Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add KATHAROseq samples to SIFs. #128

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

add KATHAROseq samples to SIFs. #128

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b23f359
add KARATHOseq samples to SIFs.
Feb 23, 2024
c5a221d
changed SIF file-naming convention
Feb 23, 2024
48b2174
Merge branch 'master' into fix_katharoseq
charles-cowart Feb 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 11 additions & 2 deletions sequence_processing_pipeline/Pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -573,15 +573,17 @@ def generate_sample_info_files(self, addl_info=None):
df = pd.concat([df, addl_info],
ignore_index=True).drop_duplicates()

df = df[df["sample_name"].str.startswith("BLANK") == True] # noqa
blanks = df[df["sample_name"].str.startswith("BLANK")]
katharo = df[df["sample_name"].str.startswith("KATHARO")]
df = pd.concat([blanks, katharo])
samples = list(df.to_records(index=False))
projects = df.project_name.unique()

paths = []
for project in projects:
samples_in_proj = [x for x, y in samples if y == project]
some_path = join(self.output_path,
f'{self.run_id}_{project}_blanks.tsv')
f'{self.run_id}_{project}_wetlab.tsv')
paths.append(some_path)
with open(some_path, 'w') as f:
# write out header to disk
Expand Down Expand Up @@ -609,6 +611,13 @@ def generate_sample_info_files(self, addl_info=None):
row['description'] = sample.replace('_', '.')
row['collection_timestamp'] = self.get_date_from_run_id()

# Although KATHARO samples may contain valuable metadata
# in their columns, none of them appear to match the
# expected values for SIF columns. Hence, the new columns
# for KATHARO samples will be populated with the same
# defaults as BLANKs.
# (possible exception would be well_description and
# experiment_design_description -> description)
row = [row[x] for x in Pipeline.sif_header]
f.write('\t'.join(row) + '\n')

Expand Down
26 changes: 13 additions & 13 deletions sequence_processing_pipeline/tests/test_Pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,11 +365,11 @@ def test_generate_sample_information_files(self):
# filenames.
obs = [x.split('sequence_processing_pipeline/')[1] for x in paths]
exp = [(f'tests/data/output_dir/{self.good_run_id}'
'_NYU_BMS_Melanoma_13059_blanks.tsv'),
'_NYU_BMS_Melanoma_13059_wetlab.tsv'),
(f'tests/data/output_dir/{self.good_run_id}'
'_Feist_11661_blanks.tsv'),
'_Feist_11661_wetlab.tsv'),
(f'tests/data/output_dir/{self.good_run_id}'
'_Gerwick_6123_blanks.tsv')]
'_Gerwick_6123_wetlab.tsv')]

# sort the lists to ensure both are in a fixed order.
obs.sort()
Expand All @@ -380,13 +380,13 @@ def test_generate_sample_information_files(self):
# confirm files contain the expected number of lines.
# This is going to be based on the number of samples named 'BLANK*'
# in good-sample-sheet.csv.
exp_lines = {f'{self.good_run_id}_NYU_BMS_Melanoma_13059_blanks.tsv':
exp_lines = {f'{self.good_run_id}_NYU_BMS_Melanoma_13059_wetlab.tsv':
33,
f'{self.good_run_id}_Feist_11661_blanks.tsv': 8,
f'{self.good_run_id}_Gerwick_6123_blanks.tsv': 2}
f'{self.good_run_id}_Feist_11661_wetlab.tsv': 8,
f'{self.good_run_id}_Gerwick_6123_wetlab.tsv': 2}

exp_first_lines = {
f'{self.good_run_id}_NYU_BMS_Melanoma_13059_blanks.tsv':
f'{self.good_run_id}_NYU_BMS_Melanoma_13059_wetlab.tsv':
'BLANK1.1A\t2021-10-21\t193\t'
'Control\tNegative\tSterile w'
'ater blank\turban biome\tres'
Expand All @@ -397,15 +397,15 @@ def test_generate_sample_information_files(self):
'genome\t256318\tBLANK1.1A\tN'
'YU_BMS_Melanoma\tTRUE\t'
'UCSD\tFALSE',
f'{self.good_run_id}_Feist_11661_blanks.tsv':
f'{self.good_run_id}_Feist_11661_wetlab.tsv':
'BLANK.40.12G\t2021-10-21\t193\tControl'
'\tNegative\tSterile water blank\turban '
'biome\tresearch facility\tsterile water'
'\tmisc environment\tUSA:CA:San Diego\tB'
'LANK.40.12G\t32.5\t-117.25\tcontrol bla'
'nk\tmetagenome\t256318\tBLANK.40.12G\t'
'Feist\tTRUE\tUCSD\tFALSE',
f'{self.good_run_id}_Gerwick_6123_blanks.tsv':
f'{self.good_run_id}_Gerwick_6123_wetlab.tsv':
'BLANK.41.12G\t2021-10-21\t193\tControl'
'\tNegative\tSterile water blank\turban'
' biome\tresearch facility\tsterile wat'
Expand All @@ -416,7 +416,7 @@ def test_generate_sample_information_files(self):
}

exp_last_lines = {
f'{self.good_run_id}_NYU_BMS_Melanoma_13059_blanks.tsv':
f'{self.good_run_id}_NYU_BMS_Melanoma_13059_wetlab.tsv':
'BLANK4.4H\t2021-10-21\t193\t'
'Control\tNegative\tSterile w'
'ater blank\turban biome\tres'
Expand All @@ -427,15 +427,15 @@ def test_generate_sample_information_files(self):
'genome\t256318\tBLANK4.4H\tN'
'YU_BMS_Melanoma\tTRUE\t'
'UCSD\tFALSE',
f'{self.good_run_id}_Feist_11661_blanks.tsv':
f'{self.good_run_id}_Feist_11661_wetlab.tsv':
'BLANK.43.12H\t2021-10-21\t193\tControl'
'\tNegative\tSterile water blank\turban'
' biome\tresearch facility\tsterile wat'
'er\tmisc environment\tUSA:CA:San Diego'
'\tBLANK.43.12H\t32.5\t-117.25\tcontrol'
' blank\tmetagenome\t256318\tBLANK.43.1'
'2H\tFeist\tTRUE\tUCSD\tFALSE',
f'{self.good_run_id}_Gerwick_6123_blanks.tsv':
f'{self.good_run_id}_Gerwick_6123_wetlab.tsv':
'BLANK.41.12G\t2021-10-21\t193\tContro'
'l\tNegative\tSterile water blank\turb'
'an biome\tresearch facility\tsterile '
Expand Down Expand Up @@ -1822,7 +1822,7 @@ def test_generate_sample_information_files(self):
obs = [x.split('sequence_processing_pipeline/')[1] for x in paths]

exp = [(f'tests/data/output_dir/{self.good_run_id}'
'_ABTX_20230208_ABTX_11052_blanks.tsv')]
'_ABTX_20230208_ABTX_11052_wetlab.tsv')]

# sort the lists to ensure both are in a fixed order.
obs.sort()
Expand Down
Loading