本文整理汇总了Python中qiita_ware.ebi.EBISubmission.generate_demultiplexed_fastq方法的典型用法代码示例。如果您正苦于以下问题:Python EBISubmission.generate_demultiplexed_fastq方法的具体用法?Python EBISubmission.generate_demultiplexed_fastq怎么用?Python EBISubmission.generate_demultiplexed_fastq使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类qiita_ware.ebi.EBISubmission
的用法示例。
在下文中一共展示了EBISubmission.generate_demultiplexed_fastq方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: submit_EBI
# 需要导入模块: from qiita_ware.ebi import EBISubmission [as 别名]
# 或者: from qiita_ware.ebi.EBISubmission import generate_demultiplexed_fastq [as 别名]
def submit_EBI(artifact_id, action, send, test=False, test_size=False):
"""Submit an artifact to EBI
Parameters
----------
artifact_id : int
The artifact id
action : %s
The action to perform with this data
send : bool
True to actually send the files
test : bool
If True some restrictions will be ignored, only used in parse_EBI_reply
test_size : bool
If True the EBI-ENA restriction size will be changed to 6000
"""
# step 1: init and validate
ebi_submission = EBISubmission(artifact_id, action)
# step 2: generate demux fastq files
try:
ebi_submission.generate_demultiplexed_fastq()
except Exception:
error_msg = format_exc()
if isdir(ebi_submission.full_ebi_dir):
rmtree(ebi_submission.full_ebi_dir)
LogEntry.create('Runtime', error_msg,
info={'ebi_submission': artifact_id})
raise
# step 3: generate and write xml files
ebi_submission.generate_xml_files()
# before we continue let's check the size of the submission
to_review = [ebi_submission.study_xml_fp,
ebi_submission.sample_xml_fp,
ebi_submission.experiment_xml_fp,
ebi_submission.run_xml_fp,
ebi_submission.submission_xml_fp]
total_size = sum([stat(tr).st_size for tr in to_review if tr is not None])
# note that the max for EBI is 10M but let's play it safe
max_size = 8.5e+6 if not test_size else 6000
if total_size > max_size:
LogEntry.create(
'Runtime', 'The submission: %d is larger than allowed (%d), will '
'try to fix: %d' % (artifact_id, max_size, total_size))
# transform current metadata to dataframe for easier curation
rows = {k: dict(v) for k, v in viewitems(ebi_submission.samples)}
df = pd.DataFrame.from_dict(rows, orient='index')
# remove unique columns and same value in all columns
nunique = df.apply(pd.Series.nunique)
nsamples = len(df.index)
cols_to_drop = set(
nunique[(nunique == 1) | (nunique == nsamples)].index)
# maximize deletion by removing also columns that are almost all the
# same or almost all unique
cols_to_drop = set(
nunique[(nunique <= int(nsamples * .01)) |
(nunique >= int(nsamples * .5))].index)
cols_to_drop = cols_to_drop - {'taxon_id', 'scientific_name',
'description'}
all_samples = ebi_submission.sample_template.ebi_sample_accessions
samples = {k: all_samples[k] for k in ebi_submission.samples}
ebi_submission.write_xml_file(
ebi_submission.generate_sample_xml(samples, cols_to_drop),
ebi_submission.sample_xml_fp)
# now let's recalculate the size to make sure it's fine
new_total_size = sum([stat(tr).st_size
for tr in to_review if tr is not None])
LogEntry.create(
'Runtime', 'The submission: %d after cleaning is %d and was %d' % (
artifact_id, total_size, new_total_size))
if new_total_size > max_size:
raise ComputeError(
'Even after cleaning the submission: %d is too large. Before '
'cleaning: %d, after: %d' % (
artifact_id, total_size, new_total_size))
if send:
# getting aspera's password
old_ascp_pass = environ.get('ASPERA_SCP_PASS', '')
if old_ascp_pass == '':
environ['ASPERA_SCP_PASS'] = qiita_config.ebi_seq_xfer_pass
ascp_passwd = environ['ASPERA_SCP_PASS']
LogEntry.create('Runtime',
('Submission of sequences of pre_processed_id: '
'%d completed successfully' % artifact_id))
# step 4: sending sequences
if action != 'MODIFY':
LogEntry.create('Runtime',
("Submitting sequences for pre_processed_id: "
"%d" % artifact_id))
for cmd in ebi_submission.generate_send_sequences_cmd():
stdout, stderr, rv = system_call(cmd)
if rv != 0:
error_msg = ("ASCP Error:\nStd output:%s\nStd error:%s" % (
stdout, stderr))
environ['ASPERA_SCP_PASS'] = old_ascp_pass
#.........这里部分代码省略.........
示例2: submit_EBI
# 需要导入模块: from qiita_ware.ebi import EBISubmission [as 别名]
# 或者: from qiita_ware.ebi.EBISubmission import generate_demultiplexed_fastq [as 别名]
def submit_EBI(preprocessed_data_id, action, send):
"""Submit a preprocessed data to EBI
Parameters
----------
preprocessed_data_id : int
The preprocesssed data id
action : %s
The action to perform with this data
send : bool
True to actually send the files
"""
# step 1: init and validate
ebi_submission = EBISubmission(preprocessed_data_id, action)
# step 2: generate demux fastq files
ebi_submission.study.ebi_submission_status = 'submitting'
try:
ebi_submission.generate_demultiplexed_fastq()
except:
error_msg = format_exc()
if isdir(ebi_submission.full_ebi_dir):
rmtree(ebi_submission.full_ebi_dir)
ebi_submission.study.ebi_submission_status = 'failed: %s' % error_msg
LogEntry.create('Runtime', error_msg,
info={'ebi_submission': preprocessed_data_id})
raise
# step 3: generate and write xml files
ebi_submission.generate_xml_files()
if send:
# step 4: sending sequences
old_ascp_pass = environ.get('ASPERA_SCP_PASS', '')
environ['ASPERA_SCP_PASS'] = qiita_config.ebi_seq_xfer_pass
LogEntry.create('Runtime',
("Submitting sequences for pre_processed_id: "
"%d" % preprocessed_data_id))
try:
for cmd in ebi_submission.generate_send_sequences_cmd():
try:
stdout, stderr, _ = system_call(cmd)
except Exception as e:
stdout = ''
stderr = str(e)
le = LogEntry.create(
'Fatal', "Command: %s\nError: %s\n" % (cmd, str(e)),
info={'ebi_submission': preprocessed_data_id})
ebi_submission.study.ebi_submission_status = (
"failed: ASCP submission, log id: %d" % le.id)
raise ComputeError("EBI Submission failed! Log id: "
"%d" % le.id)
finally:
open(ebi_submission.ascp_reply, 'a').write(
'stdout:\n%s\n\nstderr: %s' % (stdout, stderr))
finally:
environ['ASPERA_SCP_PASS'] = old_ascp_pass
LogEntry.create('Runtime',
('Submission of sequences of pre_processed_id: '
'%d completed successfully' %
preprocessed_data_id))
# step 5: sending xml and parsing answer
xmls_cmds = ebi_submission.generate_curl_command()
LogEntry.create('Runtime',
("Submitting XMLs for pre_processed_id: "
"%d" % preprocessed_data_id))
try:
xml_content, stderr, _ = system_call(xmls_cmds)
except Exception as e:
xml_content = ''
stderr = str(e)
le = LogEntry.create('Fatal',
"Command: %s\nError: %s\n" % (
cmd, str(e)),
info={'ebi_submission': preprocessed_data_id})
ebi_submission.study.ebi_submission_status = (
"failed: XML submission, log id: %d" % le.id)
raise ComputeError("EBI Submission failed! Log id: %d" % le.id)
else:
LogEntry.create('Runtime',
('Submission of sequences of pre_processed_id: '
'%d completed successfully' %
preprocessed_data_id))
finally:
open(ebi_submission.curl_reply, 'w').write(
'stdout:\n%s\n\nstderr: %s' % (xml_content, stderr))
try:
st_acc, sa_acc, bio_acc, ex_acc, run_acc = \
ebi_submission.parse_EBI_reply(xml_content)
except EBISubmissionError as e:
le = LogEntry.create(
'Fatal', "Command: %s\nError: %s\n" % (xml_content, str(e)),
info={'ebi_submission': preprocessed_data_id})
ebi_submission.study.ebi_submission_status = (
"failed: XML parsing, log id: %d" % le.id)
raise ComputeError("EBI Submission failed! Log id: %d" % le.id)
#.........这里部分代码省略.........
示例3: submit_EBI
# 需要导入模块: from qiita_ware.ebi import EBISubmission [as 别名]
# 或者: from qiita_ware.ebi.EBISubmission import generate_demultiplexed_fastq [as 别名]
def submit_EBI(artifact_id, action, send, test=False):
"""Submit an artifact to EBI
Parameters
----------
artifact_id : int
The artifact id
action : %s
The action to perform with this data
send : bool
True to actually send the files
test : bool
If True some restrictions will be ignored, only used in parse_EBI_reply
"""
# step 1: init and validate
ebi_submission = EBISubmission(artifact_id, action)
# step 2: generate demux fastq files
try:
ebi_submission.generate_demultiplexed_fastq()
except Exception:
error_msg = format_exc()
if isdir(ebi_submission.full_ebi_dir):
rmtree(ebi_submission.full_ebi_dir)
LogEntry.create('Runtime', error_msg,
info={'ebi_submission': artifact_id})
raise
# step 3: generate and write xml files
ebi_submission.generate_xml_files()
if send:
# getting aspera's password
old_ascp_pass = environ.get('ASPERA_SCP_PASS', '')
if old_ascp_pass == '':
environ['ASPERA_SCP_PASS'] = qiita_config.ebi_seq_xfer_pass
ascp_passwd = environ['ASPERA_SCP_PASS']
LogEntry.create('Runtime',
('Submission of sequences of pre_processed_id: '
'%d completed successfully' % artifact_id))
# step 4: sending sequences
if action != 'MODIFY':
LogEntry.create('Runtime',
("Submitting sequences for pre_processed_id: "
"%d" % artifact_id))
for cmd in ebi_submission.generate_send_sequences_cmd():
stdout, stderr, rv = system_call(cmd)
if rv != 0:
error_msg = ("ASCP Error:\nStd output:%s\nStd error:%s" % (
stdout, stderr))
environ['ASPERA_SCP_PASS'] = old_ascp_pass
raise ComputeError(error_msg)
open(ebi_submission.ascp_reply, 'a').write(
'stdout:\n%s\n\nstderr: %s' % (stdout, stderr))
environ['ASPERA_SCP_PASS'] = old_ascp_pass
# step 5: sending xml and parsing answer
xmls_cmds = ebi_submission.generate_curl_command(
ebi_seq_xfer_pass=ascp_passwd)
LogEntry.create('Runtime',
("Submitting XMLs for pre_processed_id: "
"%d" % artifact_id))
xml_content, stderr, rv = system_call(xmls_cmds)
if rv != 0:
error_msg = ("Error:\nStd output:%s\nStd error:%s" % (
xml_content, stderr))
raise ComputeError(error_msg)
else:
LogEntry.create('Runtime',
('Submission of sequences of pre_processed_id: '
'%d completed successfully' % artifact_id))
open(ebi_submission.curl_reply, 'w').write(
'stdout:\n%s\n\nstderr: %s' % (xml_content, stderr))
try:
st_acc, sa_acc, bio_acc, ex_acc, run_acc = \
ebi_submission.parse_EBI_reply(xml_content, test=test)
except EBISubmissionError as e:
error = str(e)
le = LogEntry.create(
'Fatal', "Command: %s\nError: %s\n" % (xml_content, error),
info={'ebi_submission': artifact_id})
raise ComputeError(
"EBI Submission failed! Log id: %d\n%s" % (le.id, error))
if action == 'ADD' or test:
if st_acc:
ebi_submission.study.ebi_study_accession = st_acc
if sa_acc:
ebi_submission.sample_template.ebi_sample_accessions = sa_acc
if bio_acc:
ebi_submission.sample_template.biosample_accessions = bio_acc
if ex_acc:
ebi_submission.prep_template.ebi_experiment_accessions = ex_acc
ebi_submission.artifact.ebi_run_accessions = run_acc
else:
st_acc, sa_acc, bio_acc, ex_acc, run_acc = None, None, None, None, None
return st_acc, sa_acc, bio_acc, ex_acc, run_acc