def test_cluster(self):
mod_dir = os.path.dirname(inspect.getfile(seqcluster)).replace("seqcluster/", "")
os.chdir(os.path.join(mod_dir, "data/examples"))
arg = namedtuple('args', 'debug print_debug MIN_SEQ')
args = arg(True, True, 1)
seqL = parse_ma_file("seqs_set.ma")
c = pybedtools.BedTool("2_clusters_2_seqs_shared")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info("Start reduceloci test")
clus_obj = detect_clusters(c, seqL, args.MIN_SEQ)
clusLred = reduceloci(clus_obj, ".")
def test_database(self):
if find_cmd("sqlite3"):
with make_workdir() as workdir:
arg = namedtuple('args', 'debug print_debug json ')
args = arg(True, True, "../../data/examples/seqcluster.json")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Create database")
make_database(data)
def test_database(self):
if find_cmd("sqlite3"):
with make_workdir() as workdir:
arg = namedtuple('args', 'debug print_debug json ')
args = arg(True, True, "../../data/examples/seqcluster.json")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Create database")
make_database(data)
def test_databse(self):
if find_cmd("sqlite3"):
mod_dir = os.path.dirname(inspect.getfile(seqcluster)).replace("seqcluster/", "")
os.chdir(os.path.join(mod_dir, "data/examples"))
arg = namedtuple('args', 'debug print_debug json ')
args = arg(True, True, "seqcluster.json")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Create databse")
make_database(data)
def test_predict(self):
if find_cmd("tRNAscan-SE"):
mod_dir = os.path.dirname(inspect.getfile(seqcluster)).replace("seqcluster/", "")
os.chdir(os.path.join(mod_dir, "data/examples"))
out_dir = os.path.join(mod_dir, "data/examples/predictions")
arg = namedtuple('args', 'debug print_debug MIN_SEQ json reference')
args = arg(True, True, 1, "seqcluster.json", "../genomes/genome.fa")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Start prediction")
make_predictions(data, out_dir, args)
def test_databse(self):
if find_cmd("sqlite3"):
mod_dir = os.path.dirname(inspect.getfile(seqcluster)).replace(
"seqcluster/", "")
os.chdir(os.path.join(mod_dir, "data/examples"))
arg = namedtuple('args', 'debug print_debug json ')
args = arg(True, True, "seqcluster.json")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Create databse")
make_database(data)
def test_predict(self):
if find_cmd("tRNAscan-SE"):
mod_dir = os.path.dirname(inspect.getfile(seqcluster)).replace(
"seqcluster/", "")
os.chdir(os.path.join(mod_dir, "data/examples"))
out_dir = os.path.join(mod_dir,
"data/examples/test_out_predictions")
arg = namedtuple('args',
'debug print_debug MIN_SEQ json reference')
args = arg(True, True, 1, "seqcluster.json",
"../genomes/genome.fa")
initialize_logger(".", args.debug, args.print_debug)
logger = mylog.getLogger(__name__)
logger.info(args)
logger.info("Reading data")
data = load_data(args.json)
logger.info("Start prediction")
is_tRNA(data, out_dir, args)
def main(**kwargs):
kwargs = parse_cl(sys.argv[1:])
initialize_logger(kwargs['args'].out, kwargs['args'].debug, kwargs['args'].print_debug)
logger = mylog.getLogger(__name__)
start = time.time()
if "prepare" in kwargs:
logger.info("Run prepare")
prepare(kwargs["args"])
elif "cluster" in kwargs:
logger.info("Run cluster")
cluster(kwargs["args"])
elif "report" in kwargs:
logger.info("Run report")
report(kwargs["args"])
elif "predict" in kwargs:
logger.info("Run predictions")
predictions(kwargs["args"])
elif "target" in kwargs:
logger.info("Run target annotation")
targets_enrichment(kwargs["args"])
elif "seqbuster" in kwargs:
logger.info("Run seqbuster")
miraligner(kwargs["args"])
elif "explore" in kwargs:
logger.info("Run explore")
explore(kwargs["args"])
elif "stats" in kwargs:
logger.info("Run stats")
stats(kwargs["args"])
elif "collapse" in kwargs:
logger.info("Run collapse")
collapse_fastq(kwargs["args"])
elif "simulator" in kwargs:
logger.info("Run simulator")
simulate(kwargs["args"])
logger.info('It took %.3f minutes' % ((time.time()-start)/60))
from seqcluster.libs.utils import file_exists
import seqcluster.libs.logger as mylog
from seqcluster.libs import do
from seqcluster.libs.read import load_data
from seqcluster.libs.mystats import up_threshold
from seqcluster.detect.cluster import detect_clusters, clean_bam_file, peak_calling, detect_complexity
from seqcluster.detect.description import best_precursor
from seqcluster.libs.annotation import anncluster
from seqcluster.libs.inputs import parse_ma_file
from seqcluster.detect.metacluster import reduceloci, _get_seqs
from seqcluster.libs.tool import generate_position_bed
from seqcluster.libs.classes import *
import seqcluster.libs.parameters as param
from seqcluster.db import make_database
logger = mylog.getLogger(__name__)
def cluster(args):
"""
Creating clusters
"""
args = _check_args(args)
read_stats_file = op.join(args.dir_out, "read_stats.tsv")
if file_exists(read_stats_file):
os.remove(read_stats_file)
bam_file, seq_obj = _clean_alignment(args)
logger.info("Parsing matrix file")
from operator import itemgetter
from seqcluster.libs import pysen
import numpy as np
import seqcluster.libs.logger as mylog
from seqcluster.libs.classes import *
# from seqcluster.function.peakdetect import peakdetect as peakdetect
logger = mylog.getLogger(__name__)
def sort_precursor(c, loci):
"""
Sort loci according to number of sequences mapped there.
"""
# Original Py 2.7 code
#data_loci = map(lambda (x): [x, loci[x].chr, int(loci[x].start), int(loci[x].end), loci[x].strand, len(c.loci2seq[x])], c.loci2seq.keys())
# 2to3 suggested Py 3 rewrite
data_loci = [[x, loci[x].chr, int(loci[x].start), int(loci[x].end), loci[x].strand, len(c.loci2seq[x])] for x in list(c.loci2seq.keys())]
data_loci = sorted(data_loci, key=itemgetter(5), reverse=True)
return data_loci
def best_precursor(clus, loci):
"""
Select best precursor asuming size around 100 nt
"""
data_loci = sort_precursor(clus, loci)
current_size = data_loci[0][5]
best = 0
import seqcluster.libs.logger as mylog
import os
from seqcluster.libs.classes import annotation, dbannotation
logger = mylog.getLogger("run")
def read_gtf_line(cols, field="name"):
"""parse gtf line to get class/name information"""
field = field.lower()
try:
group = cols[2]
attrs = cols[8].split(";")
name = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith(field)]
if not name:
name = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith("gene_id")]
if not name:
name = ["None"]
biotype = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith("biotype")]
if biotype:
group = biotype[0]
c = cols[0]
s = int(cols[3])
e = int(cols[4])
st = cols[6]
return [c, s, e, st, group, name[0]]
except(Exception, e):
logger.error(cols)
logger.error("File is not in correct format")
logger.error("Expect chr source feature start end . strand attributes")
