Patch for support additional Data File types

isatools/model/datafile.py

@@ -202,6 +202,42 @@ def __ne__(self, other):
         return not self == other
 
 
+class ImageFile(DataFile):
+    """Represents an Image file in an experimental graph."""
+
+    def __init__(self, filename="", id_="", generated_from=None, comments=None):
+        super().__init__(filename=filename, id_=id_, generated_from=generated_from, comments=comments)
+
+        self.label = "Image File"
+
+    def __repr__(self):
+        return (
+            "isatools.model.ImageFile(filename='{0.filename}', "
+            "generated_from={0.generated_from}, comments={0.comments})".format(self)
+        )
+
+    def __str__(self):
+        return """ImageFile(
+    filename={data_file.filename}
+    generated_from={num_generated_from} Sample objects
+    comments={num_comments} Comment objects
+)""".format(data_file=self, num_generated_from=len(self.generated_from), num_comments=len(self.comments))
+
+    def __hash__(self):
+        return hash(repr(self))
+
+    def __eq__(self, other):
+        return (
+            isinstance(other, ImageFile)
+            and self.filename == other.filename
+            and self.generated_from == other.generated_from
+            and self.comments == other.comments
+        )
+
+    def __ne__(self, other):
+        return not self == other
+
+
 class RawSpectralDataFile(DataFile):
     """Represents a raw spectral data file in an experimental graph."""
 
@@ -428,6 +464,44 @@ def __ne__(self, other):
         return not self == other
 
 
+class MetaboliteAssignmentFile(DataFile):
+    """Represents a metabolite assignment file in an experimental graph."""
+
+    def __init__(self, filename="", id_="", generated_from=None, comments=None):
+        super().__init__(filename=filename, id_=id_, generated_from=generated_from, comments=comments)
+
+        self.label = "Metabolite Assignment File"
+
+    def __repr__(self):
+        return (
+            "isatools.model.MetaboliteAssignmentFile("
+            "filename='{data_file.filename}', "
+            "generated_from={data_file.generated_from}, "
+            "comments={data_file.comments})".format(data_file=self)
+        )
+
+    def __str__(self):
+        return """MetaboliteAssignmentFile(
+    filename={data_file.filename}
+    generated_from={num_generated_from} Sample objects
+    comments={num_comments} Comment objects
+)""".format(data_file=self, num_generated_from=len(self.generated_from), num_comments=len(self.comments))
+
+    def __hash__(self):
+        return hash(repr(self))
+
+    def __eq__(self, other):
+        return (
+            isinstance(other, MetaboliteAssignmentFile)
+            and self.filename == other.filename
+            and self.generated_from == other.generated_from
+            and self.comments == other.comments
+        )
+
+    def __ne__(self, other):
+        return not self == other
+
+
 class DerivedArrayDataMatrixFile(DataFile):
     """Represents a derived array data matrix file in an experimental graph."""
 

isatools/resources/config/xml/histology.xml

@@ -1 +1,50 @@
-<isatab-config-file xmlns="http://www.ebi.ac.uk/bii/isatab_configuration#"><isatab-configuration table-name="histology" isatab-assay-type="generic_assay" isatab-conversion-target="generic"><measurement term-label="histology" term-accession="http://purl.obolibrary.org/obo/OBI_0600020" source-abbreviation="OBI"/><technology term-label="" term-accession="" source-abbreviation=""/><field header="Sample Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="true" is-hidden="false" is-forced-ontology="false"><description><![CDATA[Samples represent major outputs resulting from a protocol application other than the special case outputs of Extract or a Labeled Extract.]]></description><default-value><![CDATA[]]></default-value></field><protocol-field protocol-type ="histology"/><field header="Assay Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="true" is-hidden="false" is-forced-ontology="false"><description><![CDATA[User-defined name for an assay.]]></description><default-value><![CDATA[]]></default-value><generated-value-template>[INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT].Extract-[EXTRACT_COUNT].LE-[LABEL_COUNT].ASSAY-[HYB_COUNT]</generated-value-template></field><field header="Raw Data File" data-type="String" is-file-field="true" is-multiple-value="false" is-required="false" is-hidden="false" is-forced-ontology="false"><description><![CDATA[Name (or URI) of the data file generated by an assay]]></description><default-value><![CDATA[]]></default-value></field><field header="Image File" data-type="String" is-file-field="true" is-multiple-value="false" is-required="false" is-hidden="false" is-forced-ontology="false"><description><![CDATA[Name (or URI) of the image files generated by an assay.]]></description><default-value><![CDATA[]]></default-value><generated-value-template>[INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT]</generated-value-template></field><field header="Normalization Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="false" is-hidden="false" is-forced-ontology="false"><description><![CDATA[User-defined name for each normalization applied]]></description><default-value><![CDATA[]]></default-value></field><field header="Data Transformation Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="false" is-hidden="false" is-forced-ontology="false"><description><![CDATA[User-defined name for each data transformation applied]]></description><default-value><![CDATA[]]></default-value></field><field header="Derived Data File" data-type="String" is-file-field="true" is-multiple-value="false" is-required="false" is-hidden="false" is-forced-ontology="false"><description><![CDATA[Name (or URI) of the data file generated by an assay.]]></description><default-value><![CDATA[]]></default-value></field><structured-field name="factors"/></isatab-configuration></isatab-config-file>
+<isatab-config-file xmlns="http://www.ebi.ac.uk/bii/isatab_configuration#">
+    <isatab-configuration table-name="histology" isatab-assay-type="generic_assay" isatab-conversion-target="generic">
+        <measurement term-label="histology" term-accession="http://purl.obolibrary.org/obo/OBI_0600020"
+                     source-abbreviation="OBI"/>
+        <technology term-label="" term-accession="" source-abbreviation=""/>
+        <field header="Sample Name" data-type="String" is-file-field="false" is-multiple-value="false"
+               is-required="true" is-hidden="false" is-forced-ontology="false">
+            <description>
+                <![CDATA[Samples represent major outputs resulting from a protocol application other than the special case outputs of Extract or a Labeled Extract.]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <protocol-field protocol-type="histology"/>
+        <field header="Assay Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="true"
+               is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+            <generated-value-template>
+                [INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT].Extract-[EXTRACT_COUNT].LE-[LABEL_COUNT].ASSAY-[HYB_COUNT]
+            </generated-value-template>
+        </field>
+        <field header="Raw Data File" data-type="String" is-file-field="true" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[Name (or URI) of the data file generated by an assay]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Image File" data-type="String" is-file-field="true" is-multiple-value="false" is-required="false"
+               is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[Name (or URI) of the image files generated by an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+            <generated-value-template>[INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT]
+            </generated-value-template>
+        </field>
+        <field header="Normalization Name" data-type="String" is-file-field="false" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for each normalization applied]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Data Transformation Name" data-type="String" is-file-field="false" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for each data transformation applied]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Derived Data File" data-type="String" is-file-field="true" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[Name (or URI) of the data file generated by an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <structured-field name="factors"/>
+    </isatab-configuration>
+</isatab-config-file>

isatools/resources/config/xml/phenotyping_imaging.xml

@@ -0,0 +1,46 @@
+<isatab-config-file xmlns="http://www.ebi.ac.uk/bii/isatab_configuration#">
+    <isatab-configuration table-name="phenotyping_imaging" isatab-assay-type="generic_assay"
+                          isatab-conversion-target="generic">
+        <measurement term-label="phenotyping analysis"
+                     term-accession="" source-abbreviation=""/>
+        <technology term-label="imaging" term-accession="" source-abbreviation=""/>
+        <field header="Sample Name" data-type="String" is-file-field="false" is-multiple-value="true" is-required="true"
+               is-hidden="false" is-forced-ontology="false">
+            <description>
+                <![CDATA[Samples represent major outputs resulting from a protocol application other than the special case outputs of Extract or a Labeled Extract.]]></description>
+            <default-value><![CDATA[]]></default-value>
+            <generated-value-template>[INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT]
+            </generated-value-template>
+        </field>
+        <protocol-field protocol-type="imaging"/>
+        <field header="Assay Name" data-type="String" is-file-field="false" is-multiple-value="false" is-required="true"
+               is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+            <generated-value-template>
+                [INSTITUTION].Group-[GROUP_NO].Subject-[SUBJECT_NO].[SAMPLE_EXTRACT].Extract-[EXTRACT_COUNT].LE-[LABEL_COUNT].ASSAY-[HYB_COUNT]
+            </generated-value-template>
+        </field>
+        <field header="Image File" data-type="String" is-file-field="true" is-multiple-value="false"
+               is-required="true" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[Name (or URI) of the data file generated by an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Normalization Name" data-type="String" is-file-field="false" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for each normalization applied]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Data Transformation Name" data-type="String" is-file-field="false" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[User-defined name for each data transformation applied.]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <field header="Derived Data File" data-type="String" is-file-field="true" is-multiple-value="false"
+               is-required="false" is-hidden="false" is-forced-ontology="false">
+            <description><![CDATA[Name (or URI) of the data file generated by an assay.]]></description>
+            <default-value><![CDATA[]]></default-value>
+        </field>
+        <structured-field name="factors"/>
+    </isatab-configuration>
+</isatab-config-file>

tests/isajson/test_isajson.py

@@ -460,6 +460,18 @@ def test_json_load_and_dump_bii_s_test(self):
         assays = [a for a in studies["assays"] if a["filename"] == "a_assay.txt"][0]
         self.assertEqual(assays["materials"]["otherMaterials"][1]["type"], "Extract Name")
 
+
+    def test_json_load_and_dump_imagefile_test(self):
+        # Load into ISA objects
+        with open(os.path.join(utils.JSON_DATA_DIR, "ISA-Image", "isa-image.json")) as isajson_fp:
+            investigation = isajson.load(isajson_fp)
+
+        # Dump into ISA JSON from ISA objects
+        investigation_reload = json.loads(json.dumps(investigation, cls=isajson.ISAJSONEncoder))
+        studies = [s for s in investigation_reload["studies"] if s["filename"] == "s_study.txt"][0]
+        assays = [a for a in studies["assays"] if a["filename"] == "a_assay.txt"][0]
+        self.assertEqual(assays["dataFiles"][1]["type"], "Image File")
+
     def test_json_load_and_dump_isa_labeled_extract(self):
         # Load into ISA objects
         with open(os.path.join(utils.JSON_DATA_DIR, "TEST-ISA-LabeledExtract1", "isa-test-le1.json")) as isajson_fp:

tests/isatab/validate/test_core.py

@@ -43,6 +43,14 @@ def test_bii_s_7(self):
             report = validate(fp=data_file, config_dir=self.default_conf)
         self.assertEqual(len(report["warnings"]), 1)
 
+    def test_imaging(self):
+        data_path = path.join(path.dirname(path.abspath(__file__)), "..", "..", "data", "tab", "Imaging")
+        with open(path.join(data_path, "i_Investigation.txt"), "r") as data_file:
+            report = validate(fp=data_file, config_dir=self.default_conf)
+            print(report["errors"])
+        self.assertEqual(len(report["errors"]), 0)
+
+
     def test_print_rule(self):
         raw_rule = INVESTIGATION_RULES_MAPPING[0]
         rule = Rule(**raw_rule)

tests/model/test_datafile.py

@@ -81,6 +81,7 @@ class TestSubDataFile(TestCase):
     def setUp(self):
         self.types = {
             "RawDataFile": RawDataFile,
+            "ImageFile": ImageFile,
             "DerivedDataFile": DerivedDataFile,
             "RawSpectralDataFile": RawSpectralDataFile,
             "DerivedArrayDataFile": DerivedArrayDataFile,
@@ -92,6 +93,7 @@ def setUp(self):
             "PostTranslationalModificationAssignmentFile": PostTranslationalModificationAssignmentFile,
             "AcquisitionParameterDataFile": AcquisitionParameterDataFile,
             "FreeInductionDecayDataFile": FreeInductionDecayDataFile,
+            "MetaboliteAssignmentFile": MetaboliteAssignmentFile
         }
         self.classes = {}
         for filetype in self.types:

tests/utils/test_isatab_configurator.py

@@ -50,7 +50,7 @@ def test_load_config_metagenome_seq(self):
         from isatools.io import isatab_configurator as configurator
 
         config_dict = configurator.load(self._config_dir)
-        self.assertEqual(len(config_dict), 30)
+        self.assertEqual(len(config_dict), 31)
         self.assertEqual(
             config_dict[("metagenome sequencing", "nucleotide sequencing")].isatab_configuration[0].table_name,
             "metagenome_seq",