Add MEDIAN_TARGET_COVERAGE to HsMetrics. Fix RnaSeqMetrics regex

MultiQC · Nov 2, 2023 · 0c51184 · 0c51184
1 parent b4e3a37
commit 0c51184
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 12 deletions.
diff --git a/multiqc/modules/picard/HsMetrics.py b/multiqc/modules/picard/HsMetrics.py
@@ -238,6 +238,13 @@ def _general_stats_table(module, data):
             "scale": "Blues",
             "suffix": " X",
         }
+        headers["MEDIAN_TARGET_COVERAGE"] = {
+            "title": "Median Target Coverage",
+            "description": "The median coverage of reads that mapped to target regions of an experiment.",
+            "min": 0,
+            "suffix": "X",
+            "scale": "GnBu",
+        }
         try:
             covs = picard_config["general_stats_target_coverage"]
             assert isinstance(covs, list)
@@ -249,7 +256,7 @@ def _general_stats_table(module, data):
         for c in covs:
             headers["PCT_TARGET_BASES_{}X".format(c)] = {
                 "id": f"{module.anchor}_target_bases_{c}X",
-                "title": "% Target Bases {}X".format(c),
+                "title": "Target Bases &ge; {}X".format(c),
                 "description": "Percent of target bases with coverage &ge; {}X".format(c),
                 "max": 100,
                 "min": 0,
@@ -345,7 +352,7 @@ def _generate_table_header_config(table_cols, hidden_table_cols):
                 "description": FIELD_DESCRIPTIONS[h] if h in FIELD_DESCRIPTIONS else None,
             }
             if h.find("PCT") > -1:
-                headers[h]["title"] = "% {}".format(headers[h]["title"])
+                headers[h]["title"] = headers[h]["title"]
                 headers[h]["modify"] = lambda x: x * 100.0
                 headers[h]["max"] = 100
                 headers[h]["suffix"] = "%"

diff --git a/multiqc/modules/picard/MarkDuplicates.py b/multiqc/modules/picard/MarkDuplicates.py
@@ -152,7 +152,7 @@ def save_table_results(s_name, keys, parsed_data, recompute_merged_metrics):
     # Add to general stats table
     headers = {
         "PERCENT_DUPLICATION": {
-            "title": "% Dups",
+            "title": "Duplication",
             "description": "Mark Duplicates - Percent Duplication",
             "max": 100,
             "min": 0,

diff --git a/multiqc/modules/picard/RnaSeqMetrics.py b/multiqc/modules/picard/RnaSeqMetrics.py
@@ -100,15 +100,15 @@ def parse_reports(module):
     # Add to general stats table
     headers = dict()
     headers["PCT_RIBOSOMAL_BASES"] = {
-        "title": "% rRNA",
+        "title": "rRNA",
         "description": "Percent of aligned bases overlapping ribosomal RNA regions",
         "max": 100,
         "min": 0,
         "suffix": "%",
         "scale": "Reds",
     }
     headers["PCT_MRNA_BASES"] = {
-        "title": "% mRNA",
+        "title": "mRNA",
         "description": "Percent of aligned bases overlapping UTRs and coding regions of mRNA transcripts",
         "max": 100,
         "min": 0,
@@ -130,9 +130,9 @@ def parse_reports(module):
     warn_rrna = ""
     rrna_missing = []
     for s_name, metrics in data_by_sample.items():
-        if metrics["RIBOSOMAL_BASES"] == "":
+        if metrics["RIBOSOMAL_BASES"] == "NA":
             rrna_missing.append(s_name)
-    if len(rrna_missing):
+    if rrna_missing:
         if len(rrna_missing) < 5:
             missing_samples = "for samples <code>{}</code>".format("</code>, <code>".join(rrna_missing))
         else:

diff --git a/multiqc/modules/picard/RrbsSummaryMetrics.py b/multiqc/modules/picard/RrbsSummaryMetrics.py
@@ -71,7 +71,7 @@ def parse_reports(module):
     # Add to general stats table
     headers = dict()
     headers["PCT_CPG_BASES_CONVERTED"] = {
-        "title": "% CpG Methylated",
+        "title": "CpG Methylated",
         "description": "Percentage of times a CpG cytosine was converted",
         "max": 100,
         "min": 0,
@@ -81,7 +81,7 @@ def parse_reports(module):
         "modify": lambda x: 100 - util.multiply_hundred(x),
     }
     headers["PCT_NON_CPG_BASES_CONVERTED"] = {
-        "title": "% Non-CpG Methylated",
+        "title": "Non-CpG Methylated",
         "description": "Percentage of times a non-CpG cytosine was converted",
         "max": 100,
         "min": 0,

diff --git a/multiqc/modules/picard/TargetedPcrMetrics.py b/multiqc/modules/picard/TargetedPcrMetrics.py
@@ -67,7 +67,7 @@ def parse_reports(module):
     # Add to general stats table
     headers = {
         "PCT_AMPLIFIED_BASES": {
-            "title": "% Amplified Bases",
+            "title": "Amplified Bases",
             "description": "The fraction of aligned bases that mapped to or near an amplicon.",
             "min": 0,
             "max": 100,

diff --git a/multiqc/modules/picard/util.py b/multiqc/modules/picard/util.py
@@ -96,7 +96,7 @@ def is_line_right_before_table(
         picard_classes = [picard_class]
     return (
         (line.startswith("## METRICS CLASS") or line.startswith("## HISTOGRAM"))
-        and (not picard_classes or any(c in line for c in picard_classes))
+        and (not picard_classes or any(c.upper() in line.upper() for c in picard_classes))
         or sentieon_algo
         and line.startswith("#SentieonCommandLine:")
         and f" --algo {sentieon_algo}" in line
@@ -132,7 +132,7 @@ def extract_sample_name(
 
     picard_command = (
         line.startswith("# ")
-        and any(pt in line for pt in picard_tools)
+        and any(pt.upper() in line.upper() for pt in picard_tools)
         and any(
             f" {po}=" in line.upper()
             or f" --{po}=" in line.upper()