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.pipelines.samplekey import SampleKey
  23 from htsworkflow.util.conversion import unicode_or_none, parse_flowcell_id
  24 from htsworkflow.util import makebed
  25 from htsworkflow.util import opener
  26
  27
  28 from django.core.exceptions import ObjectDoesNotExist
  29 from django.http import HttpResponse, HttpResponseRedirect, Http404
  30 from django.shortcuts import render_to_response, get_object_or_404
  31 from django.template import RequestContext
  32 from django.template.loader import get_template
  33 from django.contrib.auth.decorators import login_required
  34 from django.conf import settings
  35
  36 LANE_LIST = [1,2,3,4,5,6,7,8]
  37 SAMPLES_CONTEXT_DEFAULTS = {
  38     'app_name': 'Flowcell/Library Tracker',
  39     'bcmagic': BarcodeMagicForm()
  40 }
  41
  42 LOGGER = logging.getLogger(__name__)
  43
  44 def count_lanes(lane_set):
  45     single = 0
  46     paired = 1
  47     short_read = 0
  48     medium_read = 1
  49     long_read = 2
  50     counts = [[0,0,0,],[0,0,0]]
  51
  52     for lane in lane_set.all():
  53         if lane.flowcell.paired_end:
  54             lane_type = paired
  55         else:
  56             lane_type = single
  57         if lane.flowcell.read_length < 40:
  58             read_type = short_read
  59         elif lane.flowcell.read_length < 100:
  60             read_type = medium_read
  61         else:
  62             read_type = long_read
  63         counts[lane_type][read_type] += 1
  64
  65     return counts
  66
  67 def create_library_context(cl):
  68     """
  69      Create a list of libraries that includes how many lanes were run
  70     """
  71     records = []
  72     #for lib in library_items.object_list:
  73     for lib in cl.result_list:
  74        summary = {}
  75        summary['library'] = lib
  76        summary['library_id'] = lib.id
  77        summary['library_name'] = lib.library_name
  78        summary['species_name' ] = lib.library_species.scientific_name
  79        if lib.amplified_from_sample is not None:
  80            summary['amplified_from'] = lib.amplified_from_sample.id
  81        else:
  82            summary['amplified_from'] = ''
  83        lanes_run = count_lanes(lib.lane_set)
  84        # suppress zeros
  85        for row in xrange(len(lanes_run)):
  86            for col in xrange(len(lanes_run[row])):
  87                if lanes_run[row][col] == 0:
  88                    lanes_run[row][col] = ''
  89        summary['lanes_run'] = lanes_run
  90        summary['is_archived'] = lib.is_archived()
  91        records.append(summary)
  92     cl.result_count = unicode(cl.paginator._count)
  93     return {'library_list': records }
  94
  95 def library(request, todo_only=False):
  96     queryset = Library.objects.filter(hidden__exact=0)
  97     if todo_only:
  98         queryset = queryset.filter(lane=None)
  99     # build changelist
 100     fcl = ChangeList(request, Library,
 101         list_filter=['affiliations', 'library_species'],
 102         search_fields=['id', 'library_name', 'amplified_from_sample__id'],
 103         list_per_page=200,
 104         queryset=queryset
 105     )
 106
 107     context = { 'cl': fcl, 'title': 'Library Index', 'todo_only': todo_only}
 108     context.update(create_library_context(fcl))
 109     t = get_template('samples/library_index.html')
 110     c = RequestContext(request, context)
 111     return HttpResponse( t.render(c) )
 112
 113 def library_not_run(request):
 114     return library(request, todo_only=True)
 115
 116 def library_to_flowcells(request, lib_id):
 117     """
 118     Display information about all the flowcells a library has been run on.
 119     """
 120     try:
 121         lib = Library.objects.get(id=lib_id)
 122     except:
 123         raise Http404('Library %s does not exist' % (lib_id,))
 124
 125     flowcell_list = []
 126     flowcell_run_results = {} # aka flowcells we're looking at
 127     for lane in lib.lane_set.all():
 128         fc = lane.flowcell
 129         flowcell_id, id = parse_flowcell_id(fc.flowcell_id)
 130         if flowcell_id not in flowcell_run_results:
 131             flowcell_run_results[flowcell_id] = get_flowcell_result_dict(flowcell_id)
 132         flowcell_list.append((fc.flowcell_id, lane.lane_number))
 133
 134     flowcell_list.sort()
 135     lane_summary_list = []
 136     eland_results = []
 137     for fc, lane_number in flowcell_list:
 138         lane_summary, err_list = _summary_stats(fc, lane_number, lib_id)
 139         lane_summary_list.extend(lane_summary)
 140
 141         eland_results.extend(_make_eland_results(fc, lane_number, flowcell_run_results))
 142
 143     context = {
 144         'page_name': 'Library Details',
 145         'lib': lib,
 146         'eland_results': eland_results,
 147         'lane_summary_list': lane_summary_list,
 148     }
 149     context.update(SAMPLES_CONTEXT_DEFAULTS)
 150
 151     return render_to_response(
 152         'samples/library_detail.html',
 153         context,
 154         context_instance = RequestContext(request))
 155
 156 def lanes_for(request, username=None):
 157     """
 158     Generate a report of recent activity for a user
 159     """
 160     query = {}
 161     if username is not None:
 162         user = HTSUser.objects.get(username=username)
 163         query.update({'library__affiliations__users__id':user.id})
 164     fcl = ChangeList(request, Lane,
 165         list_filter=[],
 166         search_fields=['flowcell__flowcell_id', 'library__id', 'library__library_name'],
 167         list_per_page=200,
 168         queryset=Lane.objects.filter(**query)
 169     )
 170
 171     context = { 'lanes': fcl, 'title': 'Lane Index'}
 172
 173     return render_to_response(
 174         'samples/lanes_for.html',
 175         context,
 176         context_instance = RequestContext(request)
 177     )
 178
 179
 180 def summaryhtm_fc_cnm(request, flowcell_id, cnm):
 181     """
 182     returns a Summary.htm file if it exists.
 183     """
 184     fc_id, status = parse_flowcell_id(flowcell_id)
 185     d = get_flowcell_result_dict(fc_id)
 186
 187     if d is None:
 188         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 189
 190     if cnm not in d:
 191         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 192
 193     summary_filepath = d[cnm]['summary']
 194
 195     if summary_filepath is None:
 196         return HttpResponse('<b>Summary.htm for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 197
 198     f = open(summary_filepath, 'r')
 199
 200     return HttpResponse(f)
 201
 202
 203 def result_fc_cnm_eland_lane(request, flowcell_id, cnm, lane):
 204     """
 205     returns an eland_file upon calling.
 206     """
 207     fc_id, status = parse_flowcell_id(flowcell_id)
 208     d = get_flowcell_result_dict(fc_id)
 209
 210     if d is None:
 211         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 212
 213     if cnm not in d:
 214         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 215
 216     erd = d[cnm]['eland_results']
 217     lane = int(lane)
 218
 219     if lane not in erd:
 220         return HttpResponse('<b>Results for Flowcell %s; %s; lane %s not found.</b>' % (fc_id, cnm, lane))
 221
 222     filepath = erd[lane]
 223
 224     #f = opener.autoopen(filepath, 'r')
 225     # return HttpResponse(f, mimetype="application/x-elandresult")
 226
 227     f = open(filepath, 'r')
 228     return HttpResponse(f, mimetype='application/x-bzip2')
 229
 230
 231
 232 def bedfile_fc_cnm_eland_lane_ucsc(request, fc_id, cnm, lane):
 233     """
 234     returns a bed file for a given flowcell, CN-M (i.e. C1-33), and lane (ucsc compatible)
 235     """
 236     return bedfile_fc_cnm_eland_lane(request, fc_id, cnm, lane, ucsc_compatible=True)
 237
 238
 239 def bedfile_fc_cnm_eland_lane(request, flowcell_id, cnm, lane, ucsc_compatible=False):
 240     """
 241     returns a bed file for a given flowcell, CN-M (i.e. C1-33), and lane
 242     """
 243     fc_id, status = parse_flowcell_id(flowcell_id)
 244     d = get_flowcell_result_dict(fc_id)
 245
 246     if d is None:
 247         return HttpResponse('<b>Results for Flowcell %s not found.</b>' % (fc_id))
 248
 249     if cnm not in d:
 250         return HttpResponse('<b>Results for Flowcell %s; %s not found.</b>' % (fc_id, cnm))
 251
 252     erd = d[cnm]['eland_results']
 253     lane = int(lane)
 254
 255     if lane not in erd:
 256         return HttpResponse('<b>Results for Flowcell %s; %s; lane %s not found.</b>' % (fc_id, cnm, lane))
 257
 258     filepath = erd[lane]
 259
 260     # Eland result file
 261     fi = opener.autoopen(filepath, 'r')
 262     # output memory file
 263
 264     name, description = makebed.make_description( fc_id, lane )
 265
 266     bedgen = makebed.make_bed_from_eland_generator(fi, name, description)
 267
 268     if ucsc_compatible:
 269         return HttpResponse(bedgen)
 270     else:
 271         return HttpResponse(bedgen, mimetype="application/x-bedfile")
 272
 273
 274 def _summary_stats(flowcell_id, lane_id, library_id):
 275     """
 276     Return the summary statistics for a given flowcell, lane, and end.
 277     """
 278     fc_id, status = parse_flowcell_id(flowcell_id)
 279     fc_result_dict = get_flowcell_result_dict(fc_id)
 280
 281     summary_list = []
 282     err_list = []
 283
 284     if fc_result_dict is None:
 285         err_list.append('Results for Flowcell %s not found.' % (fc_id))
 286         return (summary_list, err_list)
 287
 288     for cycle_width in fc_result_dict:
 289         xmlpath = fc_result_dict[cycle_width]['run_xml']
 290
 291         if xmlpath is None:
 292             err_list.append('Run xml for Flowcell %s(%s) not found.' % (fc_id, cycle_width))
 293             continue
 294
 295         run = load_pipeline_run_xml(xmlpath)
 296         gerald_summary = run.gerald.summary.lane_results
 297         key = SampleKey(lane=lane_id, sample='s')
 298         eland_results = list(run.gerald.eland_results.find_keys(key))
 299         key = SampleKey(lane=lane_id, sample=library_id)
 300         eland_results.extend(run.gerald.eland_results.find_keys(key))
 301         for key in eland_results:
 302             eland_summary = run.gerald.eland_results.results[key]
 303             # add information to lane_summary
 304             eland_summary.flowcell_id = flowcell_id
 305
 306             read = key.read-1 if key.read is not None else 0
 307             try:
 308                 eland_summary.clusters = gerald_summary[read][key.lane].cluster
 309             except IndexError as e:
 310                 eland_summary.clustes = None
 311             eland_summary.cycle_width = cycle_width
 312             if hasattr(eland_summary, 'genome_map'):
 313                 eland_summary.summarized_reads = runfolder.summarize_mapped_reads(
 314                                                    eland_summary.genome_map,
 315                                                    eland_summary.mapped_reads)
 316
 317             # grab some more information out of the flowcell db
 318             flowcell = FlowCell.objects.get(flowcell_id=flowcell_id)
 319             #pm_field = 'lane_%d_pM' % (lane_id)
 320             lanes = flowcell.lane_set.filter(lane_number=lane_id)
 321             eland_summary.flowcell = flowcell
 322             eland_summary.lanes = lanes
 323
 324             summary_list.append(eland_summary)
 325
 326         #except Exception, e:
 327         #    summary_list.append("Summary report needs to be updated.")
 328         #    LOGGER.error("Exception: " + str(e))
 329
 330     return (summary_list, err_list)
 331
 332
 333 def get_eland_result_type(pathname):
 334     """
 335     Guess the eland result file type from the filename
 336     """
 337     path, filename = os.path.split(pathname)
 338     if 'extended' in filename:
 339         return 'extended'
 340     elif 'multi' in filename:
 341         return 'multi'
 342     elif 'result' in filename:
 343         return 'result'
 344     else:
 345         return 'unknown'
 346
 347 def _make_eland_results(flowcell_id, lane_number, interesting_flowcells):
 348     fc_id, status = parse_flowcell_id(flowcell_id)
 349     cur_fc = interesting_flowcells.get(fc_id, None)
 350     if cur_fc is None:
 351       return []
 352
 353     flowcell = FlowCell.objects.get(flowcell_id=flowcell_id)
 354     lanes = flowcell.lane_set.filter(lane_number=lane_number)
 355     # Loop throw storage devices if a result has been archived
 356     storage_id_list = []
 357     if cur_fc is not None:
 358         for lts in flowcell.longtermstorage_set.all():
 359             for sd in lts.storage_devices.all():
 360                 # Use barcode_id if it exists
 361                 if sd.barcode_id is not None and sd.barcode_id != '':
 362                     storage_id_list.append(sd.barcode_id)
 363                 # Otherwise use UUID
 364                 else:
 365                     storage_id_list.append(sd.uuid)
 366
 367     # Formatting for template use
 368     if len(storage_id_list) == 0:
 369         storage_ids = None
 370     else:
 371         storage_ids = ', '.join([ '<a href="/inventory/%s/">%s</a>' % (s,s) for s in storage_id_list ])
 372
 373     results = []
 374     for cycle in cur_fc.keys():
 375         result_path = cur_fc[cycle]['eland_results'].get(lanes[0], None)
 376         result_link = make_result_link(fc_id, cycle, lanes[0], result_path)
 377         results.append({'flowcell_id': fc_id,
 378                         'flowcell': flowcell,
 379                         'run_date': flowcell.run_date,
 380                         'cycle': cycle,
 381                         'lane': lanes[0],
 382                         'summary_url': make_summary_url(flowcell_id, cycle),
 383                         'result_url': result_link[0],
 384                         'result_label': result_link[1],
 385                         'bed_url': result_link[2],
 386                         'storage_ids': storage_ids
 387         })
 388     return results
 389
 390 def make_summary_url(flowcell_id, cycle_name):
 391     url = '/results/%s/%s/summary/' % (flowcell_id, cycle_name)
 392     return url
 393
 394 def make_result_link(flowcell_id, cycle_name, lane, eland_result_path):
 395     if eland_result_path is None:
 396         return ("", "", "")
 397
 398     result_type = get_eland_result_type(eland_result_path)
 399     result_url = '/results/%s/%s/eland_result/%s' % (flowcell_id, cycle_name, lane)
 400     result_label = 'eland %s' % (result_type,)
 401     bed_url = None
 402     if result_type == 'result':
 403        bed_url_pattern = '/results/%s/%s/bedfile/%s'
 404        bed_url = bed_url_pattern % (flowcell_id, cycle_name, lane)
 405
 406     return (result_url, result_label, bed_url)
 407
 408 def _files(flowcell_id, lane):
 409     """
 410     Sets up available files for download
 411     """
 412     lane = int(lane)
 413
 414     flowcell_id, id = parse_flowcell_id(flowcell_id)
 415     d = get_flowcell_result_dict(flowcell_id)
 416
 417     if d is None:
 418         return ''
 419
 420     output = []
 421
 422     # c_name == 'CN-M' (i.e. C1-33)
 423     for c_name in d:
 424
 425         if d[c_name]['summary'] is not None:
 426             output.append('<a href="/results/%s/%s/summary/">summary(%s)</a>' \
 427                           % (flowcell_id, c_name, c_name))
 428
 429         erd = d[c_name]['eland_results']
 430         if lane in erd:
 431             result_type = get_eland_result_type(erd[lane])
 432             result_url_pattern = '<a href="/results/%s/%s/eland_result/%s">eland %s(%s)</a>'
 433             output.append(result_url_pattern % (flowcell_id, c_name, lane, result_type, c_name))
 434             if result_type == 'result':
 435                 bed_url_pattern = '<a href="/results/%s/%s/bedfile/%s">bedfile(%s)</a>'
 436                 output.append(bed_url_pattern % (flowcell_id, c_name, lane, c_name))
 437
 438     if len(output) == 0:
 439         return ''
 440
 441     return '(' + '|'.join(output) + ')'
 442
 443 def library_id_to_admin_url(request, lib_id):
 444     lib = Library.objects.get(id=lib_id)
 445     return HttpResponseRedirect('/admin/samples/library/%s' % (lib.id,))
 446
 447 def library_dict(library_id):
 448     """
 449     Given a library id construct a dictionary containing important information
 450     return None if nothing was found
 451     """
 452     try:
 453         lib = Library.objects.get(id = library_id)
 454     except Library.DoesNotExist, e:
 455         return None
 456
 457     #lane_info = lane_information(lib.lane_set)
 458     lane_info = []
 459     for lane in lib.lane_set.all():
 460         lane_info.append( {'flowcell':lane.flowcell.flowcell_id,
 461                            'lane_number': lane.lane_number,
 462                            'paired_end': lane.flowcell.paired_end,
 463                            'read_length': lane.flowcell.read_length,
 464                            'status_code': lane.status,
 465                            'status': LANE_STATUS_MAP[lane.status]} )
 466
 467     info = {
 468         # 'affiliations'?
 469         # 'aligned_reads': lib.aligned_reads,
 470         #'amplified_into_sample': lib.amplified_into_sample, # into is a colleciton...
 471         #'amplified_from_sample_id': lib.amplified_from_sample,
 472         #'antibody_name': lib.antibody_name(), # we have no antibodies.
 473         'antibody_id': lib.antibody_id,
 474         'cell_line_id': lib.cell_line_id,
 475         'cell_line': unicode_or_none(lib.cell_line),
 476         'experiment_type': lib.experiment_type.name,
 477         'experiment_type_id': lib.experiment_type_id,
 478         'gel_cut_size': lib.gel_cut_size,
 479         'hidden': lib.hidden,
 480         'id': lib.id,
 481         'insert_size': lib.insert_size,
 482         'lane_set': lane_info,
 483         'library_id': lib.id,
 484         'library_name': lib.library_name,
 485         'library_species': lib.library_species.scientific_name,
 486         'library_species_id': lib.library_species_id,
 487         #'library_type': lib.library_type.name,
 488         'library_type_id': lib.library_type_id,
 489         'made_for': lib.made_for,
 490         'made_by': lib.made_by,
 491         'notes': lib.notes,
 492         'replicate': lib.replicate,
 493         'stopping_point': lib.stopping_point,
 494         'successful_pM': unicode_or_none(lib.successful_pM),
 495         'undiluted_concentration': unicode_or_none(lib.undiluted_concentration)
 496         }
 497     if lib.library_type_id is None:
 498         info['library_type'] = None
 499     else:
 500         info['library_type'] = lib.library_type.name
 501     return info
 502
 503 @csrf_exempt
 504 def library_json(request, library_id):
 505     """
 506     Return a json formatted library dictionary
 507     """
 508     require_api_key(request)
 509     # what validation should we do on library_id?
 510
 511     lib = library_dict(library_id)
 512     if lib is None:
 513         raise Http404
 514
 515     lib_json = json.dumps(lib)
 516     return HttpResponse(lib_json, mimetype='application/json')
 517
 518 @csrf_exempt
 519 def species_json(request, species_id):
 520     """
 521     Return information about a species.
 522     """
 523     raise Http404
 524
 525 def species(request, species_id):
 526     species = get_object_or_404(Species, id=species_id)
 527
 528     context = RequestContext(request,
 529                              { 'species': species })
 530
 531     return render_to_response("samples/species_detail.html", context)
 532
 533 def antibodies(request):
 534     context = RequestContext(request,
 535                              {'antibodies': Antibody.objects.order_by('antigene')})
 536     return render_to_response("samples/antibody_index.html", context)
 537
 538 @login_required
 539 def user_profile(request):
 540     """
 541     Information about the user
 542     """
 543     context = {
 544                 'page_name': 'User Profile',
 545                 'media': '',
 546                 #'bcmagic': BarcodeMagicForm(),
 547                 #'select': 'settings',
 548             }
 549     context.update(SAMPLES_CONTEXT_DEFAULTS)
 550     return render_to_response('registration/profile.html', context,
 551                               context_instance=RequestContext(request))
 552
 553