def plgs(fastas,
raw_folder,
out_folder,
apex3d_kwds={},
peptide3d_kwds={},
iadbs_kwds={}):
"""Run PLGS.
Run complete PLGS analysis.
Args:
fastas (str): Path to fasta file.
raw_folder (str): Path to the raw folder acquired Waters data.
out_folder (str): Path to folder for the output.
apex3d_kwds (dict): Arguments for apex3d.
peptide3d_kwds (dict): Arguments for peptide3d.
iadbs_kwds (dict): Arguments for iadbs.
Returns:
dict: parsed parameters from the xml files.
"""
a, _ = apex3d(raw_folder, out_folder,
**apex3d_kwds) # this will make .bin only
p, _ = peptide3d(a.with_suffix('.bin'), out_folder,
**peptide3d_kwds) # this will make .xml only
i, _ = iadbs(p, out_folder, fastas, **iadbs_kwds)
create_params_file(a, p, i) # for projectizer2.0
search_stats = get_search_stats()
rows2csv(
i.parent / 'stats.csv',
[list(search_stats), list(search_stats.values())])
# C:/SYMPHONY_PIPELINE/2019-008/O191017-04
local_folder = local_output_folder / sample_set / acquired_name
a = apex3d(raw_folder, local_folder, **apex3d_kwds)
if peptide3d_kwds['timeout'] >= 0:
p = peptide3d(a.with_suffix('.bin'), local_folder,
**peptide3d_kwds)
if iadbs_kwds['timeout'] >= 0:
i = iadbs(p, local_folder, fasta_file, parameters_file,
**iadbs_kwds)
if i is not None:
params = create_params_file(a, p, i) # for projectizer2.0
with open(a.parent / "params.json", 'w') as f:
json.dump(params, f)
search_stats = get_search_stats(i)
rows2csv(i.parent / 'stats.csv',
[list(search_stats),
list(search_stats.values())])
if net_folder:
# Y:/RES/2019-008
net_set_folder = Path(net_folder) / sample_set
net_set_folder.mkdir(parents=True, exist_ok=True)
# if reanalysing, the old folder is preserved,
# and a version number appended to the new one
# e.g. Y:/RES/2019-008/O191017-04
# replaced with: Y:/RES/2019-008/O191017-04__v1
final_net_folder = find_free_path(net_set_folder / acquired_name)
try: #replace that with the general save moving routine with check-sums
move_folder(local_folder, final_net_folder)
if local_folder.parent.exists(
) and not local_folder.parent.glob('*'):
local_folder.parent.rmdir()
help=
"Paths to outputs of the iaDBs. If ending with '.xml', will use directly. If supplied folders, these will be searched recursively for files like '**/*_IA_workflow.xml'."
)
args = p.parse_args()
try:
print('Welcome to stats.csv maker')
from fs_ops.csv import rows2csv
from fs_ops.paths import find_suffixed_files
from waters.parsers import iaDBsXMLparser
xmls = list(
find_suffixed_files(args.paths, ['**/*_IA_workflow.xml'], ['.xml']))
print('Supplied paths:')
pprint(xmls)
for xml in xmls:
XML = iaDBsXMLparser(xml)
info = XML.info()
pprint(info)
print('dumping to csv')
rows2csv(xml.parent / 'stats.csv', [list(info), list(info.values())])
except Exception as e:
print(e)
print()
print('Let Thor enlight your path with lightnings!')
print('And have a nice day..')
input('press ENTER')
data_path = Path("~/Projects/WatersData/O190303_78/O190303_78_IA_workflow.xml").expanduser()
assert data_path.exists()
iaDBsXML = iaDBsXMLparser(data_path)
prots = iaDBsXML.prot_ids()
iaDBsXML.get_tag_counts()
iaDBsXML.proteins()
iaDBsXML.products()
iaDBsXML.get_tag_counts()
iaDBsXML.parameters()
iaDBsXML.query_masses()
iaDBsXML.count_proteins_per_hit()
info = iaDBsXML.info()
rows2csv(Path("~/Projects/waters/data/info.csv").expanduser(),
[list(info), list(info.values())])
scripts_loc = Path(r"C:\Users\stefan\AppData\Local\Programs\Python\Python38\Scripts")
sendto_loc = Path(r"C:\Users\stefan\AppData\Roaming\Microsoft\Windows\SendTo")
os.link(scripts_loc/"iadbs2csv.py", sendto_loc/"_iadbs2csv.py")
os.link(scripts_loc/"iadbs2stats.py", sendto_loc/"_iadbs2stats.py")
prots.columns
tree = iaDBsXML.tree
tree.
data_path2 = Path("~/Projects/waters/data/T180222_10/T180222_10_IA_workflow.xml").expanduser()
iaDBsXML2 = iaDBsXMLparser(data_path2)
print(iaDBsXML.get_tag_counts())