSAllMode"] = False
1058 OptionsInfo["HighlightSMARTSPatternMol"] = None
1059
1060 OptionsInfo["HighlightSMARTSDataLabels"] = []
1061 OptionsInfo["HighlightSMARTSDataLabelsMap"] = {}
1062
1063 OptionsInfo["HighlightSMARTSCanonicalDataLabelsMap"] = {}
1064 OptionsInfo["HighlightSMARTSPatternsMap"] = {}
1065 OptionsInfo["HighlightSMARTSPatternMolsMap"] = {}
1066
1067 OptionsInfo["HighlightSMARTSDelim"] = Options["--highlightSMARTSDelim"]
1068
1069 if re.match("^None$", Options["--highlightSMARTS"], re.I):
1070 # Nothing to proecess...
1071 return
1072
1073 HighlightSMARTS = Options["--highlightSMARTS"].strip()
1074 if not HighlightSMARTS:
1075 MiscUtil.PrintError("No valid values specified using \"--highlightSMARTS\" option.")
1076
1077 OptionsInfo["HighlightSMARTS"] = HighlightSMARTS
1078 HighlightSMARTSWords = HighlightSMARTS.split(OptionsInfo["HighlightSMARTSDelim"])
1079
1080 if len(HighlightSMARTSWords) == 1:
1081 PatternMol = Chem.MolFromSmarts(HighlightSMARTS)
1082 if PatternMol is None:
1083 MiscUtil.PrintError("The value specified, %s, using option \"--highlightSMARTS\" is not a valid SMARTS: Failed to create pattern molecule" % Options["--highlightSMARTS"])
1084 OptionsInfo["HighlightSMARTSAllMode"] = True
1085 OptionsInfo["HighlightSMARTSPatternMol"] = PatternMol
1086 return
1087
1088 if len(HighlightSMARTSWords) % 2:
1089 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified using \"--highlightSMARTS\" option must be an even number." % (len(HighlightSMARTSWords)))
1090
1091 HighlightSMARTSAllMode = False
1092
1093 for Index in range(0, len(HighlightSMARTSWords), 2):
1094 DataLabel = HighlightSMARTSWords[Index].strip()
1095 SMARTSPattern = HighlightSMARTSWords[Index + 1].strip()
1096
1097 PatternMol = Chem.MolFromSmarts(SMARTSPattern)
1098 if PatternMol is None:
1099 MiscUtil.PrintError("The value specified, %s, using option \"--highlightSMARTS\" is not a valid SMARTS: Failed to create pattern molecule" % Options["--highlightSMARTS"])
1100
1101 if DataLabel in OptionsInfo["HighlightSMARTSDataLabelsMap"]:
1102 MiscUtil.PrintError("The datalabel, %s, specified in pair, \"%s, %s\", using option \"--highlightSMARTS\" is not a valid: Multiple occurences of data label" % (DataLabel, DataLabel, SMARTSPattern))
1103
1104 OptionsInfo["HighlightSMARTSDataLabels"].append(DataLabel)
1105 OptionsInfo["HighlightSMARTSDataLabelsMap"][DataLabel] = DataLabel
1106 OptionsInfo["HighlightSMARTSCanonicalDataLabelsMap"][DataLabel.lower()] = DataLabel
1107 OptionsInfo["HighlightSMARTSPatternsMap"][DataLabel] = SMARTSPattern
1108 OptionsInfo["HighlightSMARTSPatternMolsMap"][DataLabel] = PatternMol
1109
1110 def ProcessHighlightDataOptions():
1111 """Process highlight values and colors option."""
1112
1113 ProcessHighlightValuesOption()
1114 ProcessHighlightValuesRangesOption()
1115 ProcessHighlightValuesClassesOption()
1116
1117 ProcessHighlightColorsOption()
1118 ProcessHighlightColorsRangesOption()
1119 ProcessHighlightColorsRandomOption()
1120
1121 def ProcessHighlightValuesOption():
1122 """Process highlight values option."""
1123
1124 OptionsInfo["HighlightValues"] = None
1125 OptionsInfo["HighlightValuesLabels"] = []
1126
1127 OptionsInfo["HighlightValuesLabelsMap"] = {}
1128 OptionsInfo["HighlightValuesCanonicalLabelsMap"] = {}
1129
1130 OptionsInfo["HighlightValuesTypesMap"] = {}
1131 OptionsInfo["HighlightValuesCriteriaMap"] = {}
1132 OptionsInfo["HighlightValuesCriteriaValuesMap"] = {}
1133
1134 HighlightValues = Options["--highlightValues"].strip()
1135 if re.match("^None$", HighlightValues, re.I):
1136 return
1137
1138 OptionsInfo["HighlightValues"] = HighlightValues
1139 HighlightValuesWords = HighlightValues.split(",")
1140
1141 if len(HighlightValuesWords) % 4:
1142 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified using \"--highlightValues\" option must be a multiple of 4." % (len(HighlightValuesWords)))
1143
1144 for Index in range(0, len(HighlightValuesWords), 4):
1145 DataLabel = HighlightValuesWords[Index].strip()
1146 DataType = HighlightValuesWords[Index + 1].strip()
1147 DataCriterion = HighlightValuesWords[Index + 2].strip()
1148 DataValue = HighlightValuesWords[Index + 3].strip()
1149
1150 if not re.match("^(numeric|text|regex)$", DataType, re.I):
1151 MiscUtil.PrintError("The data type, %s, specified in quratet \"%s,%s,%s,%s\", using \"--highlightValues\" option is not valid. Supported values: numeric, regex or text." % (DataType, DataLabel, DataType, DataCriterion, DataValue))
1152
1153 if re.match("^regex$", DataType, re.I):
1154 if not re.match("^(eq|ne)$", DataCriterion, re.I):
1155 MiscUtil.PrintError("The data criterion, %s, specified in quratet \"%s,%s,%s,%s\", using \"--highlightValues\" option is not valid. Supported values: eq or ne" % (DataType, DataLabel, DataType, DataCriterion, DataValue))
1156 else:
1157 if not re.match("^(gt|lt|ge|le|eq|ne)$", DataCriterion, re.I):
1158 MiscUtil.PrintError("The data criterion, %s, specified in quratet \"%s,%s,%s,%s\", using \"--highlightValues\" option is not valid. Supported values: gt, lt, ge, le, eq, or ne." % (DataType, DataLabel, DataType, DataCriterion, DataValue))
1159
1160 # Check criterion value...
1161 if re.match("^numeric$", DataType, re.I):
1162 if not MiscUtil.IsNumber(DataValue):
1163 MiscUtil.PrintError("The data value, %s, specified in quratet \"%s,%s,%s,%s\", using \"--highlightValues\" option is not valid. It must be a number for data type, %s" % (DataType, DataLabel, DataType, DataCriterion, DataValue, DataType))
1164 DataValue = float(DataValue)
1165
1166 # Track values...
1167 if DataLabel in OptionsInfo["HighlightValuesLabelsMap"]:
1168 MiscUtil.PrintError("The data label, %s, specified in quratet \"%s,%s,%s,%s\", using \"--highlightValues\" option is not valid: Multiple occurences of data label" % (DataLabel, DataLabel, DataType, DataCriterion, DataValue))
1169
1170 OptionsInfo["HighlightValuesLabels"].append(DataLabel)
1171 OptionsInfo["HighlightValuesLabelsMap"][DataLabel] = DataLabel
1172 OptionsInfo["HighlightValuesCanonicalLabelsMap"][DataLabel.lower()] = DataLabel
1173
1174 OptionsInfo["HighlightValuesTypesMap"][DataLabel] = DataType
1175 OptionsInfo["HighlightValuesCriteriaMap"][DataLabel] = DataCriterion
1176 OptionsInfo["HighlightValuesCriteriaValuesMap"][DataLabel] = DataValue
1177
1178 def ProcessHighlightValuesRangesOption():
1179 """Process highlight values ranges option."""
1180
1181 OptionsInfo["HighlightRanges"] = None
1182 OptionsInfo["HighlightRangesLabels"] = []
1183
1184 OptionsInfo["HighlightRangesLabelsMap"] = {}
1185 OptionsInfo["HighlightRangesCanonicalLabelsMap"] = {}
1186
1187 OptionsInfo["HighlightRangesTypesMap"] = {}
1188 OptionsInfo["HighlightRangesCriteriaLowerMap"] = {}
1189 OptionsInfo["HighlightRangesCriteriaLowerValuesMap"] = {}
1190 OptionsInfo["HighlightRangesCriteriaUpperMap"] = {}
1191 OptionsInfo["HighlightRangesCriteriaUpperValuesMap"] = {}
1192
1193 HighlightRanges = Options["--highlightValuesRanges"].strip()
1194 if re.match("^None$", HighlightRanges, re.I):
1195 return
1196
1197 OptionsInfo["HighlightRanges"] = HighlightRanges
1198 HighlightRangesWords = HighlightRanges.split(",")
1199
1200 if len(HighlightRangesWords) % 6:
1201 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified in sextet \"%s\" using \"--highlightValuesRanges\" option must be a multiple of 6." % (len(HighlightRangesWords), HighlightRanges))
1202
1203 for Index in range(0, len(HighlightRangesWords), 6):
1204 DataLabel = HighlightRangesWords[Index].strip()
1205 DataType = HighlightRangesWords[Index + 1].strip()
1206 LowerBoundDataCriterion = HighlightRangesWords[Index + 2].strip()
1207 LowerBoundDataValue = HighlightRangesWords[Index + 3].strip()
1208 UpperBoundDataCriterion = HighlightRangesWords[Index + 4].strip()
1209 UpperBoundDataValue = HighlightRangesWords[Index + 5].strip()
1210
1211 SpecifiedSextet = "%s,%s,%s,%s,%s,%s" % (DataLabel, DataType, LowerBoundDataCriterion, LowerBoundDataValue, UpperBoundDataCriterion, UpperBoundDataValue)
1212
1213 CanonicalDataLabel = DataLabel.lower()
1214 if CanonicalDataLabel in OptionsInfo["HighlightValuesCanonicalLabelsMap"]:
1215 MiscUtil.PrintError("The data label specified, %s, using option \"--highlightRanges\" has already been used in \"--highlightValues\" option" % DataLabel)
1216
1217 if not re.match("^(numeric|text)$", DataType, re.I):
1218 MiscUtil.PrintError("The data type, %s, specified in sextet \"%s\" using \"--highlightValuesRanges\" option is not valid. Supported values: numeric text." % (DataType, SpecifiedSextet))
1219
1220 if not re.match("^(lt|le)$", LowerBoundDataCriterion, re.I):
1221 MiscUtil.PrintError("The lower bound criterion, %s, specified in sextet \"%s\" using \"--highlightValuesRanges\" option is not valid. Supported values: lt or le." % (LowerBoundDataCriterion, SpecifiedSextet))
1222
1223 if not re.match("^(gt|ge)$", UpperBoundDataCriterion, re.I):
1224 MiscUtil.PrintError("The upper bound criterion, %s, specified in sextet \"%s\" using \"--highlightValuesRanges\" option is not valid. Supported values: gt or ge." % (UpperBoundDataCriterion, SpecifiedSextet))
1225
1226 if re.match("^numeric$", DataType, re.I):
1227 if not MiscUtil.IsNumber(LowerBoundDataValue):
1228 MiscUtil.PrintError("The lower bound data value, %s, specified in sextet \"%s\", using \"--highlightValuesRanges\" option is not valid. It must be a number for \"%s\" data type." % (LowerBoundDataValue, SpecifiedSextet, DataType))
1229
1230 if not MiscUtil.IsNumber(UpperBoundDataValue):
1231 MiscUtil.PrintError("The upper bound data value, %s, specified in sextet \"%s\", using \"--highlightValuesRanges\" option is not valid. It must be a number for \"%s\"data type." % (UpperBoundDataValue, SpecifiedSextet, DataType))
1232
1233 if float(LowerBoundDataValue) >= float(UpperBoundDataValue):
1234 MiscUtil.PrintError("The lower bound data value, %s, must be less than upper bound value, %s, specified in sextet \"%s\" using \"--highlightValuesRanges\" option." % (LowerBoundDataValue, UpperBoundDataValue, SpecifiedSextet))
1235
1236 LowerBoundDataValue = float(LowerBoundDataValue)
1237 UpperBoundDataValue = float(UpperBoundDataValue)
1238 else:
1239 if LowerBoundDataValue >= UpperBoundDataValue:
1240 MiscUtil.PrintError("The lower bound data value, %s, must be less than upper bound value, %s, specified in sextet \"%s\", using \"--highlightValuesRanges\" option is not valid. It must be a number for data type, %s" % (LowerBoundDataValue, UpperBoundDataValue, SpecifiedSextet, DataType))
1241
1242 # Track values...
1243 if DataLabel in OptionsInfo["HighlightRangesLabelsMap"]:
1244 MiscUtil.PrintError("The data label, %s, specified in sextet \"%s\", using \"--highlightValuesRanges\" option is not valid. Multiple occurences of data label" % (DataLabel, SpecifiedSextet))
1245
1246 OptionsInfo["HighlightRangesLabels"].append(DataLabel)
1247 OptionsInfo["HighlightRangesLabelsMap"][DataLabel] = DataLabel
1248 OptionsInfo["HighlightRangesCanonicalLabelsMap"][CanonicalDataLabel] = DataLabel
1249
1250 OptionsInfo["HighlightRangesTypesMap"][DataLabel] = DataType
1251
1252 OptionsInfo["HighlightRangesCriteriaLowerMap"][DataLabel] = LowerBoundDataCriterion
1253 OptionsInfo["HighlightRangesCriteriaLowerValuesMap"][DataLabel] = LowerBoundDataValue
1254 OptionsInfo["HighlightRangesCriteriaUpperMap"][DataLabel] = UpperBoundDataCriterion
1255 OptionsInfo["HighlightRangesCriteriaUpperValuesMap"][DataLabel] = UpperBoundDataValue
1256
1257 def ProcessHighlightValuesClassesOption():
1258 """Process highlight values classes option."""
1259
1260 OptionsInfo["HighlightClasses"] = None
1261 OptionsInfo["HighlightClassesRules"] = None
1262 OptionsInfo["HighlightClassesSynonymsMap"] = None
1263 OptionsInfo["HighlightClassesRandom"] = False
1264
1265 OptionsInfo["HighlightClassesLabels"] = []
1266 OptionsInfo["HighlightClassesLabelsMap"] = {}
1267 OptionsInfo["HighlightClassesCanonicalLabelsMap"] = {}
1268
1269 OptionsInfo["HighlightClassesTypesMap"] = {}
1270 OptionsInfo["HighlightClassesCriteriaMap"] = {}
1271 OptionsInfo["HighlightClassesCriteriaValuesMap"] = {}
1272
1273 HighlightClasses = Options["--highlightValuesClasses"].strip()
1274 if re.match("^None$", HighlightClasses, re.I):
1275 return
1276
1277 OptionsInfo["HighlightClasses"] = HighlightClasses
1278
1279 if re.match("^RuleOf5$", HighlightClasses, re.I):
1280 HighlightClassessRules = "MolecularWeight,numeric,le,500,HydrogenBondDonors,numeric,le,5,HydrogenBondAcceptors,numeric,le,10,LogP,numeric,le,5"
1281 elif re.match("^RuleOf3$", HighlightClasses, re.I):
1282 HighlightClassessRules = "MolecularWeight,numeric,le,300,HydrogenBondDonors,numeric,le,3,HydrogenBondAcceptors,numeric,le,3,LogP,numeric,le,3,RotatableBonds,numeric,le,3,TPSA,numeric,le,60"
1283 elif re.match("^DrugLike$", HighlightClasses, re.I):
1284 HighlightClassessRules = "MolecularWeight,numeric,le,500,HydrogenBondDonors,numeric,le,5,HydrogenBondAcceptors,numeric,le,10,LogP,numeric,le,5,RotatableBonds,numeric,le,10,TPSA,numeric,le,140"
1285 elif re.match("^Random$", HighlightClasses, re.I):
1286 if OptionsInfo["HighlightValues"] is not None:
1287 MiscUtil.PrintError("The value specified, %s, using option \"--highlightValuesClasses\" is not allowed in conjunction with \"--highlightValues\" option." % HighlightClasses)
1288 if OptionsInfo["HighlightRanges"] is not None:
1289 MiscUtil.PrintError("The value specified, %s, using option \"--highlightValuesClasses\" is not allowed in conjunction with \"--highlightRanges\" option ." % HighlightClasses)
1290
1291 OptionsInfo["HighlightClassesRandom"] = True
1292 return
1293 else:
1294 MiscUtil.PrintError("The value specified, %d, using option \"--highlightValuesClasses\" is not supported." % HighlightClasses)
1295 return
1296
1297 OptionsInfo["HighlightClassesRules"] = HighlightClassessRules
1298
1299 # Process rules for highlighting values...
1300 HighlightClassesWords = HighlightClassessRules.split(",")
1301 for Index in range(0, len(HighlightClassesWords), 4):
1302 DataLabel = HighlightClassesWords[Index].strip()
1303 DataType = HighlightClassesWords[Index + 1].strip()
1304 DataCriterion = HighlightClassesWords[Index + 2].strip()
1305 DataValue = HighlightClassesWords[Index + 3].strip()
1306
1307 DataValue = float(DataValue)
1308
1309 if DataLabel in OptionsInfo["HighlightClassesLabelsMap"]:
1310 MiscUtil.PrintWarning("Ignoring duplicate datalabel, %s, specified in highlighting values rule for class, %s, in \"--highlightClassesValue\" option..." % (DataLabel, HighlightClasses))
1311 continue
1312
1313 OptionsInfo["HighlightClassesLabels"].append(DataLabel)
1314 OptionsInfo["HighlightClassesLabelsMap"][DataLabel] = DataLabel
1315
1316 OptionsInfo["HighlightClassesTypesMap"][DataLabel] = DataType
1317 OptionsInfo["HighlightClassesCriteriaMap"][DataLabel] = DataCriterion
1318 OptionsInfo["HighlightClassesCriteriaValuesMap"][DataLabel] = DataValue
1319
1320 # Set up synonyms for data labels corresponding to physicochemical properties
1321 # calculated by MayaChemTools and RDKit...
1322 OptionsInfo["HighlightClassesSynonymsMap"] = {}
1323 OptionsInfo["HighlightClassesSynonymsMap"]["MolecularWeight"] = ["MolecularWeight", "MolWt"]
1324 OptionsInfo["HighlightClassesSynonymsMap"]["HydrogenBondDonors"] = ["HydrogenBondDonors", "NHOHCount"]
1325 OptionsInfo["HighlightClassesSynonymsMap"]["HydrogenBondAcceptors"] = ["HydrogenBondAcceptors", "NOCount"]
1326 OptionsInfo["HighlightClassesSynonymsMap"]["LogP"] = ["SLogP", "MolLogP"]
1327 OptionsInfo["HighlightClassesSynonymsMap"]["RotatableBonds"] = ["RotatableBonds", "NumRotatableBonds"]
1328 OptionsInfo["HighlightClassesSynonymsMap"]["TPSA"] = ["TPSA", "TPSA"]
1329
1330 def ProcessHighlightColorsOption():
1331 """Process highlight colors option."""
1332
1333 OptionsInfo["HighlightColors"] = None
1334 OptionsInfo["HighlightColorsType"] = None
1335 OptionsInfo["HighlightColorsList"] = None
1336
1337 HighlightColors = "colorclass,table-success, table-danger"
1338 if not re.match("^auto$", Options["--highlightColors"], re.I):
1339 HighlightColors = Options["--highlightColors"].strip()
1340 if MiscUtil.IsEmpty(HighlightColors):
1341 MiscUtil.PrintError("The value specified using \"--highlightColors\" is empty.")
1342
1343 OptionsInfo["HighlightColors"] = re.sub(" ", "", HighlightColors)
1344 HighlightColorsList = [Color.lower() for Color in OptionsInfo["HighlightColors"].split(",")]
1345
1346 if len(HighlightColorsList) != 3:
1347 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified using \"--highlightColors\" option must be 3." % (len(HighlightColorsList)))
1348
1349 ColorsType, Color1, Color2 = HighlightColorsList
1350 if not re.match("^(colorclass|colorspec)$", ColorsType, re.I):
1351 MiscUtil.PrintError("The color type, %s, specified using \"--highlightColors\" option is not valid. Supported values: colorclass or colorspec." % ColorsType)
1352
1353 ColorsList = [Color1, Color2]
1354 if re.match("^colorclass$", ColorsType, re.I):
1355 CheckOptionTableClassColorValues("--highlightColors", ColorsList)
1356
1357 OptionsInfo["HighlightColorsList"] = ColorsList
1358 OptionsInfo["HighlightColorsType"] = ColorsType
1359
1360 def ProcessHighlightColorsRangesOption():
1361 """Process highlight colors ranges option."""
1362
1363 OptionsInfo["HighlightColorsRanges"] = None
1364 OptionsInfo["HighlightColorsRangesType"] = None
1365 OptionsInfo["HighlightColorsRangesList"] = None
1366
1367 HighlightColors = "colorclass,table-success, table-warning, table-danger"
1368 if not re.match("^auto$", Options["--highlightColorsRanges"], re.I):
1369 HighlightColors = Options["--highlightColorsRanges"].strip()
1370 if MiscUtil.IsEmpty(HighlightColors):
1371 MiscUtil.PrintError("The value specified using \"--highlightColorsRanges\" is empty.")
1372
1373 OptionsInfo["HighlightColorsRanges"] = re.sub(" ", "", HighlightColors)
1374 HighlightColorsList = [Color.lower() for Color in OptionsInfo["HighlightColorsRanges"].split(",")]
1375
1376 if len(HighlightColorsList) != 4:
1377 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified using \"--highlightColorsRanges\" option must be 4." % (len(HighlightColorsList)))
1378
1379 ColorsType, Color1, Color2, Color3 = HighlightColorsList
1380 if not re.match("^(colorclass|colorspec)$", ColorsType, re.I):
1381 MiscUtil.PrintError("The color type, %s, specified using \"--highlightColorsRanges\" option is not valid. Supported values: colorclass or colorspec." % ColorsType)
1382
1383 ColorsList = [Color1, Color2, Color3]
1384 if re.match("^colorclass$", ColorsType, re.I):
1385 CheckOptionTableClassColorValues("--highlightColorsRanges", ColorsList)
1386
1387 OptionsInfo["HighlightColorsRangesList"] = ColorsList
1388 OptionsInfo["HighlightColorsRangesType"] = ColorsType
1389
1390 def ProcessHighlightColorsRandomOption():
1391 """Process highlight colors random option."""
1392
1393 OptionsInfo["HighlightColorsRandom"] = None
1394 OptionsInfo["HighlightColorsRandomType"] = None
1395 OptionsInfo["HighlightColorsRandomList"] = None
1396
1397 HighlightColors = "colorclass,table-primary,table-success,table-danger,table-info,table-warning,table-secondary"
1398 if not re.match("^auto$", Options["--highlightColorsRandom"], re.I):
1399 HighlightColors = Options["--highlightColorsRandom"].strip()
1400 if MiscUtil.IsEmpty(HighlightColors):
1401 MiscUtil.PrintError("The value specified using \"--highlightColorsRandom\" is empty.")
1402
1403 OptionsInfo["HighlightColorsRandom"] = re.sub(" ", "", HighlightColors)
1404 HighlightColorsList = [Color.lower() for Color in OptionsInfo["HighlightColorsRandom"].split(",")]
1405
1406 if len(HighlightColorsList) <= 1:
1407 MiscUtil.PrintError("The number of comma delimited paramater names and values, %d, specified using \"--highlightColorsRandom\" option must be > 1." % (len(HighlightColorsList)))
1408
1409 ColorsType = HighlightColorsList[0]
1410 ColorsList = HighlightColorsList[1:]
1411
1412 if not re.match("^(colorclass|colorspec)$", ColorsType, re.I):
1413 MiscUtil.PrintError("The color type, %s, specified using \"--highlightColorsRandim\" option is not valid. Supported values: colorclass or colorspec." % ColorsType)
1414
1415 if re.match("^colorclass$", ColorsType, re.I):
1416 CheckOptionTableClassColorValues("--highlightColorsRandom", ColorsList)
1417
1418 OptionsInfo["HighlightColorsRandomList"] = ColorsList
1419 OptionsInfo["HighlightColorsRandomType"] = ColorsType
1420
1421 def CheckOptionTableClassColorValues(OptionName, ColorsList):
1422 """Check names of table color classes and issue a warning for unknown names."""
1423
1424 TableClassColors = ["thead-dark", "thead-light", "table-primary", "table-success", "table-danger", "table-info", "table-warning", "table-active", "table-secondary", "table-light", "table-dark", "bg-primary", "bg-success", "bg-danger", "bg-info", "bg-warning", "bg-secondary", "bg-dark", "bg-light"]
1425
1426 for Color in ColorsList:
1427 if not Color in TableClassColors:
1428 MiscUtil.PrintWarning("The color class name, %s, specified using option \"%s\" appears to be a unknown name..." % (Color, OptionName))
1429
1430 def ProcessOptions():
1431 """Process and validate command line arguments and options."""
1432
1433 MiscUtil.PrintInfo("Processing options...")
1434
1435 # Validate options...
1436 ValidateOptions()
1437
1438 OptionsInfo["Infile"] = Options["--infile"]
1439 OptionsInfo["Outfile"] = Options["--outfile"]
1440 OptionsInfo["Overwrite"] = Options["--overwrite"]
1441
1442 # No need for any RDKit specific --outfileParams....
1443 OptionsInfo["InfileParams"] = MiscUtil.ProcessOptionInfileParameters("--infileParams", Options["--infileParams"], OptionsInfo["Infile"])
1444
1445 AlignmentSMARTSPattern = None
1446 if not re.match("^None$", Options["--alignmentSMARTS"], re.I):
1447 AlignmentSMARTSPattern = Options["--alignmentSMARTS"]
1448 OptionsInfo["AlignmentSMARTSPattern"] = AlignmentSMARTSPattern
1449
1450 Compute2DCoords = True
1451 if re.match("^no$", Options["--compute2DCoords"], re.I):
1452 Compute2DCoords = False
1453 OptionsInfo["Compute2DCoords"] = Compute2DCoords
1454
1455 CounterCol = True
1456 if re.match("^no$", Options["--counterCol"], re.I):
1457 CounterCol = False
1458 OptionsInfo["CounterCol"] = CounterCol
1459
1460 ColVisibility = True
1461 if re.match("^no$", Options["--colVisibility"], re.I):
1462 ColVisibility = False
1463 OptionsInfo["ColVisibility"] = ColVisibility
1464
1465 OptionsInfo["ColVisibilityCtrlMax"] = int(Options["--colVisibilityCtrlMax"])
1466
1467 Footer = None
1468 if not re.match("^None$", Options["--footer"], re.I):
1469 Footer = Options["--footer"]
1470 OptionsInfo["Footer"] = Footer
1471
1472 FooterClass = Options["--footerClass"].strip()
1473 if MiscUtil.IsEmpty(FooterClass):
1474 MiscUtil.PrintError("The value specified using option \"--footerClass\" is empty.")
1475 OptionsInfo["FooterClass"] = FooterClass
1476
1477 FreezeCols = True
1478 if re.match("^no$", Options["--freezeCols"], re.I):
1479 FreezeCols = False
1480 OptionsInfo["FreezeCols"] = FreezeCols
1481
1482 Header = None
1483 if not re.match("^None$", Options["--header"], re.I):
1484 Header = Options["--header"]
1485 OptionsInfo["Header"] = Header
1486
1487 HeaderStyle = Options["--headerStyle"].strip()
1488 if MiscUtil.IsEmpty(HeaderStyle):
1489 MiscUtil.PrintError("The value specified using option \"--headerStyle\" is empty.")
1490 OptionsInfo["HeaderStyle"] = HeaderStyle
1491
1492 ProcessHighlightSMARTSOption()
1493 ProcessHighlightDataOptions()
1494
1495 OptionsInfo["KeysNavigation"] = True
1496 if re.match("^no$", Options["--keysNavigation"], re.I):
1497 OptionsInfo["KeysNavigation"] = False
1498
1499 SizeValues = Options["--molImageSize"].split(",")
1500 OptionsInfo["MolImageWidth"] = int(SizeValues[0])
1501 OptionsInfo["MolImageHeight"] = int(SizeValues[1])
1502
1503 OptionsInfo["MolImageEncoded"] = True
1504 if re.match("^no$", Options["--molImageEncoded"], re.I):
1505 OptionsInfo["MolImageEncoded"] = False
1506
1507 OptionsInfo["Paging"] = True
1508 if re.match("^no$", Options["--paging"], re.I):
1509 OptionsInfo["Paging"] = False
1510
1511 PagingType = Options["--pagingType"]
1512 if not re.match("^(numbers|simple|simple_numbers|full|full_numbers|simple_number)$", Options["--pagingType"], re.I):
1513 MiscUtil.PrintWarning("The paging type name, %s, specified using option \"--pagingType\" appears to be a unknown type..." % (PagingType))
1514 OptionsInfo["PagingType"] = PagingType.lower()
1515
1516 OptionsInfo["PageLength"] = int(Options["--pageLength"])
1517
1518 OptionsInfo["RegexSearch"] = True
1519 if re.match("^no$", Options["--regexSearch"], re.I):
1520 OptionsInfo["RegexSearch"] = False
1521
1522 OptionsInfo["ShowMolName"] = True
1523 OptionsInfo["ShowMolNameDataLabel"] = "Name"
1524 if re.match("^no$", Options["--showMolName"], re.I):
1525 OptionsInfo["ShowMolName"] = False
1526
1527 OptionsInfo["ShowMolNameAuto"] = True if re.match("^auto$", Options["--showMolName"], re.I) else False
1528
1529 OptionsInfo["ScrollX"] = True
1530 if re.match("^no$", Options["--scrollX"], re.I):
1531 OptionsInfo["ScrollX"] = False
1532
1533 OptionsInfo["ScrollY"] = True
1534 if re.match("^no$", Options["--scrollY"], re.I):
1535 OptionsInfo["ScrollY"] = False
1536
1537 OptionsInfo["ScrollYSize"] = Options["--scrollYSize"]
1538 if re.match("vh$", Options["--scrollYSize"], re.I):
1539 ScrollYSize = int(re.sub("vh$", "", Options["--scrollYSize"]))
1540 if ScrollYSize <= 0:
1541 MiscUtil.PrintError("The value specified, %s, for option \"--scrollYSize\" is not valid. Supported value: > 0 followed by \"vh\"" % Options["--scrollYSize"])
1542
1543 TableStyle = None
1544 if not re.match("^None$", Options["--tableStyle"], re.I):
1545 if re.match("^All$", Options["--tableStyle"], re.I):
1546 TableStyle = "table table-striped table-bordered table-hover table-dark"
1547 else:
1548 TableStyle = re.sub(" ", "", Options["--tableStyle"])
1549 for Style in [Style for Style in TableStyle.split(",")]:
1550 if not re.match("^(table|table-striped|table-bordered|table-hover|table-dark|table-sm)$", Style, re.I):
1551 MiscUtil.PrintWarning("The table style name, %s, specified using option \"-t, --tableStyle\" appears to be a unknown style..." % (Style))
1552 TableStyle = re.sub(",", " ", TableStyle.lower())
1553 OptionsInfo["TableStyle"] = TableStyle
1554
1555 TableHeaderStyle = None
1556 if not re.match("^None$", Options["--tableHeaderStyle"], re.I):
1557 TableHeaderStyle = Options["--tableHeaderStyle"]
1558 TableHeaderStyle = TableHeaderStyle.lower()
1559 CheckOptionTableClassColorValues("--tableHeaderStyle", [TableHeaderStyle])
1560 OptionsInfo["TableHeaderStyle"] = TableHeaderStyle
1561
1562 OptionsInfo["TableFooter"] = True
1563 if re.match("^no$", Options["--tableFooter"], re.I):
1564 OptionsInfo["TableFooter"] = False
1565
1566 OptionsInfo["WrapText"] = True
1567 if re.match("^no$", Options["--wrapText"], re.I):
1568 OptionsInfo["WrapText"] = False
1569
1570 OptionsInfo["WrapTextWidth"] = int(Options["--wrapTextWidth"])
1571
1572 def RetrieveOptions():
1573 """Retrieve command line arguments and options."""
1574
1575 # Get options...
1576 global Options
1577 Options = docopt(_docoptUsage_)
1578
1579 # Set current working directory to the specified directory...
1580 WorkingDir = Options["--workingdir"]
1581 if WorkingDir:
1582 os.chdir(WorkingDir)
1583
1584 # Handle examples option...
1585 if "--examples" in Options and Options["--examples"]:
1586 MiscUtil.PrintInfo(MiscUtil.GetExamplesTextFromDocOptText(_docoptUsage_))
1587 sys.exit(0)
1588
1589 def ValidateOptions():
1590 """Validate option values."""
1591
1592 if not re.match("^None$", Options["--alignmentSMARTS"], re.I):
1593 PatternMol = Chem.MolFromSmarts(Options["--alignmentSMARTS"])
1594 if PatternMol is None:
1595 MiscUtil.PrintError("The value specified, %s, using option \"--alignmentSMARTS\" is not a valid SMARTS: Failed to create pattern molecule" % Options["--alignmentSMARTS"])
1596
1597 MiscUtil.ValidateOptionTextValue("-c, --compute2DCoords", Options["--compute2DCoords"], "yes no auto")
1598
1599 MiscUtil.ValidateOptionTextValue("--counterCol", Options["--counterCol"], "yes no")
1600 MiscUtil.ValidateOptionTextValue("--colVisibility", Options["--colVisibility"], "yes no")
1601 MiscUtil.ValidateOptionIntegerValue("--colVisibilityCtrlMax", Options["--colVisibilityCtrlMax"], {">": 0})
1602
1603 MiscUtil.ValidateOptionTextValue("--freezeCols", Options["--freezeCols"], "yes no")
1604 MiscUtil.ValidateOptionTextValue("--highlightValuesClasses", Options["--highlightValuesClasses"], "RuleOf5 RuleOf3 DrugLike Random None")
1605
1606 MiscUtil.ValidateOptionFilePath("-i, --infile", Options["--infile"])
1607 MiscUtil.ValidateOptionFileExt("-i, --infile", Options["--infile"], "sdf sd mol smi csv tsv txt")
1608
1609 MiscUtil.ValidateOptionFileExt("-o, --outfile", Options["--outfile"], "html")
1610 MiscUtil.ValidateOptionsOutputFileOverwrite("-o, --outfile", Options["--outfile"], "--overwrite", Options["--overwrite"])
1611 MiscUtil.ValidateOptionsDistinctFileNames("-i, --infile", Options["--infile"], "-o, --outfile", Options["--outfile"])
1612
1613 MiscUtil.ValidateOptionTextValue("-k, --keysNavigation", Options["--keysNavigation"], "yes no")
1614
1615 MiscUtil.ValidateOptionNumberValues("-m, --molImageSize", Options["--molImageSize"], 2, ",", "integer", {">": 0})
1616 MiscUtil.ValidateOptionTextValue("--molImageEncoded", Options["--molImageEncoded"], "yes no")
1617
1618 MiscUtil.ValidateOptionTextValue("-p, --paging", Options["--paging"], "yes no")
1619 MiscUtil.ValidateOptionIntegerValue("--pageLength", Options["--pageLength"], {">": 0})
1620 MiscUtil.ValidateOptionTextValue("-r, --regexSearch", Options["--regexSearch"], "yes no")
1621
1622 MiscUtil.ValidateOptionTextValue("--showMolName", Options["--showMolName"], "yes no auto")
1623
1624 MiscUtil.ValidateOptionTextValue("--scrollX", Options["--scrollX"], "yes no")
1625 MiscUtil.ValidateOptionTextValue("--scrollY", Options["--scrollY"], "yes no")
1626 if not re.search("vh$", Options["--scrollYSize"], re.I):
1627 MiscUtil.ValidateOptionIntegerValue("--scrollYSize", Options["--scrollYSize"], {">": 0})
1628
1629 MiscUtil.ValidateOptionTextValue("--tableFooter", Options["--tableFooter"], "yes no")
1630
1631 MiscUtil.ValidateOptionTextValue("--wrapText", Options["--wrapText"], "yes no")
1632 MiscUtil.ValidateOptionIntegerValue("--wrapTextWidth", Options["--wrapTextWidth"], {">": 0})
1633
1634 # Setup a usage string for docopt...
1635 _docoptUsage_ = """
1636 RDKitDrawMoleculesAndDataTable.py - Generate a HTML data table
1637
1638 Usage:
1639 RDKitDrawMoleculesAndDataTable.py [--alignmentSMARTS <SMARTS>]
1640 [--compute2DCoords <yes or no>] [--counterCol <yes or no>]
1641 [--colVisibility <yes or no>] [--colVisibilityCtrlMax <number>] [--footer <text>]
1642 [--footerClass <text>] [--freezeCols <yes or no>] [--header <text>]
1643 [--headerStyle <text>] [--highlightSMARTS <SMARTS,...>] [--highlightSMARTSDelim <text>]
1644 [--highlightValues <datalabel,datatype,criterion,value,...>]
1645 [--highlightValuesRanges <datalabel,datatype,criterion1,vaue1,criterion2,value2...>]
1646 [--highlightValuesClasses <RuleOf5,RuleOf3,...>]
1647 [--highlightColors <colortype,color1,color2>]
1648 [--highlightColorsRanges <colortype,color1,color2,color3>]
1649 [--highlightColorsRandom <colottype,color1,color2,...>]
1650 [--infileParams <Name,Value,...>] [--keysNavigation <yes or no>]
1651 [--molImageSize <width,height>] [--molImageEncoded <yes or no> ] [--overwrite]
1652 [--paging <yes or no>] [--pagingType <numbers,simple, ...>] [--pageLength <number>]
1653 [--regexSearch <yes or no>] [--showMolName <yes or no>]
1654 [--scrollX <yes or no>] [--scrollY <yes or no>] [--scrollYSize <number>]
1655 [--tableStyle <table,table-striped,...>] [--tableFooter <yes or no>]
1656 [--tableHeaderStyle <thead-dark,thead-light,...>] [--wrapText <yes or no>]
1657 [--wrapTextWidth <number>] [-w <dir>] -i <infile> -o <outfile>
1658 RDKitDrawMoleculesAndDataTable.py -h | --help | -e | --examples
1659
1660 Description:
1661 Generate an interactive HTML table with columns corresponding to molecules
1662 and available alphanumerical data in an input file. The drawing of molecules are
1663 embedded in the columns as in line SVG images.
1664
1665 The interactive HTML table may contain multiple columns with drawing of
1666 molecules. These columns are automatically generated for each data field in SD
1667 file or a column name in SMILES and CSV/TSV file containing SMILES
1668 string in their names. The first molecular drawing column in the HTML table
1669 represents primary molecular structure data available in an input file. It
1670 corresponds to MOL block is SD file or a first column containing SMILES string
1671 in its name in SMILES and CSV/TSV files.
1672
1673 The interactive table requires internet access for viewing in a browser and
1674 employs the following frameworks: JQuery, Bootstrap, and DataTable. It provides
1675 the following functionality: sorting by columns, page length control, page
1676 navigation, searching data with regular expressions, and horizontal/vertical
1677 scrolling, row highlighting during hovering, a counter column, freezing of primary
1678 structure and counter columns, and column visibility control.
1679
1680 The supported input file formats are: Mol (.mol), SD (.sdf, .sd), SMILES (.smi),
1681 CSV/TSV (.csv, .tsv, .txt)
1682
1683 The supported output file format is HTML (.html).
1684
1685 Options:
1686 -a, --alignmentSMARTS <SMARTS> [default: none]
1687 SMARTS pattern for aligning molecules to a common template. This option is
1688 only used for primary molecular data in SD, SMILES and CSV/TSV files. It is
1689 ignored for all other molecular coordinates corresponding to data fields in SD
1690 file or columns in SMILES and CSV/TSV files containing SMILES string in their
1691 names.
1692 -c, --compute2DCoords <yes or no> [default: yes]
1693 Compute 2D coordinates of molecules before drawing. Default: yes for SMILES
1694 strings in SMILES, CSV/TSV, and SD file data fields. In addition, 2D coordinated are
1695 always calculated for molecules corresponding to data fields in SD file or columns
1696 in SMILES and CSV/TSV files containing SMILES string in their names.
1697 --counterCol <yes or no> [default: yes]
1698 Show a counter column as the first column in the table. It contains the position
1699 for each row in the table.
1700 --colVisibility <yes or no> [default: yes]
1701 Show a dropdown button to toggle visibility of columns in the table. The counter
1702 and primary structure columns are excluded from the list.
1703 --colVisibilityCtrlMax <number> [default: 25]
1704 Maximum number of columns to show in column visibility dropdown button. The
1705 rest of the data columns are not listed in the dropdown and are shown in the table.
1706 A word to the wise: The display of too many columns appear to hang interactive
1707 Javascript framework for Bootstrap and DataTables.
1708 --freezeCols <yes or no> [default: yes]
1709 Lock counter and primary structure columns in place during horizontal scrolling.
1710 --footer <text> [default: none]
1711 Footer text to insert at the bottom of the HTML page after the table.
1712 --footerClass <text> [default: small text-center text-muted]
1713 Footer class style to use with <p> tag.
1714 -e, --examples
1715 Print examples.
1716 -h, --help
1717 Print this help message.
1718 --header <text> [default: none]
1719 Header text to insert at the top of the HTML page before the table.
1720 --headerStyle <text> [default: h5]
1721 Header style to use. Possible values: h1 to h6.
1722 --highlightSMARTS <SMARTS,...> [default: none]
1723 SMARTS pattern for highlighting atoms and bonds in molecules. All matched
1724 substructures are highlighted.
1725
1726 The SMARTS string is used to highlight atoms and bonds in drawing of
1727 molecules present in a HTML table across multiple columns. These columns
1728 correspond to data field labels in SD file or a column name in SMILES and
1729 CSV/TSV file containing SMILES string in their names. The first molecular
1730 drawing column in HTML table corresponds to primary molecular structure
1731 data available in an input file. It is identified by a label 'Structure' across
1732 all input formats.
1733
1734 A single SMARTS string is used to highlight a common substructure across
1735 all columns containing drawing of molecules in HTML table.
1736
1737 Format:
1738
1739 SMARTS
1740 Structure,SMARTS1,DataLabel,SMARTS2,...
1741 Structure,SMARTS1,Collabel,SMARTS2,...
1742
1743 Example:
1744
1745 c1ccccc1
1746 Structure,c1ccccc1,SMILESR1,c1ccccc1,SMILESR2,c1ccccc1
1747
1748 --highlightSMARTSDelim <text> [default: ,]
1749 Delimiter for parsing SMARTS patterns specified using '--highlightSMARTS'
1750 option. Default: ',' comma character. Possible value: Any arbitrary text or
1751 a valid character. You may use arbitrary text as a delimiter to handle
1752 presence of special characters such as comma, semicolon, tilde etc. in
1753 SMARTS patterns.
1754 --highlightValues <datalabel,datatype,criterion,value,...> [default: none]
1755 Highlighting methodology to use for highlighting alphanumerical data
1756 corresponding to data fields in SD file or column names in SMILES and
1757 CSV/TSV text files.
1758
1759 Input text contains these quartets: DataLabel, DataType, Criterion, Value.
1760 Possible datatype values: numeric, text. Possible criterion values for numeric
1761 and text: gt, lt, ge, le.
1762
1763 The 'datalabel' corresponds to either data field label in SD file or column name
1764 in SMILES and CSV/TSV text files.
1765
1766 Examples:
1767
1768 MolecularWeight,numeric,le,500
1769 MolecularWeight,numeric,le,450,SLogP,numeric,le,5
1770 Name,text,eq,Aspirin
1771 Name,regex,eq,acid|amine
1772
1773 --highlightValuesRanges <datalabel,datatype,...> [default: none]
1774 Highlighting methodology to use for highlighting ranges of alphanumerical
1775 data corresponding to data fields in SD file or column names in SMILES and
1776 CSV/TSV text files.
1777
1778 Input text contains these sextets: DataLabel, DataType, CriterionLowerBound,
1779 LowerBoundValue, CriterionUpperBound, UpperBoundValue.
1780
1781 Possible datatype values: numeric or text. Possible criterion values: Lower
1782 bound value - lt, le; Upper bound value: gt, ge.
1783
1784 The 'datalabel' corresponds to either data field label in SD file or column name
1785 in SMILES and CSV/TSV text files.
1786
1787 Examples:
1788
1789 MolecularWeight,numeric,lt,450,gt,1000
1790 MolecularWeight,numeric,lt,450,gt,1000,SLogP,numeric,lt,0,gt,5
1791
1792 --highlightValuesClasses <RuleOf5,RuleOf3,...> [default: none]
1793 Highlighting methodology to use for highlighting ranges of numerical data
1794 data corresponding to specific set of data fields in SD file or column names in
1795 SMILES and CSV/TSV text files. Possible values: RuleOf5, RuleOf3, DrugLike,
1796 Random.
1797
1798 The following value classes are supported: RuleOf5, RuleOf3, LeadLike, DrugLike.
1799 LeadLike is equivalent to RuleOf3.
1800
1801 Each supported class encompasses a specific set of data labels along with
1802 appropriate criteria to compare and highlight column values, except for
1803 'Random' class. The data labels in these classes are automatically associated
1804 with appropriate data fields in SD file or column names in SMILES and CSV/TSV
1805 text files.
1806
1807 No data labels are associated with 'Random' class. It is used to highlight
1808 available alphanumeric data by randomly selecting a highlight color from the
1809 list of colors specified using '--highlightColorsRandom' option. The 'Random'
1810 class value is not allowed in conjunction with '--highlightValues' or
1811 '--highlightValuesRanges'.
1812
1813 The rules to highlight values for the supported classes are as follows.
1814
1815 RuleOf5 [ Ref 91 ]:
1816
1817 MolecularWeight,numeric,le,500 (MolecularWeight <= 500)
1818 HydrogenBondDonors,numeric,le,5 (HydrogenBondDonors <= 5)
1819 HydrogenBondAcceptors,numeric,le,10 (HydrogenBondAcceptors <= 10)
1820 LogP,numeric,le,5 (LogP <= 5)
1821
1822 RuleOf3 or LeadLike [ Ref 92 ]:
1823
1824 MolecularWeight,numeric,le,300 (MolecularWeight <= 300)
1825 HydrogenBondDonors,numeric,le,3 (HydrogenBondDonors <= 3)
1826 HydrogenBondAcceptors,numeric,le,3 (HydrogenBondAcceptors <= 3)
1827 LogP,numeric,le,3 (LogP <= 3)
1828 RotatableBonds,numeric,le,3 (RotatableBonds <= 3)
1829 TPSA,numeric,le,60 (TPSA <= 60)
1830
1831 DrugLike:
1832
1833 MolecularWeight,numeric,le,500 (MolecularWeight <= 500)
1834 HydrogenBondDonors,numeric,le,5 (HydrogenBondDonors <= 5)
1835 HydrogenBondAcceptors,numeric,le,10 (HydrogenBondAcceptors <= 10)
1836 LogP,numeric,le,5 (LogP <= 5)
1837 RotatableBonds,numeric,le,10 (RotatableBonds <= 10)
1838 TPSA,numeric,le,140 (TPSA <= 140)
1839
1840 The following synonyms are automatically detected for data labels used
1841 by MayaChemTools and RDKit packages during the calculation of
1842 physicochemical properties.
1843
1844 MayaChemTools: MolecularWeight, HydrogenBondDonors, HydrogenBondAcceptors,
1845 SLogP, RotatableBonds, TPSA.
1846
1847 RDKit: MolWt, NHOHCount, NOCount, MolLogP, NumRotatableBonds, TPSA
1848
1849 --highlightColors <colortype,color1,color2> [default: auto]
1850 Background colors used to highlight column values based on criterion
1851 specified by '--highlightValues' and '--highlightColorsClasses' option. Default
1852 value: colorclass,table-success, table-danger.
1853
1854 The first color is used to highlight column values that satisfy the specified
1855 criterion for the column. The second color highlights the rest of the values
1856 in the column.
1857
1858 Possible values for colortype: colorclass or colorspec.
1859
1860 Any valid bootstrap contextual color class is supported for 'colorclass'
1861 color type. For example: table-primary (Blue), table-success (Green),
1862 table-danger (Red), table-info (Light blue), table-warning (Orange),
1863 table-secondary (Grey), table-light (Light grey), and table-dark (Dark grey).
1864
1865 The following bootstrap color classes may also used: bg-primary bg-success,
1866 bg-danger bg-info, bg-warning, bg-secondary.
1867
1868 Any valid color name or hexadecimal color specification is supported for
1869 'colorspec' color type: For example: red, green, blue, #ff000, #00ff00, #0000ff.
1870 --highlightColorsRanges <colortype,color1,color2,color3> [default: auto]
1871 Background colors used to highlight column values using criteria specified
1872 by '--highlightValuesRanges' option. Default value: colorclass, table-success,
1873 table-warning, table-danger.
1874
1875 The first and third color are used to highlight column values lower and higher
1876 than the specified values for the lower and upper bound. The middle color highlights
1877 the rest of the values in the column.
1878
1879 The supported color type and values are explained in the section for '--highlightColors'.
1880 --highlightColorsRandom <colortype,color1,color2,...> [default: auto]
1881 Background color list to use for randomly selecting a color to highlight
1882 column values during 'Random" value of '--highlightValuesClasses' option.
1883
1884 Default value: colorclass,table-primary,table-success,table-danger,table-info,
1885 table-warning,table-secondary.
1886
1887 The supported color type and values are explained in the section for '--highlightColors'.
1888 -i, --infile <infile>
1889 Input file name.
1890 --infileParams <Name,Value,...> [default: auto]
1891 A comma delimited list of parameter name and value pairs for reading
1892 molecules from files. The supported parameter names for different file
1893 formats, along with their default values, are shown below:
1894
1895 SD, MOL: removeHydrogens,yes,sanitize,yes,strictParsing,yes
1896 SMILES: smilesColumn,1,smilesNameColumn,2,smilesDelimiter,space,
1897 sanitize,yes
1898
1899 Possible values for smilesDelimiter: space, comma or tab.
1900 -k, --keysNavigation <yes or no> [default: yes]
1901 Provide Excel like keyboard cell navigation for the table.
1902 -m, --molImageSize <width,height> [default: 200,150]
1903 Image size of a molecule in pixels.
1904 --molImageEncoded <yes or no> [default: yes]
1905 Base64 encode SVG image of a molecule for inline embedding in a HTML page.
1906 The inline SVG image may fail to display in browsers without encoding.
1907 -o, --outfile <outfile>
1908 Output file name.
1909 --overwrite
1910 Overwrite existing files.
1911 -p, --paging <yes or no> [default: yes]
1912 Provide page navigation for browsing data in the table.
1913 --pagingType <numbers, simple, ...> [default: full_numbers]
1914 Type of page navigation. Possible values: numbers, simple, simple_numbers,
1915 full, full_numbers, or first_last_numbers.
1916
1917 numbers - Page number buttons only
1918 simple - 'Previous' and 'Next' buttons only
1919 simple_numbers - 'Previous' and 'Next' buttons, plus page numbers
1920 full - 'First', 'Previous', 'Next' and 'Last' buttons
1921 full_numbers - 'First', 'Previous', 'Next' and 'Last' buttons, plus
1922 page numbers
1923 first_last_numbers - 'First' and 'Last' buttons, plus page numbers
1924
1925 --pageLength <number> [default: 15]
1926 Number of rows to show per page.
1927 -r, --regexSearch <yes or no> [default: yes]
1928 Allow regular expression search through alphanumerical data in the table.
1929 -s, --showMolName <yes or no> [default: auto]
1930 Show molecule names in a column next to the column corresponding to primary
1931 structure data in SD and SMILES file. The default value is yes for SD and SMILES file.
1932 This option is ignored for CSV/TSV text files.
1933 --scrollX <yes or no> [default: yes]
1934 Provide horizontal scroll bar in the table as needed.
1935 --scrollY <yes or no> [default: yes]
1936 Provide vertical scroll bar in the table as needed.
1937 --scrollYSize <number> [default: 75vh]
1938 Maximum height of table viewport either in pixels or percentage of the browser
1939 window height before providing a vertical scroll bar. Default: 75% of the height of
1940 browser window.
1941 -t, --tableStyle <table,table-striped,...> [default: table,table-hover,table-sm]
1942 Style of table. Possible values: table, table-striped, table-bordered,
1943 table-hover, table-dark, table-sm, none, or All. Default: 'table,table-hover'. A
1944 comma delimited list of any valid Bootstrap table styles is also supported.
1945 --tableFooter <yes or no> [default: yes]
1946 Show column headers at the end of the table.
1947 --tableHeaderStyle <thead-dark,thead-light,...> [default: thead-dark]
1948 Style of table header. Possible values: thead-dark, thead-light, or none.
1949 The names of the following contextual color classes are also supported:
1950 table-primary (Blue), table-success (Green), table-danger (Red), table-info
1951 (Light blue), table-warning (Orange), table-active (Grey), table-light (Light
1952 grey), and table-dark (Dark grey).
1953 -w, --workingdir <dir>
1954 Location of working directory which defaults to the current directory.
1955 --wrapText <yes or no> [default: yes]
1956 Wrap alphanumeric text using <br/> delimiter for display in a HTML table.
1957 --wrapTextWidth <number> [default: 40]
1958 Maximum width in characters before wraping alphanumeric text for display
1959 in a HTML table.
1960
1961 Examples:
1962 To generate a HTML table containing structure and alphanumeric data for
1963 molecules in a SD file along with all the bells and whistles to interact with
1964 the table, type:
1965
1966 % RDKitDrawMoleculesAndDataTable.py -i Sample.sdf -o SampleOut.html
1967
1968 To generate a HTML table containing structure and alphanumeric data for
1969 molecules in a SMILES file along with all the bells and whistles to interact
1970 with the table, type:
1971
1972 % RDKitDrawMoleculesAndDataTable.py -i Sample.smi -o SampleOut.html
1973
1974 To generate a HTML table containing multiple structure columns for molecules
1975 in a CSV file along with all the bells and whistles to interact with the table, type:
1976
1977 % RDKitDrawMoleculesAndDataTable.py -i SampleSeriesRGroupsD3R.csv
1978 -o SampleSeriesRGroupsD3ROut.html
1979
1980 To generate a HTML table containing structure and alphanumeric data for
1981 molecules in a SD file along without any bells and whistles to interact with
1982 the table, type:
1983
1984 % RDKitDrawMoleculesAndDataTable.py --colVisibility no --freezeCols no
1985 --keysNavigation no --paging no --regexSearch no --scrollX no
1986 --scrollY no -i Sample.sdf -o SampleOut.html
1987
1988 To generate a HTML table containing structure and alphanumeric data for
1989 molecules in a SD file along with highlighting molecular weight values
1990 using a specified criterion, type:
1991
1992 % RDKitDrawMoleculesAndDataTable.py --highlightValues
1993 "MolecularWeight,numeric,le,500" -i Sample.sdf -o SampleOut.html
1994
1995 To generate a HTML table containing structure and alphanumeric data for
1996 molecules in a SD file along with highlighting range of molecular weight values
1997 using a specified criterion, type:
1998
1999 % RDKitDrawMoleculesAndDataTable.py --highlightValuesRanges
2000 "MolecularWeight,numeric,lt,400,gt,500" -i Sample.sdf -o SampleOut.html
2001
2002 To generate a HTML table containing structure and alphanumeric data for
2003 molecules in a SD file along with highlighting molecular weight values and
2004 ranges of SLogP values using a specified criterion and color schemes, type:
2005
2006 % RDKitDrawMoleculesAndDataTable.py --highlightValues
2007 "MolecularWeight,numeric,le,500" --highlightValuesRanges
2008 "SLogP,numeric,lt,0,gt,5" --highlightColors "colorclass,table-success,
2009 table-danger" --highlightColorsRanges "colorclass,table-danger,
2010 table-success,table-warning" -i Sample.sdf -o SampleOut.html
2011
2012 To generate a HTML table containing structure and alphanumeric data for
2013 molecules in a SD file along with highlighting RuleOf5 physicochemical
2014 properties using a pre-defined set of criteria, type:
2015
2016 % RDKitDrawMoleculesAndDataTable.py --highlightValuesClasses RuleOf5
2017 -i Sample.sdf -o SampleOut.html
2018
2019 To generate a HTML table containing structure and alphanumeric data for
2020 molecules in a SD file along with all the bells and whistles to interact
2021 with the table and highlight a specific SMARTS pattern in molecules, type:
2022
2023 % RDKitDrawMoleculesAndDataTable.py --highlightSMARTS "c1ccccc1"
2024 -i Sample.sdf -o SampleOut.html
2025
2026 To generate a HTML table containing structure and alphanumeric data for
2027 molecules in a SD file along with highlighting of values using random colors
2028 from a default list of colors, type:
2029
2030 % RDKitDrawMoleculesAndDataTable.py --highlightValuesClasses Random
2031 -i Sample.sdf -o SampleOut.html
2032
2033 To generate a HTML table containing structure and alphanumeric data for
2034 molecules in a SD file along with highlighting of values using random colors
2035 from a specified list of colors, type:
2036
2037 % RDKitDrawMoleculesAndDataTable.py --highlightValuesClasses Random
2038 --highlightColorsRandom "colorspec,Lavendar,MediumPurple,SkyBlue,
2039 CornflowerBlue,LightGreen,MediumSeaGreen,Orange,Coral,Khaki,Gold,
2040 Salmon,LightPink,Aquamarine,MediumTurquoise,LightGray"
2041 -i Sample.sdf -o SampleOut.html
2042
2043 To generate a HTML table containing structure and alphanumeric data for
2044 molecules in a SMILES file specific columns, type:
2045
2046 % RDKitDrawMoleculesAndDataTable.py --infileParams "smilesDelimiter,
2047 comma, smilesColumn,1,smilesNameColumn,2"
2048 -i SampleSMILES.csv -o SampleOut.html
2049
2050 Author:
2051 Manish Sud(msud@san.rr.com)
2052
2053 See also:
2054 RDKitConvertFileFormat.py, RDKitDrawMolecules.py, RDKitRemoveDuplicateMolecules.py,
2055 RDKitSearchFunctionalGroups.py, RDKitSearchSMARTS.py
2056
2057 Copyright:
2058 Copyright (C) 2024 Manish Sud. All rights reserved.
2059
2060 The functionality available in this script is implemented using RDKit, an
2061 open source toolkit for cheminformatics developed by Greg Landrum.
2062
2063 This file is part of MayaChemTools.
2064
2065 MayaChemTools is free software; you can redistribute it and/or modify it under
2066 the terms of the GNU Lesser General Public License as published by the Free
2067 Software Foundation; either version 3 of the License, or (at your option) any
2068 later version.
2069
2070 """
2071
2072 if __name__ == "__main__":
2073 main()
