Merge branch 'CW-3590' into 'dev'

rename newly added 'run_ids' column to 'run_id' [CW-3590] Closes CW-3590 See merge request epi2melabs/workflows/wf-cas9!55
epi2me-labs · Feb 21, 2024 · 7811221 · 7811221
2 parents baf8246 + 954dc2f
commit 7811221
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 8 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v1.1.1]
+### Changed
+- The name of the column with run IDs from `run_ids` to `run_id`.
+
 ## [v1.1.0]
 ### Added
 - A column with sequencing run IDs to the output summary CSV files.

diff --git a/bin/workflow_glue/build_tables.py b/bin/workflow_glue/build_tables.py
@@ -47,7 +47,7 @@ def main(args):
     """Entry point."""
     header = [
         'chr', 'start', 'end', 'target', 'nreads', 'nbases',
-        'tsize', 'coverage_frac', 'median_cov', 'p', 'n', 'sample_id', 'run_ids']
+        'tsize', 'coverage_frac', 'median_cov', 'p', 'n', 'sample_id', 'run_id']
 
     frames = []
 
@@ -125,7 +125,7 @@ def main(args):
             'mean_read_length': 1})
 
         df_all = df_all[[
-            'sample', 'run_ids', 'chr', 'start', 'end', 'target', 'tsize',
+            'sample', 'run_id', 'chr', 'start', 'end', 'target', 'tsize',
             'kbases', 'coverage_frac', 'median_cov', 'nreads',
             'mean_read_length', 'strand_bias']]
         df_all.sort_values(
@@ -149,16 +149,16 @@ def main(args):
         sample_df['nreads'] = df['nreads'].sum()
         sample_df = sample_df.round(2)
         sample_df['sample_id'] = sid
-        # the `run_ids` column should contain the same value for all rows for this
+        # the `run_id` column should contain the same value for all rows for this
         # sample
-        sample_df["run_ids"], = df["run_ids"].unique()
+        sample_df["run_id"], = df["run_id"].unique()
         dfs.append(sample_df)
 
     if dfs:
         sample_summary = pd.concat(dfs, axis=1).T
         sample_summary.set_index('sample_id', drop=True, inplace=True)
-        # move the `run_ids` column to the beginning of the dataframe
-        sample_summary.insert(0, "run_ids", sample_summary.pop("run_ids"))
+        # move the `run_id` column to the beginning of the dataframe
+        sample_summary.insert(0, "run_id", sample_summary.pop("run_id"))
     else:
         sample_summary = pd.DataFrame()
 

diff --git a/main.nf b/main.nf
@@ -210,7 +210,7 @@ process target_summary {
     # Add sample_id column
     sed -i "s/\$/\t${meta.alias}/" ${meta.alias}_target_summary.bed
 
-    # Add run_ids column
+    # Add run_id column
     sed -i "s/\$/\t${meta.run_ids.join(',')}/" ${meta.alias}_target_summary.bed
 
     rm median_coverage.bed pos.bed neg.bed

diff --git a/nextflow.config b/nextflow.config
@@ -53,7 +53,7 @@ manifest {
     description     = 'Summarise the results of Cas9 enrichment sequencing.'
     mainScript      = 'main.nf'
     nextflowVersion = '>=23.04.2'
-    version         = 'v1.1.0'
+    version         = 'v1.1.1'
 
 }