Update Qualimap: add additional entries for qualimap when region stats present

CHANGELOG.md

@@ -41,6 +41,8 @@
   - Catch zero division in sambamba markdup ([#1654](https://github.com/ewels/MultiQC/issues/1654))
 - **Samtools**
   - Added additional (by default hidden) column for `flagstat` that displays percentage of mapped reads in a bam ([#1733](https://github.com/ewels/MultiQC/issues/1733))
+- **Qualimap**
+  - Added additional (by default hidden) columns in general stats for BamQC results that displays region on-target stats if region bed has been supplied
 
 ## [MultiQC v1.13](https://github.com/ewels/MultiQC/releases/tag/v1.13) - 2022-09-08
 

multiqc/modules/qualimap/QM_BamQC.py

@@ -91,6 +91,10 @@ def parse_genome_results(self, f):
         "mean_mapping_quality": r"mean mapping quality = ([\d,\.]+)",
         "general_error_rate": r"general error rate = ([\d,\.]+)",
         "mean_coverage": r"mean coverageData = ([\d,\.]+)",
+        "regions_size": r"regions size = ([\d,\.]+)",
+    }
+    regexes_secondary = {
+        "regions_mapped_reads": r"number of mapped reads = ([\d,]+)",
     }
     d = dict()
     for k, r in regexes.items():
@@ -103,6 +107,17 @@ def parse_genome_results(self, f):
                     d[k] = r_search.group(1)
             else:
                 d[k] = r_search.group(1)
+
+    for k, r in regexes_secondary.items():
+        r_search = re.findall(r, f["f"], re.MULTILINE)
+        print(r_search)
+        if len(r_search) > 1:
+            if "\d" in r:
+                try:
+                    d[k] = float(r_search[1].replace(",", ""))
+                except ValueError:
+                    d[k] = r_search[1]
+
     # Check we have an input filename
     if "bam_file" not in d:
         log.debug("Couldn't find an input filename in genome_results file {}".format(f["fn"]))
@@ -119,6 +134,8 @@ def parse_genome_results(self, f):
         self.general_stats_data[s_name]["percentage_aligned"] = d["percentage_aligned"]
         self.general_stats_data[s_name]["general_error_rate"] = d["general_error_rate"] * 100
         self.general_stats_data[s_name]["mean_coverage"] = d["mean_coverage"]
+        self.general_stats_data[s_name]["regions_size"] = d["regions_size"]
+        self.general_stats_data[s_name]["regions_mapped_reads"] = d["regions_mapped_reads"]
     except KeyError:
         pass
 
@@ -592,6 +609,20 @@ def general_stats_headers(self):
         "format": "{0:.2f}",
         "hidden": True,
     }
+    self.general_stats_headers["regions_size"] = {
+        "title": "{} Region size".format(config.read_count_prefix),
+        "description": "Size of target region",
+        "suffix": " bp",
+        "scale": "RdYlGn",
+        "hidden": True,
+    }
+    self.general_stats_headers["regions_mapped_reads"] = {
+        "title": "{} Aligned".format(config.read_count_prefix),
+        "description": "Number of mapped reads on target region ({})".format(config.read_count_desc),
+        "scale": "RdYlGn",
+        "shared_key": "read_count",
+        "hidden": True,
+    }
 
 
 def _calculate_bases_within_thresholds(bases_by_depth, total_size, depth_thresholds):