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 1694491cf26b05d93e8c75e158bc4bfc67bc40f6..8bdccd87bb344e829f56e0d37dac4976ee437c7f 100644
--- a/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
+++ b/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
@@ -20,6 +20,13 @@ def extract_strains():
line = lines[i]
strains.append(line[0].upper())
return ",".join(strains)
+
+def strain_canonical(strainId):
+ """Return the canonical form of the strainId"""
+ if strainId.lower().startswith('jjs-din'):
+ return "JJS-DIn" + strainId[7:]
+ else:
+ return strainId.upper()
def assign_properties(dataset, metadata):
"""Assign properties to the data set from information in the data."""
@@ -38,7 +45,7 @@ def assign_properties(dataset, metadata):
value = metadata.get(prop)
if (key == "STRAIN"):
value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
+ dataset.setPropertyValue(key, strain_canonical(value))
def convert_data_to_tsv(tr, dataset, location):
"""Create a tsv file containing the data and add it to the data set."""
diff --git a/eu_basynthec/dist/etc/proteomics/data-set-handler.py b/eu_basynthec/dist/etc/proteomics/data-set-handler.py
index 81da79a7eda66c1182a2b31d2be4b13436f2918a..6473491df43604c6732f3f7e9883d58d059e596f 100644
--- a/eu_basynthec/dist/etc/proteomics/data-set-handler.py
+++ b/eu_basynthec/dist/etc/proteomics/data-set-handler.py
@@ -12,6 +12,13 @@ def retrieve_experiment(tr, exp_id):
exp = tr.getExperiment(exp_id)
return exp
+def strain_canonical(strainId):
+ """Return the canonical form of the strainId"""
+ if strainId.lower().startswith('jjs-din'):
+ return "JJS-DIn" + strainId[7:]
+ else:
+ return strainId.upper()
+
def assign_properties(dataset, metadata):
"""Assign properties to the data set from information in the data."""
propertyNameMap = {
@@ -28,8 +35,8 @@ def assign_properties(dataset, metadata):
value = metadata.get(prop)
if (key == "STRAIN"):
value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
-
+ dataset.setPropertyValue(key, strain_canonical(value))
+
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)
diff --git a/eu_basynthec/dist/etc/shared/shared-classes.py b/eu_basynthec/dist/etc/shared/shared-classes.py
index 85911070ab2460befe13e521846122e1b7abd846..b502be6edf4f4d435c2d704959722e8f39abcf33 100644
--- a/eu_basynthec/dist/etc/shared/shared-classes.py
+++ b/eu_basynthec/dist/etc/shared/shared-classes.py
@@ -139,14 +139,30 @@ class ValidationHelper:
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("^JJS-MGP[0-9]{1,3}|^JJS-DIN[0-9]{1,3}|^MS|CHASSIS\s*[1-3]|WT 168 TRP\+")
-def isStrainIdValid(strainId):
- """Return true if the strain id passes validation (has the form sepecified in the regex)"""
- strainId = strainId.strip().upper()
- match = strainIdRegex.match(strainId)
+#
+# Strain validation stuff
+#
+strainIdRegex = re.compile("^ms|chassis\s*[1-3]|wt 168 trp\+")
+strainIdRegexFull = re.compile("^jjs-mgp[0-9]{1,3}|^jjs-din[0-9]{1,3}|^ms|chassis\s*[1-3]|wt 168 trp\+")
+strainIds = {}
+home_dir = os.environ.get('HOME', '')
+if os.path.exists(home_dir + '/var/strainids.txt'):
+ for sid in open(home_dir + '/var/strainids.txt').readlines():
+ strainIds[sid.strip().lower()] = 1
+
+def _match(regex, strainId):
+ match = regex.match(strainId)
if match is None:
return False
- return match.end() == len(strainId)
+ return len(match.group(0)) == len(strainId)
+
+def isStrainIdValid(strainId):
+ """Return true if the strain id passes validation (has the form specified in the regex and is in Chris' strain db)"""
+ strainIdLower = strainId.lower()
+ if len(strainIds) > 0:
+ return strainIds.has_key(strainIdLower) or _match(strainIdRegex, strainIdLower)
+ else:
+ return _match(strainIdRegexFull, strainIdLower)
def strainValidationErrorMessageFragment(strain):
"""Return a sentence fragment describing the strain validation error."""
diff --git a/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py b/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
index df05c0e01b490a91de6ddc5e4ebd0b59e2a19a22..1b7eb9a5f794eb5370cabcdcbb7f323742f2a807 100644
--- a/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
+++ b/eu_basynthec/dist/etc/transcriptomics/data-set-handler.py
@@ -37,6 +37,13 @@ def retrieve_experiment(tr, exp_id):
exp = tr.getExperiment(exp_id)
return exp
+def strain_canonical(strainId):
+ """Return the canonical form of the strainId"""
+ if strainId.lower().startswith('jjs-din'):
+ return "JJS-DIn" + strainId[7:]
+ else:
+ return strainId.upper()
+
def assign_properties(dataset, metadata):
"""Assign properties to the data set from information in the data."""
propertyNameMap = {
@@ -54,7 +61,7 @@ def assign_properties(dataset, metadata):
value = metadata.get(prop)
if (key == "STRAIN"):
value = value + " (STRAIN)"
- dataset.setPropertyValue(key, value.upper())
+ dataset.setPropertyValue(key, strain_canonical(value))
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."""
diff --git a/eu_basynthec/sourceTest/examples/Transcriptomics-Example.xlsx b/eu_basynthec/sourceTest/examples/Transcriptomics-Example.xlsx
index 583ce54ebc47b44dbd9e0974cb26be60018d7ab8..8c93558fdd8c202048cbcdc515dd60efce7db3b1 100644
Binary files a/eu_basynthec/sourceTest/examples/Transcriptomics-Example.xlsx and b/eu_basynthec/sourceTest/examples/Transcriptomics-Example.xlsx differ
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 11ea320a123db6cc6bddb150b0fb5d3770d646bd..e1019cba5e5fe14b404a7fdfdecffa95b3ea2c8c 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
@@ -74,7 +74,7 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
assertNotNull(strainProperty);
assert null != strainProperty;
- assertEquals("MGP253,MGP776", strainProperty.getValue());
+ assertEquals("JJS-MGP253,JJS-MGP776", strainProperty.getValue());
NewExternalData tsvDataSet =
atomicOperationDetails.recordedObject().getDataSetRegistrations().get(2);
@@ -91,10 +91,10 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
String[] contents = tsvSplitFolder.list();
Arrays.sort(contents);
String[] expectedContents =
- { "Transcriptomics-Example.xlsx_MGP253.tsv",
- "Transcriptomics-Example.xlsx_MGP776.tsv" };
+ { "Transcriptomics-Example.xlsx_JJS-MGP253.tsv",
+ "Transcriptomics-Example.xlsx_JJS-MGP776.tsv" };
assertEquals(Arrays.asList(expectedContents), Arrays.asList(contents));
- File tsvSplitFile = new File(tsvSplitFolder, "Transcriptomics-Example.xlsx_MGP253.tsv");
+ File tsvSplitFile = new File(tsvSplitFolder, "Transcriptomics-Example.xlsx_JJS-MGP253.tsv");
checkSplitTsvContent(tsvSplitFile);
context.assertIsSatisfied();
}
@@ -108,7 +108,7 @@ public class TranscriptomicsDataSetRegistratorTest extends AbstractBaSynthecData
private void checkTsvContent(File tsvFile) throws IOException
{
String content = FileUtils.readFileToString(tsvFile);
- assertEquals("Locustag\tMGP253-1 66687802\tMGP776-2 66730002\n"
+ assertEquals("Locustag\tJJS-MGP253-1 66687802\tJJS-MGP776-2 66730002\n"
+ "BSU00010\t13.7953\t13.5517\n" + "BSU00020\t13.5907\t13.3277\n"
+ "BSU00030\t13.8489\t13.6306\n" + "BSU00040\t14.3564\t14.1073\n"
+ "BSU00050\t14.5239\t14.1992\n" + "BSU00060\t14.3293\t13.933\n"