feat: report mean gap-compressed identity for primary and supplementary alignments

williamrowell · williamrowell · commit 7e886c3498e2 · 2025-08-27T15:03:30.000-07:00
diff --git a/docs/family.md b/docs/family.md
@@ -173,6 +173,7 @@ The `Sample` struct contains sample specific data and metadata. The struct has t
 | Array\[String\] | stat_read_quality_median | Median read quality |  |
 | Array\[String\] | stat_mapped_read_count | Count of reads mapped to reference |  |
 | Array\[String\] | stat_mapped_percent | Percent of reads mapped to reference |  |
+| Array\[String\] | stat_mean_gap_compressed_identity | Mean gap-compressed identity |  |
 | Array\[String\] | inferred_sex | Inferred sex | Sex is inferred based on relative depth of chrY alignments. |
 | Array\[String\] | stat_mean_depth | Mean depth | |
 
diff --git a/docs/singleton.md b/docs/singleton.md
@@ -129,6 +129,7 @@ flowchart TD
 | String | stat_read_quality_median | Median read quality |  |
 | String | stat_mapped_read_count | Count of reads mapped to reference |  |
 | String | stat_mapped_percent | Percent of reads mapped to reference |  |
+| String | stat_mean_gap_compressed_identity | Mean gap-compressed identity |  |
 | String | inferred_sex | Inferred sex | Sex is inferred based on relative depth of chrY alignments. |
 | String | stat_mean_depth | Mean depth | |
 
diff --git a/wdl-ci.config.json b/wdl-ci.config.json
@@ -362,6 +362,12 @@
                   "test_tasks": [
                     "compare_string"
                   ]
+                },
+                "stat_mean_gap_compressed_identity": {
+                  "value": "99.77",
+                  "test_tasks": [
+                    "compare_string"
+                  ]
                 }
               }
             }
diff --git a/workflows/downstream/downstream.wdl b/workflows/downstream/downstream.wdl
@@ -212,19 +212,20 @@ workflow downstream {
     String stat_phase_block_ng50          = hiphase.stat_phase_block_ng50
 
     # bam stats
-    File   bam_statistics           = bam_stats.bam_statistics
-    File   read_length_plot         = bam_stats.read_length_plot
-    File?  read_quality_plot        = bam_stats.read_quality_plot
-    File   mapq_distribution_plot   = bam_stats.mapq_distribution_plot
-    File   mg_distribution_plot     = bam_stats.mg_distribution_plot
-    String stat_num_reads           = bam_stats.stat_num_reads
-    String stat_read_length_mean    = bam_stats.stat_read_length_mean
-    String stat_read_length_median  = bam_stats.stat_read_length_median
-    String stat_read_quality_mean   = bam_stats.stat_read_quality_mean
-    String stat_read_quality_median = bam_stats.stat_read_quality_median
-    String stat_mapped_read_count   = bam_stats.stat_mapped_read_count
-    String stat_mapped_percent      = bam_stats.stat_mapped_percent
-    File   trgt_coverage_dropouts   = coverage_dropouts.dropouts
+    File   bam_statistics                    = bam_stats.bam_statistics
+    File   read_length_plot                  = bam_stats.read_length_plot
+    File?  read_quality_plot                 = bam_stats.read_quality_plot
+    File   mapq_distribution_plot            = bam_stats.mapq_distribution_plot
+    File   mg_distribution_plot              = bam_stats.mg_distribution_plot
+    String stat_num_reads                    = bam_stats.stat_num_reads
+    String stat_read_length_mean             = bam_stats.stat_read_length_mean
+    String stat_read_length_median           = bam_stats.stat_read_length_median
+    String stat_read_quality_mean            = bam_stats.stat_read_quality_mean
+    String stat_read_quality_median          = bam_stats.stat_read_quality_median
+    String stat_mapped_read_count            = bam_stats.stat_mapped_read_count
+    String stat_mapped_percent               = bam_stats.stat_mapped_percent
+    String stat_mean_gap_compressed_identity = bam_stats.stat_mean_gap_compressed_identity
+    File   trgt_coverage_dropouts            = coverage_dropouts.dropouts
 
     # small variant stats
     File   small_variant_stats     = bcftools_stats_roh_small_variants.stats
diff --git a/workflows/family.wdl b/workflows/family.wdl
@@ -228,6 +228,7 @@ workflow humanwgs_family {
     'read_quality_median': downstream.stat_read_quality_median,
     'mapped_read_count': downstream.stat_mapped_read_count,
     'mapped_percent': downstream.stat_mapped_percent,
+    'mean_gap_compressed_identity': downstream.stat_mean_gap_compressed_identity,
     'mean_depth': upstream.stat_mean_depth,
     'inferred_sex': upstream.inferred_sex,
     'stat_phased_basepairs': downstream.stat_phased_basepairs,
@@ -267,18 +268,19 @@ workflow humanwgs_family {
     File  msg_file           = consolidate_stats.messages
 
     # bam stats
-    Array[File]   bam_statistics           = downstream.bam_statistics
-    Array[File]   read_length_plot         = downstream.read_length_plot
-    Array[File?]  read_quality_plot        = downstream.read_quality_plot
-    Array[File]   mapq_distribution_plot   = downstream.mapq_distribution_plot
-    Array[File]   mg_distribution_plot     = downstream.mg_distribution_plot
-    Array[String] stat_num_reads           = downstream.stat_num_reads
-    Array[String] stat_read_length_mean    = downstream.stat_read_length_mean
-    Array[String] stat_read_length_median  = downstream.stat_read_length_median
-    Array[String] stat_read_quality_mean   = downstream.stat_read_quality_mean
-    Array[String] stat_read_quality_median = downstream.stat_read_quality_median
-    Array[String] stat_mapped_read_count   = downstream.stat_mapped_read_count
-    Array[String] stat_mapped_percent      = downstream.stat_mapped_percent
+    Array[File]   bam_statistics                    = downstream.bam_statistics
+    Array[File]   read_length_plot                  = downstream.read_length_plot
+    Array[File?]  read_quality_plot                 = downstream.read_quality_plot
+    Array[File]   mapq_distribution_plot            = downstream.mapq_distribution_plot
+    Array[File]   mg_distribution_plot              = downstream.mg_distribution_plot
+    Array[String] stat_num_reads                    = downstream.stat_num_reads
+    Array[String] stat_read_length_mean             = downstream.stat_read_length_mean
+    Array[String] stat_read_length_median           = downstream.stat_read_length_median
+    Array[String] stat_read_quality_mean            = downstream.stat_read_quality_mean
+    Array[String] stat_read_quality_median          = downstream.stat_read_quality_median
+    Array[String] stat_mapped_read_count            = downstream.stat_mapped_read_count
+    Array[String] stat_mapped_percent               = downstream.stat_mapped_percent
+    Array[String] stat_mean_gap_compressed_identity = downstream.stat_mean_gap_compressed_identity
 
     # merged, haplotagged alignments
     Array[File]   merged_haplotagged_bam       = downstream.merged_haplotagged_bam
diff --git a/workflows/singleton.wdl b/workflows/singleton.wdl
@@ -173,6 +173,7 @@ workflow humanwgs_singleton {
     'read_quality_median': [downstream.stat_read_quality_median],
     'mapped_read_count': [downstream.stat_mapped_read_count],
     'mapped_percent': [downstream.stat_mapped_percent],
+    'mean_gap_compressed_identity': [downstream.stat_mean_gap_compressed_identity],
     'mean_depth': [upstream.stat_mean_depth],
     'inferred_sex': [upstream.inferred_sex],
     'stat_phased_basepairs': [downstream.stat_phased_basepairs],
@@ -211,18 +212,19 @@ workflow humanwgs_singleton {
     File msg_file   = consolidate_stats.messages
 
     # bam stats
-    File   bam_statistics           = downstream.bam_statistics
-    File   read_length_plot         = downstream.read_length_plot
-    File?  read_quality_plot        = downstream.read_quality_plot
-    File   mapq_distribution_plot   = downstream.mapq_distribution_plot
-    File   mg_distribution_plot     = downstream.mg_distribution_plot
-    String stat_num_reads           = downstream.stat_num_reads
-    String stat_read_length_mean    = downstream.stat_read_length_mean
-    String stat_read_length_median  = downstream.stat_read_length_median
-    String stat_read_quality_mean   = downstream.stat_read_quality_mean
-    String stat_read_quality_median = downstream.stat_read_quality_median
-    String stat_mapped_read_count   = downstream.stat_mapped_read_count
-    String stat_mapped_percent      = downstream.stat_mapped_percent
+    File   bam_statistics                    = downstream.bam_statistics
+    File   read_length_plot                  = downstream.read_length_plot
+    File?  read_quality_plot                 = downstream.read_quality_plot
+    File   mapq_distribution_plot            = downstream.mapq_distribution_plot
+    File   mg_distribution_plot              = downstream.mg_distribution_plot
+    String stat_num_reads                    = downstream.stat_num_reads
+    String stat_read_length_mean             = downstream.stat_read_length_mean
+    String stat_read_length_median           = downstream.stat_read_length_median
+    String stat_read_quality_mean            = downstream.stat_read_quality_mean
+    String stat_read_quality_median          = downstream.stat_read_quality_median
+    String stat_mapped_read_count            = downstream.stat_mapped_read_count
+    String stat_mapped_percent               = downstream.stat_mapped_percent
+    String stat_mean_gap_compressed_identity = downstream.stat_mean_gap_compressed_identity
 
     # merged, haplotagged alignments
     File   merged_haplotagged_bam       = downstream.merged_haplotagged_bam
diff --git a/workflows/wdl-common b/workflows/wdl-common
@@ -1 +1 @@
-Subproject commit 4c516f7627a5b9ed3e7b5ea4d4cec5b49958a1f2
+Subproject commit d34a646b262aca7f5ba012c2b3fb59093df5cb9c

Original file line number	Diff line number	Diff line change
`@@ -362,6 +362,12 @@`
`362`	`362`	`"test_tasks": [`
`363`	`363`	`"compare_string"`
`364`	`364`	`]`
	`365`	`+ },`
	`366`	`+ "stat_mean_gap_compressed_identity": {`
	`367`	`+ "value": "99.77",`
	`368`	`+ "test_tasks": [`
	`369`	`+ "compare_string"`
	`370`	`+ ]`
`365`	`371`	`}`
`366`	`372`	`}`
`367`	`373`	`}`