From 98af93886d666b0d35d99737a4c36336d8742168 Mon Sep 17 00:00:00 2001
From: cramakri <cramakri>
Date: Mon, 11 Jul 2011 12:37:40 +0000
Subject: [PATCH] LMS-2391 Split TSV files where necessary. Switched tab to
spaces in all python code.
SVN: 22070
---
eu_basynthec/dist/etc/data-set-validator.py | 4 +-
.../etc/growth-profiles/data-set-handler.py | 143 +++++----
.../etc/growth-profiles/data-set-validator.py | 102 +++----
.../dist/etc/metabolomics/data-set-handler.py | 88 +++---
.../etc/metabolomics/data-set-validator.py | 116 +++----
.../dist/etc/proteomics/data-set-handler.py | 88 +++---
.../dist/etc/proteomics/data-set-validator.py | 124 ++++----
.../dist/etc/shared/shared-classes.py | 282 +++++++++---------
.../etc/transcriptomics/data-set-handler.py | 231 +++++++++-----
.../etc/transcriptomics/data-set-validator.py | 128 ++++----
.../sourceTest/examples/OD600-Example.xlsx | Bin 9914 -> 10077 bytes
...stractBaSynthecDataSetRegistratorTest.java | 19 +-
.../cisd/dss/TimeSeriesDataExcelTest.java | 3 +-
.../OD600DataSetRegistratorTest.java | 30 +-
...TranscriptomicsDataSetRegistratorTest.java | 30 +-
15 files changed, 782 insertions(+), 606 deletions(-)
diff --git a/eu_basynthec/dist/etc/data-set-validator.py b/eu_basynthec/dist/etc/data-set-validator.py
index 6b1f13c649b..8af662eac42 100644
--- a/eu_basynthec/dist/etc/data-set-validator.py
+++ b/eu_basynthec/dist/etc/data-set-validator.py
@@ -2,5 +2,5 @@ import os
import re
def validate_data_set_file(file):
- errors = []
- return errors
+ errors = []
+ return errors
diff --git a/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py b/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
index 4f4df43954f..bc76e78a48d 100644
--- a/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
+++ b/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
@@ -2,58 +2,92 @@ from datetime import datetime
from eu.basynthec.cisd.dss import TimeSeriesDataExcel
def retrieve_experiment(tr, exp_id):
- """Get the specified experiment form the server. Return the experiment."""
- if exp_id is None:
- exp = None
- else:
- exp = tr.getExperiment(exp_id)
- return exp
+ """Get the specified experiment form the server. Return the experiment."""
+ if exp_id is None:
+ exp = None
+ else:
+ exp = tr.getExperiment(exp_id)
+ return exp
def extract_strains():
- """Extract the strains from the data sheet"""
- strains = []
- lines = timeSeriesData.getRawDataLines()
- for i in range(1, len(lines)):
- line = lines[i]
- strains.append(line[0])
- return ",".join(strains)
+ """Extract the strains from the data sheet"""
+ strains = []
+ lines = timeSeriesData.getRawDataLines()
+ for i in range(1, len(lines)):
+ line = lines[i]
+ strains.append(line[0])
+ return ",".join(strains)
def assign_properties(dataset, metadata):
- """Assign properties to the data set from information in the data."""
- propertyNameMap = {
- "STRAIN_NAMES": "STRAIN_NAMES",
- "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
- "CELL LOCATION": "CELL_LOCATION",
- "VALUE TYPE": "VALUE_TYPE",
- "VALUE UNIT": "VALUE_UNIT",
- "SCALE": "SCALE"
- }
-
- for prop in metadata.keySet():
- key = propertyNameMap.get(prop)
- if key is not None:
- value = metadata.get(prop)
- if (key == "STRAIN"):
- value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
-
+ """Assign properties to the data set from information in the data."""
+ propertyNameMap = {
+ "STRAIN_NAMES": "STRAIN_NAMES",
+ "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
+ "CELL LOCATION": "CELL_LOCATION",
+ "VALUE TYPE": "VALUE_TYPE",
+ "VALUE UNIT": "VALUE_UNIT",
+ "SCALE": "SCALE"
+ }
+
+ for prop in metadata.keySet():
+ key = propertyNameMap.get(prop)
+ if key is not None:
+ value = metadata.get(prop)
+ if (key == "STRAIN"):
+ value = value + " (STRAIN)"
+ dataset.setPropertyValue(key, value.upper())
+
def convert_data_to_tsv(tr, dataset, location):
- """Create a tsv file containing the data and add it to the data set."""
- tr.createNewDirectory(dataset, location)
- tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
- tsv = open(tsvFileName, 'w')
- for line in timeSeriesData.getRawDataLines():
- for i in range(0, len(line) - 1):
- tsv.write(line[i])
- tsv.write("\t")
- tsv.write(line[len(line) - 1])
- tsv.write("\n")
- tsv.close()
-
+ """Create a tsv file containing the data and add it to the data set."""
+ tr.createNewDirectory(dataset, location)
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ for line in timeSeriesData.getRawDataLines():
+ for i in range(0, len(line) - 1):
+ tsv.write(line[i])
+ tsv.write("\t")
+ tsv.write(line[len(line) - 1])
+ tsv.write("\n")
+ tsv.close()
+
+def convert_data_to_split_tsv(tr, dataset, location):
+ """Create one tsv file per strain in the original data."""
+ raw_data_lines = timeSeriesData.getRawDataLines()
+
+ # Extract the header -- this is shared by all files
+ header_line = raw_data_lines[0]
+ # In the header we don't need the strain, but we start with a run number
+ header = 'RunNumber\t' + '\t'.join(header_line[1:len(header_line)])
+
+ tr.createNewDirectory(dataset, location)
+
+ # Keep track of the strains, since a strain can be measured multiple times
+ data_per_strain = {}
+
+ lines_len = len(raw_data_lines)
+ for i in range(1, len(raw_data_lines)):
+ line = raw_data_lines[i]
+ strain_name = line[0]
+ strain_data = data_per_strain.setdefault(strain_name, [])
+ # Append the line -- this is run number + the data
+ strain_data.append(str(len(strain_data)) + '\t' + '\t'.join(line[1:len(line)]))
+
+ # Create the files
+ for strain in data_per_strain.iterkeys():
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + "_" + strain + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ tsv.write(header)
+
+ strain_data = data_per_strain[strain]
+ for line in strain_data:
+ tsv.write("\n")
+ tsv.write(line)
+ tsv.close()
+
def store_original_data(tr, dataset, location):
- """Put the original data into the data set."""
- tr.createNewDirectory(dataset, location)
- tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
+ """Put the original data into the data set."""
+ tr.createNewDirectory(dataset, location)
+ tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
tr = service.transaction(incoming)
@@ -73,6 +107,9 @@ store_original_data(tr, original_dataset, "xls")
tsv_dataset = tr.createNewDataSet("TSV_MULTISTRAIN_EXPORT")
convert_data_to_tsv(tr, tsv_dataset, "tsv-multi")
+tsv_split_dataset = tr.createNewDataSet("TSV_EXPORT")
+convert_data_to_split_tsv(tr, tsv_split_dataset, "tsv")
+
# Make the original contain these
contained_codes = [original_dataset.getDataSetCode(), tsv_dataset.getDataSetCode()]
dataset.setContainedDataSetCodes(contained_codes)
@@ -80,10 +117,10 @@ dataset.setContainedDataSetCodes(contained_codes)
# If no experiment has been set, then get the experiment from the excel file
if dataset.getExperiment() is None:
- exp_id = metadata.get("EXPERIMENT")
- exp = retrieve_experiment(tr, exp_id)
- if exp is not None:
- dataset.setExperiment(exp)
- original_dataset.setExperiment(exp)
- tsv_dataset.setExperiment(exp)
-
+ exp_id = metadata.get("EXPERIMENT")
+ exp = retrieve_experiment(tr, exp_id)
+ if exp is not None:
+ dataset.setExperiment(exp)
+ original_dataset.setExperiment(exp)
+ tsv_dataset.setExperiment(exp)
+ tsv_split_dataset.setExperiment(exp)
diff --git a/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py b/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
index b2f2c0bd96c..3bdb793b652 100644
--- a/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
+++ b/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
@@ -1,60 +1,60 @@
def validate_data(timeSeriesData, errors):
- dataLines = timeSeriesData.getRawDataLines()
- lineCount = 0
- for line in dataLines:
- # The header needs to be Abs
- if lineCount is 0:
- if line[0] != "Strain":
- errors.append(createFileValidationError("The first data column must be 'Strain'"))
- break
- lineCount = lineCount + 1
- continue
+ dataLines = timeSeriesData.getRawDataLines()
+ lineCount = 0
+ for line in dataLines:
+ # The header needs to be Abs
+ if lineCount is 0:
+ if line[0] != "Strain":
+ errors.append(createFileValidationError("The first data column must be 'Strain'"))
+ break
+ lineCount = lineCount + 1
+ continue
- # The compound id should be one of these forms
- strain = line[0]
- if not isStrainIdValid(strain):
- errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be MGP[0-999] (instead of " + strain + ")."))
- lineCount = lineCount + 1
+ # The compound id should be one of these forms
+ strain = line[0]
+ if not isStrainIdValid(strain):
+ errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be MGP[0-999] (instead of " + strain + ")."))
+ lineCount = lineCount + 1
def validate_metadata(time_series_data, errors):
- metadata = time_series_data.getMetadataMap()
- validationHelper = ValidationHelper(metadata, errors)
-
- # validate the header format
- validationHelper.validateDefaultHeaderFormat()
-
- # validate the timepoint type
- validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
- "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
+ metadata = time_series_data.getMetadataMap()
+ validationHelper = ValidationHelper(metadata, errors)
+
+ # validate the header format
+ validationHelper.validateDefaultHeaderFormat()
+
+ # validate the timepoint type
+ validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
+ "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
- # validate the cell location
- validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
- "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
+ # validate the cell location
+ validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
+ "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
- # validate the value type
- validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
- "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
- "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
+ # validate the value type
+ validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
+ "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
+ "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
- # validate the value unit
- validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
- "value unit", ['DIMENSIONLESS'], "'DIMENSIONLESS'")
-
- # validate the scale
- validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
- ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
+ # validate the value unit
+ validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
+ "value unit", ['DIMENSIONLESS'], "'DIMENSIONLESS'")
+
+ # validate the scale
+ validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
+ ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
def validate_data_set_file(file):
- errors = []
- time_series_data = create_time_series_excel(file.getAbsolutePath())
- if time_series_data is None:
- errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
- return errors
-
- # validate the metadata
- validate_metadata(time_series_data, errors)
-
- # validate the data
- validate_data(time_series_data, errors)
-
- return errors
+ errors = []
+ time_series_data = create_time_series_excel(file.getAbsolutePath())
+ if time_series_data is None:
+ errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
+ return errors
+
+ # validate the metadata
+ validate_metadata(time_series_data, errors)
+
+ # validate the data
+ validate_data(time_series_data, errors)
+
+ return errors
diff --git a/eu_basynthec/dist/etc/metabolomics/data-set-handler.py b/eu_basynthec/dist/etc/metabolomics/data-set-handler.py
index 9cdbf69004f..56737bf7a8d 100644
--- a/eu_basynthec/dist/etc/metabolomics/data-set-handler.py
+++ b/eu_basynthec/dist/etc/metabolomics/data-set-handler.py
@@ -2,47 +2,47 @@ from datetime import datetime
from eu.basynthec.cisd.dss import TimeSeriesDataExcel
def retrieve_experiment(tr, exp_id):
- """Get the specified experiment form the server. Return the experiment."""
- if exp_id is None:
- exp = None
- else:
- exp = tr.getExperiment(exp_id)
- return exp
+ """Get the specified experiment form the server. Return the experiment."""
+ if exp_id is None:
+ exp = None
+ else:
+ exp = tr.getExperiment(exp_id)
+ return exp
def assign_properties(dataset, metadata):
- """Assign properties to the data set from information in the data."""
- propertyNameMap = {
- "STRAIN":"STRAIN_NAMES",
- "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
- "CELL LOCATION": "CELL_LOCATION",
- "VALUE TYPE": "VALUE_TYPE",
- "VALUE UNIT": "VALUE_UNIT",
- "SCALE": "SCALE"
- }
-
- for prop in metadata.keySet():
- key = propertyNameMap.get(prop)
- if key is not None:
- value = metadata.get(prop)
- dataset.setPropertyValue(key, value.upper())
-
+ """Assign properties to the data set from information in the data."""
+ propertyNameMap = {
+ "STRAIN":"STRAIN_NAMES",
+ "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
+ "CELL LOCATION": "CELL_LOCATION",
+ "VALUE TYPE": "VALUE_TYPE",
+ "VALUE UNIT": "VALUE_UNIT",
+ "SCALE": "SCALE"
+ }
+
+ for prop in metadata.keySet():
+ key = propertyNameMap.get(prop)
+ if key is not None:
+ value = metadata.get(prop)
+ dataset.setPropertyValue(key, value.upper())
+
def convert_data_to_tsv(tr, dataset, location):
- """Create a tsv file containing the data and add it to the data set."""
- tr.createNewDirectory(dataset, location)
- tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
- tsv = open(tsvFileName, 'w')
- for line in timeSeriesData.getRawDataLines():
- for i in range(0, len(line) - 1):
- tsv.write(line[i])
- tsv.write("\t")
- tsv.write(line[len(line) - 1])
- tsv.write("\n")
- tsv.close()
-
+ """Create a tsv file containing the data and add it to the data set."""
+ tr.createNewDirectory(dataset, location)
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ for line in timeSeriesData.getRawDataLines():
+ for i in range(0, len(line) - 1):
+ tsv.write(line[i])
+ tsv.write("\t")
+ tsv.write(line[len(line) - 1])
+ tsv.write("\n")
+ tsv.close()
+
def store_original_data(tr, dataset, location):
- """Put the original data into the data set."""
- tr.createNewDirectory(dataset, location)
- tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
+ """Put the original data into the data set."""
+ tr.createNewDirectory(dataset, location)
+ tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
tr = service.transaction(incoming)
@@ -52,7 +52,7 @@ timeSeriesData = TimeSeriesDataExcel.createTimeSeriesDataExcel(incoming.getAbsol
dataset = tr.createNewDataSet("METABOLITE_INTENSITIES")
metadata = timeSeriesData.getMetadataMap()
assign_properties(dataset, metadata)
-
+
# Store the original and tsv data in data sets
original_dataset = tr.createNewDataSet("EXCEL_ORIGINAL")
store_original_data(tr, original_dataset, "xls")
@@ -67,11 +67,11 @@ dataset.setContainedDataSetCodes(contained_codes)
# If no experiment has been set, then get the experiment from the excel file
if dataset.getExperiment() is None:
- exp_id = metadata.get("EXPERIMENT")
- exp = retrieve_experiment(tr, exp_id)
- if exp is not None:
- dataset.setExperiment(exp)
- original_dataset.setExperiment(exp)
- tsv_dataset.setExperiment(exp)
+ exp_id = metadata.get("EXPERIMENT")
+ exp = retrieve_experiment(tr, exp_id)
+ if exp is not None:
+ dataset.setExperiment(exp)
+ original_dataset.setExperiment(exp)
+ tsv_dataset.setExperiment(exp)
diff --git a/eu_basynthec/dist/etc/metabolomics/data-set-validator.py b/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
index 79d9b3d462a..0e77b3af1eb 100644
--- a/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
@@ -1,67 +1,67 @@
def validate_data(time_series_data, errors):
- chebiRegex = re.compile("^CHEBI:[0-9]+")
- bsbmeRegex = re.compile("^BSBME:[0-9]+")
- dataLines = time_series_data.getRawDataLines()
- lineCount = 0
- for line in dataLines:
- # The header needs to be CompoundID
- if lineCount is 0:
- if line[0] != "CompoundID":
- errors.append(createFileValidationError("The first data column must be 'CompoundID'"))
- break
- lineCount = lineCount + 1
- continue
+ chebiRegex = re.compile("^CHEBI:[0-9]+")
+ bsbmeRegex = re.compile("^BSBME:[0-9]+")
+ dataLines = time_series_data.getRawDataLines()
+ lineCount = 0
+ for line in dataLines:
+ # The header needs to be CompoundID
+ if lineCount is 0:
+ if line[0] != "CompoundID":
+ errors.append(createFileValidationError("The first data column must be 'CompoundID'"))
+ break
+ lineCount = lineCount + 1
+ continue
- # The compound id should be one of these forms
- compoundId = line[0]
- if not chebiRegex.match(compoundId):
- if not bsbmeRegex.match(compoundId):
- errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be of the format 'CHEBI:#' or 'BSBME:#' (instead of " + compoundId + ")."))
- lineCount = lineCount + 1
-
+ # The compound id should be one of these forms
+ compoundId = line[0]
+ if not chebiRegex.match(compoundId):
+ if not bsbmeRegex.match(compoundId):
+ errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be of the format 'CHEBI:#' or 'BSBME:#' (instead of " + compoundId + ")."))
+ lineCount = lineCount + 1
+
def validate_metadata(time_series_data, errors):
- metadata = time_series_data.getMetadataMap()
- validationHelper = ValidationHelper(metadata, errors)
-
- # validate the strain
- validationHelper.validateStrain()
-
- # validate the header format
- validationHelper.validateDefaultHeaderFormat()
-
- # validate the timepoint type
- validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
- "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
+ metadata = time_series_data.getMetadataMap()
+ validationHelper = ValidationHelper(metadata, errors)
+
+ # validate the strain
+ validationHelper.validateStrain()
+
+ # validate the header format
+ validationHelper.validateDefaultHeaderFormat()
+
+ # validate the timepoint type
+ validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
+ "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
- # validate the cell location
- validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
- "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
+ # validate the cell location
+ validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
+ "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
- # validate the value type
- validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
- "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
- "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
+ # validate the value type
+ validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
+ "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
+ "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
- # validate the value unit
- validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
- "value unit", ['MM', 'UM', 'RATIOT1', 'RATIOCS'], "'mM', 'uM', 'RatioT1', 'RatioCs'")
-
- # validate the scale
- validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
- ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
+ # validate the value unit
+ validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
+ "value unit", ['MM', 'UM', 'RATIOT1', 'RATIOCS'], "'mM', 'uM', 'RatioT1', 'RatioCs'")
+
+ # validate the scale
+ validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
+ ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
def validate_data_set_file(file):
- errors = []
- time_series_data = create_time_series_excel(file.getAbsolutePath())
- if time_series_data is None:
- errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
- return errors
-
- # validate the metadata
- validate_metadata(time_series_data, errors)
-
- # validate the data
- validate_data(time_series_data, errors)
-
- return errors
+ errors = []
+ time_series_data = create_time_series_excel(file.getAbsolutePath())
+ if time_series_data is None:
+ errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
+ return errors
+
+ # validate the metadata
+ validate_metadata(time_series_data, errors)
+
+ # validate the data
+ validate_data(time_series_data, errors)
+
+ return errors
diff --git a/eu_basynthec/dist/etc/proteomics/data-set-handler.py b/eu_basynthec/dist/etc/proteomics/data-set-handler.py
index 4ab87d54b49..369cf170b58 100644
--- a/eu_basynthec/dist/etc/proteomics/data-set-handler.py
+++ b/eu_basynthec/dist/etc/proteomics/data-set-handler.py
@@ -2,48 +2,48 @@ from datetime import datetime
from eu.basynthec.cisd.dss import TimeSeriesDataExcel
def retrieve_experiment(tr, exp_id):
- """Get the specified experiment form the server. Return the experiment."""
- if exp_id is None:
- exp = None
- else:
- exp = tr.getExperiment(exp_id)
- return exp
+ """Get the specified experiment form the server. Return the experiment."""
+ if exp_id is None:
+ exp = None
+ else:
+ exp = tr.getExperiment(exp_id)
+ return exp
def assign_properties(dataset, metadata):
- """Assign properties to the data set from information in the data."""
- propertyNameMap = {
- "STRAIN":"STRAIN_NAMES",
- "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
- "CELL LOCATION": "CELL_LOCATION",
- "VALUE UNIT": "VALUE_UNIT",
- "SCALE": "SCALE"
- }
-
- for prop in metadata.keySet():
- key = propertyNameMap.get(prop)
- if key is not None:
- value = metadata.get(prop)
- if (key == "STRAIN"):
- value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
-
+ """Assign properties to the data set from information in the data."""
+ propertyNameMap = {
+ "STRAIN":"STRAIN_NAMES",
+ "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
+ "CELL LOCATION": "CELL_LOCATION",
+ "VALUE UNIT": "VALUE_UNIT",
+ "SCALE": "SCALE"
+ }
+
+ for prop in metadata.keySet():
+ key = propertyNameMap.get(prop)
+ if key is not None:
+ value = metadata.get(prop)
+ if (key == "STRAIN"):
+ value = value + " (STRAIN)"
+ dataset.setPropertyValue(key, value.upper())
+
def convert_data_to_tsv(tr, dataset, location):
- """Create a tsv file containing the data and add it to the data set."""
- tr.createNewDirectory(dataset, location)
- tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
- tsv = open(tsvFileName, 'w')
- for line in timeSeriesData.getRawDataLines():
- for i in range(0, len(line) - 1):
- tsv.write(line[i])
- tsv.write("\t")
- tsv.write(line[len(line) - 1])
- tsv.write("\n")
- tsv.close()
-
+ """Create a tsv file containing the data and add it to the data set."""
+ tr.createNewDirectory(dataset, location)
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ for line in timeSeriesData.getRawDataLines():
+ for i in range(0, len(line) - 1):
+ tsv.write(line[i])
+ tsv.write("\t")
+ tsv.write(line[len(line) - 1])
+ tsv.write("\n")
+ tsv.close()
+
def store_original_data(tr, dataset, location):
- """Put the original data into the data set."""
- tr.createNewDirectory(dataset, location)
- tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
+ """Put the original data into the data set."""
+ tr.createNewDirectory(dataset, location)
+ tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
tr = service.transaction(incoming)
@@ -68,11 +68,11 @@ dataset.setContainedDataSetCodes(contained_codes)
# If no experiment has been set, then get the experiment from the excel file
if dataset.getExperiment() is None:
- exp_id = metadata.get("EXPERIMENT")
- exp = retrieve_experiment(tr, exp_id)
- if exp is not None:
- dataset.setExperiment(exp)
- original_dataset.setExperiment(exp)
- tsv_dataset.setExperiment(exp)
+ exp_id = metadata.get("EXPERIMENT")
+ exp = retrieve_experiment(tr, exp_id)
+ if exp is not None:
+ dataset.setExperiment(exp)
+ original_dataset.setExperiment(exp)
+ tsv_dataset.setExperiment(exp)
diff --git a/eu_basynthec/dist/etc/proteomics/data-set-validator.py b/eu_basynthec/dist/etc/proteomics/data-set-validator.py
index 63c80b68f35..c794234bf4b 100644
--- a/eu_basynthec/dist/etc/proteomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/proteomics/data-set-validator.py
@@ -1,69 +1,69 @@
def validate_data(time_series_data, errors):
- gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
- column_header_regex = re.compile("(\+|-)?[0-9]+::(value|mean|median|std|var|error|iqr)")
- dataLines = time_series_data.getRawDataLines()
- lineCount = 0
- for line in dataLines:
- # The header needs to be GeneLocus
- if lineCount is 0:
- if line[0] != "GeneLocus":
- errors.append(createFileValidationError("The first data column must be 'GeneLocus'"))
- break
- lineCount = lineCount + 1
- has_human_readable = line[1] == "HumanReadable"
-
- if has_human_readable:
- range_start = 2
- else:
- range_start = 1
- for i in range(range_start, len(line)):
- if not column_header_regex.match(line[i].lower()):
- errors.append(createFileValidationError("Column " + str(i) + " header must be of the format Timepoint::(value|mean|median|std|var|error|iqr), (instead of " + line[i] + ")."))
- continue
+ gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
+ column_header_regex = re.compile("(\+|-)?[0-9]+::(value|mean|median|std|var|error|iqr)")
+ dataLines = time_series_data.getRawDataLines()
+ lineCount = 0
+ for line in dataLines:
+ # The header needs to be GeneLocus
+ if lineCount is 0:
+ if line[0] != "GeneLocus":
+ errors.append(createFileValidationError("The first data column must be 'GeneLocus'"))
+ break
+ lineCount = lineCount + 1
+ has_human_readable = line[1] == "HumanReadable"
+
+ if has_human_readable:
+ range_start = 2
+ else:
+ range_start = 1
+ for i in range(range_start, len(line)):
+ if not column_header_regex.match(line[i].lower()):
+ errors.append(createFileValidationError("Column " + str(i) + " header must be of the format Timepoint::(value|mean|median|std|var|error|iqr), (instead of " + line[i] + ")."))
+ continue
- # The compound id should be one of these forms
- gene_locus = line[0]
- if not gene_locus_regex.match(gene_locus):
- errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be of the format 'BSU#', 'BSU_misc_RNA_#', 'VMG_#_#', or 'VMG_#_#_c' (instead of " + gene_locus + ")."))
- lineCount = lineCount + 1
-
+ # The compound id should be one of these forms
+ gene_locus = line[0]
+ if not gene_locus_regex.match(gene_locus):
+ errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be of the format 'BSU#', 'BSU_misc_RNA_#', 'VMG_#_#', or 'VMG_#_#_c' (instead of " + gene_locus + ")."))
+ lineCount = lineCount + 1
+
def validate_metadata(time_series_data, errors):
- metadata = time_series_data.getMetadataMap()
- validationHelper = ValidationHelper(metadata, errors)
-
- # validate the strain
- validationHelper.validateStrain()
-
- # validate the header format
- validationHelper.validateExplicitHeaderFormat("TIME::VALUE_TYPE")
-
- # validate the timepoint type
- validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
- "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
+ metadata = time_series_data.getMetadataMap()
+ validationHelper = ValidationHelper(metadata, errors)
+
+ # validate the strain
+ validationHelper.validateStrain()
+
+ # validate the header format
+ validationHelper.validateExplicitHeaderFormat("TIME::VALUE_TYPE")
+
+ # validate the timepoint type
+ validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
+ "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
- # validate the cell location
- validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
- "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
+ # validate the cell location
+ validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
+ "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
- # validate the value unit
- validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
- "value unit", ['MM', 'UM', 'PERCENT', 'RATIOT1', 'RATIOCS', 'AU', 'DIMENSIONLESS'], "'mM', 'uM', 'Percent', 'RatioT1', 'RatioCs', 'AU', 'Dimensionless'")
-
- # validate the scale
- validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
- ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
+ # validate the value unit
+ validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
+ "value unit", ['MM', 'UM', 'PERCENT', 'RATIOT1', 'RATIOCS', 'AU', 'DIMENSIONLESS'], "'mM', 'uM', 'Percent', 'RatioT1', 'RatioCs', 'AU', 'Dimensionless'")
+
+ # validate the scale
+ validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
+ ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
def validate_data_set_file(file):
- errors = []
- time_series_data = create_time_series_excel(file.getAbsolutePath())
- if time_series_data is None:
- errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
- return errors
-
- # validate the metadata
- validate_metadata(time_series_data, errors)
-
- # validate the data
- validate_data(time_series_data, errors)
-
- return errors
+ errors = []
+ time_series_data = create_time_series_excel(file.getAbsolutePath())
+ if time_series_data is None:
+ errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
+ return errors
+
+ # validate the metadata
+ validate_metadata(time_series_data, errors)
+
+ # validate the data
+ validate_data(time_series_data, errors)
+
+ return errors
diff --git a/eu_basynthec/dist/etc/shared/shared-classes.py b/eu_basynthec/dist/etc/shared/shared-classes.py
index 6d474765692..72e6fd1ae05 100644
--- a/eu_basynthec/dist/etc/shared/shared-classes.py
+++ b/eu_basynthec/dist/etc/shared/shared-classes.py
@@ -13,156 +13,156 @@ OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
OPENBIS_DATA_SHEET_NAME = "openbis-data"
class TimeSeriesDataExcel:
- """
- An abstraction for accessing time series data following the BaSynthec conventions
- from an Excel file. This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, file, fileReader):
- self.file = file
- self.fileReader = fileReader
-
- def getRawMetadataLines(self):
- """Get the raw lines of the metadata sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
- + OPENBIS_METADATA_SHEET_NAME + "]", ex)
- return []
+ """
+ An abstraction for accessing time series data following the BaSynthec conventions
+ from an Excel file. This class ported from Java, thus the camelCase naming.
+ """
+ def __init__(self, file, fileReader):
+ self.file = file
+ self.fileReader = fileReader
+
+ def getRawMetadataLines(self):
+ """Get the raw lines of the metadata sheet."""
+ try:
+ return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
+ except IOException, ex:
+ operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
+ + OPENBIS_METADATA_SHEET_NAME + "]", ex)
+ return []
- def getRawDataLines(self):
- """Get the raw lines of the data sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
- + OPENBIS_DATA_SHEET_NAME + "]", ex)
- return []
+ def getRawDataLines(self):
+ """Get the raw lines of the data sheet."""
+ try:
+ return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
+ except IOException, ex:
+ operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
+ + OPENBIS_DATA_SHEET_NAME + "]", ex)
+ return []
- def getMetadataMap(self):
- """
- Return the metadata has a hashmap, with all keys uppercased.
-
- Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
- that can be ignored], that is the property name is in column 1 and property value is in
- column 2, and everything else can be ignored.
- """
- metadataMap = {}
- metadataLines = self.getRawMetadataLines()
-
- # Skip the first line, this is just the header
- for i in range(1, metadataLines.size()):
- line = metadataLines.get(i)
- value = line[1];
- if "BLANK" == value:
- value = None
- metadataMap[line[0].upper()] = value
- return metadataMap
-
+ def getMetadataMap(self):
+ """
+ Return the metadata has a hashmap, with all keys uppercased.
+
+ Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
+ that can be ignored], that is the property name is in column 1 and property value is in
+ column 2, and everything else can be ignored.
+ """
+ metadataMap = {}
+ metadataLines = self.getRawMetadataLines()
+
+ # Skip the first line, this is just the header
+ for i in range(1, metadataLines.size()):
+ line = metadataLines.get(i)
+ value = line[1];
+ if "BLANK" == value:
+ value = None
+ metadataMap[line[0].upper()] = value
+ return metadataMap
+
def create_time_series_excel(fileName):
- """Factory method for the TimeSeriesData object. Returns None if it cannot be created."""
- file = java.io.File(fileName)
- try:
- workbook = ExcelFileReader.getExcelWorkbook(file)
- fileReader = ExcelFileReader(workbook, True)
- return TimeSeriesDataExcel(file, fileReader)
- except IllegalArgumentException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- except IOException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- return None
+ """Factory method for the TimeSeriesData object. Returns None if it cannot be created."""
+ file = java.io.File(fileName)
+ try:
+ workbook = ExcelFileReader.getExcelWorkbook(file)
+ fileReader = ExcelFileReader(workbook, True)
+ return TimeSeriesDataExcel(file, fileReader)
+ except IllegalArgumentException, ex:
+ operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
+ except IOException, ex:
+ operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
+ return None
-
+
class ValidationHelper:
- """
- Methods for simplifying validation in BaSynthec.
- This class is ported from Java, thus the camelCase naming.
- """
- def __init__(self, metadataMap, errors):
- self.metadataMap = metadataMap
- self.errors = errors
+ """
+ Methods for simplifying validation in BaSynthec.
+ This class is ported from Java, thus the camelCase naming.
+ """
+ def __init__(self, metadataMap, errors):
+ self.metadataMap = metadataMap
+ self.errors = errors
- def checkIsSpecified(self, property, displayName):
- """Verify that a property is specified; if not, add a validation error to the list."""
- if self.metadataMap.get(property) is None:
- self.errors.append(ValidationError.createFileValidationError("A " + displayName
- + " must be specified."))
- return False
- return True
-
- def validateStrain(self):
- """Verify that the strain is specified and of the correct format"""
- if not self.checkIsSpecified("STRAIN", "strain"):
- return
- strain = self.metadataMap.get("STRAIN")
- if not isStrainIdValid(strain):
- self.errors.append(createFileValidationError("Strain must be MGP[0-999] (instead of " + strain + ")."))
-
- def validateDefaultHeaderFormat(self):
- """Validate that header format is either not specified or matches default (TIME)"""
- if self.metadataMap.get("HEADER FORMAT") is None:
- return
- format = self.metadataMap.get("HEADER FORMAT")
- expected_format = "TIME"
- if expected_format != format:
- self.errors.append(createFileValidationError("Header format must be " + expected_format + " (not " + format + ")."))
-
- def validateExplicitHeaderFormat(self, expected_format):
- """Validate that header format is specified and matches the expected_format argument"""
- if not self.checkIsSpecified("HEADER FORMAT", "header format"):
- return
- format = self.metadataMap.get("HEADER FORMAT")
- if expected_format != format:
- self.errors.append(createFileValidationError("Header format must be " + expected_format + " (not " + format + ")."))
-
- def validateControlledVocabularyProperty(self, property, displayName, allowedValues, allowedValuesDisplay):
- """Validate that the property is specified and in the list of allowed values"""
- if not self.checkIsSpecified(property, displayName):
- return
- value = self.metadataMap.get(property).upper()
- if value not in allowedValues:
- if len(allowedValues) > 1:
- self.errors.append(createFileValidationError("The " + displayName + " must be one of " + allowedValuesDisplay + " (not " + value + ")."))
- else:
- self.errors.append(createFileValidationError("The " + displayName + " must be " + allowedValuesDisplay + " (not " + value + ")."))
-
- def validateStartDataRowCol(self):
- if self.checkIsSpecified("START DATA ROW", "Start Data Row"):
- value = self.metadataMap.get("START DATA ROW")
- match = re.match("[0-9]+", value)
- if match is None:
- self.errors.append(createFileValidationError("The Start Data Row must be a number (not " + value + ")."))
- if self.checkIsSpecified("START DATA COL", "Start Data Col"):
- value = self.metadataMap.get("START DATA COL")
- match = re.match("[A-Z]", value)
- if match is None:
- self.errors.append(createFileValidationError("The Start Data Col must be a letter between A and Z (not " + value + ")."))
-
+ def checkIsSpecified(self, property, displayName):
+ """Verify that a property is specified; if not, add a validation error to the list."""
+ if self.metadataMap.get(property) is None:
+ self.errors.append(ValidationError.createFileValidationError("A " + displayName
+ + " must be specified."))
+ return False
+ return True
+
+ def validateStrain(self):
+ """Verify that the strain is specified and of the correct format"""
+ if not self.checkIsSpecified("STRAIN", "strain"):
+ return
+ strain = self.metadataMap.get("STRAIN")
+ if not isStrainIdValid(strain):
+ self.errors.append(createFileValidationError("Strain must be MGP[0-999] (instead of " + strain + ")."))
+
+ def validateDefaultHeaderFormat(self):
+ """Validate that header format is either not specified or matches default (TIME)"""
+ if self.metadataMap.get("HEADER FORMAT") is None:
+ return
+ format = self.metadataMap.get("HEADER FORMAT")
+ expected_format = "TIME"
+ if expected_format != format:
+ self.errors.append(createFileValidationError("Header format must be " + expected_format + " (not " + format + ")."))
+
+ def validateExplicitHeaderFormat(self, expected_format):
+ """Validate that header format is specified and matches the expected_format argument"""
+ if not self.checkIsSpecified("HEADER FORMAT", "header format"):
+ return
+ format = self.metadataMap.get("HEADER FORMAT")
+ if expected_format != format:
+ self.errors.append(createFileValidationError("Header format must be " + expected_format + " (not " + format + ")."))
+
+ def validateControlledVocabularyProperty(self, property, displayName, allowedValues, allowedValuesDisplay):
+ """Validate that the property is specified and in the list of allowed values"""
+ if not self.checkIsSpecified(property, displayName):
+ return
+ value = self.metadataMap.get(property).upper()
+ if value not in allowedValues:
+ if len(allowedValues) > 1:
+ self.errors.append(createFileValidationError("The " + displayName + " must be one of " + allowedValuesDisplay + " (not " + value + ")."))
+ else:
+ self.errors.append(createFileValidationError("The " + displayName + " must be " + allowedValuesDisplay + " (not " + value + ")."))
+
+ def validateStartDataRowCol(self):
+ if self.checkIsSpecified("START DATA ROW", "Start Data Row"):
+ value = self.metadataMap.get("START DATA ROW")
+ match = re.match("[0-9]+", value)
+ if match is None:
+ self.errors.append(createFileValidationError("The Start Data Row must be a number (not " + value + ")."))
+ if self.checkIsSpecified("START DATA COL", "Start Data Col"):
+ value = self.metadataMap.get("START DATA COL")
+ match = re.match("[A-Z]", value)
+ if match is None:
+ self.errors.append(createFileValidationError("The Start Data Col must be a letter between A and Z (not " + value + ")."))
+
strainIdRegex = re.compile("^MGP[0-9]{1,3}")
def isStrainIdValid(strainId):
- """Return true if the strain id passes validation (has the form MGP[:digit:]{1,3})"""
- match = strainIdRegex.match(strainId)
- if match is None:
- return False
- return match.end() == len(strainId)
-
+ """Return true if the strain id passes validation (has the form MGP[:digit:]{1,3})"""
+ match = strainIdRegex.match(strainId)
+ if match is None:
+ return False
+ return match.end() == len(strainId)
+
def getInitialDataRowAndCol(metadata):
- """Extract the initial row and column as specified in the metadata. Returns an array with [row, col]."""
- # get the raw value from the map
- first_data_row = metadata.get("START DATA ROW")
- first_data_col = metadata.get("START DATA COL")
+ """Extract the initial row and column as specified in the metadata. Returns an array with [row, col]."""
+ # get the raw value from the map
+ first_data_row = metadata.get("START DATA ROW")
+ first_data_col = metadata.get("START DATA COL")
- # convert the row numeric string to an int
- if first_data_row is None:
- first_data_row = 0
- else:
- first_data_row = int(float(first_data_row)) - 1
+ # convert the row numeric string to an int
+ if first_data_row is None:
+ first_data_row = 0
+ else:
+ first_data_row = int(float(first_data_row)) - 1
- # convert the column spreadsheet value to an int
- if first_data_col is None:
- first_data_col = 0
- else:
- # columns start at A
- first_data_col = ord(first_data_col) - ord('A')
- return [first_data_row, first_data_col]
+ # convert the column spreadsheet value to an int
+ if first_data_col is None:
+ first_data_col = 0
+ else:
+ # columns start at A
+ first_data_col = ord(first_data_col) - ord('A')
+ return [first_data_row, first_data_col]
diff --git a/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py b/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
index d7d875f0585..81078ecaa8a 100644
--- a/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
+++ b/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
@@ -3,87 +3,159 @@ from eu.basynthec.cisd.dss import TimeSeriesDataExcel
import re
def getInitialDataRowAndCol(metadata):
- """Extract the initial row and column as specified in the metadata. Returns an array with [row, col]."""
- # get the raw value from the map
- first_data_row = metadata.get("START DATA ROW")
- first_data_col = metadata.get("START DATA COL")
-
- # convert the row numeric string to an int
- if first_data_row is None:
- first_data_row = 0
- else:
- first_data_row = int(float(first_data_row)) - 1
-
- # convert the column spreadsheet value to an int
- if first_data_col is None:
- first_data_col = 0
- else:
- # columns start at A
- first_data_col = ord(first_data_col) - ord('A')
- return [first_data_row, first_data_col]
+ """Extract the initial row and column as specified in the metadata. Returns an array with [row, col]."""
+ # get the raw value from the map
+ first_data_row = metadata.get("START DATA ROW")
+ first_data_col = metadata.get("START DATA COL")
+
+ # convert the row numeric string to an int
+ if first_data_row is None:
+ first_data_row = 0
+ else:
+ first_data_row = int(float(first_data_row)) - 1
+
+ # convert the column spreadsheet value to an int
+ if first_data_col is None:
+ first_data_col = 0
+ else:
+ # columns start at A
+ first_data_col = ord(first_data_col) - ord('A')
+ return [first_data_row, first_data_col]
def retrieve_experiment(tr, exp_id):
- """Get the specified experiment form the server. Return the experiment."""
- if exp_id is None:
- exp = None
- else:
- exp = tr.getExperiment(exp_id)
- return exp
+ """Get the specified experiment form the server. Return the experiment."""
+ if exp_id is None:
+ exp = None
+ else:
+ exp = tr.getExperiment(exp_id)
+ return exp
def assign_properties(dataset, metadata):
- """Assign properties to the data set from information in the data."""
- propertyNameMap = {
- "STRAIN_NAMES": "STRAIN_NAMES",
- "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
- "CELL LOCATION": "CELL_LOCATION",
- "VALUE TYPE": "VALUE_TYPE",
- "VALUE UNIT": "VALUE_UNIT",
- "SCALE": "SCALE"
- }
-
- for prop in metadata.keySet():
- key = propertyNameMap.get(prop)
- if key is not None:
- value = metadata.get(prop)
- if (key == "STRAIN"):
- value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
-
+ """Assign properties to the data set from information in the data."""
+ propertyNameMap = {
+ "STRAIN_NAMES": "STRAIN_NAMES",
+ "TIMEPOINT TYPE": "TIMEPOINT_TYPE",
+ "CELL LOCATION": "CELL_LOCATION",
+ "VALUE TYPE": "VALUE_TYPE",
+ "VALUE UNIT": "VALUE_UNIT",
+ "SCALE": "SCALE"
+ }
+
+ for prop in metadata.keySet():
+ key = propertyNameMap.get(prop)
+ if key is not None:
+ value = metadata.get(prop)
+ if (key == "STRAIN"):
+ value = value + " (STRAIN)"
+ dataset.setPropertyValue(key, value.upper())
+
def convert_data_to_tsv(tr, start_row, start_col, dataset, location):
- """Create a tsv file containing the data and add it to the data set."""
- tr.createNewDirectory(dataset, location)
- tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
- tsv = open(tsvFileName, 'w')
- raw_data = timeSeriesData.getRawDataLines()
- for i in range(start_row, len(raw_data)):
- line = raw_data[i]
- # write the metabolite id
- tsv.write(line[0])
- tsv.write("\t")
- for j in range(start_col, len(line) - 1):
- tsv.write(line[j])
- tsv.write("\t")
- tsv.write(line[len(line) - 1])
- tsv.write("\n")
- tsv.close()
-
+ """Create a tsv file containing the data and add it to the data set."""
+ tr.createNewDirectory(dataset, location)
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ raw_data = timeSeriesData.getRawDataLines()
+ for i in range(start_row, len(raw_data)):
+ line = raw_data[i]
+ # write the metabolite id
+ tsv.write(line[0])
+ tsv.write("\t")
+ for j in range(start_col, len(line) - 1):
+ tsv.write(line[j])
+ tsv.write("\t")
+ tsv.write(line[len(line) - 1])
+ tsv.write("\n")
+ tsv.close()
+
+class SplitColumnInfo:
+ """
+ A class that stores, for each column in the file, the column number, the strain name,
+ the biological replicate, the hybridization number, and the column offset in the resulting file
+ """
+ def __init__(self, column, strain_name, bio_replicate, hybrid_number, output_col):
+ self.column = column
+ self.strain_name = strain_name
+ self.bio_replicate = bio_replicate
+ self.hybrid_number = hybrid_number
+ self.output_col = output_col
+
+ tsv = None
+
+
+def convert_data_to_split_tsv(tr, start_row, start_col, dataset, location):
+ """Create one tsv file per strain in the original data."""
+ raw_data = timeSeriesData.getRawDataLines()
+
+ # Keep track of the mapping from columns to strains and strains to columns
+ column_infos = []
+ strain_column_info = {}
+
+ # Extract the column / strain mapping
+ header_line = raw_data[start_row]
+ header_regex = re.compile("^(MGP[0-9]{1,3})-([0-9]) ([0-9]+)")
+ for i in range(start_col, len(header_line)):
+ match = header_regex.match(header_line[i])
+ strain_name = match.group(1)
+ strain_cols = strain_column_info.setdefault(strain_name, [])
+ column_info = SplitColumnInfo(i, strain_name, match.group(2), match.group(3), len(strain_cols))
+ strain_cols.append(column_info)
+ column_infos.append(column_info)
+
+ # create the files
+ tr.createNewDirectory(dataset, location)
+ for strain in strain_column_info.iterkeys():
+ tsvFileName = tr.createNewFile(dataset, location, incoming.getName() + "_" + strain + ".tsv")
+ tsv = open(tsvFileName, 'w')
+ for column_info in strain_column_info[strain]:
+ column_info.tsv = tsv
+
+ # Write the header
+ line = raw_data[start_row]
+ tag = line[0]
+ # write the first column to each file
+ for strain in strain_column_info.iterkeys():
+ strain_column_info[strain][0].tsv.write(tag)
+
+ for column_info in column_infos:
+ column_info.tsv.write('\t')
+ column_info.tsv.write(column_info.bio_replicate)
+ column_info.tsv.write(' ')
+ column_info.tsv.write(column_info.hybrid_number)
+
+ # Write the data to the files
+ for i in range(start_row + 1, len(raw_data)):
+ line = raw_data[i]
+ tag = line[0]
+ for strain in strain_column_info.iterkeys():
+ strain_column_info[strain][0].tsv.write('\n')
+ # write the first column to each file
+ strain_column_info[strain][0].tsv.write(tag)
+ # Write the remaining data to each file
+ for column_info in column_infos:
+ column_info.tsv.write('\t')
+ column_info.tsv.write(line[column_info.column])
+
+ # Close each file
+ for strain in strain_column_info.iterkeys():
+ strain_column_info[strain][0].tsv.close()
+
def store_original_data(tr, dataset, location):
- """Put the original data into the data set."""
- tr.createNewDirectory(dataset, location)
- tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
+ """Put the original data into the data set."""
+ tr.createNewDirectory(dataset, location)
+ tr.moveFile(incoming.getAbsolutePath(), dataset, location + "/" + incoming.getName())
def extract_strains(start_row, start_col):
- """Extract the strain names from the header."""
- strains = []
- line = timeSeriesData.getRawDataLines()[start_row]
- header_regex = re.compile("^(MGP[0-9]{1,3})-([0-9]) ([0-9]+)")
- for i in range(start_col, len(line)):
- match = header_regex.match(line[i])
- strains.append(match.group(1))
- return ",".join(strains)
+ """Extract the strain names from the header."""
+ strains = []
+ line = timeSeriesData.getRawDataLines()[start_row]
+ header_regex = re.compile("^(MGP[0-9]{1,3})-([0-9]) ([0-9]+)")
+ for i in range(start_col, len(line)):
+ match = header_regex.match(line[i])
+ strains.append(match.group(1))
+ return ",".join(strains)
-
+
tr = service.transaction(incoming)
timeSeriesData = TimeSeriesDataExcel.createTimeSeriesDataExcel(incoming.getAbsolutePath())
@@ -102,6 +174,9 @@ store_original_data(tr, original_dataset, "xls")
tsv_dataset = tr.createNewDataSet("TSV_MULTISTRAIN_EXPORT")
convert_data_to_tsv(tr, dataStart[0], dataStart[1], tsv_dataset, "tsv-multi")
+tsv_split_dataset = tr.createNewDataSet("TSV_EXPORT")
+convert_data_to_split_tsv(tr, dataStart[0], dataStart[1], tsv_split_dataset, "tsv")
+
# Make the original contain these
contained_codes = [original_dataset.getDataSetCode(), tsv_dataset.getDataSetCode()]
dataset.setContainedDataSetCodes(contained_codes)
@@ -109,11 +184,11 @@ dataset.setContainedDataSetCodes(contained_codes)
# If no experiment has been set, then get the experiment from the excel file
if dataset.getExperiment() is None:
- exp_id = metadata.get("EXPERIMENT")
- exp = retrieve_experiment(tr, exp_id)
- if exp is not None:
- dataset.setExperiment(exp)
- original_dataset.setExperiment(exp)
- tsv_dataset.setExperiment(exp)
-
+ exp_id = metadata.get("EXPERIMENT")
+ exp = retrieve_experiment(tr, exp_id)
+ if exp is not None:
+ dataset.setExperiment(exp)
+ original_dataset.setExperiment(exp)
+ tsv_dataset.setExperiment(exp)
+ tsv_split_dataset.setExperiment(exp)
diff --git a/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py b/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
index ff0208622f0..7eece315c6a 100644
--- a/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
@@ -1,75 +1,75 @@
def validate_header(line, first_data_col, errors):
- """Validate the header, returning False if there is no point in continuing validation"""
- if line[0] != "Locustag":
- errors.append(createFileValidationError("The first data column must be 'Locustag' (not " + line[0] + ")."))
- return False
- header_regex = re.compile("^MGP[0-9]{1,3}-[0-9] [0-9]+")
- for i in range(first_data_col, len(line)):
- match = header_regex.match(line[i])
- if match is None:
- errors.append(createFileValidationError("The column header + " + str(i) + " must be of the form [STRAIN]-[BIOLOGICAL REPLICATE] [HYBRIDIZATION NUMBER]"))
+ """Validate the header, returning False if there is no point in continuing validation"""
+ if line[0] != "Locustag":
+ errors.append(createFileValidationError("The first data column must be 'Locustag' (not " + line[0] + ")."))
+ return False
+ header_regex = re.compile("^MGP[0-9]{1,3}-[0-9] [0-9]+")
+ for i in range(first_data_col, len(line)):
+ match = header_regex.match(line[i])
+ if match is None:
+ errors.append(createFileValidationError("The column header + " + str(i) + " must be of the form [STRAIN]-[BIOLOGICAL REPLICATE] [HYBRIDIZATION NUMBER]"))
def validate_data(time_series_data, first_data_row, first_data_col, errors):
- gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
- dataLines = time_series_data.getRawDataLines()
- for i in range(first_data_row, len(dataLines)):
- line = dataLines[i]
- # The header needs to be CompoundID
- if i is first_data_row:
- if not validate_header(line, first_data_col, errors):
- break
- continue
+ gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
+ dataLines = time_series_data.getRawDataLines()
+ for i in range(first_data_row, len(dataLines)):
+ line = dataLines[i]
+ # The header needs to be CompoundID
+ if i is first_data_row:
+ if not validate_header(line, first_data_col, errors):
+ break
+ continue
- # The compound id should be one of these forms
- gene_locus = line[0]
- if not gene_locus_regex.match(gene_locus):
- errors.append(createFileValidationError("Line " + str(i + 1) + ", column 1 must be of the format 'BSU#', 'BSU_misc_RNA_#', 'VMG_#_#', or 'VMG_#_#_c' (instead of " + gene_locus + ")."))
-
+ # The compound id should be one of these forms
+ gene_locus = line[0]
+ if not gene_locus_regex.match(gene_locus):
+ errors.append(createFileValidationError("Line " + str(i + 1) + ", column 1 must be of the format 'BSU#', 'BSU_misc_RNA_#', 'VMG_#_#', or 'VMG_#_#_c' (instead of " + gene_locus + ")."))
+
def validate_metadata(time_series_data, errors):
- metadata = time_series_data.getMetadataMap()
- validationHelper = ValidationHelper(metadata, errors)
-
- # validate the header format
- validationHelper.validateExplicitHeaderFormat("STRAIN-BIOREP HYBRID")
-
- # validate the timepoint type
- validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
- "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
+ metadata = time_series_data.getMetadataMap()
+ validationHelper = ValidationHelper(metadata, errors)
+
+ # validate the header format
+ validationHelper.validateExplicitHeaderFormat("STRAIN-BIOREP HYBRID")
+
+ # validate the timepoint type
+ validationHelper.validateControlledVocabularyProperty("TIMEPOINT TYPE",
+ "time point type", ['EX', 'IN', 'SI'], "'EX', 'IN', 'SI'")
- # validate the cell location
- validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
- "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
+ # validate the cell location
+ validationHelper.validateControlledVocabularyProperty("CELL LOCATION",
+ "cell location", ['CE', 'ES', 'ME', 'CY', 'NC'], "'CE', 'ES', 'ME', 'CY', 'NC'")
- # validate the value type
- validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
- "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
- "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
+ # validate the value type
+ validationHelper.validateControlledVocabularyProperty("VALUE TYPE",
+ "value type", ['VALUE', 'MEAN', 'MEDIAN', 'STD', 'VAR', 'ERROR', 'IQR'],
+ "'Value', 'Mean', 'Median', 'Std', 'Var', 'Error', 'Iqr'")
- # validate the value unit
- validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
- "value unit", ['MM', 'UM', 'PERCENT', 'RATIOT1', 'RATIOCS', 'AU', 'DIMENSIONLESS'], "'mM', 'uM', 'Percent', 'RatioT1', 'RatioCs', 'AU', 'Dimensionless'")
-
- # validate the scale
- validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
- ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
-
- # validate the data position specification
- validationHelper.validateStartDataRowCol()
+ # validate the value unit
+ validationHelper.validateControlledVocabularyProperty("VALUE UNIT",
+ "value unit", ['MM', 'UM', 'PERCENT', 'RATIOT1', 'RATIOCS', 'AU', 'DIMENSIONLESS'], "'mM', 'uM', 'Percent', 'RatioT1', 'RatioCs', 'AU', 'Dimensionless'")
+
+ # validate the scale
+ validationHelper.validateControlledVocabularyProperty("SCALE", "scale",
+ ['LIN', 'LOG2', 'LOG10', 'LN'], "'lin', 'log2', 'log10', 'ln'")
+
+ # validate the data position specification
+ validationHelper.validateStartDataRowCol()
def validate_data_set_file(file):
- errors = []
- time_series_data = create_time_series_excel(file.getAbsolutePath())
- if time_series_data is None:
- errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
- return errors
-
- # validate the metadata
- validate_metadata(time_series_data, errors)
-
- data_start = getInitialDataRowAndCol(time_series_data.getMetadataMap())
-
- # validate the data
- validate_data(time_series_data, data_start[0], data_start[1], errors)
-
- return errors
+ errors = []
+ time_series_data = create_time_series_excel(file.getAbsolutePath())
+ if time_series_data is None:
+ errors.append(createFileValidationError(file.getName() + " is not an Excel file."))
+ return errors
+
+ # validate the metadata
+ validate_metadata(time_series_data, errors)
+
+ data_start = getInitialDataRowAndCol(time_series_data.getMetadataMap())
+
+ # validate the data
+ validate_data(time_series_data, data_start[0], data_start[1], errors)
+
+ return errors
diff --git a/eu_basynthec/sourceTest/examples/OD600-Example.xlsx b/eu_basynthec/sourceTest/examples/OD600-Example.xlsx
index 4f83f9ce28149ce85353f1e0456bfaddba7aa093..cee4d575d2575a349bfb7c3a456c3dfae9f8b5f8 100644
GIT binary patch
delta 3751
zcmY*c2{aU38y?IsG{%zM*bU0QHr9x-FJ(*iHAHsd6Jr-j%rL}+EFqJ9-=#?u#yX6w
zsmLxZ2*0oIobNmTJ?FXSp7%cIdCz<Ax$n78yUDz1Egp<2#3KX<6aauW6#&2h006>$
zrNjJ#d|dtgeWb$g`r^#{{N`jJT?{i<!R?|!>gDTkGsu=|n-~|dq-u3>Ii3r3!rH|?
zKX>#7ho}8iA*u$#gn@zbmM)y}0B;}7mha#wmebQYyQ)b&>-X{e@Jd`m%=mPDFq`2i
zFxJW1AGPSK_vLZqm-L4KU$Ka^8UF<E3y@I%_;=^ZafH9H`5J@Z0k1ocEkNPv+lEbh
zj!MZwCZ$s+8T$z@5XqFDT4IEsS0zQ~YGXS?Ct0aI{y0KN<oL8o;dSI!#D;sXS(9#s
zk>m9>-SF&P?K2mm1HQVRm3?Xy?yp`2e>HoINAYLsXHGv-jqI$ScFA)HVm5`YX{c!X
zBn4ElLPJtOl&OaEJ{<kh?>Xw%wdTl=;7+T+-Gj?q7VBE18LXQ0^d13s3^^hS$|^gt
zXX&(^vE9nLpN-_A`!4ihFsjtBfsnRr5G9ytdK;s#SM@_h0#Z~e>0$r))Jso=_#(Q*
zd3_};^wp8wqQClKT7lZ|ReGy>i&A$r=3gE7x6^wd<6m%RmBL}?=T|>CH||TdQs)eD
z%5uj-N`c07=t8N26NT`Tv-zoM<9zWN^1Ncl`f6-+z(Slp8Y}u@W%cYUO+yS_5G5#I
zab9r*^AjS2%6@TM(2~oA+Z?SMZ#`FbL9~x~W>U%G+fG=~n1)~Ey?D@?TIbGTt--eA
z5j48^8#%AZ#-2b)oNONZ+{nf-^@X8@^8WSbH=ZiCvUwh?NJX7V?P&lATs>@e!Toxd
zqUK#|erNL#iTNd=U34KErsE7ytB-cCiD5yU16S&AqR8NiEw5L$_D&Z#9!2xYMn=_k
zvU;zC<|P~~@XrYOHl;ZGn7un}e;`x~Z5GKCFiFBTf*kl@u$Qz*ZBt;vH_f<5!}vB1
z7CDnuos(qTC#F>opsH;HpL|$hU@MK@rGVx4F1|#PDMRegt3J#2fxbHzi;8^%^mF7^
z7lp)rpn}muasBUVH!2F6R&0N({201l^26M0zN){+5Z7}ZE=D5~(5UgkPv;)>J6i`}
zcb!ueRwOoQ!{P?zsS<U&K;%)ySfHBYS5>>RTbjs^&HcJ&KAd@A-s}?Pz>)E5B{$U?
zG(@X9@u&8Pp)_?-6=~(M;Px3nxJ=$uQGO+%Tv@VHduKKX0U$qDUhc?D&lXKMyS)}2
zd~pDV^auzs4+M8eCxgtWn6MHTF~H}EQ+K{A#g$%7JYdJf(6M6fz!@7T7<g#t?7y2|
z(FOqkXBRQYT%0JmKW{a6F}PTTC1!Ew{Rtlj?~d_dS&Yh8)21!Iu(_$1_kMN@>Uz*6
za2MbGS+htbP$!I#X<=af_7sOp@ShEOQ@DV(Q58VzA)c-^yR35=YIi;wKhZ%sE;`VM
zNS150)4Sq|Q%=)^P9_d^dfwFJcCOMSR8Vt{-!JA9Lk;Ubf09g-1#F9z&!U`lK?7O3
z(OpkGfuOk{bLRYXkBHmMI+Y`G5A}0k;Vo&`LgM?~;>?H8j4U)PUq=~kV88hq%)lL(
zGjiPSv91Wmv*e4VuSGtwELAo+5Hir4YOY3$2_ptnZQpakwGb-sx@!3HT6Cc+v#%?n
zbk#B)B|$sHr2Nds(4bM-99W)((>+_8*i(wzPm?Es$tDLrkq4XWpF`|<M@GS2pZTg4
zxqPj~bOn%ht$OX&xD)D+IfA>qNfK{!b10B+_)EuVhi|~NT^alqQNHy42Rrj7ZK;>A
zPtr$8_Xj)nv63mxv_T33do^B047E}fb;u6X632w-?;{ZMm@0A1@y5LeZn^Y5O~RKI
z;<jk~@soG<i5#tdi`>7es}l!sD+%Q<KQ}xvRlKO-RQ05Kd2YIvBv*ISB*9E$?8;I4
z27_;TpaEvezTmZqX8d~Y(oK3;!pb)Zv4_oi>GY!9Y$YTa$lUPqvG>=5H=k+KrSMCe
zD4~N5U&m5}NzLZ7Pd1?;{h2#&*RVn@Ukn<y5nm(r@uRR=D$c0ox8_5wHAKzI6(8h%
zkCB$tgXH~d46K1!%)H{R;<Mesf}(aZOYc4!Dfx9^Ll9Rv)*|*R)nx&6hVs^sa4cjR
z(n}tH=t-S4P2(J=_KH8FWssjkgL`!fWtBTsWRV<PZuwSDq6O;5vHMVCa({WCy9;gp
zp<aJ+H|aYcd_NrteW;~Qv=F@dt=`ut=roN#U1u8<Sk`r)^>x^WIO*r_M+3?yD&b2-
zq9+^oSBs=$cPJqnm29xq=q{G^YRL$kXe=KLauO}sU(`*!nAWgtU_~QNQ93@2f*_LM
zv7Xd_B?X&WH82-EG_iiQJ8QVE@2MC*VyD6MrOU`#jz}<MoBaol*gIwXso8O2)^y{p
z@W&STRn0my6~U0ARJC)dXxNaq+-6WKKU<=@?>sa<4N<Te?DY^o9{xwwK(<P2cIXr?
z&bj6aPun~P>U@$mYBFae7;3SIgS_j|1DC9WifjgBUCRLDFP#F2xBp~0mu4e5mjTSZ
zeW<zc?o0LAyX<Zg4a`ZS)`n*d!*{MXk9WDlsT}a`ng3wbqtcqL*yhp$*D`)d>wN^l
z5XvI1d>zlC+5Y_kl#E{uOwEQh-a-woaGl34-yPPB&xY7H*N5l$gv-Y+H)N0V2{v$L
zy*!Y*HK@rhe#`wIMBIAur}%Sa{j_W~(?7+ZD}yrpPU7N~#3OL7aGJZ;^{v$BAwxTP
zqBER|-nxE-A~I|QO5`cN0d|PzG4&qH5?e@FlwV6im4>HJydYS1ZhH3ds#Cl3m9?>z
z@U;4H66VxhctAfASMbJleJp>0K7FFd(*rvaB&p)UI4n-fhT5(j<a*!A5U5X$?tg_G
zpu~WWbUY%xiam3$GwWEApfac2bo49v5_xM;o-=%Zb;~D^WGYyciYaYCU1P~OY@yZY
z<ya}B<jG&mJc3jzIwBi4wF<=*#_S#pHIs_&MDox|oS;0-1_tN64tFggU)#-y`-Wx~
z!(n$LPJBSBV$#oiZ8%e<qI0J5k;fIAk;Z3#_gPvY>+)pZ^B<8P=7>uW<)1IZ5>?oE
z788z}1Q_JIKe*mxId%D^ZPVj>HR*25;xo6K1=f2Oo9KaFs#cM-0m?sr{R)WkN52yi
z@66Ljf}9S=gb&nT)y-V*b~x;bUMP@^GV^|YrGgQM|Ls})``y9E<W>Gv$1U&}uS`JG
zewb}eAfs5P5Tr6ij5hg78!7|h9iBC(nT;-bWa5gHq3@6AW&G6b_TW<_LZ`sO*bi9E
zu}sd?H|M86no7sM@NoO39s(JRvMO-tGc2;1i2LekL>`+I??J2iHHW?t!(L0V&&TBo
zz)1LA^`ws-lI+YcFUX`!Ded#82-b_-v^8q4R-nkS;X&<BxNB>5qxL>vgq;p=-oQ!z
z<~PABKhA<#?kvbV)+Em4vxntp^HIhNg8FWgc;k#r<jh$#72-#~4+M^^EVf*c@8=3>
zJUPCXVt1UvTiT+V>RudP%-t1l8)H6`0kcXxm4Z5f=eHGfa*`O+DC?I=Zj)K`zU(|(
z--*JbqU>n_Y$npis6#bw3qXQ+8OZ05TToB-uGkXUTtZ|l0<j~DJHt@i^F#JFx#UW>
z69j$*?e*U6&kK%MFuZsP%9|yiZv~e_@(?n-f2b=KxP99n>U1~^UW~7e^LlEEDWdia
zjBmXMw&~K=DNN3IueB5qnsF-`tf^ZLf~<RcE9O>A&6Y`{Izp=U$pXEnP^PEWwSUuo
z0#j75v0#~HRwfY@mcWHFRVJt`qimczbeuhKEEA&8OF|*zQ=p3PJ3`9)1gN=8#SucV
z(wb#@K4Zl~x{?zP5tT`qBQgmpOO!!BQGTo0Ux}yI)%?^Y_(~^Pu$b_cmWH!}!^-3{
ze-!Hk>Iz=QbEAw^M8%vb-4dbiL<j-KT6@_XT{Z=KCT@6b6S1nf#(A!5&TUI%1$~6W
zQCq_Eexyja{DN`Mr7`RWp|&#n2+-iO-Tpz!Mt#!!hj_NKGMfwZTSE)m&H+q_-^;+>
zHpcd-fZ<&(>N&><8%vm&OK4JfA|3Y#**VV}|7oFwpW)8J_jkMZBV4dFtp@Thx&A`C
z8C?vTbjoff-PV!wsxMKVqc5d}l=eQ-<ETRL>ltrmIVf2)qYus+CK7l)Cf7V(=$eVC
zk>TzR+z0rPkIVTup78RKC1d<%^s6-1PA`?BC@`^fETGjE)1NvGCA=aOC?}(S85Y7K
zs7HG+GT;3S_H0Yj!wd=(P4$;;+ekIxLVLCN`;+~e<oX6a1aI#YL>jcKR9rry+!(U;
zd>{fu79k~#9NgC;I?{8*f(m>Ft8BHC(wB&rd%6u1U5cA`y?m&qbC!xV$J1#s&$@ml
zxop1XWeGC~SmWQmQ`O3VGP85;C(uX(%)qytK?O$J%6_qRoDbF#vRpOu%<Mt|mt-u9
zG$WI}ukAf1#anHUCYf?7TdhA9*$hcly=^p>7Js}n)HkDGGH%?#A#jyYlb>AfH`O}1
z^%7X5mK{fX;R8u2XRjkTW93Grx)b5)VuI0*VMfb9UuY%Jn!SrgBktifj%mHC;?ffx
z$6H*VE?)CC{=Apvw~iYI=SwV*`+AP%0;05@zBx1MO!4MtRx0;xhB1xCs1ext1kb4d
zKFtPhfov+;e@z~yP1uwo0|SQh!~R%;bK~a)1^`&jjo*J`3xcL+!`Q+vQ*J>qXHZs5
zKAaKu--i<b;P{VwzT#rToN=*YKEPRF|F+F@&HpE1xX(#k7*P>M*q{47PwYSm05JWZ
Xk|H0*LPVXS7LzF=L>(*q_ul^ilL*ze
delta 3573
zcma)<cTf}Fvd5Fqk={w@5SmEuy%SmlgwRCkH6hXjq(ndvL|Q_TB7*dyQUsMEMT!xX
zCSpJcMI?aqDpD@*_j~U*@BVRT?wQ%y-8tXc*_kuD^Eor{Hp_;3YK(`~f_(=N08k<W
z02l!PKm<}I9333sjz$MaN1%{JHkRlwvP_-A+x$|*@W=FoKu44fyIH>(wH@_T^JG4<
ze&59ND(rZZTg=5bj%>j*V{rFpr%H1>_?a6~&~V)aZ$I=<;ns)ADPHrl^|kc{Y;*G1
z#8?Cs6m#$Wi`q%di`xl|RSAb;#sKNu4x?YK`i2wnIYBELx3c}B8(1XhOqkmNP3czv
zPQp7<?Mw*&L7#i5BThP^qEk<reJ90z1sFg$i!_J`&$4efhP-~lE=LG^QURSUoB#Me
zncqLnDzBqtgmG&@aBrslMq###Pk?mo6QNB|9kh29g~-I1{(!CB@6>S7SPois36_T+
zkcd&{@*W-Iv{7y4<UnZEh7#R2r#CI(sKjOcK2|0e6cNo#e{EH7@>{N^jPlCh$pQ0T
zqmg@XqXdb0Y2Mu3dM8XdjCFX*GWOc^if5p_F#U4LVlT*S42lyd_)wgUd)+V*O7rJV
z&ZF~Z8?WpOP8=<Z{rle3V2!iFR~~f}J&jsTbzJ+dGFR>To!mb0I78IUm7#Cdbg=J|
z{JgU7TKBxv%exBsLUnpRG4VNldaY#Yl)hbQ2c}SH$7DJdTq*e(a`Ut~g*F&OQBnCF
z{RvAii^0`af+W)#=p{_c^y=2f5^=6HNdLl`--jCIquPN{w-YExnjM?J8%#HDB=N;Q
z-JL41m3r<D^aW4*hgkF*oc?~72H?;3vqRHYF5J8E-D{Hwouw*qSiClxC_8JmQpiBH
z^x{`?(kxFs#J0paJUceD+KDKbRGK%W`ZhOV3}dY8A;xO69VF-~e;nC+vfr~~?3ps@
z$kG&*;L6xADjJ`rB|SW8#1j|RAeTbtD1W>B3dwtO&ec-fIao-b$e0C*4E)qzlIbYq
zv#Rr>Be|qn=-XJqxoSwb+Wq$MY!D}$X8;_txW`p3#bfb|iszX!(EkJF{ZI*mZLRp=
za17kWE;vH%Kx?Ae`g-ckD!qL4mm8}!n6M-JlvK`I@}+L_^sgopSKohjov2RjRyhcm
z85J416(f1Mn>e8R%JV9}qI&wEdCV}vkHc#8HL7u9*C|ms-ek!aUex?@gp@N}Ka6jy
zUe)1D-w7T}k(Pw-sktBlnp~g!NA|xj?5c6hmK`G1cmSyJqOEnq!4Isx7=_TTx9J|~
zPbF2=YgF&8=bgq^#ZjB*rZ|Ged;MGPK=j6*=pS5aUS`mvVvr)|jeblH0BkV<09*iE
zgD5)=BT9iO%5w>MYR05XL{FSiJs5mOdy}@hA`mJ{@KkY}>HDQEoNh+JCH=7A<j=J1
z9+x-F)P*1PamDXWl5pi9aTe>Kk=c>#t3HZ)H>QM53gxYsPC0Ap=;R_f^~8tr_9;SH
zPam@#zgo$|444#jacJm2qU0WPf4a#vWL)WZPXmh~Pt;Suf(Rp;G+ftzIyb)$W~r|;
zHASlDF6EmtRj3ckerW$uQfSGB4FGSjV&#iP#Dcm@&fGb@D7?*krB|>5m>C~VK}&g9
z<Aa6dPJ2_Mf_H|*<(29iUyWE2)vl0|azczvnbH|d>jO+x+lZBlj0icTO>ng_hnfT|
zRsfUtaB0+knEIDZFjve()nXX=QeM>aB~OJ>nf1}sy2A0G7B!4eu#|RDz|xHu;xSix
zPVYQ*&MXy>qZzUb0P-++8ZW%I_>!=^kAD2pzEaWXbH?(c^VU1ssn?w;DDp>-&@a6;
zn1GrNILn3%0;|?+mT$X<tP_;ZkFI(CMXn*HLZRX7+%t8)HN1hxTw4r!uDy+8<B~C}
zg)@hUxB9+?>Vn1O7AoMIh63|fhZ&Z1)lrq>^fg9g)qbw%i#Jm#Yj-KegWwrpYN~!t
zN2}F<3?4|Ul9Y*z8&|G#_rBZe-oQ^_t91SRgb7K7P;U|R=*BmLp~eCdIBWAgi82c_
zy<6`1D)~;a=9-33lt7t=VXn<UOd6#byN>_D<&fB~<vQ8uJu6ldiTOs+R_r<_iyEPb
z>?YsMt)S_a@=w1%=?&w;*Hg%>tO~Y2#`)k~@xbrS1>3znBgX)XOcO5homOu0cVY=0
zm9+NsB*poUHEd0EL#X%w2F)_YmgpnQHx*8s2N1p$$ZW%JYaw*xk8UnSGA-ziMy{7L
zb~ij;mE{d*U(VMZ112JB_RX80Pq>!%3g>`&SC4ON3z5v{@&NC=Yt=xL=v*PK7K(vL
zmZLOR(jkPK@)JaBTNN^EYq=$L*LDg^HrODt)vGsr3tj_8<aU9sY$|bSJ4#?sD|TeX
zI|y{2<EFx8HIh3t<JaGoTj3;;>|P=8ASb@4k!6wXGP5{B$f}-A_fBsJ`Eq@qYQNcq
z`w?^nK`W5c`lF=Zj6wTV6EP4<_oP01md&1C+?jCx(Tt(Z0WaMCm!){sAZVXD{8iQG
z?*b1nIn->IDKhy^d3w|?%fTC2E?ngG)Ep43;)<GYBQ|09*}ZeF>De6F=q8(EuXcZ3
zg4yAJ+vwhZYSgLz$0>NzrioV(Gb2S?sxv*3ozr=f5Yyo^;#nDLJl+-}GhHk74Lc}6
zH1;d)_axhJGA5WTb%ZZ+KJ>PG!0t7YV^^g?!qX^f<pO&kX52S);X4C-v<TicQLQ-m
z)zv*CbEK|0a)*)^{AWZ2Em(7WqBpa=xl1}9E>6e28eN#rIDkzyMEmMnElW6dKdsyC
z8g{d4okdLS=+BHay6t-tbnH8cdpZ|1aeht)urenjX9G|Is4sFs0ORALTj3Y15qpvT
zwaUPlB7{pup(<O<&6;!Iwu2u?M8Wg{^#onnD8j#`Z2e$yB1k%g9eHg!^J5n=ppdC#
z+^$6iC_T8$$A5Ff^5E=aT?s`+K3kz|e!m+a{sS-TAIqbqCsl=ET)qZ<>9#iAqR~L!
zx5LDftjFc*t7La+GWAH75wex=GT1oTt*1ViCdxRpS&gdPQT0LAbN0-~&V6;he1k*D
ztfKnEnYG0EOfS5+rrFdjrU9IIb+X>+akqbr+u~k0N!5C=@@*-064vO&t{{{CvdT}z
zt;}!=wU(q%Tb^6d7+?eUo!XJ4Q?=Cjm1yhfTx!}8mgPeMw!L&XAl{0iD>3h|Bqm`Z
zTRp^yclgA`Rpw)`9CflE6nsA0Q;KQ5W~3v;Cec>M@fKTiIc&bN;k&X$mgMgFg~64Z
zMyWm#R7;z}84;}$oo;k|x)S8pY#388e+pf~X*Bt;BU6&}5yWqwd1PgB2N=x8Y=5F7
zk6FK+xyrV+-m^u#24l!RBe~}f@C1zcI){u;cwI!+$4#VKrvr}35P}lv+6p%;cAvGL
z+y7!+?~O-w@W_5Y6C>OBp3)sK*l>LxFLxBO^B(;!e-}oFSAbpx=0eRTlp2kS%U_Re
zL<MS99V~UmwA19d-E~VFRes`Qo%(r<VSA4GQKyN>=0Ikz!IsCGU@9MT=|jwoOJMnt
z;8E8yxKCH~j7+#Bzb0sXlNqm+kif<l-(?RQYkp{0Lh~ZIVYD%MI`$3cJhLz}D{NlS
zfH_<X4<jo+y9`E#*1Hj84#Ar4<?{tSkc&I|uB{%#Zi}q+eYY|Xdfa&IR&rKS%Ew*<
zWAJk?C3(>0O?GBwb&jlhj3_+fJ*>anpO%rk_R)DS?H|-BGBFKq+sDezCvPkFM7Kf7
zDYx{&<zDA`je>LEH8Qy5JMr5MHnbiPkyw|X6$6#Ro`Oay8_2F2JfAjmi;q4Pd$z;T
zHZsvEdo%E?=lzs5vZCkqQXr%1dw|YaMADp%SxDs8r!64Wj5U=lMj0d_ry=%KFy|6y
zo@+5`Le5p3F<|y^=;(Hg&$#e+>E>tPD6G$rf@)#L)aw8hc{ODM{`)%B7dk52AA`_z
zM{rMmd|}&K;HvV23nq*l7+%>Oe9<HJ#^7d<@(FZ~dnWXdsC~^nD*9LJ-L@cM&VB3i
zVZn3G|C>(c|399-MAKN~W*EOH5MyorPL?f^NO5j}k1DL3`ALnUl8g!#aIlU}#m^v+
zW0{8Sr%~g#>vCwce-?*yMQuO{s{(6tmmWR?=Loa(iv#*0)-^8a#Y17Q4dcQrXb>v2
z!J*`-i2i-M0i~t1IFoT-+2<fg1hy%Ajc5JwIGe}Np+J6Ghe2e}G#9=IgDK$s`ViB=
zJ13IP=@9P`ua>0YT5TevE=a+jbv*t>OZOI?63pteI}7v4Vwh|BX>+N)DBST)*@4F6
z1vnv|ae<`$&0nz<1!?i)f43}l6t=td<pmf~+s;m9>luG7@a~%dHlgTO9P*kHVas*-
zVGzs;ielkFwN09Rc(sgCSC=V{(cnJGX9?QbE;CsTbJy>U;HxYb2~kh=Yl>K-JYU`H
zrKgAlpUVU>iw?=ZEnRt7slvLzZRL5iV8BKMG}j8&kkS0}zrtOI!h!d3bx?u7u^cx7
zWe5Ji{e<cP7jfdEqCEc&c^Av_pTorQzsSeV^Y82PAH_wm2)+<WQvCIRIHD*!D3cF&
SAgTqV$0>>lQ_c$ikM>`?U7F?q
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/AbstractBaSynthecDataSetRegistratorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/AbstractBaSynthecDataSetRegistratorTest.java
index 3a05bdbb6ca..4cf7b8ae70c 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/AbstractBaSynthecDataSetRegistratorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/AbstractBaSynthecDataSetRegistratorTest.java
@@ -82,6 +82,15 @@ public abstract class AbstractBaSynthecDataSetRegistratorTest extends
one(openBisService).createDataSetCode();
will(returnValue(excelDataSetCode));
+ // Some if there is a multistrain data set type, it needs to be taken care of in
+ // addition to the normal one
+ if (tsvDataSetType == TSV_MULTISTRAIN_EXPORT_DATA_SET_TYPE)
+ {
+ String tsvMultistrain = DATA_SET_CODE + "-TSV-MULTISTRAIN";
+ one(openBisService).createDataSetCode();
+ will(returnValue(tsvMultistrain));
+ }
+
String tsvDataSetCode = DATA_SET_CODE + "-TSV";
one(openBisService).createDataSetCode();
will(returnValue(tsvDataSetCode));
@@ -103,13 +112,13 @@ public abstract class AbstractBaSynthecDataSetRegistratorTest extends
{
one(dataSetValidator).assertValidDataSet(
TSV_MULTISTRAIN_EXPORT_DATA_SET_TYPE,
- new File(new File(stagingDirectory, tsvDataSetCode), "tsv-multi"));
- } else
- {
- one(dataSetValidator).assertValidDataSet(TSV_DATA_SET_TYPE,
- new File(new File(stagingDirectory, tsvDataSetCode), "tsv"));
+ new File(new File(stagingDirectory, DATA_SET_CODE
+ + "-TSV-MULTISTRAIN"), "tsv-multi"));
}
+ one(dataSetValidator).assertValidDataSet(TSV_DATA_SET_TYPE,
+ new File(new File(stagingDirectory, tsvDataSetCode), "tsv"));
+
one(openBisService).performEntityOperations(with(atomicatOperationDetails));
will(returnValue(new AtomicEntityOperationResult()));
}
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/TimeSeriesDataExcelTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/TimeSeriesDataExcelTest.java
index 0d566507204..d2be9831e7f 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/TimeSeriesDataExcelTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/TimeSeriesDataExcelTest.java
@@ -105,7 +105,8 @@ public class TimeSeriesDataExcelTest extends AssertJUnit
{ "MGP1", "OD600", "0.05", "0.064" },
{ "MGP100", "OD600", "0.05", "0.064" },
{ "MGP20", "OD600", "0.05", "0.064" },
- { "MGP999", "OD600", "0.05", "0.064" } };
+ { "MGP999", "OD600", "0.05", "0.064" },
+ { "MGP1", "OD600", "0.05", "0.064" } };
assertLinesAreEqual(dataLines, expectedData);
}
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java
index a8a036d19b6..8205496cd8a 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java
@@ -16,10 +16,13 @@
package eu.basynthec.cisd.dss.growthprofiles;
+import java.io.File;
import java.io.IOException;
+import java.util.Arrays;
import java.util.HashMap;
import java.util.Properties;
+import org.apache.commons.io.FileUtils;
import org.testng.annotations.Test;
import ch.systemsx.cisd.common.test.RecordingMatcher;
@@ -50,7 +53,7 @@ public class OD600DataSetRegistratorTest extends AbstractBaSynthecDataSetRegistr
handler.handle(markerFile);
- assertEquals(3, atomicOperationDetails.recordedObject().getDataSetRegistrations().size());
+ assertEquals(4, atomicOperationDetails.recordedObject().getDataSetRegistrations().size());
NewExternalData dataSet =
atomicOperationDetails.recordedObject().getDataSetRegistrations().get(0);
@@ -64,7 +67,20 @@ public class OD600DataSetRegistratorTest extends AbstractBaSynthecDataSetRegistr
assertNotNull(strainProperty);
assert null != strainProperty;
- assertEquals("MGP1,MGP100,MGP20,MGP999", strainProperty.getValue());
+
+ NewExternalData tsvSplitDataSet =
+ atomicOperationDetails.recordedObject().getDataSetRegistrations().get(3);
+ String location = tsvSplitDataSet.getLocation();
+ File tsvSplitFolder = new File(workingDirectory, "/1/" + location);
+ String[] contents = tsvSplitFolder.list();
+ Arrays.sort(contents);
+ String[] expectedContents =
+ { "OD600-Example.xlsx_MGP1.tsv", "OD600-Example.xlsx_MGP100.tsv",
+ "OD600-Example.xlsx_MGP20.tsv", "OD600-Example.xlsx_MGP999.tsv" };
+ assertEquals(Arrays.asList(expectedContents), Arrays.asList(contents));
+ File tsvSplitFile = new File(tsvSplitFolder, "OD600-Example.xlsx_MGP1.tsv");
+ checkTsvSplitContent(tsvSplitFile);
+
context.assertIsSatisfied();
}
@@ -73,4 +89,14 @@ public class OD600DataSetRegistratorTest extends AbstractBaSynthecDataSetRegistr
{
return "dist/etc/growth-profiles/";
}
+
+ private void checkTsvSplitContent(File tsvFile) throws IOException
+ {
+ String content = FileUtils.readFileToString(tsvFile);
+ assertEquals(
+ "RunNumber\tHumanReadable\t-19020.0\t-17220.0\t-15360.0\t-13620.0\t-11820.0\t-10020.0\t-8220.0\t-7020.0\t-4920.0\t-2820.0\t-1020.0\t-120.0\t720.0\t1500.0\t3660.0\t5460.0\t6060.0\t7200.0\t9000.0\n"
+ + "0\tOD600\t0.05\t0.064\t0.077\t0.089\t0.107\t0.127\t0.155\t0.176\t0.24\t0.33\t0.43\t0.49\t0.58\t0.66\t0.975\t1.42\t1.49\t2.09\t3.22\n"
+ + "1\tOD600\t0.05\t0.064\t0.077\t0.089\t0.107\t0.127\t0.155\t0.176\t0.24\t0.33\t0.43\t0.49\t0.58\t0.66\t0.975\t1.42\t1.49\t2.09\t3.22",
+ content);
+ }
}
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsDataSetRegistratorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsDataSetRegistratorTest.java
index d8da395faf3..1131553c802 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsDataSetRegistratorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsDataSetRegistratorTest.java
@@ -18,6 +18,7 @@ package eu.basynthec.cisd.dss.transcriptomics;
import java.io.File;
import java.io.IOException;
+import java.util.Arrays;
import java.util.HashMap;
import java.util.Properties;
@@ -52,7 +53,7 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
handler.handle(markerFile);
- assertEquals(3, atomicOperationDetails.recordedObject().getDataSetRegistrations().size());
+ assertEquals(4, atomicOperationDetails.recordedObject().getDataSetRegistrations().size());
NewExternalData dataSet =
atomicOperationDetails.recordedObject().getDataSetRegistrations().get(0);
@@ -75,6 +76,19 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
new File(new File(workingDirectory, "/1/" + location),
"Transcriptomics-Example.xlsx.tsv");
checkTsvContent(tsvFile);
+
+ NewExternalData tsvSplitDataSet =
+ atomicOperationDetails.recordedObject().getDataSetRegistrations().get(3);
+ location = tsvSplitDataSet.getLocation();
+ File tsvSplitFolder = new File(workingDirectory, "/1/" + location);
+ String[] contents = tsvSplitFolder.list();
+ Arrays.sort(contents);
+ String[] expectedContents =
+ { "Transcriptomics-Example.xlsx_MGP253.tsv",
+ "Transcriptomics-Example.xlsx_MGP776.tsv" };
+ assertEquals(Arrays.asList(expectedContents), Arrays.asList(contents));
+ File tsvSplitFile = new File(tsvSplitFolder, "Transcriptomics-Example.xlsx_MGP253.tsv");
+ checkSplitTsvContent(tsvSplitFile);
context.assertIsSatisfied();
}
@@ -102,4 +116,18 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
+ "BSU00260\t11.7669\t11.4658\n" + "BSU00270\t12.2675\t11.8745\n"
+ "BSU00280\t12.5574\t12.1608\n", content);
}
+
+ private void checkSplitTsvContent(File tsvFile) throws IOException
+ {
+ String content = FileUtils.readFileToString(tsvFile);
+ assertEquals("Locustag\t1 66687802\n" + "BSU00010\t13.7953\n" + "BSU00020\t13.5907\n"
+ + "BSU00030\t13.8489\n" + "BSU00040\t14.3564\n" + "BSU00050\t14.5239\n"
+ + "BSU00060\t14.3293\n" + "BSU00070\t14.481\n" + "BSU00090\t15.474\n"
+ + "BSU00100\t14.4332\n" + "BSU00110\t15.2669\n" + "BSU00120\t15.3344\n"
+ + "BSU_misc_RNA_1\t15.4497\n" + "BSU00130\t13.6604\n" + "BSU00180\t9.8208\n"
+ + "BSU_misc_RNA_2\t13.6614\n" + "BSU00190\t13.464\n" + "BSU00200\t14.6102\n"
+ + "BSU00210\t13.5285\n" + "BSU00220\t13.1007\n" + "BSU00230\t11.8547\n"
+ + "BSU00240\t10.8623\n" + "BSU00250\t11.6694\n" + "BSU00260\t11.7669\n"
+ + "BSU00270\t12.2675\n" + "BSU00280\t12.5574", content);
+ }
}
--
GitLab