fixing outstanding roundtrip issues object , documenting in notebook

ISA-tools · Feb 8, 2024 · a9a75ea · a9a75ea
1 parent 2bf8347
commit a9a75ea
Show file tree

Hide file tree

Showing 8 changed files with 2,096 additions and 284 deletions.
diff --git a/isa-cookbook/content/notebooks/isa-api-programmatic-BH2023-multiomics-isa.ipynb b/isa-cookbook/content/notebooks/isa-api-programmatic-BH2023-multiomics-isa.ipynb
diff --git a/isatools/isatab/dump/write.py b/isatools/isatab/dump/write.py
@@ -302,7 +302,6 @@ def flatten(current_list):
                             protocol_types_dict
                         )
                         if oname_label is not None:
-                            print("FROM TAB DUMPER: ",oname_label)
                             columns.append(oname_label)
                         elif node.executes_protocol.protocol_type.term.lower() \
                                 in protocol_types_dict["nucleic acid hybridization"][SYNONYMS]:
@@ -375,7 +374,7 @@ def pbar(x):
                             )
                             if oname_label is not None:
                                 df_dict[oname_label][-1] = node.name
-                                print("N from ISA-tab dump write", node.name)
+
                             elif node.executes_protocol.protocol_type.term.lower() in \
                                     protocol_types_dict["nucleic acid hybridization"][SYNONYMS]:
                                 df_dict["Hybridization Assay Name"][-1] = \

diff --git a/isatools/isatab/load/ProcessSequenceFactory.py b/isatools/isatab/load/ProcessSequenceFactory.py
@@ -280,13 +280,13 @@ def get_node_by_label_and_key(labl, this_key):
                     protocol_ref = str(object_series[object_label])
                     process_key = process_keygen(protocol_ref, column_group, _cg, DF.columns, object_series, _, DF)
 
-                    # TODO: Keep process key sequence here to reduce number of
-                    # passes on Protocol REF columns?
+                    # TODO: Keep process key sequence here to reduce number of passes on Protocol REF columns?
 
                     try:
                         process = processes[process_key]
                     except KeyError:
-                        process = Process(executes_protocol=protocol_ref)
+                        # TODO: Fix name formatting using protocol type or pattern
+                        process = Process(executes_protocol=protocol_ref, name="TOTO-{}-".format(_) + protocol_ref)
                         processes.update(dict([(process_key, process)]))
 
                     output_node_index = find_gt(node_cols, object_label_index)
@@ -336,7 +336,6 @@ def get_node_by_label_and_key(labl, this_key):
                     name_column_hits = [n for n in column_group if n in _LABELS_ASSAY_NODES]
                     if len(name_column_hits) == 1:
                         process.name = str(object_series[name_column_hits[0]])
-                        # print("process name at load:", process.name, name_column_hits[0])
                     for pv_column in [c for c in column_group if c.startswith('Parameter Value[')]:
                         category_key = next(iter(_RX_PARAMETER_VALUE.findall(pv_column)))
                         if category_key not in [x.category.parameter_name.term for x in process.parameter_values]:

diff --git a/isatools/model/process.py b/isatools/model/process.py
@@ -47,9 +47,9 @@ def __init__(self, id_='', name=None, executes_protocol=None, date_=None,
         Identifiable.__init__(self)
 
         self.id = id_
-        self.name = ""
+        self.name = ''
         if name:
-            self.name = name
+            self.__name = name
 
         if executes_protocol is None:
             self.__executes_protocol = Protocol()
@@ -308,7 +308,12 @@ def from_assay_dict(self, process, technology_type):
         self.executes_protocol = indexes.get_protocol(process['executesProtocol']['@id'])
         self.load_comments(process.get('comments', []))
         allowed_protocol_type_terms = [
-            "nucleic acid sequencing", "nucleic acid hybridization", "data transformation", "data normalization"
+            "nucleic acid sequencing",
+            "nmr spectroscopy",
+            "mass spectrometry",
+            "nucleic acid hybridization",
+            "data transformation",
+            "data normalization"
         ]
         if self.executes_protocol.protocol_type.term in allowed_protocol_type_terms or (
                 self.executes_protocol.protocol_type.term == 'data collection'

diff --git a/isatools/net/mw2isa/__init__.py b/isatools/net/mw2isa/__init__.py
@@ -494,7 +494,7 @@ def create_nmr_assay_records(lol, study_id, analysis_id, fv_records):
             "Parameter Value[binned increment]",
             "Parameter Value[binned data exclusion range ]",
             "NMR Assay Name",
-            "Free Induction Data File",
+            "Free Induction Decay Data File",
             "Protocol REF",
             "Parameter Value[software]",
             "Data Transformation Name",

diff --git a/isatools/resources/config/json/default/isotopomer_nmr.json b/isatools/resources/config/json/default/isotopomer_nmr.json
@@ -4,7 +4,7 @@
   "protocols": [
     {
       "inputs": "#sample",
-      "protocol": "extraction",
+      "protocol": "metabolite extraction",
       "outputs": "#material"
     },
     {
@@ -24,5 +24,5 @@
     "data transformation"
   ],
   "description": [
-    "(Sample)->(extraction)->(Material)->(NMR spectroscopy)->(FreeInductionDecayFiles)->(data transformation)->(DerivedSpectralDataFiles)" ]
+    "(Sample)->(extraction)->(Material)->(NMR spectroscopy)->(DataFiles)->(data transformation)->(DataFiles)" ]
 }
diff --git a/isatools/resources/config/json/default/metaboliteprofiling_nmr.json b/isatools/resources/config/json/default/metaboliteprofiling_nmr.json
@@ -4,7 +4,7 @@
   "protocols": [
     {
       "inputs": "#sample",
-      "protocol": "extraction",
+      "protocol": "metabolite extraction",
       "outputs": "#material"
     },
     {
@@ -24,5 +24,5 @@
     "data transformation"
   ],
   "description": [
-    "(Sample)->(extraction)->(Material)->(NMR spectroscopy)->(FreeInductionDecayFiles)->(data transformation)->(DerivedSpectralDataFiles)" ]
+    "(Sample)->(extraction)->(Material)->(NMR spectroscopy)->(Files)->(data transformation)->(DataFiles)" ]
 }
diff --git a/isatools/resources/config/yaml/assay-options.yml b/isatools/resources/config/yaml/assay-options.yml
@@ -32,7 +32,7 @@
         - Derived Spectral Data File
         - Metabolite Assignment File
 -
-    measurement type: isotopomer distribution analysis
+    measurement type: isotopomer analysis
     technology type: NMR spectroscopy
     protocol type: NMR spectroscopy
     parameter-like file: