Include XML tree structure for each ena data source, ena_*.xml

1 files changed, 123 insertions, 0 deletions

diff --git a/Code/parse_ena_xml.py b/Code/parse_ena_xml.py
index 8cb7946..eb1f610 100644
--- a/Code/parse_ena_xml.py
+++ b/Code/parse_ena_xml.py
@@ -37,6 +37,29 @@ MAX_DESCRIPTION_LENGTH = 6000 # max number to characters to keep in json file
 
 
 def parse_run(fname):
+    '''
+    Each record has the following format:
+    (Use Data/temp/xmltreeview.py to get the following output)
+
+        0: RUN_SET [-]
+            1: RUN [accession, alias, broker_name, center_name, run_center, run_date]
+                2: IDENTIFIERS [-]
+                    3: PRIMARY_ID [-]
+                    3: SUBMITTER_ID [namespace]
+                2: TITLE [-]
+                2: EXPERIMENT_REF [accession, refcenter, refname]
+                2: RUN_LINKS [-]
+                    3: RUN_LINK [-]
+                        4: XREF_LINK [-]
+                            5: DB [-]
+                            5: ID [-]
+                2: RUN_ATTRIBUTES [-]
+                    3: RUN_ATTRIBUTE [-]
+                        4: TAG [-]
+                        4: VALUE [-]
+
+    '''
+
     d = {}
     
     root = xml.etree.ElementTree.parse(fname).getroot()
@@ -71,6 +94,37 @@ def parse_run(fname):
 
 
 def parse_study(fname):
+    '''
+    Each record has the following format:
+    (Use Data/temp/xmltreeview.py to get the following output)
+
+        0: PROJECT_SET [-]
+            1: PROJECT [accession, alias, center_name, broker_name]
+                2: IDENTIFIERS [-]
+                    3: PRIMARY_ID [-]
+                    3: SUBMITTER_ID [namespace]
+                2: NAME [-]
+                2: TITLE [-]
+                2: DESCRIPTION [-]
+                2: SUBMISSION_PROJECT [-]
+                    3: SEQUENCING_PROJECT [-]
+                    3: ORGANISM [-]
+                        4: TAXON_ID [-]
+                        4: SCIENTIFIC_NAME [-]
+                2: RELATED_PROJECTS [-]
+                    3: RELATED_PROJECT [-]
+                        4: PARENT_PROJECT [accession]
+                2: PROJECT_LINKS [-]
+                    3: PROJECT_LINK [-]
+                        4: XREF_LINK [-]
+                            5: DB [-]
+                            5: ID [-]
+                2: PROJECT_ATTRIBUTES [-]
+                    3: PROJECT_ATTRIBUTE [-]
+                        4: TAG [-]
+                        4: VALUE [-]
+    '''
+
     d = {}
     root = xml.etree.ElementTree.parse(fname).getroot()
 
@@ -100,6 +154,32 @@ def parse_study(fname):
 
 
 def parse_sample(fname):
+    '''
+    Each record has the following format:
+    (Use Data/temp/xmltreeview.py to get the following output)
+
+        0: SAMPLE_SET [-]
+            1: SAMPLE [accession, alias, center_name, broker_name]
+                2: IDENTIFIERS [-]
+                    3: PRIMARY_ID [-]
+                    3: SECONDARY_ID [-]
+                    3: EXTERNAL_ID [namespace]
+                2: TITLE [-]
+                2: SAMPLE_NAME [-]
+                    3: TAXON_ID [-]
+                    3: SCIENTIFIC_NAME [-]
+                    3: COMMON_NAME [-]
+                2: SAMPLE_LINKS [-]
+                    3: SAMPLE_LINK [-]
+                        4: XREF_LINK [-]
+                            5: DB [-]
+                            5: ID [-]
+                2: SAMPLE_ATTRIBUTES [-]
+                    3: SAMPLE_ATTRIBUTE [-]
+                        4: TAG [-]
+                        4: VALUE [-]
+    '''
+
     d = {}
     root = xml.etree.ElementTree.parse(fname).getroot()
 
@@ -139,6 +219,49 @@ def parse_sample(fname):
 
 
 def parse_experiment(fname):
+    '''
+    Each record has the following format:
+    (Use Data/temp/xmltreeview.py to get the following output)
+
+        0: EXPERIMENT_SET [-]
+            1: EXPERIMENT [accession, alias, broker_name, center_name]
+                2: IDENTIFIERS [-]
+                    3: PRIMARY_ID [-]
+                    3: SUBMITTER_ID [namespace]
+                2: TITLE [-]
+                2: STUDY_REF [accession]
+                    3: IDENTIFIERS [-]
+                        4: PRIMARY_ID [-]
+                        4: SECONDARY_ID [-]
+                2: DESIGN [-]
+                    3: DESIGN_DESCRIPTION [-]
+                    3: SAMPLE_DESCRIPTOR [accession]
+                        4: IDENTIFIERS [-]
+                            5: PRIMARY_ID [-]
+                            5: EXTERNAL_ID [namespace]
+                    3: LIBRARY_DESCRIPTOR [-]
+                        4: LIBRARY_NAME [-]
+                        4: LIBRARY_STRATEGY [-]
+                        4: LIBRARY_SOURCE [-]
+                        4: LIBRARY_SELECTION [-]
+                        4: LIBRARY_LAYOUT [-]
+                            5: PAIRED [-]
+                        4: LIBRARY_CONSTRUCTION_PROTOCOL [-]
+                2: PLATFORM [-]
+                    3: ILLUMINA [-]
+                        4: INSTRUMENT_MODEL [-]
+                2: PROCESSING [-]
+                2: EXPERIMENT_LINKS [-]
+                    3: EXPERIMENT_LINK [-]
+                        4: XREF_LINK [-]
+                            5: DB [-]
+                            5: ID [-]
+                2: EXPERIMENT_ATTRIBUTES [-]
+                    3: EXPERIMENT_ATTRIBUTE [-]
+                        4: TAG [-]
+                        4: VALUE [-]
+    '''
+
     d = {}
     
     root = xml.etree.ElementTree.parse(fname).getroot()