htsworkflow/frontend/samples/views.py

   1 # Create your views here.
   2 import StringIO
   3 import logging
   4 import os
   5 import sys
   6
   7 try:
   8     import json
   9 except ImportError, e:
  10     import simplejson as json
  11
  12 from django.contrib.csrf.middleware import csrf_exempt
  13 from htsworkflow.frontend.auth import require_api_key
  14 from htsworkflow.frontend.experiments.models import FlowCell, Lane, LANE_STATUS_MAP
  15 from htsworkflow.frontend.samples.changelist import ChangeList
  16 from htsworkflow.frontend.samples.models import Antibody, Library, Species, HTSUser
  17 from htsworkflow.frontend.samples.results import get_flowcell_result_dict
  18 from htsworkflow.frontend.bcmagic.forms import BarcodeMagicForm
  19 from htsworkflow.pipelines.runfolder import load_pipeline_run_xml
  20 from htsworkflow.pipelines import runfolder
  21 from htsworkflow.pipelines.eland import ResultLane
  22 from htsworkflow.util.conversion import unicode_or_none, parse_flowcell_id
  23 from htsworkflow.util import makebed
  24 from htsworkflow.util import opener
  25
  26
  27 from django.core.exceptions import ObjectDoesNotExist
  28 from django.http import HttpResponse, HttpResponseRedirect, Http404
  29 from django.shortcuts import render_to_response, get_object_or_404
  30 from django.template import RequestContext
  31 from django.template.loader import get_template
  32 from django.contrib.auth.decorators import login_required
  33 from django.conf import settings
  34
  35 LANE_LIST = [1,2,3,4,5,6,7,8]
  36 SAMPLES_CONTEXT_DEFAULTS = {
  37     'app_name': 'Flowcell/Library Tracker',
  38     'bcmagic': BarcodeMagicForm()
  39 }
  40
  41 def count_lanes(lane_set):
  42     single = 0
  43     paired = 1
  44     short_read = 0
  45     medium_read = 1
  46     long_read = 2
  47     counts = [[0,0,0,],[0,0,0]]
  48
  49     for lane in lane_set.all():
  50         if lane.flowcell.paired_end:
  51             lane_type = paired
  52         else:
  53             lane_type = single
  54         if lane.flowcell.read_length < 40:
  55             read_type = short_read
  56         elif lane.flowcell.read_length < 100:
  57             read_type = medium_read
  58         else:
  59             read_type = long_read
  60         counts[lane_type][read_type] += 1
  61
  62     return counts
  63
  64 def create_library_context(cl):
  65     """
  66      Create a list of libraries that includes how many lanes were run
  67     """
  68     records = []
  69     #for lib in library_items.object_list:
  70     for lib in cl.result_list:
  71        summary = {}
  72        summary['library'] = lib
  73        summary['library_id'] = lib.id
  74        summary['library_name'] = lib.library_name
  75        summary['species_name' ] = lib.library_species.scientific_name
  76        if lib.amplified_from_sample is not None:
  77            summary['amplified_from'] = lib.amplified_from_sample.id
  78        else:
  79            summary['amplified_from'] = ''
  80        lanes_run = count_lanes(lib.lane_set)
  81        # suppress zeros
  82        for row in xrange(len(lanes_run)):
  83            for col in xrange(len(lanes_run[row])):
  84                if lanes_run[row][col] == 0:
  85                    lanes_run[row][col] = ''
  86        summary['lanes_run'] = lanes_run
  87        summary['is_archived'] = lib.is_archived()
  88        records.append(summary)
  89     cl.result_count = unicode(cl.paginator._count)
  90     return {'library_list': records }
  91
  92 def library(request, todo_only=False):
  93     queryset = Library.objects.filter(hidden__exact=0)
  94     if todo_only:
  95         queryset = queryset.filter(lane=None)
  96     # build changelist
  97     fcl = ChangeList(request, Library,
  98         list_filter=['affiliations', 'library_species'],
  99         search_fields=['id', 'library_name', 'amplified_from_sample__id'],
 100         list_per_page=200,
 101         queryset=queryset
 102     )
 103
 104     context = { 'cl': fcl, 'title': 'Library Index', 'todo_only': todo_only}
 105     context.update(create_library_context(fcl))
 106     t = get_template('samples/library_index.html')
 107     c = RequestContext(request, context)
 108     return HttpResponse( t.render(c) )
 109
 110 def library_not_run(request):
 111     return library(request, todo_only=True)
 112
 113 def library_to_flowcells(request, lib_id):
 114     """
 115     Display information about all the flowcells a library has been run on.
 116     """
 117
 118     try:
 119       lib = Library.objects.get(id=lib_id)
 120     except:
 121       return HttpResponse("Library %s does not exist" % (lib_id))
 122
 123     flowcell_list = []
 124     flowcell_run_results = {} # aka flowcells we're looking at
 125     for lane in lib.lane_set.all():
 126         fc = lane.flowcell
 127         flowcell_id, id = parse_flowcell_id(fc.flowcell_id)
 128         if flowcell_id not in flowcell_run_results:
 129             flowcell_run_results[flowcell_id] = get_flowcell_result_dict(flowcell_id)
 130         flowcell_list.append((fc.flowcell_id, lane.lane_number))
 131
 132     flowcell_list.sort()
 133     lane_summary_list = []
 134     eland_results = []
 135     for fc, lane_number in flowcell_list:
 136         lane_summary, err_list = _summary_stats(fc, lane_number)
 137         lane_summary_list.extend(lane_summary)
 138
 139         eland_results.extend(_make_eland_results(fc, lane_number, flowcell_run_results))
 140
 141     context = {
 142         'page_name': 'Library Details',
 143         'lib': lib,
 144         'eland_results': eland_results,
 145         'lane_summary_list': lane_summary_list,
 146     }
 147     context.update(SAMPLES_CONTEXT_DEFAULTS)
 148
 149     return render_to_response(
 150         'samples/library_detail.html',
 151         context,
 152         context_instance = RequestContext(request))
 153
 154 def lanes_for(request, username=None):
 155     """
 156     Generate a report of recent activity for a user
 157     """
 158     query = {}
 159     if username is not None:
 160         user = HTSUser.objects.get(username=username)
 161         query.update({'library__affiliations__users__id':user.id})
 162     fcl = ChangeList(request, Lane,
 163         list_filter=[],
 164         search_fields=['flowcell__flowcell_id', 'library__id', 'library__library_name'],
 165         list_per_page=200,
 166         queryset=Lane.objects.filter(**query)
 167     )
 168
 169     context = { 'lanes': fcl, 'title': 'Lane Index'}
 170
 171     return render_to_response(
 172         'samples/lanes_for.html',
 173         context,
 174         context_instance = RequestContext(request)
 175     )
 176
 177
 178 def summaryhtm_fc_cnm(request, flowcell_id, cnm):
 179     """
 180     returns a Summary.htm file if it exists.
 181     """
 182     fc_id, status = parse_flowcell_id(flowcell_id)
 183     d = get_flowcell_result_dict(fc_id)
 184
 185     if d is None:
 186         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 187
 188     if cnm not in d:
 189         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 190
 191     summary_filepath = d[cnm]['summary']
 192
 193     if summary_filepath is None:
 194         return HttpResponse('<b>Summary.htm for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 195
 196     f = open(summary_filepath, 'r')
 197
 198     return HttpResponse(f)
 199
 200
 201 def result_fc_cnm_eland_lane(request, flowcell_id, cnm, lane):
 202     """
 203     returns an eland_file upon calling.
 204     """
 205     fc_id, status = parse_flowcell_id(flowcell_id)
 206     d = get_flowcell_result_dict(fc_id)
 207
 208     if d is None:
 209         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 210
 211     if cnm not in d:
 212         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 213
 214     erd = d[cnm]['eland_results']
 215     lane = int(lane)
 216
 217     if lane not in erd:
 218         return HttpResponse('<b>Results for Flowcell %s; %s; lane %s not found.</b>' % (fc_id, cnm, lane))
 219
 220     filepath = erd[lane]
 221
 222     #f = opener.autoopen(filepath, 'r')
 223     # return HttpResponse(f, mimetype="application/x-elandresult")
 224
 225     f = open(filepath, 'r')
 226     return HttpResponse(f, mimetype='application/x-bzip2')
 227
 228
 229
 230 def bedfile_fc_cnm_eland_lane_ucsc(request, fc_id, cnm, lane):
 231     """
 232     returns a bed file for a given flowcell, CN-M (i.e. C1-33), and lane (ucsc compatible)
 233     """
 234     return bedfile_fc_cnm_eland_lane(request, fc_id, cnm, lane, ucsc_compatible=True)
 235
 236
 237 def bedfile_fc_cnm_eland_lane(request, flowcell_id, cnm, lane, ucsc_compatible=False):
 238     """
 239     returns a bed file for a given flowcell, CN-M (i.e. C1-33), and lane
 240     """
 241     fc_id, status = parse_flowcell_id(flowcell_id)
 242     d = get_flowcell_result_dict(fc_id)
 243
 244     if d is None:
 245         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 246
 247     if cnm not in d:
 248         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 249
 250     erd = d[cnm]['eland_results']
 251     lane = int(lane)
 252
 253     if lane not in erd:
 254         return HttpResponse('<b>Results for Flowcell %s; %s; lane %s not found.</b>' % (fc_id, cnm, lane))
 255
 256     filepath = erd[lane]
 257
 258     # Eland result file
 259     fi = opener.autoopen(filepath, 'r')
 260     # output memory file
 261
 262     name, description = makebed.make_description( fc_id, lane )
 263
 264     bedgen = makebed.make_bed_from_eland_generator(fi, name, description)
 265
 266     if ucsc_compatible:
 267         return HttpResponse(bedgen)
 268     else:
 269         return HttpResponse(bedgen, mimetype="application/x-bedfile")
 270
 271
 272 def _summary_stats(flowcell_id, lane_id):
 273     """
 274     Return the summary statistics for a given flowcell, lane, and end.
 275     """
 276     fc_id, status = parse_flowcell_id(flowcell_id)
 277     fc_result_dict = get_flowcell_result_dict(fc_id)
 278
 279     summary_list = []
 280     err_list = []
 281
 282     if fc_result_dict is None:
 283         err_list.append('Results for Flowcell %s not found.' % (fc_id))
 284         return (summary_list, err_list)
 285
 286     for cycle_width in fc_result_dict:
 287         xmlpath = fc_result_dict[cycle_width]['run_xml']
 288
 289         if xmlpath is None:
 290             err_list.append('Run xml for Flowcell %s(%s) not found.' % (fc_id, cycle_width))
 291             continue
 292
 293         run = load_pipeline_run_xml(xmlpath)
 294         gerald_summary = run.gerald.summary.lane_results
 295         for end in range(len(gerald_summary)):
 296             end_summary = run.gerald.eland_results.results[end]
 297             if end_summary.has_key(lane_id):
 298                 eland_summary = run.gerald.eland_results.results[end][lane_id]
 299             else:
 300                 eland_summary = ResultLane(lane_id=lane_id, end=end)
 301             # add information to lane_summary
 302             eland_summary.flowcell_id = flowcell_id
 303             if len(gerald_summary) > end and gerald_summary[end].has_key(lane_id):
 304                 eland_summary.clusters = gerald_summary[end][lane_id].cluster
 305             else:
 306                 eland_summary.clusters = None
 307             eland_summary.cycle_width = cycle_width
 308             if hasattr(eland_summary, 'genome_map'):
 309                 eland_summary.summarized_reads = runfolder.summarize_mapped_reads(
 310                                                    eland_summary.genome_map,
 311                                                    eland_summary.mapped_reads)
 312
 313             # grab some more information out of the flowcell db
 314             flowcell = FlowCell.objects.get(flowcell_id=flowcell_id)
 315             #pm_field = 'lane_%d_pM' % (lane_id)
 316             lane_obj = flowcell.lane_set.get(lane_number=lane_id)
 317             eland_summary.flowcell = flowcell
 318             eland_summary.lane = lane_obj
 319
 320             summary_list.append(eland_summary)
 321
 322         #except Exception, e:
 323         #    summary_list.append("Summary report needs to be updated.")
 324         #    logging.error("Exception: " + str(e))
 325
 326     return (summary_list, err_list)
 327
 328
 329 def get_eland_result_type(pathname):
 330     """
 331     Guess the eland result file type from the filename
 332     """
 333     path, filename = os.path.split(pathname)
 334     if 'extended' in filename:
 335         return 'extended'
 336     elif 'multi' in filename:
 337         return 'multi'
 338     elif 'result' in filename:
 339         return 'result'
 340     else:
 341         return 'unknown'
 342
 343 def _make_eland_results(flowcell_id, lane_number, interesting_flowcells):
 344     fc_id, status = parse_flowcell_id(flowcell_id)
 345     cur_fc = interesting_flowcells.get(fc_id, None)
 346     if cur_fc is None:
 347       return []
 348
 349     flowcell = FlowCell.objects.get(flowcell_id=flowcell_id)
 350     lane = flowcell.lane_set.get(lane_number=lane_number)
 351     # Loop throw storage devices if a result has been archived
 352     storage_id_list = []
 353     if cur_fc is not None:
 354         for lts in flowcell.longtermstorage_set.all():
 355             for sd in lts.storage_devices.all():
 356                 # Use barcode_id if it exists
 357                 if sd.barcode_id is not None and sd.barcode_id != '':
 358                     storage_id_list.append(sd.barcode_id)
 359                 # Otherwise use UUID
 360                 else:
 361                     storage_id_list.append(sd.uuid)
 362
 363     # Formatting for template use
 364     if len(storage_id_list) == 0:
 365         storage_ids = None
 366     else:
 367         storage_ids = ', '.join([ '<a href="/inventory/%s/">%s</a>' % (s,s) for s in storage_id_list ])
 368
 369     results = []
 370     for cycle in cur_fc.keys():
 371         result_path = cur_fc[cycle]['eland_results'].get(lane, None)
 372         result_link = make_result_link(fc_id, cycle, lane, result_path)
 373         results.append({'flowcell_id': fc_id,
 374                         'flowcell': flowcell,
 375                         'run_date': flowcell.run_date,
 376                         'cycle': cycle,
 377                         'lane': lane,
 378                         'summary_url': make_summary_url(flowcell_id, cycle),
 379                         'result_url': result_link[0],
 380                         'result_label': result_link[1],
 381                         'bed_url': result_link[2],
 382                         'storage_ids': storage_ids
 383         })
 384     return results
 385
 386 def make_summary_url(flowcell_id, cycle_name):
 387     url = '/results/%s/%s/summary/' % (flowcell_id, cycle_name)
 388     return url
 389
 390 def make_result_link(flowcell_id, cycle_name, lane, eland_result_path):
 391     if eland_result_path is None:
 392         return ("", "", "")
 393
 394     result_type = get_eland_result_type(eland_result_path)
 395     result_url = '/results/%s/%s/eland_result/%s' % (flowcell_id, cycle_name, lane)
 396     result_label = 'eland %s' % (result_type,)
 397     bed_url = None
 398     if result_type == 'result':
 399        bed_url_pattern = '/results/%s/%s/bedfile/%s'
 400        bed_url = bed_url_pattern % (flowcell_id, cycle_name, lane)
 401
 402     return (result_url, result_label, bed_url)
 403
 404 def _files(flowcell_id, lane):
 405     """
 406     Sets up available files for download
 407     """
 408     lane = int(lane)
 409
 410     flowcell_id, id = parse_flowcell_id(flowcell_id)
 411     d = get_flowcell_result_dict(flowcell_id)
 412
 413     if d is None:
 414         return ''
 415
 416     output = []
 417
 418     # c_name == 'CN-M' (i.e. C1-33)
 419     for c_name in d:
 420
 421         if d[c_name]['summary'] is not None:
 422             output.append('<a href="/results/%s/%s/summary/">summary(%s)</a>' \
 423                           % (flowcell_id, c_name, c_name))
 424
 425         erd = d[c_name]['eland_results']
 426         if lane in erd:
 427             result_type = get_eland_result_type(erd[lane])
 428             result_url_pattern = '<a href="/results/%s/%s/eland_result/%s">eland %s(%s)</a>'
 429             output.append(result_url_pattern % (flowcell_id, c_name, lane, result_type, c_name))
 430             if result_type == 'result':
 431                 bed_url_pattern = '<a href="/results/%s/%s/bedfile/%s">bedfile(%s)</a>'
 432                 output.append(bed_url_pattern % (flowcell_id, c_name, lane, c_name))
 433
 434     if len(output) == 0:
 435         return ''
 436
 437     return '(' + '|'.join(output) + ')'
 438
 439 def library_id_to_admin_url(request, lib_id):
 440     lib = Library.objects.get(id=lib_id)
 441     return HttpResponseRedirect('/admin/samples/library/%s' % (lib.id,))
 442
 443 def library_dict(library_id):
 444     """
 445     Given a library id construct a dictionary containing important information
 446     return None if nothing was found
 447     """
 448     try:
 449         lib = Library.objects.get(id = library_id)
 450     except Library.DoesNotExist, e:
 451         return None
 452
 453     #lane_info = lane_information(lib.lane_set)
 454     lane_info = []
 455     for lane in lib.lane_set.all():
 456         lane_info.append( {'flowcell':lane.flowcell.flowcell_id,
 457                            'lane_number': lane.lane_number,
 458                            'paired_end': lane.flowcell.paired_end,
 459                            'read_length': lane.flowcell.read_length,
 460                            'status_code': lane.status,
 461                            'status': LANE_STATUS_MAP[lane.status]} )
 462
 463     info = {
 464         # 'affiliations'?
 465         # 'aligned_reads': lib.aligned_reads,
 466         #'amplified_into_sample': lib.amplified_into_sample, # into is a colleciton...
 467         #'amplified_from_sample_id': lib.amplified_from_sample,
 468         #'antibody_name': lib.antibody_name(), # we have no antibodies.
 469         'antibody_id': lib.antibody_id,
 470         'cell_line_id': lib.cell_line_id,
 471         'cell_line': unicode_or_none(lib.cell_line),
 472         'experiment_type': lib.experiment_type.name,
 473         'experiment_type_id': lib.experiment_type_id,
 474         'gel_cut_size': lib.gel_cut_size,
 475         'hidden': lib.hidden,
 476         'id': lib.id,
 477         'insert_size': lib.insert_size,
 478         'lane_set': lane_info,
 479         'library_id': lib.id,
 480         'library_name': lib.library_name,
 481         'library_species': lib.library_species.scientific_name,
 482         'library_species_id': lib.library_species_id,
 483         #'library_type': lib.library_type.name,
 484         'library_type_id': lib.library_type_id,
 485         'made_for': lib.made_for,
 486         'made_by': lib.made_by,
 487         'notes': lib.notes,
 488         'replicate': lib.replicate,
 489         'stopping_point': lib.stopping_point,
 490         'successful_pM': unicode_or_none(lib.successful_pM),
 491         'undiluted_concentration': unicode_or_none(lib.undiluted_concentration)
 492         }
 493     if lib.library_type_id is None:
 494         info['library_type'] = None
 495     else:
 496         info['library_type'] = lib.library_type.name
 497     return info
 498
 499 @csrf_exempt
 500 def library_json(request, library_id):
 501     """
 502     Return a json formatted library dictionary
 503     """
 504     require_api_key(request)
 505     # what validation should we do on library_id?
 506
 507     lib = library_dict(library_id)
 508     if lib is None:
 509         raise Http404
 510
 511     lib_json = json.dumps(lib)
 512     return HttpResponse(lib_json, mimetype='application/json')
 513
 514 @csrf_exempt
 515 def species_json(request, species_id):
 516     """
 517     Return information about a species.
 518     """
 519     raise Http404
 520
 521 def species(request, species_id):
 522     species = get_object_or_404(Species, id=species_id)
 523
 524     context = RequestContext(request,
 525                              { 'species': species })
 526
 527     return render_to_response("samples/species_detail.html", context)
 528
 529 def antibodies(request):
 530     context = RequestContext(request,
 531                              {'antibodies': Antibody.objects.order_by('antigene')})
 532     return render_to_response("samples/antibody_index.html", context)
 533
 534 @login_required
 535 def user_profile(request):
 536     """
 537     Information about the user
 538     """
 539     context = {
 540                 'page_name': 'User Profile',
 541                 'media': '',
 542                 #'bcmagic': BarcodeMagicForm(),
 543                 #'select': 'settings',
 544             }
 545     context.update(SAMPLES_CONTEXT_DEFAULTS)
 546     return render_to_response('registration/profile.html', context,
 547                               context_instance=RequestContext(request))
 548
 549