def randomize(self):
_annotation = annotation()
_annotation.randomize()
self.annotation = _annotation
self.name = self.generate_name()
self.identifiers = self.generate_identifiers(
randomizer.randint(self.field_min_number, self.field_max_number))
def randomize(self, headers):
common.usedRandomize()
_annotation = annotation()
_annotation.randomize()
self.annotation = _annotation
self.name = self.generate_name()
self.headers = randomizer.sample(headers,
randomizer.randint(0, len(headers)))
def load_annotation_file(self, annotation_file):
"""TODO: Docstring for load_annotation_file.
:returns: TODO
"""
list_of_annotations = []
num_annotations = 0
root = ET.parse(annotation_file).getroot()
folder = root.find('folder').text
filename = root.find('filename').text
size = root.find('size')
disp_width = int(size.find('width').text)
disp_height = int(size.find('height').text)
for obj in root.findall('object'):
bbox = obj.find('bndbox')
xmin = int(bbox.find('xmin').text)
xmax = int(bbox.find('xmax').text)
ymin = int(bbox.find('ymin').text)
ymax = int(bbox.find('ymax').text)
width = xmax - xmin
height = ymax - ymin
if width > (kMaxRatio * disp_width) or height > (kMaxRatio *
disp_height):
continue
if ((xmin < 0) or (ymin < 0) or (xmax <= xmin) or (ymax <= ymin)):
continue
objAnnotation = annotation()
objAnnotation.setbbox(xmin, xmax, ymin, ymax)
objAnnotation.setWidthHeight(disp_width, disp_height)
objAnnotation.setImagePath(os.path.join(folder, filename))
list_of_annotations.append(objAnnotation)
num_annotations = num_annotations + 1
return list_of_annotations, num_annotations
logger.info('A extraction of information is done.')
################# R1 : get sample information ########
(sample_dic, sample_list, normal_list, tumor_list, paired_list,
unpaired_list) = get_sample_list(sample_file)
print sample_dic
file_dic = get_file_name(options.basecall, sample_list)
print_sample(sample_list, normal_list, tumor_list, paired_list, unpaired_list)
############## Generation of picard object
picard = picard(params, options.basecall, file_dic)
bwa = bwa(params, file_dic)
gatk = gatk(params, options.basecall, file_dic)
somatic = somatic(params, file_dic)
breakmer = breakmer(options.basecall, file_dic)
anno = annotation(params, file_dic)
################ R2 : Extract Illumina Barcodes and Illumina Basecalls To Sam ####################
job_id = get_start_jobid()
cmd = []
cmd.append(picard.ExtractIlluminaBarcodes())
cmd.append(picard.IlluminaBasecallsToSam())
cmd2 = '\n'.join(cmd)
file_name = '01.BaseCall.%s' % job_id
wfile = open('%s/%s.sh' % (log_dir, file_name), 'w')
wfile.write('%s\n' % pbs_header1(file_name, cpu_no['basecall'], cmd2))
wfile.close()
cmd3 = 'qsub %s/%s.sh' % (log_dir, file_name)
import heatmap
import annotation
import volcano_plot
import scatter_and_violin_plots
# The outputs are already in the output_file. Running this client file will
# give you the same thing as the outputs in that file
# Will output a heatmap
print(heatmap.heatmap())
# Will output a new csv file: results_L-vs-NL_full_annotated
# It will show up within the Final Project folder
# This will take some time as it needs to query
print(annotation.annotation("results_L-vs-NL_full.csv"))
# Will output a volcano plot
print(volcano_plot.volcano_plot())
# Will output a scatter plot
print(scatter_and_violin_plots.scatterplot())
# Will output a violin plot
print(scatter_and_violin_plots.violin_plot())
def randomize(self):
rnd = randomizer.randint(self.min_list_size, self.max_list_size)
for x in range(0, rnd):
_annotation = annotation()
_annotation.randomize()
self.annotation_list.append(_annotation)
################# R1 : get sample information ########
(sample_dic, sample_list, normal_list, tumor_list, paired_list, unpaired_list) = get_sample_list(sample_file)
print sample_dic
file_dic = get_file_name(options.basecall, sample_list)
print_sample(sample_list, normal_list, tumor_list, paired_list, unpaired_list)
############## Generation of picard object
picard = picard(params, options.basecall, file_dic)
bwa = bwa(params, file_dic)
gatk = gatk(params, options.basecall, file_dic)
somatic = somatic(params, file_dic)
breakmer = breakmer(options.basecall, file_dic)
anno = annotation(params, file_dic)
################ R2 : Extract Illumina Barcodes and Illumina Basecalls To Sam ####################
job_id = get_start_jobid()
cmd = []
cmd.append(picard.ExtractIlluminaBarcodes())
cmd.append(picard.IlluminaBasecallsToSam())
cmd2 = '\n'.join(cmd)
file_name = '01.BaseCall.%s' % job_id
wfile = open('%s/%s.sh' % (log_dir, file_name),'w')
wfile.write('%s\n' % pbs_header1(file_name, cpu_no['basecall'], cmd2))
wfile.close()
def main(args):
programDirectory = os.path.dirname(os.path.abspath(__file__))
#read the project file
projects = {}
for file in os.listdir(os.path.join(programDirectory,"projects")):
if file.endswith(".txt") and not file.endswith("example.txt"):
with open(os.path.join(programDirectory,"projects" ,file)) as ongoing_fd:
projectID=file.split("/")[-1]
projectID=file.replace(".txt","")
#the user has selected a project manually, and it is not this one
#then there is really nothing to do.
if not (args.project and (args.project != projectID)):
projects[projectID]={};
for line in ongoing_fd:
try:
if line[0] != "#":
info=line.strip();
info = info.split("\t")
projects[projectID][info[0]]=info[1:]
except:
#the pipeline should not crash if the user adds some newlines etc to the project file
pass
# Read the config file
(working_dir, available_tools, account, exclude,modules,recursive) = readConfigFile.readConfigFile(programDirectory)
path_to_bam=""
default_working_dir=working_dir
for project in projects:
#initiate the project parameters based on the project dictionary
project_path = projects[project]["bam"]
projectName = project
#set the output,genmod and frequency db path
if not projects[project]["output"]:
working_dir = default_working_dir
else:
working_dir= projects[project]["output"][0]
if not projects[project]["genmod"]:
genmod_file = os.path.join(programDirectory,"genmod")
else:
genmod_file=projects[project]["genmod"][0]
if not projects[project]["db"]:
frequency_db=os.path.join(working_dir, project,"FindSV","database")
else:
frequency_db=projects[project]["db"][0]
processFilesPath = os.path.join(working_dir, project,"process")
#create a directory to keep track of the analysed files
if not (os.path.exists(processFilesPath)):
os.makedirs(processFilesPath)
#initate the processFiles
processFiles = initiateProcessFile(available_tools, processFilesPath)
#search for the projects bam files
bamfiles=detect_bam_files(project_path, projectName,path_to_bam,recursive)
#function used to find variants
processFiles= calling.variantCalling(
programDirectory, project_path, projectName, working_dir,
path_to_bam, available_tools, account, modules,bamfiles, exclude, processFiles,
processFilesPath)
#combine the results o the variant calling
processFiles = combine.combine(programDirectory, processFiles,
processFilesPath, account,bamfiles)
#a function used to build databases from vcf files
processFiles = database.buildDatabase(programDirectory, processFiles,
processFilesPath, account)
# Function that filters the variant files and finds genomic features of
# the variants
processFiles = filter.applyFilter(programDirectory, processFiles,
processFilesPath, account,frequency_db)
#function used to annotate the samples
processFiles = annotation.annotation(programDirectory, processFiles,
processFilesPath, account,genmod_file)
#the funciton used for cleaning the vcf file, this is the final step of the pipeline
processFiles = cleaning.cleaning(programDirectory, processFiles,
processFilesPath, account)
return