From f3116ff874faf007b0060a37aead45bcfb226fa1 Mon Sep 17 00:00:00 2001
From: Auden Cote-L'Heureux <52716489+AudenCote@users.noreply.github.com>
Date: Fri, 26 Jan 2024 11:40:30 -0500
Subject: [PATCH] Updating header in 5b_SummaryStats.py

---
 PTL1/Genomes/Scripts/5b_SummaryStats.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/PTL1/Genomes/Scripts/5b_SummaryStats.py b/PTL1/Genomes/Scripts/5b_SummaryStats.py
index efc0856..f2a9ec1 100644
--- a/PTL1/Genomes/Scripts/5b_SummaryStats.py
+++ b/PTL1/Genomes/Scripts/5b_SummaryStats.py
@@ -1,3 +1,14 @@
+# Last updated Sept 2023
+# Author: Auden Cote-L'Heureux
+
+# This script produces both taxon- and sequence-level statistics to describe the ReadyToGo files
+# output by PhyloToL Part 1, as well as some OG-level information from the Hook (OG reference)
+# database. It relies on the utility script CUB.py to calculate composition statistics (GC content, 
+# Effective Number of Codons, etc.). Both sequence level and taxon-level stats are summarized in tab-separated 
+# outputs written to the Output folder. This script requires that the OG reference database is available as an 
+# amino acid fasta file  in the Databases/db_OG folder with the same file name as the .dmnd file used in script 4. 
+# This script is intended to be run as part of the PhyloToL 6 Part 1 pipeline using the script wrapper.py.
+
 import os, sys
 import argparse
 from Bio import SeqIO