IGVF-1074-matrix-content-summary (#561)

Author: ian-whaling

src/igvfd/mappings/matrix_file.json

@@ -1,6 +1,6 @@
 {
-    "hash": "b767a0bcf0eef30b08783183aec26a58",
-    "index_name": "matrix_file_b767a0bc",
+    "hash": "a79f62652a66ba16923ef19aab86eb29",
+    "index_name": "matrix_file_a79f6265",
     "item_type": "matrix_file",
     "mapping": {
         "dynamic_templates": [

src/igvfd/tests/fixtures/schemas/matrix_file.py

@@ -6,11 +6,11 @@ def matrix_file(testapp, lab, award, analysis_set_with_sample, reference_file):
     item = {
         'award': award['@id'],
         'lab': lab['@id'],
-        'md5sum': 'b64eed10-78b9-4674-95e5-dae39f35f132',
+        'md5sum': '01b08bb5485ac730df19af55ba4bb01c',
         'file_format': 'hdf5',
         'file_set': analysis_set_with_sample['@id'],
         'file_size': 8491803,
-        'content_type': 'parse gene count matrix',
+        'content_type': 'sparse gene count matrix',
         'reference_files': [
             reference_file['@id']
         ],

src/igvfd/tests/test_types_file.py

@@ -73,8 +73,7 @@ def test_types_file_s3_uri_non_submittable(testapp, analysis_set_with_sample, aw
 def test_types_aligment_file_content_summary(testapp, alignment_file):
     res = testapp.get(alignment_file['@id'])
     assert res.json.get('content_summary') == 'unfiltered alignments'
-
-    res = testapp.patch_json(
+    testapp.patch_json(
         alignment_file['@id'],
         {
             'redacted': True,
@@ -88,8 +87,7 @@ def test_types_aligment_file_content_summary(testapp, alignment_file):
 def test_types_signal_file_content_summary(testapp, signal_file):
     res = testapp.get(signal_file['@id'])
     assert res.json.get('content_summary') == 'plus strand signal of all reads'
-
-    res = testapp.patch_json(
+    testapp.patch_json(
         signal_file['@id'],
         {
             'filtered': True,
@@ -99,3 +97,18 @@ def test_types_signal_file_content_summary(testapp, signal_file):
     )
     res = testapp.get(signal_file['@id'])
     assert res.json.get('content_summary') == 'filtered normalized unstranded signal of all reads'
+
+
+def test_types_matrix_file_content_summary(testapp, matrix_file):
+    res = testapp.get(matrix_file['@id'])
+    assert res.json.get('content_summary') == 'cell by gene sparse gene count matrix'
+    testapp.patch_json(
+        matrix_file['@id'],
+        {
+            'dimension1': 'variant',
+            'dimension2': 'treatment',
+            'content_type': 'transcriptome annotations'
+        }
+    )
+    res = testapp.get(matrix_file['@id'])
+    assert res.json.get('content_summary') == 'variant by treatment transcriptome annotations'

src/igvfd/types/file.py

@@ -62,6 +62,7 @@
     'hdf5': '.h5',
     'idat': '.idat',
     'PWM': '.pwm',
+    'mtx': '.mtx',
     'rcc': '.rcc',
     'sra': '.sra',
     'tagAlign': '.tagAlign.gz',
@@ -331,13 +332,8 @@ def unique_keys(self, properties):
             'notSubmittable': True
         }
     )
-    def content_summary(self, request, content_type, file_format):
-        phrases = [
-            file_format,
-            content_type
-        ]
-        non_empty_phrases = [x for x in phrases if x != '']
-        return ' '.join(non_empty_phrases)
+    def content_summary(self, request, dimension1, dimension2, content_type):
+        return f'{dimension1} by {dimension2} {content_type}'
 
 
 @collection(