def loadPicardRNAseqMetrics(infiles, outfile):
'''load picardRNAseqMetrics'''
P.concatenate_and_load(infiles,
outfile,
regex_filename="(.*).picardRNAseqMetrics",
cat="sample_id",
options='-i "sample_id"')
def merge_and_load_region_metagenes(infiles, outfile):
P.concatenate_and_load(
infiles,
outfile,
regex_filename=".+/(.+)-(.+)-(.+)\.vs\.(.+).tsv.gz",
cat="source,condition,replicate,geneset",
options=" -i source -i condition -i replicate -i geneset")
def loadpicardAlignmentSummary(infiles, outfile):
'''load the complexity metrics to a single table in the db'''
P.concatenate_and_load(infiles,
outfile,
regex_filename="(.*).picardAlignmentStats",
cat="sample_id",
options='-i "sample_id"')
def load_quasar(infiles, outfile):
P.concatenate_and_load(
infiles,
outfile,
regex_filename="quasar_out.dir/(.+).pileup.bed.quasarin.tsv",
options=
"-i track -i annotations.rsID -i annotations.chr -i annotations.pos0 --replace-header",
header="track,rsID,chr,pos,betas,beta_ses,pval")
def mergeAllQuants(infiles, outfile):
job_memory = "6G"
P.concatenate_and_load(infiles,
outfile,
regex_filename="quantification.dir/(.+).sf",
options="-i transcript_id"
" -i Name -i Length -i EffectiveLength"
" -i TPM -i NumReads -i track"
" -i source")
def loadTranscriptClassification(infiles, outfile):
P.concatenate_and_load(infiles,
outfile,
regex_filename=".+/(.+).class.gz",
options="-i transcript_id -i gene_id"
" -i match_gene_id -i match_transcript_id"
" -i source",
job_memory="64G")
def loadDuplicationMetrics(infiles, outfile):
'''
Import duplication metrics into project database.
'''
P.concatenate_and_load(
infiles, outfile,
regex_filename="(.*)-count/.*.txt",
has_titles=True,
options="",
cat="sample")
def loadRawQcMetricsPerBarcode(infiles, outfile):
'''
load the total UMI and barcode rank into a sqlite database
'''
P.concatenate_and_load(
infiles, outfile,
regex_filename="(.*)-count/.*.txt",
has_titles=True,
options="",
cat="sample")
def loadCellrangerCountMetrics(infiles, outfile):
'''
load the summary statistics for each run into a csvdb file
'''
P.concatenate_and_load(
infiles, outfile,
regex_filename="(.*)-count/.*.txt",
has_titles=True,
options="",
cat="sample")
def loadSalmon(infiles, outfile):
'''load the salmon results'''
tables = [x.replace(".log", "/quant.sf") for x in infiles]
P.concatenate_and_load(tables,
outfile,
regex_filename=".*/(.*)/quant.sf",
cat="sample_id",
options="-i Name",
job_memory=PARAMS["sql_himem"])
def mergeAllQuants(infiles, outfile):
job_threads = 3
P.concatenate_and_load(
infiles,
outfile,
regex_filename="quantification.dir/(.*)_agg-agg-agg.sf",
options="-i Name -i Length -i EffectiveLength"
" -i TPM -i NumReads -i track"
" -i source",
job_memory="64G")
if not os.path.isfile("mapping_rates.txt"):
statement = ''' bash /shared/sudlab1/General/projects/UTRONs/MyFiles/scripts/mapping_rates_script.sh '''
P.run(statement)
else:
pass
def loadUtronIDs(infiles, outfile):
job_threads = 3
header = "track,transcript_id"
options = "-i track -i transcript_id"
if not outfile == "all_utrons_ids.load":
header += ",match_transcript_id"
options += " -i match_transcript_id"
P.concatenate_and_load(infiles,
outfile,
regex_filename=".+/(.+)\..+\.ids.gz",
has_titles=False,
cat="track",
header=header,
options=options,
job_memory="64G")
def loadSeedTables(infiles, outfile):
P.concatenate_and_load(infiles, outfile,
regex_filename=".+/(.+)\.(?:meme|dreme|memechip).tsv")
def mergeAndLoadTrackComparisons(infiles, outfile):
P.concatenate_and_load(infiles, outfile,
regex_filename=(".+/(.+)_to_(.+).tomtom"),
cat="track1,track2",
options="-i track1 -i track2")
