def remove_file_node_elevation(self, ):
''' Need lock for caller!'''
self._osm_file = self.get_osm_file_path()
tmpf = self._osm_file.rstrip(".osm") + "-nid-to-elevation.txt"
if os.path.exists(tmpf):
if iprint >= 2: print("remove", tmpf, tmpf + ".old")
movefile(tmpf, tmpf + ".old")
def add_file(logger: Logger, filename: str, verbose: str = "info"):
"""
set up file handler to the logger with handlers
:param logger: the logger
:param filename: name of the logfile
:type filename: str
:param verbose: verbose level
:type verbose: str
"""
file_defined = False
for handler in logger.handlers:
if isinstance(handler, FileHandler):
file_defined = True
if not file_defined:
# back up
if isfile(filename):
movefile(filename, filename + "-bak")
fh = FileHandler(filename)
verbose = getattr(logging, verbose.upper())
logger.setLevel(verbose)
fh.setLevel(logging.DEBUG)
logger.addHandler(fh)
def _copyIfNewerVisit(args, sourceDirname, names):
prefixLen = args[0]
destDirname = args[1] + sourceDirname[prefixLen:]
move = args[2]
dirName = _basename(destDirname)
if (excludeFromCopying.search(dirName) != None):
# Don't recurse into subdirectories
del names[:]
return
# Create the corresponding destination dir if necessary
mkdir(destDirname)
# Iterate through the contents of this directory
for name in names:
source = sourceDirname + '/' + name
if ((excludeFromCopying.search(name) == None) and \
(not os.path.isdir(source))):
# Copy files if newer
dest = destDirname + '/' + name
if (newer(source, dest)):
if move:
print 'mv ' + source + ' ' + dest
shutil.movefile(source, dest)
else:
print 'cp ' + source + ' ' + dest
shutil.copyfile(source, dest)
def __init__(self, tag=""):
self.lg_index = 0
self.my_ip = get_my_ip()
if not os.path.exists(folder):
os.makedirs(folder)
try:
self.my_tname = tag + ip2tarekc[self.my_ip]
except:
self.my_tname = tag + self.my_ip.split(".", 2)[-1]
if iprint >= 2: print(self.my_tname)
self.fd_list = []
self.fnames = []
self.freshness = 0 # latest log always named 0: log-tarekc-`0`-date-txt
tmp = glob.glob(folder + "log*") # log/log*
for fn in tmp:
try:
st = fn.replace(fnamePrefix + self.my_tname + "-",
"").split("-", 1)
ind = int(st[0]) + 1
newfn = fnamePrefix + self.my_tname + "-%d-" % ind + st[-1]
movefile(fn, newfn)
if iprint >= 2: print(fn, newfn)
except:
pass
fmain = fnamePrefix + self.my_tname + "-0-" + datetime.datetime.now(
).strftime("%Y-%m-%d-%H-%M-%S") + ".txt"
if iprint >= 1: print("create", fmain)
fd = open(fmain, "w")
self.fd_list.append(fd)
self.fnames.append(fmain)
self.lg(self.my_tname)
self.lg(self.my_ip)
self.lg(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
self.lg(time.time())
self.lg("\n")
def copyOrMoveFileToDestination(self, move):
src = os.path.join(self.downloadedFileDirectory,
self.downloadedFileName)
destDir = os.path.join(self.destinationSeriesPath,
'Season ' + str(self.seasonNo))
if not os.path.exists(destDir):
os.makedirs(destDir)
pattern, epString = '{}E{:0>2d}', ''
for ep in self.episodeNos:
epString = pattern.format(epString, ep)
destFileName = '{}.S{:0>2d}{}{}'.format(
self.tokenizedFileName, self.seasonNo, epString,
os.path.splitext(self.downloadedFileName)[1])
dest = os.path.join(destDir, destFileName)
if os.path.exists(dest):
os.remove(dest)
if move:
self.createLocalCopy(src)
print 'Moving from.....' + src + '.....' + dest
movefile(src, dest)
print '>>> Move complete...' + dest
else:
print 'Copying from.....' + src + '.....' + dest
copyfile(src, dest)
print '>>> Copy complete...' + dest
def copyIfNewer(source, dest, move=0):
if source == dest:
# Copying in place
return
dest = removeTrailingSlash(dest)
if (not os.path.exists(source)):
# Source does not exist
return
if (not os.path.isdir(source) and newer(source, dest)):
if (move):
print 'mv ' + source + ' ' + dest
shutil.movefile(source, dest)
else:
print 'cp ' + source + ' ' + dest
shutil.copyfile(source, dest)
else:
# Walk is a special iterator that visits all of the
# children and executes the 2nd argument on them.
os.path.walk(source, _copyIfNewerVisit, [len(source), dest, move])
def _copyIfNewerVisit(args, sourceDirname, names):
prefixLen = args[0]
destDirname = args[1] + sourceDirname[prefixLen:]
move = args[2]
dirName = _basename(destDirname)
if (excludeFromCopying.search(dirName) != None):
# Don't recurse into subdirectories
del names[:]
return
# Create the corresponding destination dir if necessary
mkdir(destDirname)
# Iterate through the contents of this directory
for name in names:
source = sourceDirname + '/' + name
if ((excludeFromCopying.search(name) == None) and \
(not os.path.isdir(source))):
# Copy files if newer
dest = destDirname + '/' + name
if (newer(source, dest)):
if move:
print 'mv ' + source + ' ' + dest
shutil.movefile(source, dest)
else:
print 'cp ' + source + ' ' + dest
shutil.copyfile(source, dest)
def copyIfNewer(source, dest, move = 0):
if source == dest:
# Copying in place
return
dest = removeTrailingSlash(dest)
if (not os.path.exists(source)):
# Source does not exist
return
if (not os.path.isdir(source) and newer(source, dest)):
if (move):
print 'mv ' + source + ' ' + dest
shutil.movefile(source, dest)
else:
print 'cp ' + source + ' ' + dest
shutil.copyfile(source, dest)
else:
# Walk is a special iterator that visits all of the
# children and executes the 2nd argument on them.
os.path.walk(source, _copyIfNewerVisit, [len(source), dest, move])
def remove_file_way_speed(self, ):
''' Need lock for caller!'''
self._osm_file = self.get_osm_file_path()
tmpf = self._osm_file.rstrip(".osm") + "-nids-to-speed.txt"
if os.path.exists(tmpf):
if iprint >= 2: print("remove", tmpf, tmpf + ".old")
movefile(tmpf, tmpf + ".old")
tmpf = self.data_dir + os.sep + "cache-%s-nids-to-speed.txt" % self._address_no_space
if os.path.exists(tmpf):
if iprint >= 2: print("remove", tmpf)
os.remove(tmpf)
tmpf = self.data_dir + os.sep + "COMPLETE-way-speed" # defined in 3genOsmCache.py
if os.path.exists(tmpf):
if iprint >= 2: print("remove", tmpf)
os.remove(tmpf)
def movefile(src_fs, src_path, dst_fs, dst_path, chunk_size=16384):
"""Move a file from one filesystem to another. Will use system copyfile, if both files have a syspath.
Otherwise file will be copied a chunk at a time.
src_fs -- Source filesystem object
src_path -- Source path
dst_fs -- Destination filesystem object
dst_path -- Destination filesystem object
chunk_size -- Size of chunks to move if system copyfile is not available (default 16K)
"""
src_syspath = src_fs.getsyspath(src_path, default="")
dst_syspath = dst_fs.getsyspath(dst_path, default="")
# System copy if there are two sys paths
if src_syspath and dst_syspath:
shutil.movefile(src_syspath, dst_syspath)
return
src, dst = None
try:
# Chunk copy
src = src_fs.open(src_path, 'rb')
dst = dst_fs.open(dst_path, 'wb')
while True:
chunk = src.read(chunk_size)
if not chunk:
break
dst.write(chunk)
src_fs.remove(src)
finally:
if src is not None:
src.close()
if dst is not None:
dst.close()
def movefile(src_fs, src_path, dst_fs, dst_path, chunk_size=16384):
"""Move a file from one filesystem to another. Will use system copyfile, if both files have a syspath.
Otherwise file will be copied a chunk at a time.
src_fs -- Source filesystem object
src_path -- Source path
dst_fs -- Destination filesystem object
dst_path -- Destination filesystem object
chunk_size -- Size of chunks to move if system copyfile is not available (default 16K)
"""
src_syspath = src_fs.getsyspath(src_path, default="")
dst_syspath = dst_fs.getsyspath(dst_path, default="")
# System copy if there are two sys paths
if src_syspath and dst_syspath:
shutil.movefile(src_syspath, dst_syspath)
return
src, dst = None
try:
# Chunk copy
src = src_fs.open(src_path, 'rb')
dst = dst_fs.open(dst_path, 'wb')
while True:
chunk = src.read(chunk_size)
if not chunk:
break
dst.write(chunk)
src_fs.remove(src)
finally:
if src is not None:
src.close()
if dst is not None:
dst.close()
def create_read_array(bamfile, index, aws_upload_key, min_poly_t,
max_transcript_length):
"""Create or download a ReadArray object.
:param max_transcript_length:
:param str bamfile: filename of .bam file
:param str index: directory containing index files
:param str aws_upload_key: key where aws files should be uploaded
:param int min_poly_t: minimum number of poly_t nucleotides for a read to be valid
:returns ReadArray, UploadManager: ReadArray object, bamfile ProcessManager
"""
log.info("Filtering aligned records and constructing record database.")
# Construct translator
translator = GeneIntervals(index + "annotations.gtf",
max_transcript_length=max_transcript_length)
read_array, read_names = ReadArray.from_alignment_file(
bamfile, translator, min_poly_t)
# converting sam to bam and uploading to S3, else removing bamfile
if aws_upload_key:
log.info("Uploading bam file to S3.")
upload_bam = "aws s3 mv {fname} {s3link}{prefix}_Aligned.out.bam".format(
fname=bamfile,
s3link=aws_upload_key,
prefix=args.output_prefix)
print(upload_bam)
upload_manager = io.ProcessManager(upload_bam)
upload_manager.run_all()
else:
if os.path.exists(bamfile):
movefile(bamfile, args.output_prefix + "_Aligned.out.bam")
# log.info('Removing bamfile for memory management.')
# rm_bamfile = 'rm %s' % bamfile
# io.ProcessManager(rm_bamfile).run_all()
upload_manager = None
return read_array, upload_manager, read_names
def run(args) -> None:
"""Run SEQC on the files provided in args, given specifications provided on the
command line
:param args: parsed argv, produced by seqc.parser(). This function is only called
when args.subprocess_name is "run".
"""
# import inside module for pickle functionality
# top 2 only needed for post-filtering
import os
import multiprocessing
from seqc import log, ec2, platforms, io, version
from seqc.sequence import fastq
from seqc.alignment import star
from seqc.alignment import sam
from seqc.email_ import email_user
from seqc.read_array import ReadArray
from seqc.core import verify, download
from seqc import filter
from seqc.sequence.gtf import GeneIntervals
from seqc.summary.summary import Section, Summary
import numpy as np
import scipy.io
from shutil import copyfile
from shutil import move as movefile
from seqc.summary.summary import MiniSummary
from seqc.stats.mast import run_mast
import logging
import pickle
import pendulum
# logger = logging.getLogger('weasyprint')
# logger.handlers = [] # Remove the default stderr handler
# logger.setLevel(100)
# logger.addHandler(logging.FileHandler('weasyprint.log'))
def determine_start_point(arguments) -> (bool, bool, bool):
"""
determine where seqc should start based on which parameters were passed.
:param arguments: Namespace object, result of ArgumentParser.parse_args()
:returns merge, align, process_bamfile: indicates whether merging, alignment, and
processing bamfiles should be executed.
"""
if arguments.read_array:
return False, False, False
if arguments.alignment_file:
return False, False, True
if arguments.merged_fastq:
return False, True, True
else:
return True, True, True
def download_input(dir_, arguments):
"""parse input arguments and download any necessary data
:param str dir_: directory to download data to
:param arguments: namespace object from argparse
:return args: updated namespace object reflecting local file paths of downloaded
files
"""
# download basespace data if necessary
if arguments.basespace:
arguments.barcode_fastq, arguments.genomic_fastq = io.BaseSpace.download(
arguments.platform, arguments.basespace, dir_,
arguments.basespace_token)
# get a list of input FASTQ files
# download from AWS S3 if the URI is prefixed with s3://
arguments.genomic_fastq = download.s3_data(arguments.genomic_fastq,
dir_ + "/genomic_fastq/")
arguments.barcode_fastq = download.s3_data(arguments.barcode_fastq,
dir_ + "/barcode_fastq/")
# get merged fastq file, unzip if necessary
arguments.merged_fastq = (download.s3_data(
[arguments.merged_fastq], dir_ +
"/")[0] if arguments.merged_fastq is not None else None)
# get a path to the STAR index files
# download from AWS S3 if the URI is prefixed with s3://
if any((arguments.alignment_file, arguments.read_array)):
index_link = arguments.index + "annotations.gtf"
else:
index_link = arguments.index
index_files = download.s3_data([index_link], dir_ + "/index/")
# use the first filename in the list to get the index directory
# add a trailing slash to make the rest of the code not break;;
# e.g. test-data/index/chrStart.txt --> test-data/index/
arguments.index = os.path.dirname(index_files[0]) + "/"
# get a list of whitelisted barcodes files
# download from AWS S3 if the URI is prefixed with s3://
arguments.barcode_files = download.s3_data(arguments.barcode_files,
dir_ + "/barcodes/")
# check if `alignment_file` is specified
if arguments.alignment_file:
# get the alignment filename (*.bam)
# download from AWS S3 if the URI is prefixed with s3://
arguments.alignment_file = download.s3_data(
[arguments.alignment_file], dir_ + "/")[0]
# check if `read_array` is specified
if arguments.read_array:
# get the readarray fileanem (*.h5)
# download from AWS S3 if the URI is prefixed with s3://
arguments.read_array = download.s3_data([arguments.read_array],
dir_ + "/")[0]
return arguments
def merge_fastq_files(
technology_platform,
barcode_fastq: [str],
output_stem: str,
genomic_fastq: [str],
) -> (str, int):
"""annotates genomic fastq with barcode information; merging the two files.
:param technology_platform: class from platforms.py that defines the
characteristics of the data being processed
:param barcode_fastq: list of str names of fastq files containing barcode
information
:param output_stem: str, stem for output files
:param genomic_fastq: list of str names of fastq files containing genomic
information
:returns str merged_fastq: name of merged fastq file
"""
# hack:
# Due to the non-platform agnostic glob behavior,
# it is possible that L001_R1 is merged with L002_R2 (not L001_R2).
# to avoid this problem, we first sort.
# this is a temporary hacky solution
barcode_fastq = sorted(barcode_fastq)
genomic_fastq = sorted(genomic_fastq)
log.info("Merging genomic reads and barcode annotations.")
for bar_fq, gen_fq in zip(barcode_fastq, genomic_fastq):
log.info("Merge {} with {}".format(os.path.basename(bar_fq),
os.path.basename(gen_fq)))
merged_fastq = fastq.merge_paired(
merge_function=technology_platform.merge_function,
fout=output_stem + "_merged.fastq",
genomic=genomic_fastq,
barcode=barcode_fastq,
)
# delete genomic/barcode fastq files after merged.fastq creation
# log.info('Removing original fastq file for memory management.')
# delete_fastq = ' '.join(['rm'] + genomic_fastq + barcode_fastq)
# io.ProcessManager(delete_fastq).run_all()
return merged_fastq
def align_fastq_records(merged_fastq, dir_, star_args, star_index, n_proc,
aws_upload_key) -> (str, str, io.ProcessManager):
"""
Align fastq records.
:param merged_fastq: str, path to merged .fastq file
:param dir_: str, stem for output files
:param star_args: dict, extra keyword arguments for STAR
:param star_index: str, file path to directory containing STAR index
:param n_proc: int, number of STAR processes to initiate
:param aws_upload_key: str, location to upload files, or None if seqc was
initiated from a merged fastq file.
:return bamfile, input_data, upload_manager: (str, str, io.ProcessManager)
name of .sam file containing aligned reads, indicator of which data was used as
input, and a ProcessManager for merged fastq files
"""
log.info("Aligning merged fastq records.")
alignment_directory = dir_ + "/alignments/"
os.makedirs(alignment_directory, exist_ok=True)
if star_args is not None:
star_kwargs = dict(a.strip().split("=") for a in star_args)
else:
star_kwargs = {}
bamfile = star.align(merged_fastq, star_index, n_proc,
alignment_directory, **star_kwargs)
log.info("Gzipping merged fastq file.")
if pigz:
pigz_zip = "pigz --best -f {fname}".format(fname=merged_fastq)
else:
pigz_zip = "gzip -f {fname}".format(fname=merged_fastq)
pigz_proc = io.ProcessManager(pigz_zip)
pigz_proc.run_all()
pigz_proc.wait_until_complete() # prevents slowing down STAR alignment
merged_fastq += ".gz" # reflect gzipped nature of file
if aws_upload_key:
log.info("Uploading gzipped merged fastq file to S3.")
merge_upload = "aws s3 mv {fname} {s3link}".format(
fname=merged_fastq, s3link=aws_upload_key)
upload_manager = io.ProcessManager(merge_upload)
upload_manager.run_all()
else:
# log.info('Removing merged fastq file for memory management.')
# rm_merged = 'rm %s' % merged_fastq
# io.ProcessManager(rm_merged).run_all()
upload_manager = None
return bamfile, upload_manager
def create_read_array(bamfile, index, aws_upload_key, min_poly_t,
max_transcript_length):
"""Create or download a ReadArray object.
:param max_transcript_length:
:param str bamfile: filename of .bam file
:param str index: directory containing index files
:param str aws_upload_key: key where aws files should be uploaded
:param int min_poly_t: minimum number of poly_t nucleotides for a read to be valid
:returns ReadArray, UploadManager: ReadArray object, bamfile ProcessManager
"""
log.info("Filtering aligned records and constructing record database.")
# Construct translator
translator = GeneIntervals(index + "annotations.gtf",
max_transcript_length=max_transcript_length)
read_array, read_names = ReadArray.from_alignment_file(
bamfile, translator, min_poly_t)
# converting sam to bam and uploading to S3, else removing bamfile
if aws_upload_key:
log.info("Uploading bam file to S3.")
upload_bam = "aws s3 mv {fname} {s3link}{prefix}_Aligned.out.bam".format(
fname=bamfile,
s3link=aws_upload_key,
prefix=args.output_prefix)
print(upload_bam)
upload_manager = io.ProcessManager(upload_bam)
upload_manager.run_all()
else:
if os.path.exists(bamfile):
movefile(bamfile, args.output_prefix + "_Aligned.out.bam")
# log.info('Removing bamfile for memory management.')
# rm_bamfile = 'rm %s' % bamfile
# io.ProcessManager(rm_bamfile).run_all()
upload_manager = None
return read_array, upload_manager, read_names
# ######################## MAIN FUNCTION BEGINS HERE ################################
log.setup_logger(args.log_name, args.debug)
with ec2.instance_clean_up(
email=args.email,
upload=args.upload_prefix,
log_name=args.log_name,
debug=args.debug,
terminate=args.terminate,
running_remote=args.remote,
):
start_run_time = pendulum.now()
log.notify("SEQC=v{}".format(version.__version__))
log.notify("STAR=v{}".format(star.get_version()))
log.notify("samtools=v{}".format(sam.get_version()))
pigz, mutt = verify.executables("pigz", "mutt")
if mutt:
log.notify(
"mutt executable identified, email will be sent when run "
"terminates. ")
else:
log.notify(
"mutt was not found on this machine; an email will not be sent to "
"the user upon termination of SEQC run.")
# turn off lower coverage filter for 10x
if ((args.platform == "ten_x") or (args.platform == "ten_x_v2")
or (args.platform == "ten_x_v3")):
args.filter_low_coverage = False
if args.platform == "ten_x_v2" or args.platform == "ten_x_v3":
log.notify("Setting min_poly_t=0 for 10x v2 & v3")
args.min_poly_t = 0
max_insert_size = args.max_insert_size
if args.filter_mode == "scRNA-seq":
# for scRNA-seq
if ((args.platform == "ten_x") or (args.platform == "ten_x_v2")
or (args.platform == "ten_x_v3")):
# set max_transcript_length (max_insert_size) = 10000
max_insert_size = 10000
log.notify(
"Full length transcripts are used for read mapping in 10x data."
)
elif args.filter_mode == "snRNA-seq":
# for snRNA-seq
# e.g. 2304700 # hg38
# e.g. 4434881 # mm38
max_insert_size = args.max_insert_size
else:
# all others
max_insert_size = args.max_insert_size
log.notify("max_insert_size is set to {}".format(max_insert_size))
log.args(args)
# e.g.
# --output-prefix=test-data/_outs/test
# output_dir=test-data
# output_prefix=test
output_dir, output_prefix = os.path.split(args.output_prefix)
if not output_dir:
output_dir = "."
else:
os.makedirs(output_dir, exist_ok=True)
# check if the platform name provided is supported by seqc
# todo move into verify for run
platform_name = verify.platform_name(args.platform)
platform = platforms.AbstractPlatform.factory(
platform_name) # returns platform
n_processes = multiprocessing.cpu_count(
) - 1 # get number of processors
merge, align, process_bamfile = determine_start_point(args)
args = download_input(output_dir, args)
if args.platform == "in_drop_v5":
platform = platform.build_cb2_barcodes(args.barcode_files)
log.notify("Built cb2 barcode hash for v5 barcodes.")
if merge:
if args.min_poly_t is None: # estimate min_poly_t if it was not provided
args.min_poly_t = filter.estimate_min_poly_t(
args.barcode_fastq, platform)
log.notify("Estimated min_poly_t={!s}".format(args.min_poly_t))
args.merged_fastq = merge_fastq_files(platform, args.barcode_fastq,
args.output_prefix,
args.genomic_fastq)
# SEQC was started from input other than fastq files
if args.min_poly_t is None:
args.min_poly_t = 0
log.warn(
"Warning: SEQC started from step other than unmerged fastq with "
"empty --min-poly-t parameter. Continuing with --min-poly-t 0."
)
if align:
upload_merged = args.upload_prefix if merge else None
args.alignment_file, manage_merged = align_fastq_records(
args.merged_fastq,
output_dir,
args.star_args,
args.index,
n_processes,
upload_merged,
)
else:
manage_merged = None
if process_bamfile:
# if the starting point was a BAM file (i.e. args.alignment_file=*.bam & align=False)
# do not upload by setting this to None
upload_bamfile = args.upload_prefix if align else None
ra, manage_bamfile, read_names = create_read_array(
args.alignment_file,
args.index,
upload_bamfile,
args.min_poly_t,
max_insert_size,
)
else:
manage_bamfile = None
ra = ReadArray.load(args.read_array)
# fixme: the old read_array doesn't have read_names
read_names = None
# create the first summary section here
status_filters_section = Section.from_status_filters(
ra, "initial_filtering.html")
sections = [status_filters_section]
# Skip over the corrections if read array is specified by the user
if not args.read_array:
# Correct barcodes
log.info("Correcting barcodes and estimating error rates.")
error_rate, df_cb_correction = platform.apply_barcode_correction(
ra, args.barcode_files)
if df_cb_correction is not None and len(df_cb_correction) > 0:
df_cb_correction.to_csv(
args.output_prefix + "_cb-correction.csv.gz",
index=False,
compression="gzip",
)
# Resolve multimapping
log.info("Resolving ambiguous alignments.")
mm_results = ra.resolve_ambiguous_alignments()
# 121319782799149 / 614086965 / pos=49492038 / AAACATAACG
# 121319782799149 / 512866590 / pos=49490848 / TCAATTAATC (1 hemming dist away from TCAATTAATT)
# ra.data["rmt"][91490] = 512866590
# ra.positions[91490] = 49492038
# correct errors
log.info("Identifying RMT errors.")
df_umi_correction = platform.apply_rmt_correction(ra, error_rate)
if df_umi_correction is not None and len(df_umi_correction) > 0:
df_umi_correction.to_csv(
args.output_prefix + "_umi-correction.csv.gz",
index=False,
compression="gzip",
)
# Apply low coverage filter
if platform.filter_lonely_triplets:
log.info("Filtering lonely triplet reads")
ra.filter_low_coverage(alpha=args.low_coverage_alpha)
log.info("Saving read array.")
ra.save(args.output_prefix + ".h5")
# generate a file with read_name, corrected cb, corrected umi
# read_name already has pre-corrected cb & umi
# log.info("Saving correction information.")
# ra.create_readname_cb_umi_mapping(
# read_names, args.output_prefix + "_correction.csv.gz"
# )
# Summary sections
# create the sections for the summary object
sections += [
Section.from_cell_barcode_correction(
ra, "cell_barcode_correction.html"),
Section.from_rmt_correction(ra, "rmt_correction.html"),
Section.from_resolve_multiple_alignments(
mm_results, "multialignment.html"),
]
# create a dictionary to store output parameters
mini_summary_d = dict()
# filter non-cells
log.info("Creating counts matrix.")
sp_reads, sp_mols = ra.to_count_matrix(sparse_frame=True,
genes_to_symbols=args.index +
"annotations.gtf")
# generate 10x compatible count matrix
log.info("Creating 10x compatible counts matrix.")
ra.to_10x_count_matrix(genes_to_symbols=args.index + "annotations.gtf")
# Save sparse matrices
log.info("Saving sparse matrices")
scipy.io.mmwrite(args.output_prefix + "_sparse_read_counts.mtx",
sp_reads.data)
scipy.io.mmwrite(args.output_prefix + "_sparse_molecule_counts.mtx",
sp_mols.data)
# Indices
df = np.array([np.arange(sp_reads.shape[0]), sp_reads.index]).T
np.savetxt(
args.output_prefix + "_sparse_counts_barcodes.csv",
df,
fmt="%d",
delimiter=",",
)
# Columns
df = np.array([np.arange(sp_reads.shape[1]), sp_reads.columns]).T
np.savetxt(args.output_prefix + "_sparse_counts_genes.csv",
df,
fmt="%s",
delimiter=",")
log.info("Creating filtered counts matrix.")
cell_filter_figure = args.output_prefix + "_cell_filters.png"
# By pass low count filter for mars seq
(
sp_csv,
total_molecules,
molecules_lost,
cells_lost,
cell_description,
) = filter.create_filtered_dense_count_matrix(
sp_mols,
sp_reads,
mini_summary_d,
plot=True,
figname=cell_filter_figure,
filter_low_count=platform.filter_low_count,
filter_mitochondrial_rna=args.filter_mitochondrial_rna,
filter_low_coverage=args.filter_low_coverage,
filter_low_gene_abundance=args.filter_low_gene_abundance,
)
# Output files
files = [
cell_filter_figure,
args.output_prefix + ".h5",
args.output_prefix + "_sparse_read_counts.mtx",
args.output_prefix + "_sparse_molecule_counts.mtx",
args.output_prefix + "_sparse_counts_barcodes.csv",
args.output_prefix + "_sparse_counts_genes.csv",
"raw_feature_bc_matrix/matrix.mtx.gz",
"raw_feature_bc_matrix/barcodes.tsv.gz",
"raw_feature_bc_matrix/features.tsv.gz",
]
if os.path.exists(args.output_prefix + "_cb-correction.csv.gz"):
files.append(args.output_prefix + "_cb-correction.csv.gz")
if os.path.exists(args.output_prefix + "_umi-correction.csv.gz"):
files.append(args.output_prefix + "_umi-correction.csv.gz")
# Summary sections
# create the sections for the summary object
sections += [
Section.from_cell_filtering(cell_filter_figure,
"cell_filtering.html"),
Section.from_run_time(args.log_name, "seqc_log.html"),
]
# get alignment summary
if os.path.isfile(output_dir + "/alignments/Log.final.out"):
os.rename(
output_dir + "/alignments/Log.final.out",
args.output_prefix + "_alignment_summary.txt",
)
# Upload files and summary sections
files += [args.output_prefix + "_alignment_summary.txt"]
sections.insert(
0,
Section.from_alignment_summary(
args.output_prefix + "_alignment_summary.txt",
"alignment_summary.html",
),
)
cell_size_figure = args.output_prefix + "_cell_size_distribution.png"
index_section = Section.from_final_matrix(sp_csv, cell_size_figure,
"cell_distribution.html")
seqc_summary = Summary(args.output_prefix + "_summary", sections,
index_section)
seqc_summary.prepare_archive()
seqc_summary.import_image(cell_filter_figure)
seqc_summary.import_image(cell_size_figure)
seqc_summary.render()
# create a .tar.gz with `test_summary/*`
summary_archive = seqc_summary.compress_archive()
files += [summary_archive]
# Create a mini summary section
alignment_summary_file = args.output_prefix + "_alignment_summary.txt"
seqc_mini_summary = MiniSummary(
output_dir,
output_prefix,
mini_summary_d,
alignment_summary_file,
cell_filter_figure,
cell_size_figure,
)
seqc_mini_summary.compute_summary_fields(ra, sp_csv)
seqc_mini_summary_json, seqc_mini_summary_pdf = seqc_mini_summary.render(
)
files += [seqc_mini_summary_json, seqc_mini_summary_pdf]
# Running MAST for differential analysis
# file storing the list of differentially expressed genes for each cluster
de_gene_list_file = run_mast(
seqc_mini_summary.get_counts_filtered(),
seqc_mini_summary.get_clustering_result(),
args.output_prefix,
)
files += [de_gene_list_file]
# adding the cluster column and write down gene-cell count matrix
dense_csv = args.output_prefix + "_dense.csv"
sp_csv.insert(loc=0,
column="CLUSTER",
value=seqc_mini_summary.get_clustering_result())
sp_csv.to_csv(dense_csv)
files += [dense_csv]
if args.upload_prefix:
# Upload count matrices files, logs, and return
bucket, key = io.S3.split_link(args.upload_prefix)
for item in files:
try:
ec2.Retry(retries=5)(io.S3.upload_file)(item, bucket, key)
item_name = item.split("/")[-1]
log.info('Successfully uploaded %s to "%s%s".' %
(item, args.upload_prefix, item_name))
except FileNotFoundError:
log.notify(
"Item %s was not found! Continuing with upload..." %
item)
if manage_merged:
manage_merged.wait_until_complete()
log.info('Successfully uploaded %s to "%s"' %
(args.merged_fastq, args.upload_prefix))
if manage_bamfile:
manage_bamfile.wait_until_complete()
log.info('Successfully uploaded %s to "%s"' %
(args.alignment_file, args.upload_prefix))
log.info("SEQC run complete.")
end_run_time = pendulum.now()
running_time = end_run_time - start_run_time
log.info("Running Time={}".format(running_time.in_words()))
# upload logs
if args.upload_prefix:
# upload logs (seqc_log.txt, nohup.log)
bucket, key = io.S3.split_link(args.upload_prefix)
for item in [args.log_name, "./nohup.log"]:
try:
# Make a copy of the file with the output prefix
copyfile(item, args.output_prefix + "_" + item)
print(args.output_prefix + "_" + item)
ec2.Retry(retries=5)(io.S3.upload_file)(
args.output_prefix + "_" + item, bucket, key)
log.info('Successfully uploaded %s to "%s".' %
(item, args.upload_prefix))
except FileNotFoundError:
log.notify(
"Item %s was not found! Continuing with upload..." %
item)
else:
# move the log to output directory
movefile(args.log_name, args.output_prefix + "_" + args.log_name)
# todo local test does not send this email
if mutt:
email_body = (
'<font face="Courier New, Courier, monospace">'
"SEQC RUN COMPLETE.\n\n"
"The run log has been attached to this email and "
"results are now available in the S3 location you specified: "
'"%s"\n\n' % args.upload_prefix)
email_body = email_body.replace("\n",
"<br>").replace("\t", " ")
email_user(summary_archive, email_body, args.email)
def szukaj_w_bazie_i_katalogu(katalog_z, katalog_do):
#-do poprawki
conn = sqlite3.connect(DATABASE_FILE)
cur = conn.cursor()
kat_przesluchane = PurePosixPath(katalog_z)
kat_przesluchane_ = str(kat_przesluchane) + str(SEP)
kat_nieprzesluchane = PurePosixPath(katalog_do)
kat_nieprzesluchane_ = str(kat_nieprzesluchane) + str(SEP)
podcast_heard_val = 0
if (katalog_z == katalog_tok_fm_podcasty_result_dir_przesluchane):
podcast_heard_val = "0"
else:
podcast_heard_val = "1"
Ilosc_przenosin = 0
#Porzadek w katalogu "NIE/PRZESLUCHANE" - uwaga zmienia sie zaleznosc
for root, dirs, files in os.walk(str(kat_przesluchane_)):
for file in files:
if re.search(r'^[0-3][0-9] - [0-9A-Za-z ]*.mp3$', file):
caly_plik_sciezka = os.path.join(root, file)
#lstrip zle dziala!!!
kat_p2_ = caly_plik_sciezka.replace(kat_przesluchane_, "", 1)
#kat_p2=re.search("([a-z A-Z0-9.-]*).([0-9 -]*).([0-3][0-9] - *)([0-9a-z A-Z]*)(\.mp3)",kat_p2_).groups()
kat_p2 = re.search(
"([a-z A-Z0-9.-]*).([0-9 -]*).([0-3][0-9] - *)([0-9a-zA-Z ]*)",
kat_p2_).groups()
kat_p2_name_aud_db = ""
for i in audycje_link:
if audycje_link[i][1].lower() == kat_p2[0].strip().lower():
kat_p2_name_aud_db = i
if not kat_p2_name_aud_db:
print("Blad w nazwie katalogu:", r'"' + kat_p2[0] + r'"')
exit()
kat_p2_name_date_db = kat_p2[1] + "-" + kat_p2[2].rstrip("- ")
kat_p2_NAME_DATE_DB = datetime.strptime(
kat_p2_name_date_db, "%Y - %m-%d").strftime("%d.%m.%Y")
kat_p2_NAME_POD_DB = kat_p2[3].replace(" ", "-")
rok_miesiac = datetime.strptime(kat_p2_NAME_DATE_DB,
"%d.%m.%Y").strftime("%Y - %m")
kat_nieprzesluchane_audycja = kat_nieprzesluchane_ + audycje_link[
kat_p2_name_aud_db][1]
kat_nieprzesluchane_audycja_data = kat_nieprzesluchane_audycja + SEP + rok_miesiac
katalogi_nieprzesluchane = [
kat_nieprzesluchane_, kat_nieprzesluchane_audycja,
kat_nieprzesluchane_audycja_data
]
if kat_p2_name_aud_db:
cur.execute("SELECT name_audition, date_podcast, name_podcast FROM tokfm WHERE name_audition LIKE "
+"'%"+kat_p2_name_aud_db+"%'"\
+" AND date_podcast LIKE "+"'%"+kat_p2_NAME_DATE_DB+"%'"\
+" AND name_podcast LIKE "+"'%"+kat_p2_NAME_POD_DB+"%'"\
+" AND podcast_heard = "+podcast_heard_val\
)
rows = cur.fetchone()
if rows:
for katalog in katalogi_nieprzesluchane:
filenameResult = PurePosixPath(katalog)
if not Path(filenameResult).exists():
Path(filenameResult).mkdir()
movefile(caly_plik_sciezka,
kat_nieprzesluchane_audycja_data)
print("Przenioslem \"" + file + "\" do " +
kat_nieprzesluchane_audycja_data + SEP)
Ilosc_przenosin += 1
cur.close()
conn.close()
print("Ilosc przenosin:", Ilosc_przenosin)
