def get_sampleIDs_from_samplesheet(iem_file):
"""
Get a list of sample IDs from an IEM formatted samplesheet (SampleSheet.csv)
"""
sheet = samplesheet.IEMFile(path=iem_file)
sampleIDs = [s['Sample_ID'] for s in sheet.data['Data']['Samples']]
return (sampleIDs)
def load_samplesheet_data(samplesheet_file):
"""
Examples
--------
Example usage::
x = "SampleSheet.csv"
run_settings, run_samples = load_samplesheet_data(x)
"""
data = samplesheet.IEMFile(path=samplesheet_file)
run_settings = {}
run_settings.update(data.data['Reads'])
run_settings.update(data.data['Header'])
run_settings.update(data.data['Settings'])
run_samples = data.data['Data']['Samples']
return ((run_settings, run_samples))
import os
import sys
import csv
from util import samplesheet
from util import find
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "tuco.settings")
import django
django.setup()
from lims.models import SequencingSampleSheet
sheets_dir = os.path.realpath(sys.argv[1])
# find all the samplesheets in the dir
for sheet_file in find.find(search_dir = sheets_dir, inclusion_patterns = ['SampleSheet.csv']):
sheet = samplesheet.IEMFile(path = os.path.realpath(sheet_file))
seqtype_file = os.path.join(os.path.dirname(sheet_file), 'seqtype.txt')
Run_ID = os.path.basename(os.path.dirname(sheet_file))
# load seqtype
if os.path.exists(seqtype_file):
with open(seqtype_file) as f:
lines = f.readlines()
Seq_Type = lines[0].strip()
# get the samplesheet entry from database
sheet_instance = SequencingSampleSheet.objects.get(md5 = sheet.meta['Sheet_md5'])
# check if it already has seq_type..
if not sheet_instance.seq_type or sheet_instance.seq_type == '' and Seq_Type != '':
sheet_instance.seq_type = Seq_Type
import os
import sys
import csv
from util import samplesheet
from util import find
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "tuco.settings")
import django
django.setup()
from lims.models import SequencingRun, SequencingSampleSheet
sheets_dir = os.path.realpath(sys.argv[1])
# find all the samplesheets in the dir
for sheet_file in find.find(search_dir=sheets_dir,
inclusion_patterns=['SampleSheet.csv']):
sheet = samplesheet.IEMFile(path=sheet_file)
Run_ID = os.path.basename(os.path.dirname(sheet_file))
seqtype_file = os.path.join(os.path.dirname(sheet_file), 'seqtype.txt')
# register the SampleSheet in the database if its not there already
SequencingSampleSheet.objects.get_or_create(
run_id=SequencingRun.objects.get(run_id=Run_ID),
path=os.path.realpath(sheet.path),
md5=sheet.md5,
host=sheet.meta.get('Sheet_host', ''))
# IEMFileVersion = record.get('IEMFileVersion',''),
# Investigator_Name = record.get('Investigator_Name',''), # Investigator Name
# Project_Name = record.get('Project_Name',''), # Project Name
# Experiment_Name = record.get('Experiment_Name',''), # Experiment Name
# Date = record.get('Date',''),
# Workflow = record.get('Workflow',''),
def samplesheet_upload(request):
template = 'lims/samplesheet_upload.html'
form = SequencingSampleSheetForm()
message = ''
context = {'form': form, 'message': message}
if request.method == 'POST' and request.FILES['samplesheet']:
# print(dir(request))
run_id = request.POST['run_id']
sheet = request.FILES['samplesheet']
# set up temp storage location for file; needed for samplesheet module read methods..
# MEDIA_TMP/<timestamp>/filename
fs = FileSystemStorage()
tmp_save_path = os.path.join(
settings.MEDIA_TMP, datetime.datetime.strftime(now(), '%Y-%m-%d'),
sheet.name)
# save file to disk at location
filename = fs.save(tmp_save_path, sheet)
uploaded_file_url = fs.url(filename)
# try to parse the file as a SampleSheet.csv file
try:
sheet_obj = samplesheet.IEMFile(path=os.path.realpath(filename))
except:
context[
'message'] = "ERROR: Samplesheet file could not be parsed. Is it in the correct format?"
return render(request, template, context, status=422)
# validate the contents of the samplesheet
try:
sheet_obj.isValid(_raise=True)
except:
context[
'message'] = "ERROR: Samplesheet contains errors;\n{0}".format(
json.dumps([{
k: v
} for k, v, in sheet_obj.get_validations().items() if v]))
return render(request, template, context, status=422)
# make sure the sheet is not already in the databse
num_matches = SequencingSampleSheet.objects.filter(
md5=sheet_obj.md5).count()
if num_matches > 0:
context[
'message'] = "ERROR: This exact samplesheet has already been uploaded, please re-assign the existing version instead."
return render(request, template, context, status=409)
# try to put the samplesheet into the database
try:
sheet_instance = SequencingSampleSheet.objects.create(
run_id=SequencingRun.objects.get(run_id=run_id),
file=sheet,
md5=sheet_obj.md5,
host=sheet_obj.meta.get('Sheet_host', ''))
except:
context[
'message'] = "ERROR: Samplesheet could not be imported into the database."
return render(request, template, context, status=422)
# try to import samples from the samplesheet
try:
all_created = []
not_created = []
for record in sheet_obj.flatten():
instance, created = SequencingSample.objects.get_or_create(
run_id=SequencingRun.objects.get(run_id=run_id),
sample=record.get('Sample_ID', ''),
sample_name=record.get('Sample_Name', ''),
# paired_normal = record.get('Paired_Normal',''), # get this separately!
i7_index=record.get('I7_Index_ID', ''),
index=record.get('index', ''),
sample_project=record.get('Sample_Project', ''),
description=record.get('Description', ''),
genome_folder=record.get('GenomeFolder', ''),
samplesheet=sheet_instance)
if created:
all_created.append((instance, created))
if not created:
not_created.append((instance, created))
context[
'message'] = "The following samples from the samplesheet were successfully imported:\n{0}\n\nThe following samples were not successfully imported:\n{1}".format(
'\n'.join([i[0].__str__() for i in all_created]),
'\n'.join([i[0].__str__() for i in not_created]))
return render(request, template, context)
except:
context[
'message'] = "ERROR: An error occured while importing samples from the samplesheet into the database."
return render(request, template, context, status=422)
else:
return render(request, template, context)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Mark a run's output as 'passed' by placing a symlink in the output directory
"""
import sys
import os
from util import samplesheet
samplesheet_file = sys.argv[1]
outputDir = os.path.join("output", "reads")
sheet_obj = samplesheet.IEMFile(path=samplesheet_file)
sample_projects = list(
set([
sample['Sample_Project']
for sample in sheet_obj.data['Data']['Samples']
]))
for i, sample_project in enumerate(sample_projects):
src = os.path.join(outputDir, sample_project)
dest = os.path.join(outputDir, "passed{0}".format(i))
print(">>> Linking {0} to {1}".format(src, dest))
if os.path.exists(dest):
os.unlink(dest)
os.symlink(sample_project, dest)
