def main():
parser = argparse.ArgumentParser(description='Ferramenta de anotação do PhySketch Dataset')
parser.add_argument("-a", "--annotator", help="Executa processo de anotação", action='store_true')
parser.add_argument("-c", "--cropper", help="Executa processo de recorte de base", action='store_true')
parser.add_argument("-z", "--viewer", help="Executa processo de visualização de base", action='store_true')
parser.add_argument("-g", "--generator", help="Executa processo de geração de cenário", action='store_true')
parser.add_argument("-i", "--input", help="Pasta contendo estrutura /Dataset", required=True)
parser.add_argument("-s", "--startAt", help="Pula -s imagens", default=0, type=int)
#parser.add_argument("-o", "--output", help="Pasta de destino", required=True)
parser.add_argument("-v", "--verbose", help="Verbose", action='store_true')
args = parser.parse_args()
cfg.OUTPUT_DIR = os.path.join(args.input, "annotated")
cfg.OUTPUT_CROP_DIR = os.path.join(args.input, "cropped")
cfg.START_AT = args.startAt
if args.verbose:
log.basicConfig(format="%(levelname)s: %(message)s", level=log.DEBUG)
log.info("Verbose output.")
else:
log.basicConfig(format="%(levelname)s: %(message)s")
if args.annotator:
import annotator as an
cfg.INPUT_DIR = os.path.join(args.input, "cropped")
ant = an.Annotator()
ant.run()
elif args.cropper:
import cropper as cr
cfg.INPUT_DIR = os.path.join(args.input, "raw")
ant = cr.Cropper()
ant.run()
elif args.viewer:
import viewer as vw
cfg.INPUT_DIR = os.path.join(args.input)
vw = vw.Viewer()
elif args.generator:
import scene_generator as sc
cfg.INPUT_DIR = os.path.join(args.input)
sc = sc.SceneGenerator()
else:
log.error("ERRO: SELECIONE UM PROCESSO")
def main():
save_splices = False
save_exon_bounds = True
save_ann = True
args = get_args()
wrapper_path = "/oak/stanford/groups/horence/Roozbeh/single_cell_project/scripts/STAR_wrapper/"
#annotator_path = "{}annotators/pyensembl_{}.pkl".format(wrapper_path, args.assembly)
annotator_path = "{}annotators/{}.pkl".format(wrapper_path, args.assembly)
print(annotator_path)
gtf_df = get_gtf(args.gtf_path)
if save_exon_bounds:
exon_bounds = get_exon_bounds(gtf_df)
pickle.dump(
exon_bounds,
open(
"{}annotators/{}_exon_bounds.pkl".format(
wrapper_path, args.assembly), "wb"))
print("{}annotators/{}_exon_bounds.pkl".format(wrapper_path,
args.assembly))
if save_splices:
splices = get_splices(gtf_df)
pickle.dump(
splices,
open(
"{}annotators/{}_splices.pkl".format(wrapper_path,
args.assembly), "wb"))
print("{}annotators/{}_splices.pkl".format(wrapper_path,
args.assembly))
# if os.path.exists(annotator_path):
# ann = pickle.load(open(annotator_path, "rb"))
# else:
# ann = pyensembl.Genome(reference_name = args.assembly,
# annotation_name = "my_genome_features",
# gtf_path_or_url=args.gtf_path)
# ann.index()
if save_ann:
ann = annotator.Annotator(args.gtf_path)
print("got annotator")
pickle.dump(ann, open(annotator_path, "wb"))
print("dumped annotator to {}".format(annotator_path))
def main():
t0 = time.time()
parser = argparse.ArgumentParser(description="create class input file")
parser.add_argument("-g",
"--gtf_path",
help="the path to the gtf file to use for annotation")
parser.add_argument(
"-a",
"--assembly",
help=
"The name of the assembly to pre-load annotation (so, mm10 for the 10th mouse assembly)"
)
parser.add_argument(
"-i",
"--input_path",
help=
"the prefix to the STAR Aligned.out.sam and Chimeric.out.sam directory"
)
parser.add_argument("-I",
"--input_file",
help="specify file name of different format",
default="")
parser.add_argument(
"-s",
"--single",
action="store_true",
help="use this flag if the reads you are running on are single-ended")
parser.add_argument(
"-t",
"--tenX",
action="store_true",
help="indicate whether this is 10X data (with UMIs and barcodes)")
parser.add_argument("-T",
"--test",
action="store_true",
help="save dictionaries and don't write class input")
parser.add_argument("-n",
"--include_one_read",
action="store_true",
help="also save reads where only r1 maps")
# include_one_read = True
args = parser.parse_args()
# gtf_data = pyensembl.Genome(reference_name='hg38', annotation_name='my_genome_features', gtf_path_or_url='/scratch/PI/horence/JuliaO/single_cell/STAR_output/mm10_files/mm10.gtf')
# gtf_data.index()
wrapper_path = "/oak/stanford/groups/horence/Roozbeh/single_cell_project/scripts/STAR_wrapper/"
# annotator_path = "{}annotators/pyensembl_{}.pkl".format(wrapper_path, args.assembly)
annotator_path = "{}annotators/{}.pkl".format(wrapper_path, args.assembly)
if os.path.exists(annotator_path):
ann = pickle.load(open(annotator_path, "rb"))
else:
ann = annotator.Annotator(args.gtf_path)
# ann = pyensembl.Genome(reference_name = args.assembly,
# annotation_name = "my_genome_features",
# gtf_path_or_url=args.gtf_path)
# ann.index()
pickle.dump(ann, open(annotator_path, "wb"))
fastqIdStyle = "complete"
print("initiated annotator: {}".format(time.time() - t0))
# gtf_file = "/scratch/PI/horence/JuliaO/single_cell/STAR_output/mm10_files/mm10.gtf"
# ann = annotator.Annotator(gtf_file, 10000)
## gtf_dict = get_gtf_dict(gtf_file, 10000)
# print("loaded annotator")
# regimes = ["priorityAlign", "priorityChimeric"]
# for regime in regimes:
read_junc_dict = {}
junc_read_dict = {}
# fastq_ids = ["SRR65462{}".format(x) for x in range(73,85)]
# fastq_ids = ["SRR65462{}".format(x) for x in range(79,84)]
# fastq_ids = ["SRR6546284"]
# for fastq_id in fastq_ids:
# print("{}: {}".format(fastq_id, time.time() - t0))
# if args.single:
# samFile1 = "{}2Chimeric.out.sam".format(args.input_path)
# samFile2 = "{}2Aligned.out.sam".format(args.input_path)
# else:
# samFile1 = "{}1Chimeric.out.sam".format(args.input_path)
# samFile2 = "{}1Aligned.out.sam".format(args.input_path)
# samFile3 = "{}2Chimeric.out.sam".format(args.input_path)
# samFile4 = "{}2Aligned.out.sam".format(args.input_path)
if args.input_file != "":
bamFile1 = args.input_file
elif args.single:
bamFile1 = "{}2Aligned.out.bam".format(args.input_path)
else:
bamFile1 = "{}1Aligned.out.bam".format(args.input_path)
bamFile2 = "{}2Aligned.out.bam".format(args.input_path)
if args.single:
read_junc_dict, junc_read_dict, genomic_alignments = STAR_parseBAM(
bamFile1, "r1", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
else:
read_junc_dict, junc_read_dict, genomic_alignments = STAR_parseBAM(
bamFile1, "r1", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
read_junc_dict, junc_read_dict, _ = STAR_parseBAM(
bamFile2, "r2", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# if regime == "priorityAlign":
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile2, "r1align", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r1align", time.time() - t0)
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile1, "r1chim", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r1chim", time.time() - t0)
# elif regime == "priorityChimeric":
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile1, "r1chim", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r1chim", time.time() - t0)
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile2, "r1align", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r1align", time.time() - t0)
# if not args.single:
# if regime == "priorityAlign":
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile4, "r2align", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r2align", time.time() - t0)
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile3, "r2chim", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r2chim", time.time() - t0)
# elif regime == "priorityChimeric":
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile3, "r2chim", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r2chim", time.time() - t0)
# read_junc_dict, junc_read_dict = STAR_parseSam(samFile4, "r2align", read_junc_dict, junc_read_dict, fastqIdStyle, ann)
# print("parsed r2align", time.time() - t0)
# print("len(junc_read_dict)", len(junc_read_dict))
# print("parsed all {}".format(regime), time.time() - t0)
# write_class_file(junc_read_dict,"/scratch/PI/horence/JuliaO/single_cell/scripts/output/create_class_input/{}.tsv".format(fastq_id))
if args.test:
pickle.dump(read_junc_dict,
open("{}read_junc_dict.pkl".format(args.input_path), "wb"))
pickle.dump(junc_read_dict,
open("{}junc_read_dict.pkl".format(args.input_path), "wb"))
else:
write_class_file(
junc_read_dict,
"{}class_input_{}.tsv".format(args.input_path, "WithinBAM"),
args.single, genomic_alignments, args.tenX, args.include_one_read)
print("genomic alignments", genomic_alignments)
import flask
import json
import annotator
import article
import config
import reader
import writer
import numpy as np
application = flask.Flask(__name__)
anne = annotator.Annotator(reader.get_reader(config.reader)(**config.reader_params),
writer.get_writer(config.writer)(**config.writer_params))
valid_users = np.loadtxt('usernames.txt', delimiter = ',', dtype = 'str')
"""
Display the main page.
"""
@application.route('/', methods=['GET'])
def index():
return flask.render_template('index.html')
"""
Start the program.
"""
@application.route('/start/', methods=['GET', 'POST'])
def start():
userid = flask.request.form['userid']
if not(userid in valid_users):
t0 = time.time()
wrapper_path = "/oak/stanford/groups/horence/Roozbeh/single_cell_project/scripts/STAR_wrapper/"
#annotator_path = "{}annotators/pyensembl_{}.pkl".format(wrapper_path, args.assembly)
annotator_path = "{}annotators/{}.pkl".format(wrapper_path, args.assembly)
if os.path.exists(annotator_path):
ann = pickle.load(open(annotator_path, "rb"))
else:
# ann = pyensembl.Genome(reference_name = args.assembly,
# annotation_name = "my_genome_features",
# gtf_path_or_url=args.gtf_path)
# ann.index()
ann = annotator.Annotator(args.gtf_path)
pickle.dump(ann, open(annotator_path, "wb"))
print("initiated annotator: {}".format(time.time() - t0))
if args.single:
l = 2
else:
l = 1
for i in range(l, 3):
SJ_df = pd.read_csv("{}{}SJ.out.tab".format(args.input_path, i),
sep="\t",
names=[
"donor_chromosome", "first_intron_base",
"last_intron_base", "strand", "intron_motif",
"annotated", "num_uniquely_mapping",