From 750e55e664ef98113e25fe03f4b273aac6b335c1 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 09:15:50 +0200
Subject: [PATCH 01/13] Fist edition of Aviti index fixer script

---
 aviti_index_fixer.py | 62 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 aviti_index_fixer.py

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
new file mode 100644
index 0000000..b30ecb9
--- /dev/null
+++ b/aviti_index_fixer.py
@@ -0,0 +1,62 @@
+import click as cli
+import pandas as pd
+
+NT_COMPLIMENT = {
+    'A': 'T',
+    'T': 'A',
+    'C': 'G',
+    'G': 'C'
+}
+
+def load_manifest(path):
+    """Load the manifest from the given path."""
+    with open(path, 'r') as file:
+        manifest_content = file.read()
+    header = manifest_content.split("[SAMPLES]")[0]
+    samples = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
+    return header, samples
+
+def load_sample_dataframe(manifest_data):
+    """Extract the sample data from the manifest and convert it to a DataFrame."""
+    header = manifest_data[0]
+    sample_rows = manifest_data[1:]
+
+    sample_dicts = []
+    for row in sample_rows:
+        row_dict = dict(zip(header.split(","), row.split(",")))
+        sample_dicts.append(row_dict)
+
+    samples_info = pd.DataFrame.from_dict(sample_dicts)
+    return samples_info
+
+def reverse_complement_index(index):
+    """Return the reverse complement of a given index."""
+    return ''.join(NT_COMPLIMENT[nuc] for nuc in reversed(index))
+
+
+@cli.command()
+@cli.option('--manifest_path', required=True, help='Path to the sample manifest. e.g. ~/fc/AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv')
+@cli.option('--project', required=False, help='Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed')
+@cli.option('--swap', is_flag=True, help='Swaps index 1 and 2.')
+@cli.option('--rc1', is_flag=True, help='Exchanges index 1 for its reverse compliment.')
+@cli.option('--rc2', is_flag=True, help='Exchanges index 2 for its reverse compliment.')
+# TODO: Add option to include additional samples
+
+def main(manifest_path, project, swap, rc1, rc2):
+    """Main function to fix the samplesheet indexes for AVITI runs."""
+    # Read the samplesheet
+    manifest_header, manifest_data = load_manifest(manifest_path)
+    # Read the sample data into a data frame (look at Element_runs.py for an example)
+    samples_info = load_sample_dataframe(manifest_data)
+    # Process the indexes based on the options provided
+    if rc1:
+        samples_info['Index1'] = samples_info['Index1'].apply(reverse_complement_index)
+    if rc2:
+        samples_info['Index2'] = samples_info['Index2'].apply(reverse_complement_index)
+    if swap:
+        samples_info[['Index1', 'Index2']] = samples_info[['Index2', 'Index1']]
+    print(samples_info)
+    # Generate the updated samplesheet
+
+if __name__ == '__main__':
+    main()

From 487cbec4709c6183ba75d9a750e4e306840dc379 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 09:26:32 +0200
Subject: [PATCH 02/13] Filter projects and write output file

---
 aviti_index_fixer.py | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index b30ecb9..b8ef14d 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -46,17 +46,29 @@ def main(manifest_path, project, swap, rc1, rc2):
     """Main function to fix the samplesheet indexes for AVITI runs."""
     # Read the samplesheet
     manifest_header, manifest_data = load_manifest(manifest_path)
+    
     # Read the sample data into a data frame (look at Element_runs.py for an example)
     samples_info = load_sample_dataframe(manifest_data)
+    
     # Process the indexes based on the options provided
+    if project:
+        mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] == project)
+    else:
+        mask = pd.Series([True] * len(samples_info))
+
     if rc1:
-        samples_info['Index1'] = samples_info['Index1'].apply(reverse_complement_index)
+        samples_info.loc[mask, 'Index1'] = samples_info.loc[mask, 'Index1'].apply(reverse_complement_index)
     if rc2:
-        samples_info['Index2'] = samples_info['Index2'].apply(reverse_complement_index)
+        samples_info.loc[mask, 'Index2'] = samples_info.loc[mask, 'Index2'].apply(reverse_complement_index)
     if swap:
-        samples_info[['Index1', 'Index2']] = samples_info[['Index2', 'Index1']]
-    print(samples_info)
+        samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
+    
     # Generate the updated samplesheet
+    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True).strip()
+    # Write the updated samplesheet to a new file
+    output_path = manifest_path.replace('.csv', '_updates.csv')
+    with open(output_path, 'w') as output_file:
+        output_file.write(updated_samplesheet)
 
 if __name__ == '__main__':
     main()

From e5d6ea9cd9497e5cb679edbd4e724f9be39c32aa Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 10:21:22 +0200
Subject: [PATCH 03/13] Sort output and add option to include additional
 samples

---
 aviti_index_fixer.py | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index b8ef14d..eb72585 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -1,5 +1,6 @@
 import click as cli
 import pandas as pd
+import os
 
 NT_COMPLIMENT = {
     'A': 'T',
@@ -33,16 +34,15 @@ def reverse_complement_index(index):
     """Return the reverse complement of a given index."""
     return ''.join(NT_COMPLIMENT[nuc] for nuc in reversed(index))
 
-
 @cli.command()
 @cli.option('--manifest_path', required=True, help='Path to the sample manifest. e.g. ~/fc/AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv')
 @cli.option('--project', required=False, help='Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed')
 @cli.option('--swap', is_flag=True, help='Swaps index 1 and 2.')
 @cli.option('--rc1', is_flag=True, help='Exchanges index 1 for its reverse compliment.')
 @cli.option('--rc2', is_flag=True, help='Exchanges index 2 for its reverse compliment.')
-# TODO: Add option to include additional samples
+@cli.option('--add_sample', multiple=True, help='Include additional sample(s). Use multiple times for multiple samples, or provide a file. Each new sample should have the same format as in the existing manifest. Example: --add_sample P12345,ATCG,CGTA,1,A__Project_25_16,301-10-10-301,ATCG-CGTA,')
 
-def main(manifest_path, project, swap, rc1, rc2):
+def main(manifest_path, project, swap, rc1, rc2, add_sample):
     """Main function to fix the samplesheet indexes for AVITI runs."""
     # Read the samplesheet
     manifest_header, manifest_data = load_manifest(manifest_path)
@@ -62,11 +62,25 @@ def main(manifest_path, project, swap, rc1, rc2):
         samples_info.loc[mask, 'Index2'] = samples_info.loc[mask, 'Index2'].apply(reverse_complement_index)
     if swap:
         samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
-    
+    for additional_sample in add_sample:
+        if os.path.isfile(additional_sample):
+            # If a file is provided, read it and append to the samples_info DataFrame
+            additional_samples = pd.read_csv(additional_sample, header=None)
+            additional_samples.columns = samples_info.columns
+        else:
+            # If a sample is provided directly, create a DataFrame from it
+            additional_samples = pd.DataFrame([additional_sample.split(',')], columns=samples_info.columns)
+        samples_info = pd.concat([samples_info, additional_samples], ignore_index=True)
+
+    # Sort the samples by lane and SampleName
+    samples_info['Lane'] = samples_info['Lane'].astype(int)
+    samples_info.sort_values(by=['Lane', 'SampleName'], inplace=True)
+   
     # Generate the updated samplesheet
-    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True).strip()
+    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True)
+   
     # Write the updated samplesheet to a new file
-    output_path = manifest_path.replace('.csv', '_updates.csv')
+    output_path = manifest_path.replace('.csv', '_updated.csv')
     with open(output_path, 'w') as output_file:
         output_file.write(updated_samplesheet)
 

From 9c05440a52ec857d3bc1682970c742d0ce04fe15 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 10:40:15 +0200
Subject: [PATCH 04/13] Also update the lims_label

---
 aviti_index_fixer.py | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index eb72585..f45a752 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -13,9 +13,12 @@ def load_manifest(path):
     """Load the manifest from the given path."""
     with open(path, 'r') as file:
         manifest_content = file.read()
-    header = manifest_content.split("[SAMPLES]")[0]
-    samples = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
-    return header, samples
+    header_section = manifest_content.split("[SAMPLES]")[0]
+    samples_section = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
+    all_samples = load_sample_dataframe(samples_section)
+    samples_info = all_samples[all_samples["Project"] != "Control"].copy()
+    controls_info = all_samples[all_samples["Project"] == "Control"].copy()
+    return header_section, samples_info, controls_info
 
 def load_sample_dataframe(manifest_data):
     """Extract the sample data from the manifest and convert it to a DataFrame."""
@@ -45,11 +48,8 @@ def reverse_complement_index(index):
 def main(manifest_path, project, swap, rc1, rc2, add_sample):
     """Main function to fix the samplesheet indexes for AVITI runs."""
     # Read the samplesheet
-    manifest_header, manifest_data = load_manifest(manifest_path)
-    
-    # Read the sample data into a data frame (look at Element_runs.py for an example)
-    samples_info = load_sample_dataframe(manifest_data)
-    
+    manifest_header, samples_info, controls_info = load_manifest(manifest_path)    
+
     # Process the indexes based on the options provided
     if project:
         mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] == project)
@@ -62,6 +62,9 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
         samples_info.loc[mask, 'Index2'] = samples_info.loc[mask, 'Index2'].apply(reverse_complement_index)
     if swap:
         samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
+    if rc1 or rc2 or swap:
+        # Update lims_label if any changes were made unless the "Project" column is not "Control"
+        samples_info.loc[mask, 'lims_label'] = samples_info.loc[mask, 'Index1'] + '-' + samples_info.loc[mask, 'Index2']
     for additional_sample in add_sample:
         if os.path.isfile(additional_sample):
             # If a file is provided, read it and append to the samples_info DataFrame
@@ -77,7 +80,7 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
     samples_info.sort_values(by=['Lane', 'SampleName'], inplace=True)
    
     # Generate the updated samplesheet
-    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True)
+    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True) + controls_info.to_csv(index=False, header=False)
    
     # Write the updated samplesheet to a new file
     output_path = manifest_path.replace('.csv', '_updated.csv')

From cf6c88470091c96d1ed92ca6dd1d9af8b3d97949 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 10:53:24 +0200
Subject: [PATCH 05/13] print progress

---
 aviti_index_fixer.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index f45a752..e665502 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -58,10 +58,13 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
 
     if rc1:
         samples_info.loc[mask, 'Index1'] = samples_info.loc[mask, 'Index1'].apply(reverse_complement_index)
+        print("Reverse complementing Index1")
     if rc2:
         samples_info.loc[mask, 'Index2'] = samples_info.loc[mask, 'Index2'].apply(reverse_complement_index)
+        print("Reverse complementing Index2")
     if swap:
         samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
+        print("Swapping Index1 and Index2")
     if rc1 or rc2 or swap:
         # Update lims_label if any changes were made unless the "Project" column is not "Control"
         samples_info.loc[mask, 'lims_label'] = samples_info.loc[mask, 'Index1'] + '-' + samples_info.loc[mask, 'Index2']
@@ -74,6 +77,10 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
             # If a sample is provided directly, create a DataFrame from it
             additional_samples = pd.DataFrame([additional_sample.split(',')], columns=samples_info.columns)
         samples_info = pd.concat([samples_info, additional_samples], ignore_index=True)
+        if len(additional_samples) == 1:
+            print("Adding additional sample:", additional_samples['SampleName'].tolist()[0])
+        else:
+            print("Adding additional samples:", (", ").join(additional_samples['SampleName'].tolist()))
 
     # Sort the samples by lane and SampleName
     samples_info['Lane'] = samples_info['Lane'].astype(int)

From 5f6592d151ba6edbea32758056f9bcf1bbdde8e7 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:01:32 +0200
Subject: [PATCH 06/13] Allow for multiple projects to be specified

---
 aviti_index_fixer.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index e665502..57f52e9 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -17,7 +17,7 @@ def load_manifest(path):
     samples_section = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
     all_samples = load_sample_dataframe(samples_section)
     samples_info = all_samples[all_samples["Project"] != "Control"].copy()
-    controls_info = all_samples[all_samples["Project"] == "Control"].copy()
+    controls_info = all_samples[all_samples["Project"] == "Control"].copy() # So that we don't apply any changes to control samples
     return header_section, samples_info, controls_info
 
 def load_sample_dataframe(manifest_data):
@@ -39,7 +39,7 @@ def reverse_complement_index(index):
 
 @cli.command()
 @cli.option('--manifest_path', required=True, help='Path to the sample manifest. e.g. ~/fc/AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv')
-@cli.option('--project', required=False, help='Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed')
+@cli.option('--project', multiple=True, required=False, help='Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed. Use multiple times for multiple projects.')
 @cli.option('--swap', is_flag=True, help='Swaps index 1 and 2.')
 @cli.option('--rc1', is_flag=True, help='Exchanges index 1 for its reverse compliment.')
 @cli.option('--rc2', is_flag=True, help='Exchanges index 2 for its reverse compliment.')
@@ -52,7 +52,7 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
 
     # Process the indexes based on the options provided
     if project:
-        mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] == project)
+        mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] in project)
     else:
         mask = pd.Series([True] * len(samples_info))
 
@@ -66,7 +66,7 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
         samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
         print("Swapping Index1 and Index2")
     if rc1 or rc2 or swap:
-        # Update lims_label if any changes were made unless the "Project" column is not "Control"
+        # Update lims_label if any changes were made
         samples_info.loc[mask, 'lims_label'] = samples_info.loc[mask, 'Index1'] + '-' + samples_info.loc[mask, 'Index2']
     for additional_sample in add_sample:
         if os.path.isfile(additional_sample):

From cc8bdd57b5b05e70ef57a0146a3b5fb154581bd3 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:25:01 +0200
Subject: [PATCH 07/13] Cleanup

---
 aviti_index_fixer.py | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index 57f52e9..2ee4c60 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -1,27 +1,30 @@
+import os
 import click as cli
 import pandas as pd
-import os
 
 NT_COMPLIMENT = {
     'A': 'T',
     'T': 'A',
     'C': 'G',
-    'G': 'C'
+    'G': 'C',
 }
 
 def load_manifest(path):
     """Load the manifest from the given path."""
     with open(path, 'r') as file:
         manifest_content = file.read()
+        
     header_section = manifest_content.split("[SAMPLES]")[0]
     samples_section = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
+    
     all_samples = load_sample_dataframe(samples_section)
     samples_info = all_samples[all_samples["Project"] != "Control"].copy()
     controls_info = all_samples[all_samples["Project"] == "Control"].copy() # So that we don't apply any changes to control samples
+    
     return header_section, samples_info, controls_info
 
 def load_sample_dataframe(manifest_data):
-    """Extract the sample data from the manifest and convert it to a DataFrame."""
+    """Load the sample data into a DataFrame."""
     header = manifest_data[0]
     sample_rows = manifest_data[1:]
 
@@ -47,10 +50,8 @@ def reverse_complement_index(index):
 
 def main(manifest_path, project, swap, rc1, rc2, add_sample):
     """Main function to fix the samplesheet indexes for AVITI runs."""
-    # Read the samplesheet
     manifest_header, samples_info, controls_info = load_manifest(manifest_path)    
 
-    # Process the indexes based on the options provided
     if project:
         mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] in project)
     else:
@@ -70,11 +71,9 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
         samples_info.loc[mask, 'lims_label'] = samples_info.loc[mask, 'Index1'] + '-' + samples_info.loc[mask, 'Index2']
     for additional_sample in add_sample:
         if os.path.isfile(additional_sample):
-            # If a file is provided, read it and append to the samples_info DataFrame
             additional_samples = pd.read_csv(additional_sample, header=None)
             additional_samples.columns = samples_info.columns
         else:
-            # If a sample is provided directly, create a DataFrame from it
             additional_samples = pd.DataFrame([additional_sample.split(',')], columns=samples_info.columns)
         samples_info = pd.concat([samples_info, additional_samples], ignore_index=True)
         if len(additional_samples) == 1:
@@ -82,14 +81,10 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
         else:
             print("Adding additional samples:", (", ").join(additional_samples['SampleName'].tolist()))
 
-    # Sort the samples by lane and SampleName
     samples_info['Lane'] = samples_info['Lane'].astype(int)
     samples_info.sort_values(by=['Lane', 'SampleName'], inplace=True)
    
-    # Generate the updated samplesheet
     updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True) + controls_info.to_csv(index=False, header=False)
-   
-    # Write the updated samplesheet to a new file
     output_path = manifest_path.replace('.csv', '_updated.csv')
     with open(output_path, 'w') as output_file:
         output_file.write(updated_samplesheet)

From b3078b8a9450a8cb8057920ebac79fa8ba36f87d Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:38:50 +0200
Subject: [PATCH 08/13] Add aviti_index_fixer to README

---
 README.md | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/README.md b/README.md
index ae52508..0dbe420 100755
--- a/README.md
+++ b/README.md
@@ -2,6 +2,24 @@
 
 Repository to store standalone scripts that do not belong to any bigger package or repository.
 
+### aviti_index_fixer.py
+Given a run manifest for Aviti, it generates a new one with the provided command line options. The new manifest will be output in the same place as the old, with the extension '_updated.csv'.
+
+#### Usage
+Examples:
+- Reverse complement index 1 and 2 for project P12345 and P67890:
+`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890`
+- Swap indexes for all samples in the manifest:
+`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap`
+- Include additional samples to the manifest, specifying the samples on the commandline:
+`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"`
+- Include additional samples to the manifest, specifying the samples in a csv file (each line in the file needs to have the same format as in the manifest):
+`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv`
+
+#### Dependencies
+
+* click
+* pandas
 
 ### compute_undet_index_stats.py
 used to fetch stats about undermined indexes.

From 598299bbd995833a7a2b7236c9e8d033350f8d39 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:40:11 +0200
Subject: [PATCH 09/13] improve code blocks

---
 README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 0dbe420..44975c4 100755
--- a/README.md
+++ b/README.md
@@ -8,13 +8,13 @@ Given a run manifest for Aviti, it generates a new one with the provided command
 #### Usage
 Examples:
 - Reverse complement index 1 and 2 for project P12345 and P67890:
-`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890`
+```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890```
 - Swap indexes for all samples in the manifest:
-`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap`
+```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap```
 - Include additional samples to the manifest, specifying the samples on the commandline:
-`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"`
+```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"```
 - Include additional samples to the manifest, specifying the samples in a csv file (each line in the file needs to have the same format as in the manifest):
-`python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv`
+```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv```
 
 #### Dependencies
 

From aa480203963b52b332c41a062ea8ec2b90d7d736 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:41:07 +0200
Subject: [PATCH 10/13] Improve improved code blocks

---
 README.md | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/README.md b/README.md
index 44975c4..b01204b 100755
--- a/README.md
+++ b/README.md
@@ -8,12 +8,19 @@ Given a run manifest for Aviti, it generates a new one with the provided command
 #### Usage
 Examples:
 - Reverse complement index 1 and 2 for project P12345 and P67890:
+
 ```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890```
+
 - Swap indexes for all samples in the manifest:
+
 ```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap```
+
 - Include additional samples to the manifest, specifying the samples on the commandline:
+
 ```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"```
+
 - Include additional samples to the manifest, specifying the samples in a csv file (each line in the file needs to have the same format as in the manifest):
+
 ```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv```
 
 #### Dependencies

From 91bc9c03ac42ab4c59f0a66dbfd85fef19dbbf38 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 11:42:18 +0200
Subject: [PATCH 11/13] Code blocks, again...

---
 README.md | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index b01204b..6fceea3 100755
--- a/README.md
+++ b/README.md
@@ -8,20 +8,21 @@ Given a run manifest for Aviti, it generates a new one with the provided command
 #### Usage
 Examples:
 - Reverse complement index 1 and 2 for project P12345 and P67890:
-
-```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890```
-
+```
+python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --rc1 --rc2 --project P12345 --project P67890
+```
 - Swap indexes for all samples in the manifest:
-
-```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap```
-
+```
+python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --swap
+```
 - Include additional samples to the manifest, specifying the samples on the commandline:
-
-```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"```
-
+```
+python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample "P12345_1097,ATAC,AGGC,1,A__Project_25_16,301-10-10-301,ATAC-AGGC," --add_sample "P12345_1098,GTAC,GGGC,1,A__Project_25_16,301-10-10-301,GTAC-GGGC,"
+```
 - Include additional samples to the manifest, specifying the samples in a csv file (each line in the file needs to have the same format as in the manifest):
-
-```python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv```
+```
+python aviti_index_fixer.py --manifest_path AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv --add_sample samples.csv
+```
 
 #### Dependencies
 

From d2e786b648fcea9f2b4c4a204c449a931ecc718e Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Thu, 14 Aug 2025 13:20:37 +0200
Subject: [PATCH 12/13] ruff formatting

---
 aviti_index_fixer.py | 108 +++++++++++++++++++++++++++++--------------
 1 file changed, 74 insertions(+), 34 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index 2ee4c60..1a2e085 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -3,26 +3,30 @@
 import pandas as pd
 
 NT_COMPLIMENT = {
-    'A': 'T',
-    'T': 'A',
-    'C': 'G',
-    'G': 'C',
+    "A": "T",
+    "T": "A",
+    "C": "G",
+    "G": "C",
 }
 
+
 def load_manifest(path):
     """Load the manifest from the given path."""
-    with open(path, 'r') as file:
+    with open(path, "r") as file:
         manifest_content = file.read()
-        
+
     header_section = manifest_content.split("[SAMPLES]")[0]
     samples_section = manifest_content.split("[SAMPLES]")[1].strip().split("\n")
-    
+
     all_samples = load_sample_dataframe(samples_section)
     samples_info = all_samples[all_samples["Project"] != "Control"].copy()
-    controls_info = all_samples[all_samples["Project"] == "Control"].copy() # So that we don't apply any changes to control samples
-    
+    controls_info = all_samples[
+        all_samples["Project"] == "Control"
+    ].copy()  # So that we don't apply any changes to control samples
+
     return header_section, samples_info, controls_info
 
+
 def load_sample_dataframe(manifest_data):
     """Load the sample data into a DataFrame."""
     header = manifest_data[0]
@@ -36,58 +40,94 @@ def load_sample_dataframe(manifest_data):
     samples_info = pd.DataFrame.from_dict(sample_dicts)
     return samples_info
 
+
 def reverse_complement_index(index):
     """Return the reverse complement of a given index."""
-    return ''.join(NT_COMPLIMENT[nuc] for nuc in reversed(index))
+    return "".join(NT_COMPLIMENT[nuc] for nuc in reversed(index))
 
-@cli.command()
-@cli.option('--manifest_path', required=True, help='Path to the sample manifest. e.g. ~/fc/AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv')
-@cli.option('--project', multiple=True, required=False, help='Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed. Use multiple times for multiple projects.')
-@cli.option('--swap', is_flag=True, help='Swaps index 1 and 2.')
-@cli.option('--rc1', is_flag=True, help='Exchanges index 1 for its reverse compliment.')
-@cli.option('--rc2', is_flag=True, help='Exchanges index 2 for its reverse compliment.')
-@cli.option('--add_sample', multiple=True, help='Include additional sample(s). Use multiple times for multiple samples, or provide a file. Each new sample should have the same format as in the existing manifest. Example: --add_sample P12345,ATCG,CGTA,1,A__Project_25_16,301-10-10-301,ATCG-CGTA,')
 
+@cli.command()
+@cli.option(
+    "--manifest_path",
+    required=True,
+    help="Path to the sample manifest. e.g. ~/fc/AVITI_run_manifest_2450545934_24-1214961_250722_154957_EunkyoungChoi_untrimmed.csv",
+)
+@cli.option(
+    "--project",
+    multiple=True,
+    required=False,
+    help="Project ID, e.g. P10001. Only the indexes of samples with this specific project ID will be changed. Use multiple times for multiple projects.",
+)
+@cli.option("--swap", is_flag=True, help="Swaps index 1 and 2.")
+@cli.option("--rc1", is_flag=True, help="Exchanges index 1 for its reverse compliment.")
+@cli.option("--rc2", is_flag=True, help="Exchanges index 2 for its reverse compliment.")
+@cli.option(
+    "--add_sample",
+    multiple=True,
+    help="Include additional sample(s). Use multiple times for multiple samples, or provide a file. Each new sample should have the same format as in the existing manifest. Example: --add_sample P12345,ATCG,CGTA,1,A__Project_25_16,301-10-10-301,ATCG-CGTA,",
+)
 def main(manifest_path, project, swap, rc1, rc2, add_sample):
     """Main function to fix the samplesheet indexes for AVITI runs."""
-    manifest_header, samples_info, controls_info = load_manifest(manifest_path)    
+    manifest_header, samples_info, controls_info = load_manifest(manifest_path)
 
     if project:
-        mask = samples_info['SampleName'].apply(lambda x: x.split("_")[0] in project)
+        mask = samples_info["SampleName"].apply(lambda x: x.split("_")[0] in project)
     else:
         mask = pd.Series([True] * len(samples_info))
 
     if rc1:
-        samples_info.loc[mask, 'Index1'] = samples_info.loc[mask, 'Index1'].apply(reverse_complement_index)
+        samples_info.loc[mask, "Index1"] = samples_info.loc[mask, "Index1"].apply(
+            reverse_complement_index
+        )
         print("Reverse complementing Index1")
     if rc2:
-        samples_info.loc[mask, 'Index2'] = samples_info.loc[mask, 'Index2'].apply(reverse_complement_index)
+        samples_info.loc[mask, "Index2"] = samples_info.loc[mask, "Index2"].apply(
+            reverse_complement_index
+        )
         print("Reverse complementing Index2")
     if swap:
-        samples_info.loc[mask, ['Index1', 'Index2']] = samples_info.loc[mask, ['Index2', 'Index1']].values
+        samples_info.loc[mask, ["Index1", "Index2"]] = samples_info.loc[
+            mask, ["Index2", "Index1"]
+        ].values
         print("Swapping Index1 and Index2")
     if rc1 or rc2 or swap:
         # Update lims_label if any changes were made
-        samples_info.loc[mask, 'lims_label'] = samples_info.loc[mask, 'Index1'] + '-' + samples_info.loc[mask, 'Index2']
+        samples_info.loc[mask, "lims_label"] = (
+            samples_info.loc[mask, "Index1"] + "-" + samples_info.loc[mask, "Index2"]
+        )
     for additional_sample in add_sample:
         if os.path.isfile(additional_sample):
             additional_samples = pd.read_csv(additional_sample, header=None)
             additional_samples.columns = samples_info.columns
         else:
-            additional_samples = pd.DataFrame([additional_sample.split(',')], columns=samples_info.columns)
+            additional_samples = pd.DataFrame(
+                [additional_sample.split(",")], columns=samples_info.columns
+            )
         samples_info = pd.concat([samples_info, additional_samples], ignore_index=True)
         if len(additional_samples) == 1:
-            print("Adding additional sample:", additional_samples['SampleName'].tolist()[0])
+            print(
+                "Adding additional sample:",
+                additional_samples["SampleName"].tolist()[0],
+            )
         else:
-            print("Adding additional samples:", (", ").join(additional_samples['SampleName'].tolist()))
-
-    samples_info['Lane'] = samples_info['Lane'].astype(int)
-    samples_info.sort_values(by=['Lane', 'SampleName'], inplace=True)
-   
-    updated_samplesheet = manifest_header + "\n[SAMPLES]\n" + samples_info.to_csv(index=False, header=True) + controls_info.to_csv(index=False, header=False)
-    output_path = manifest_path.replace('.csv', '_updated.csv')
-    with open(output_path, 'w') as output_file:
+            print(
+                "Adding additional samples:",
+                (", ").join(additional_samples["SampleName"].tolist()),
+            )
+
+    samples_info["Lane"] = samples_info["Lane"].astype(int)
+    samples_info.sort_values(by=["Lane", "SampleName"], inplace=True)
+
+    updated_samplesheet = (
+        manifest_header
+        + "\n[SAMPLES]\n"
+        + samples_info.to_csv(index=False, header=True)
+        + controls_info.to_csv(index=False, header=False)
+    )
+    output_path = manifest_path.replace(".csv", "_updated.csv")
+    with open(output_path, "w") as output_file:
         output_file.write(updated_samplesheet)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     main()

From 9729e6f3ef05d64ce635b54f9ac2d17e2161c748 Mon Sep 17 00:00:00 2001
From: Sara Sjunnebo <sara.sjunnebo@gmail.com>
Date: Tue, 19 Aug 2025 11:17:30 +0200
Subject: [PATCH 13/13] Make printed output useable running notes

---
 aviti_index_fixer.py | 72 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 60 insertions(+), 12 deletions(-)

diff --git a/aviti_index_fixer.py b/aviti_index_fixer.py
index 1a2e085..e2841c3 100644
--- a/aviti_index_fixer.py
+++ b/aviti_index_fixer.py
@@ -46,6 +46,33 @@ def reverse_complement_index(index):
     return "".join(NT_COMPLIMENT[nuc] for nuc in reversed(index))
 
 
+def print_running_note(project, change_type):
+    """Print a note about the changes being made."""
+    if project:
+        project_text = "project " if len(project) == 1 else "projects "
+        project_text += (
+            project[0]
+            if len(project) == 1
+            else " and ".join(project)
+            if len(project) == 2
+            else ", ".join(project)
+        )
+    else:
+        project_text = "all samples"
+    if change_type == "swap":
+        print(
+            f"Index 1 and 2 in {project_text} were switched prior to re-demultiplexing."
+        )
+    elif change_type == "rc1":
+        print(
+            f"Index 1 in {project_text} was converted to reverse complement prior to re-demultiplexing."
+        )
+    elif change_type == "rc2":
+        print(
+            f"Index 2 in {project_text} was converted to reverse complement prior to re-demultiplexing",
+        )
+
+
 @cli.command()
 @cli.option(
     "--manifest_path",
@@ -79,41 +106,62 @@ def main(manifest_path, project, swap, rc1, rc2, add_sample):
         samples_info.loc[mask, "Index1"] = samples_info.loc[mask, "Index1"].apply(
             reverse_complement_index
         )
-        print("Reverse complementing Index1")
+        print_running_note(project, "rc1")
     if rc2:
         samples_info.loc[mask, "Index2"] = samples_info.loc[mask, "Index2"].apply(
             reverse_complement_index
         )
-        print("Reverse complementing Index2")
+        print_running_note(project, "rc2")
     if swap:
         samples_info.loc[mask, ["Index1", "Index2"]] = samples_info.loc[
             mask, ["Index2", "Index1"]
         ].values
-        print("Swapping Index1 and Index2")
+        print_running_note(project, "swap")
+
     if rc1 or rc2 or swap:
         # Update lims_label if any changes were made
         samples_info.loc[mask, "lims_label"] = (
             samples_info.loc[mask, "Index1"] + "-" + samples_info.loc[mask, "Index2"]
         )
+
+    additional_samples_table = {}
     for additional_sample in add_sample:
         if os.path.isfile(additional_sample):
             additional_samples = pd.read_csv(additional_sample, header=None)
             additional_samples.columns = samples_info.columns
+            for _, row in additional_samples.iterrows():
+                additional_samples_table[row["SampleName"]] = {
+                    "index": f"{row['Index1']}-{row['Index2']}",
+                    "lane": row["Lane"],
+                }
         else:
             additional_samples = pd.DataFrame(
                 [additional_sample.split(",")], columns=samples_info.columns
             )
+            additional_samples_table[additional_samples["SampleName"].tolist()[0]] = {
+                "index": f"{additional_samples['Index1'].tolist()[0]}-{additional_samples['Index2'].tolist()[0]}",
+                "lane": additional_samples["Lane"].tolist()[0],
+            }
         samples_info = pd.concat([samples_info, additional_samples], ignore_index=True)
-        if len(additional_samples) == 1:
-            print(
-                "Adding additional sample:",
-                additional_samples["SampleName"].tolist()[0],
-            )
-        else:
-            print(
-                "Adding additional samples:",
-                (", ").join(additional_samples["SampleName"].tolist()),
+    if len(additional_samples_table) == 1:
+        sample_name = list(additional_samples_table.keys())[0]
+        print(
+            f"Sample {sample_name} with indexes",
+            f"{additional_samples_table[sample_name]['index']}",
+            f"was added to lane {additional_samples_table[sample_name]['lane']}",
+            "prior to re-demultiplexing.",
+        )
+    elif len(additional_samples_table) > 1:
+        print(
+            "The following samples were added to the manifest prior to re-demultiplexing:\n"
+            "SampleName, Index1-Index2, Lane\n"
+            + "\n".join(
+                [
+                    f"{name}, {info['index']}, {info['lane']}"
+                    for name, info in additional_samples_table.items()
+                ]
             )
+        )
 
     samples_info["Lane"] = samples_info["Lane"].astype(int)
     samples_info.sort_values(by=["Lane", "SampleName"], inplace=True)