Remove RNA-SeQC from workflows and MultiQC

docs/CHANGELOG.rst

@@ -20,6 +20,8 @@ Added
 
 Changed
 -------
+- Remove ``rnaseqc-qc`` 3' bias statistics from MultiQC report
+- Remove ``rnaseqc-qc`` from RNA-seq workflows
 
 Fixed
 -----

resolwe_bio/processes/support_processors/multiqc.py

@@ -65,12 +65,6 @@ def create_summary_table(samples, species, build):
         json.dump(sample_summary_json, out_file)
 
 
-def parse_rnaseqc_report(report):
-    """Parse RNA-SeQC QC report file."""
-    df = pd.read_csv(report, sep="\t")
-    return dict(df.values)
-
-
 def parse_genebody_report(report):
     """Parse QoRTs gene body coverage metrics report file."""
     df = pd.read_csv(report, sep="\t", compression="gzip")
@@ -79,37 +73,6 @@ def parse_genebody_report(report):
     return dict
 
 
-def create_coverage_table(sample_names, reports):
-    """Prepare coverage metrics table."""
-    coverage_stats = [
-        "Genes used in 3' bias",
-        "Mean 3' bias",
-        "Median 3' bias",
-        "3' bias Std",
-        "3' bias MAD_Std",
-        "3' Bias, 25th Percentile",
-        "3' Bias, 75th Percentile",
-    ]
-
-    coverage_qc_json = {
-        "id": "coverage_qc",
-        "section_name": "RNA-SeQC Coverage Stats",
-        "plot_type": "table",
-        "file_format": "json",
-        "data": {},
-    }
-
-    for sample_name, report in zip(sample_names, reports):
-        report_data = parse_rnaseqc_report(report)
-
-        coverage_qc_json["data"][sample_name] = {
-            k: report_data[k] for k in coverage_stats if k in report_data
-        }
-
-    with open("rnaseqc_coverage_mqc.json", "w") as out_file:
-        json.dump(coverage_qc_json, out_file)
-
-
 def create_coverage_plot(sample_names, reports):
     """Prepare QoRTs gene body coverage plot."""
     genebody_qc_json = {
@@ -474,7 +437,7 @@ class MultiQC(Process):
     }
     category = "QC"
     data_name = "MultiQC report"
-    version = "1.23.0"
+    version = "1.24.0"
 
     class Input:
         """Input fields to process MultiQC."""
@@ -552,8 +515,6 @@ def run(self, inputs, outputs):
         unsupported_data = []
         star_quantification_samples = []
         star_quantification_reports = []
-        rnaseqc_samples = []
-        rnaseqc_reports = []
         qorts_samples = []
         qorts_reports = []
 
@@ -733,14 +694,9 @@ def run(self, inputs, outputs):
 
             elif d.process.type == "data:rnaseqc:qc:":
                 name = os.path.basename(d.output.metrics.path)
-                rnaseqc_samples.append(sample_name)
-                rnaseqc_reports.append(d.output.metrics.path)
                 create_symlink(
                     src=d.output.metrics.path, dst=os.path.join(sample_dir, name)
                 )
-                create_coverage_table(
-                    sample_names=rnaseqc_samples, reports=rnaseqc_reports
-                )
 
             elif d.process.type == "data:expression:salmon:":
                 # Symlink files/dirs without the parent directory to

resolwe_bio/processes/workflows/bbduk_salmon_qc.py

@@ -42,7 +42,7 @@ class WorkflowBbdukSalmonQc(Process):
     entity = {
         "type": "sample",
     }
-    version = "4.3.1"
+    version = "4.4.0"
     process_type = "data:workflow:rnaseq:salmon"
     category = "Pipeline"
 
@@ -449,22 +449,4 @@ def run(self, inputs, outputs):
             ]
         }
 
-        # RNA-SeQC tool is initiated only if annotation source is ENSEMBL
-        if inputs.annotation.output.source == "ENSEMBL":
-            input_rnaseqc = {
-                "alignment": alignment_qc,
-                "annotation": inputs.annotation,
-                "strand_detection_options": {
-                    "stranded": "auto",
-                    "cdna_index": inputs.salmon_index,
-                    "n_reads": 5000000,
-                },
-            }
-            rnaseqc = Data.create(
-                process=BioProcess.get_latest(slug="rnaseqc-qc"),
-                input=input_rnaseqc,
-                name=f"RNA-SeQC QC report ({inputs.reads.name})",
-            )
-            input_multiqc["data"].append(rnaseqc)
-
         Data.create(process=BioProcess.get_latest(slug="multiqc"), input=input_multiqc)

resolwe_bio/processes/workflows/bbduk_star.py

@@ -41,7 +41,7 @@ class WorkflowSTAR(Process):
         "expression-engine": "jinja",
     }
     data_name = "{{ reads|name|default('?') }}"
-    version = "1.4.0"
+    version = "1.5.0"
     entity = {
         "type": "sample",
     }
@@ -731,24 +731,4 @@ def run(self, inputs, outputs):
             "advanced": {"dirs": True, "config": True},
         }
 
-        # RNA-SeQC tool is initiated only if annotation source is ENSEMBL
-        if inputs.annotation.output.source == "ENSEMBL":
-            input_rnaseqc = {
-                "alignment": alignment_downsampled,
-                "annotation": inputs.annotation,
-                "strand_detection_options": {"stranded": inputs.assay_type},
-            }
-
-            if inputs.cdna_index:
-                input_rnaseqc["strand_detection_options"][
-                    "cdna_index"
-                ] = inputs.cdna_index
-
-            rnaseqc = Data.create(
-                process=BioProcess.get_latest(slug="rnaseqc-qc"),
-                input=input_rnaseqc,
-                name=f"RNA-SeQC QC report ({inputs.reads.name})",
-            )
-            input_multiqc["data"].append(rnaseqc)
-
         Data.create(process=BioProcess.get_latest(slug="multiqc"), input=input_multiqc)

resolwe_bio/processes/workflows/bbduk_star_featurecounts_qc.py

@@ -46,7 +46,7 @@ class WorkflowBBDukStarFcQC(Process):
     entity = {
         "type": "sample",
     }
-    version = "6.2.0"
+    version = "6.3.0"
     process_type = "data:workflow:rnaseq:featurecounts:qc"
     category = "Pipeline"
 
@@ -764,24 +764,4 @@ def run(self, inputs, outputs):
             "advanced": {"dirs": True, "config": True},
         }
 
-        # RNA-SeQC tool is initiated only if annotation source is ENSEMBL
-        if inputs.annotation.output.source == "ENSEMBL":
-            input_rnaseqc = {
-                "alignment": alignment_downsampled,
-                "annotation": inputs.annotation,
-                "strand_detection_options": {"stranded": inputs.assay_type},
-            }
-
-            if inputs.cdna_index:
-                input_rnaseqc["strand_detection_options"][
-                    "cdna_index"
-                ] = inputs.cdna_index
-
-            rnaseqc = Data.create(
-                process=BioProcess.get_latest(slug="rnaseqc-qc"),
-                input=input_rnaseqc,
-                name=f"RNA-SeQC QC report ({inputs.reads.name})",
-            )
-            input_multiqc["data"].append(rnaseqc)
-
         Data.create(process=BioProcess.get_latest(slug="multiqc"), input=input_multiqc)

resolwe_bio/tests/processes/test_support_processors.py

@@ -491,14 +491,6 @@ def test_multiqc(self):
                 },
             )
 
-            rnaseqc_report = self.run_process(
-                "rnaseqc-qc",
-                {
-                    "alignment": star_alignment.id,
-                    "annotation": annotation.id,
-                },
-            )
-
             # BED file is not part of a sample entity. Test if MultiQC process
             # correctly skips this input data object
             bed = self.run_process(
@@ -518,7 +510,6 @@ def test_multiqc(self):
                     star_quantification.id,
                     samtools_idxstats.id,
                     qorts_report.id,
-                    rnaseqc_report.id,
                     bed.id,
                 ],
                 "advanced": {