Mercurial > repos > fubar > jbrowse2dev

comparison jbrowse2/jbrowse2.py @ 5:42ca8804cd93 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
urls in minimal, bloat in complete
author fubar
date Thu, 04 Jan 2024 02:18:18 +0000
parents 22e3d068fdc9
children 88b9b105c09b
comparison
equal deleted inserted replaced
4:52842c3f2dda 5:42ca8804cd93
185 # We only expect one input genome per run. This for loop is just 185 # We only expect one input genome per run. This for loop is just
186 # easier to write than the alternative / catches any possible 186 # easier to write than the alternative / catches any possible
187 # issues. 187 # issues.
188 genome_name = genome_node["meta"]["dataset_dname"] 188 genome_name = genome_node["meta"]["dataset_dname"]
189 dsId = genome_node["meta"]["dataset_id"] 189 dsId = genome_node["meta"]["dataset_id"]
190 fapath = genome_node["path"]
190 faname = genome_name + ".fasta" 191 faname = genome_name + ".fasta"
191 faurl = "%s/api/datasets/%s/display?to_ext=fasta" % (self.giURL, dsId)
192 fapath = genome_node["path"]
193 faind = os.path.realpath(os.path.join(self.outdir, faname + ".fai")) 192 faind = os.path.realpath(os.path.join(self.outdir, faname + ".fai"))
193 if self.standalone == "complete":
194 faurl = faname
195 fadest = os.path.realpath(os.path.join(self.outdir, faname))
196 cmd = ["cp", fapath, fadest]
197 self.subprocess_check_call(cmd)
198 else:
199 faurl = "%s/api/datasets/%s/display?to_ext=fasta" % (self.giURL, dsId)
194 cmd = ["samtools", "faidx", fapath, "--fai-idx", faind] 200 cmd = ["samtools", "faidx", fapath, "--fai-idx", faind]
195 self.subprocess_check_call(cmd) 201 self.subprocess_check_call(cmd)
196 trackDict = { 202 trackDict = {
197 "name": genome_name, 203 "name": genome_name,
198 "sequence": { 204 "sequence": {
249 uri: 'https://s3.amazonaws.com/jbrowse.org/genomes/GRCh38/fasta/GRCh38.fa.gz.gzi', 255 uri: 'https://s3.amazonaws.com/jbrowse.org/genomes/GRCh38/fasta/GRCh38.fa.gz.gzi',
250 Cool will not be likely to be a good fit - see discussion at https://github.com/GMOD/jbrowse-components/issues/2438 256 Cool will not be likely to be a good fit - see discussion at https://github.com/GMOD/jbrowse-components/issues/2438
251 """ 257 """
252 log.info("#### trackData=%s" % trackData) 258 log.info("#### trackData=%s" % trackData)
253 tId = trackData["label"] 259 tId = trackData["label"]
260 dsId = trackData["metadata"]["dataset_id"]
254 url = "%s/api/datasets/%s/display?to_ext=hic " % ( 261 url = "%s/api/datasets/%s/display?to_ext=hic " % (
255 self.giURL, 262 self.giURL,
256 trackData["metadata"]["dataset_id"], 263 dsId,
257 ) 264 )
265 hname = trackData["name"]
266 if self.standalone == "complete":
267 dest = os.path.realpath(os.path.join(self.outdir, hname))
268 url = hname
269 cmd = ["cp", data, dest]
270 self.subprocess_check_call(cmd)
271 else:
272 url = "%s/api/datasets/%s/display?to_ext=hic" % (self.giURL, dsId)
258 trackDict = { 273 trackDict = {
259 "type": "HicTrack", 274 "type": "HicTrack",
260 "trackId": tId, 275 "trackId": tId,
261 "name": trackData["name"], 276 "name": hname,
262 "assemblyNames": [self.genome_name], 277 "assemblyNames": [self.genome_name],
263 "adapter": { 278 "adapter": {
264 "type": "HicAdapter", 279 "type": "HicAdapter",
265 "hicLocation": {"uri": url, "locationType": "UriLocation"}, 280 "hicLocation": {"uri": url, "locationType": "UriLocation"},
266 }, 281 },
391 self.tracksToAdd.append(trackDict) 406 self.tracksToAdd.append(trackDict)
392 self.trackIdlist.append(tId) 407 self.trackIdlist.append(tId)
393 os.unlink(gff3) 408 os.unlink(gff3)
394 409
395 def add_bigwig(self, data, trackData): 410 def add_bigwig(self, data, trackData):
396 url = "%s/api/datasets/%s/display" % ( 411 fname = trackData["name"]
397 self.giURL, 412 if self.standalone == "complete":
398 trackData["metadata"]["dataset_id"], 413 dest = os.path.realpath(os.path.join(self.outdir, fname))
399 ) 414 url = fname
415 cmd = ["cp", data, dest]
416 self.subprocess_check_call(cmd)
417 else:
418 dsId = trackData["metadata"]["dataset_id"]
419 url = "%s/api/datasets/%s/display?to_ext=fasta" % (self.giURL, dsId)
400 tId = trackData["label"] 420 tId = trackData["label"]
401 trackDict = { 421 trackDict = {
402 "type": "QuantitativeTrack", 422 "type": "QuantitativeTrack",
403 "trackId": tId, 423 "trackId": tId,
404 "name": trackData["name"], 424 "name": fname,
405 "assemblyNames": [ 425 "assemblyNames": [
406 self.genome_name, 426 self.genome_name,
407 ], 427 ],
408 "adapter": { 428 "adapter": {
409 "type": "BigWigAdapter", 429 "type": "BigWigAdapter",
419 self.tracksToAdd.append(trackDict) 439 self.tracksToAdd.append(trackDict)
420 self.trackIdlist.append(tId) 440 self.trackIdlist.append(tId)
421 441
422 def add_bam(self, data, trackData, bamOpts, bam_index=None, **kwargs): 442 def add_bam(self, data, trackData, bamOpts, bam_index=None, **kwargs):
423 tId = trackData["label"] 443 tId = trackData["label"]
424 url = "%s.bam" % trackData["label"] 444 fname = "%s.bam" % trackData["label"]
425 dest = os.path.realpath("%s/%s" % (self.outdir, url)) 445 dest = os.path.realpath("%s/%s" % (self.outdir, fname))
426 self.symlink_or_copy(os.path.realpath(data), dest) 446 if self.standalone == "minimal":
447 dsId = trackData["metadata"]["dataset_id"]
448 url = "%s/api/datasets/%s/display?to_ext=bam" % (self.giURL, dsId)
449 else:
450 url = fname
451 self.symlink_or_copy(data, dest)
427 if bam_index is not None and os.path.exists(os.path.realpath(bam_index)): 452 if bam_index is not None and os.path.exists(os.path.realpath(bam_index)):
428 # bai most probably made by galaxy and stored in galaxy dirs, need to copy it to dest 453 # bai most probably made by galaxy and stored in galaxy dirs, need to copy it to dest
429 self.subprocess_check_call( 454 self.subprocess_check_call(
430 ["cp", os.path.realpath(bam_index), dest + ".bai"] 455 ["cp", os.path.realpath(bam_index), dest + ".bai"]
431 ) 456 )
445 "assemblyNames": [self.genome_name], 470 "assemblyNames": [self.genome_name],
446 "adapter": { 471 "adapter": {
447 "type": "BamAdapter", 472 "type": "BamAdapter",
448 "bamLocation": {"locationType": "UriLocation", "uri": url}, 473 "bamLocation": {"locationType": "UriLocation", "uri": url},
449 "index": { 474 "index": {
450 "location": {"locationType": "UriLocation", "uri": url + ".bai"} 475 "location": {"locationType": "UriLocation", "uri": fname + ".bai"}
451 }, 476 },
452 "sequenceAdapter": { 477 "sequenceAdapter": {
453 "type": "IndexedFastaAdapter", 478 "type": "IndexedFastaAdapter",
454 "fastaLocation": { 479 "fastaLocation": {
455 "locationType": "UriLocation", 480 "locationType": "UriLocation",
473 tId = trackData["label"] 498 tId = trackData["label"]
474 url = "%s/api/datasets/%s/display" % ( 499 url = "%s/api/datasets/%s/display" % (
475 self.giURL, 500 self.giURL,
476 trackData["metadata"]["dataset_id"], 501 trackData["metadata"]["dataset_id"],
477 ) 502 )
478
479 url = "%s.vcf.gz" % tId 503 url = "%s.vcf.gz" % tId
480 dest = os.path.realpath("%s/%s" % (self.outdir, url)) 504 dest = os.path.realpath("%s/%s" % (self.outdir, url))
481 cmd = "bgzip -c %s > %s" % (data, dest) 505 cmd = "bgzip -c %s > %s" % (data, dest)
482 self.subprocess_popen(cmd) 506 self.subprocess_popen(cmd)
483 cmd = ["tabix", "-p", "vcf", dest] 507 cmd = ["tabix", "-p", "vcf", dest]
523 self.subprocess_check_call(["tabix", "-f", "-p", "gff", dest + ".gz"]) 547 self.subprocess_check_call(["tabix", "-f", "-p", "gff", dest + ".gz"])
524 548
525 def _sort_bed(self, data, dest): 549 def _sort_bed(self, data, dest):
526 # Only index if not already done 550 # Only index if not already done
527 if not os.path.exists(dest): 551 if not os.path.exists(dest):
528 cmd = ["sort", "-k1,1", "-k2,2n", data] 552 cmd = "sort -k1,1 -k2,2n %s | bgzip -c > %s" % (data, dest)
529 with open(dest, "w") as handle: 553 self.subprocess_popen(cmd)
530 self.subprocess_check_call(cmd, output=handle) 554 cmd = ["tabix", "-f", "-p", "bed", dest]
531 555 self.subprocess_check_call(cmd)
532 self.subprocess_check_call(["bgzip", "-f", dest])
533 self.subprocess_check_call(["tabix", "-f", "-p", "bed", dest + ".gz"])
534 556
535 def add_gff(self, data, ext, trackData): 557 def add_gff(self, data, ext, trackData):
536 url = "%s.%s" % (trackData["label"], ext) 558 url = "%s.%s" % (trackData["label"], ext)
537 dest = os.path.realpath("%s/%s" % (self.outdir, url)) 559 dest = os.path.realpath("%s/%s" % (self.outdir, url))
538 self._sort_gff(data, dest) 560 self._sort_gff(data, dest)
561 self.tracksToAdd.append(trackDict) 583 self.tracksToAdd.append(trackDict)
562 self.trackIdlist.append(tId) 584 self.trackIdlist.append(tId)
563 585
564 def add_bed(self, data, ext, trackData): 586 def add_bed(self, data, ext, trackData):
565 url = "%s.%s" % (trackData["label"], ext) 587 url = "%s.%s" % (trackData["label"], ext)
566 dest = os.path.realpath("%s/%s" % (self.outdir, url)) 588 dest = os.path.realpath("%s/%s.gz" % (self.outdir, url))
567 self._sort_bed(data, dest) 589 self._sort_bed(data, dest)
568 tId = trackData["label"] 590 tId = trackData["label"]
569 url = url + ".gz" 591 url = url + ".gz"
570 trackDict = { 592 trackDict = {
571 "type": "FeatureTrack", 593 "type": "FeatureTrack",