feat!: Support semicolon-separated lists in Factor Value fields

altamisa/isatab/models.py

@@ -315,7 +315,7 @@ class FactorValue:
     #: Factor name
     name: str
     #: Factor value
-    value: FreeTextOrTermRef
+    value: List[FreeTextOrTermRef]
     #: Factor value unit
     unit: FreeTextOrTermRef
 

altamisa/isatab/parse_assay_study.py

@@ -322,7 +322,8 @@ def build(self, line: List[str]) -> models.Material:
             models.Comment(hdr.label, line[hdr.col_no]) for hdr in self.comment_headers
         )
         factor_values = tuple(
-            self._build_complex(hdr, line, models.FactorValue) for hdr in self.factor_value_headers
+            self._build_complex(hdr, line, models.FactorValue, allow_list=True)
+            for hdr in self.factor_value_headers
         )
         material_type = self._build_freetext_or_term_ref(self.material_type_header, line)
         # Then, constructing ``Material`` is easy

altamisa/isatab/validate_assay_study.py

@@ -97,7 +97,7 @@ def has_content(value):
             [any(has_content(v) for v in char.value) for char in material.characteristics]
         )
         any_comm = any([comm.value for comm in material.comments])
-        any_fact = any([fact.value for fact in material.factor_values])
+        any_fact = any([any(has_content(v) for v in fact.value) for fact in material.factor_values])
         if not material.name and any(
             (
                 any_char,

docs/index.rst

@@ -53,7 +53,7 @@ Special Extensions
 In addition to the original ISA-Tab format specifications, AltamISA supports
  the following special modifications to improve specific use cases:
 
-- **List of values** in ``Characterics`` or ``Parameter Value`` fields by using
+- **List of values** in ``Characterics``, ``Parameter Value``, or ``Factor Value`` fields by using
   semicolon-separators (";"). Note, for ontology terms the same number of
   splits is expected in the associated field ``Term Source REF`` and
   ``Term Accession Number``.

tests/data/i_small/s_small.txt

@@ -1,6 +1,6 @@
-Source Name	Characteristics[organism]	Term Source REF	Term Accession Number	Characteristics[age]	Unit	Term Source REF	Term Accession Number	Protocol REF	Parameter Value[instrument]	Performer	Date	Sample Name	Characteristics[status]	Factor Value[treatment]
-0814	Mus musculus;Homo sapiens	NCBITAXON;NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090;http://purl.bioontology.org/ontology/NCBITAXON/9606	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0814-N1	0	yes
-0815	Mus musculus	NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0815-N1	0	yes
-0815	Mus musculus	NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel type A;scalpel type B	John Doe	2018-02-02	0815-T1	2	
-0816	Mus musculus				day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0816-T1	1	yes
-0817				150	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02			
+Source Name	Characteristics[organism]	Term Source REF	Term Accession Number	Characteristics[age]	Unit	Term Source REF	Term Accession Number	Protocol REF	Parameter Value[instrument]	Performer	Date	Sample Name	Characteristics[status]	Factor Value[treatment]	Term Source REF	Term Accession Number
+0814	Mus musculus;Homo sapiens	NCBITAXON;NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090;http://purl.bioontology.org/ontology/NCBITAXON/9606	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0814-N1	0	vaccine;yes	OBI;	http://purl.obolibrary.org/obo/VO_0000001;
+0815	Mus musculus	NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0815-N1	0	yes		
+0815	Mus musculus	NCBITAXON	http://purl.bioontology.org/ontology/NCBITAXON/10090	90	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel type A;scalpel type B	John Doe	2018-02-02	0815-T1	2			
+0816	Mus musculus				day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02	0816-T1	1	yes		
+0817				150	day	UO	http://purl.obolibrary.org/obo/UO_0000033	sample collection	scalpel	John Doe	2018-02-02					

tests/test_parse_study.py

@@ -144,7 +144,7 @@ def test_study_row_reader_small_study(small_investigation_file, small_study_file
 
     # Create new row reader and check read headers (+ string representation)
     row_reader = StudyRowReader.from_stream("S1", small_study_file)
-    assert 13 == len(row_reader.header)
+    assert 14 == len(row_reader.header)
     rep0 = "ColumnHeader(column_type='Source Name', col_no=0, span=1)"
     rep1 = "LabeledColumnHeader(column_type='Characteristics', col_no=1, span=1, label='organism')"
     assert rep0 == repr(row_reader.header[0])
@@ -181,6 +181,8 @@ def test_study_row_reader_small_study(small_investigation_file, small_study_file
         table_headers.SAMPLE_NAME,
         table_headers.CHARACTERISTICS + "[status]",
         table_headers.FACTOR_VALUE + "[treatment]",
+        table_headers.TERM_SOURCE_REF,
+        table_headers.TERM_ACCESSION_NUMBER,
     ]
 
     unit = models.OntologyTermRef(
@@ -262,14 +264,30 @@ def test_study_row_reader_small_study(small_investigation_file, small_study_file
         headers_collection,
     )
     assert expected == second_row[1]
+
+    factor_treatment2 = (
+        models.FactorValue(
+            name="treatment",
+            value=[models.OntologyTermRef("yes", None, None)],
+            unit=None,
+        ),
+    )
+    factor_treatment3 = (
+        models.FactorValue(
+            name="treatment",
+            value=[models.OntologyTermRef(None, None, None)],
+            unit=None,
+        ),
+    )
+
     expected = models.Material(
         "Sample Name",
         "S1-sample-0815-N1",
         "0815-N1",
         None,
         (models.Characteristics("status", ["0"], None),),
         (),
-        (models.FactorValue("treatment", "yes", None),),
+        factor_treatment2,
         None,
         headers_sample,
     )
@@ -310,7 +328,7 @@ def test_study_row_reader_small_study(small_investigation_file, small_study_file
         None,
         (models.Characteristics("status", ["2"], None),),
         (),
-        (models.FactorValue("treatment", "", None),),
+        factor_treatment3,
         None,
         headers_sample,
     )
@@ -329,15 +347,15 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
 
     # Create new row reader and check read headers
     reader = StudyReader.from_stream("S1", small_study_file)
-    assert 13 == len(reader.header)
+    assert 14 == len(reader.header)
 
     # Read study
     study = reader.read()
     StudyValidator(investigation, investigation.studies[0], study).validate()
 
     # Check results
     assert os.path.normpath(str(study.file)).endswith(os.path.normpath("data/i_small/s_small.txt"))
-    assert 13 == len(study.header)
+    assert 14 == len(study.header)
     assert 9 == len(study.materials)
     assert 5 == len(study.processes)
     assert 10 == len(study.arcs)
@@ -362,6 +380,8 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         table_headers.SAMPLE_NAME,
         table_headers.CHARACTERISTICS + "[status]",
         table_headers.FACTOR_VALUE + "[treatment]",
+        table_headers.TERM_SOURCE_REF,
+        table_headers.TERM_ACCESSION_NUMBER,
     ]
 
     unit = models.OntologyTermRef(
@@ -394,6 +414,34 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         ),
         models.Characteristics(name="age", value=["150"], unit=unit),
     )
+    factor_treatment1 = (
+        models.FactorValue(
+            name="treatment",
+            value=[
+                models.OntologyTermRef(
+                    name="vaccine",
+                    accession="http://purl.obolibrary.org/obo/VO_0000001",
+                    ontology_name="OBI",
+                ),
+                models.OntologyTermRef("yes", None, None),
+            ],
+            unit=None,
+        ),
+    )
+    factor_treatment2 = (
+        models.FactorValue(
+            name="treatment",
+            value=[models.OntologyTermRef("yes", None, None)],
+            unit=None,
+        ),
+    )
+    factor_treatment3 = (
+        models.FactorValue(
+            name="treatment",
+            value=[models.OntologyTermRef(None, None, None)],
+            unit=None,
+        ),
+    )
 
     expected = models.Material(
         "Source Name",
@@ -431,14 +479,26 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         headers_source,
     )
     assert expected == study.materials["S1-source-0817"]
+    expected = models.Material(
+        "Sample Name",
+        "S1-sample-0814-N1",
+        "0814-N1",
+        None,
+        (models.Characteristics("status", ["0"], None),),
+        (),
+        factor_treatment1,
+        None,
+        headers_sample,
+    )
+    assert expected == study.materials["S1-sample-0814-N1"]
     expected = models.Material(
         "Sample Name",
         "S1-sample-0815-N1",
         "0815-N1",
         None,
         (models.Characteristics("status", ["0"], None),),
         (),
-        (models.FactorValue("treatment", "yes", None),),
+        factor_treatment2,
         None,
         headers_sample,
     )
@@ -450,7 +510,7 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         None,
         (models.Characteristics("status", ["2"], None),),
         (),
-        (models.FactorValue("treatment", "", None),),
+        factor_treatment3,
         None,
         headers_sample,
     )
@@ -462,7 +522,7 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         None,
         (models.Characteristics("status", ["1"], None),),
         (),
-        (models.FactorValue("treatment", "yes", None),),
+        factor_treatment2,
         None,
         headers_sample,
     )
@@ -474,7 +534,7 @@ def test_study_reader_small_study(small_investigation_file, small_study_file):
         None,
         (models.Characteristics("status", [""], None),),
         (),
-        (models.FactorValue("treatment", "", None),),
+        factor_treatment3,
         None,
         headers_sample,
     )