Merge pull request #33 from TRON-Bioinformatics/bugfix-recurrent-vari…

…ants-tab

Bugfix recurrent variants tab

covigator/__init__.py

@@ -1,4 +1,4 @@
-VERSION = "v0.6.4"
+VERSION = "v0.6.6"
 ANALYSIS_PIPELINE_VERSION = "v0.9.3"
 
 MISSENSE_VARIANT = "missense_variant"

covigator/dashboard/tabs/recurrent_mutations.py

@@ -258,13 +258,14 @@ def update_top_occurring_variants(_, top_variants, gene_name, domain, date_range
         state=[
             State(ID_DROPDOWN_GENE, 'value'),
             State(ID_DROPDOWN_DOMAIN, 'value'),
+            State(ID_TOP_OCCURRING_VARIANTS, "value"),  # this param is needed to ensure order of callbacks
             State(ID_TOP_OCCURRING_VARIANTS_TABLE, "derived_virtual_data"),
             State(ID_TOP_OCCURRING_VARIANTS_TABLE, "derived_virtual_selected_rows"),
             State(ID_SLIDER_BIN_SIZE, 'value'),
             State(ID_DROPDOWN_DATA_SOURCE, 'value'),
         ]
     )
-    def update_needle_plot(_, gene_name, domain, rows, selected_rows_indices, bin_size, source):
+    def update_needle_plot(_, gene_name, domain, dummy, rows, selected_rows_indices, bin_size, source):
         if gene_name is not None or domain is not None:
             selected_rows = [rows[s] for s in selected_rows_indices] if selected_rows_indices else None
             plot = html.Div(
@@ -286,6 +287,7 @@ def update_needle_plot(_, gene_name, domain, rows, selected_rows_indices, bin_si
         state=[
             State(ID_DROPDOWN_GENE, 'value'),
             State(ID_DROPDOWN_DOMAIN, 'value'),
+            State(ID_TOP_OCCURRING_VARIANTS, "value"),  # this param is needed to ensure order of callbacks
             State(ID_TOP_OCCURRING_VARIANTS_TABLE, "derived_virtual_data"),
             State(ID_TOP_OCCURRING_VARIANTS_TABLE, "derived_virtual_selected_rows"),
             State(ID_DROPDOWN_SIMILARITY_METRIC, 'value'),
@@ -295,12 +297,12 @@ def update_needle_plot(_, gene_name, domain, rows, selected_rows_indices, bin_si
         ]
     )
     def update_cooccurrence_heatmap(
-            _, gene_name, domain, rows, selected_rows_indices, metric, min_cooccurrences, min_samples, source):
+            _, gene_name, domain, dummy, rows, selected_rows_indices, metric, min_cooccurrences, min_samples, source):
         if source != DataSource.ENA.name:
             plot = html.Div(
                 children=[dcc.Markdown(
                     """**The co-occurrence analysis is currently only available for the ENA dataset**""")])
-        elif gene_name is None:
+        elif gene_name is None and domain is None:
             plot = html.Div(
                 children=[dcc.Markdown(
                     """**Please, select a gene or domain to explore the co-occurrence analysis**""")])

covigator/processor/abstract_processor.py

@@ -199,6 +199,7 @@ def load_pangolin(sample: typing.Union[SampleGisaid, SampleEna], path: str) -> t
 
             # fill NA values on a per column basis...
             data.lineage.fillna(value="", inplace=True)
+            data.lineage = data.lineage.transform(lambda x: "" if x == 'None' else x)   # replace "None" values
             data.scorpio_call.fillna(value="", inplace=True)
             data.version.fillna(value="", inplace=True)
             data.pangolin_version.fillna(value="", inplace=True)

covigator/tests/resources/test.lofreq.pangolin.with_none.csv

@@ -0,0 +1,2 @@
+taxon,lineage,conflict,ambiguity_score,scorpio_call,scorpio_support,scorpio_conflict,version,pangolin_version,pangoLEARN_version,pango_version,status,note
+MN908947.3_dna:primary_assembly_primary_assembly:ASM985889v3:MN908947.3:1:29903:1_REF,None,0.0,1.0,,,,PLEARN-v1.2.123,3.1.19,2022-01-20,v1.2.123,passed_qc,

covigator/tests/unit_tests/test_processor.py

@@ -132,6 +132,15 @@ def test_load_pangolin_from_ena(self):
         self.session.add(sample)
         self.session.commit()
 
+    def test_load_pangolin_with_none(self):
+        pangolin_path = pkg_resources.resource_filename(covigator.tests.__name__, "resources/test.lofreq.pangolin.with_none.csv")
+        sample = SampleEna(run_accession="TEST", fastq_ftp="", fastq_md5="", num_fastqs=1)
+        EnaProcessor.load_pangolin(sample, path=pangolin_path)
+        self.assertEqual(sample.pangolin_lineage, "")
+
+        self.session.add(sample)
+        self.session.commit()
+
     def test_load_pangolin_from_gisaid(self):
         pangolin_path = pkg_resources.resource_filename(covigator.tests.__name__, "resources/test.lofreq.pangolin.csv")
         sample = SampleGisaid(run_accession="TEST")