From a559f61567a0cd9f3e3f5c19f5c4e0ee1507a39d Mon Sep 17 00:00:00 2001
From: Auden Cote-L'Heureux <52716489+AudenCote@users.noreply.github.com>
Date: Wed, 22 Jan 2025 12:28:04 -0500
Subject: [PATCH] Generalizing and adding examples to run_eukphylo.sh

---
 PTL2/run_eukphylo.sh | 64 +++++++++++++++++++++++---------------------
 1 file changed, 33 insertions(+), 31 deletions(-)

diff --git a/PTL2/run_eukphylo.sh b/PTL2/run_eukphylo.sh
index b5151ec..b63c485 100644
--- a/PTL2/run_eukphylo.sh
+++ b/PTL2/run_eukphylo.sh
@@ -1,18 +1,23 @@
-###GA 11/11/24
-###Updated run script to include grid and unity commands. 
-###The first block of code is specific to the grid. The second block is specific to unity. Pick one and delete the other.
+## Last updated Jan 2025 by Auden Cote-L'Heureux
+
+## This shell script is used for running EukPhylo part 2, and includes a general setup for use on an HPC that uses 
+## the Slurm workload manager. It also includes several example run commands, which correspond to examples explained in more detail in the 
+## EukPhylo Wiki (https://github.com/Katzlab/EukPhylo/wiki/EukPhylo-Part-2:-MSAs,-trees,-and-contamination-loop).
+## These run commands can also be copied and run in the terminal / command line separately, without a shell script.
+
 
 #!/bin/bash
-#SBATCH --job-name=GA1 # Job name
-#SBATCH --output=Run_phylotol.%j.out # Stdout (%j expands to jobId)
-#SBATCH --mail-type=ALL
-#SBATCH --mail-user=youremail@smith.edu ##add your email address
 
+## SLURM-SPECIFIC SETUP BELOW
 
-
-###Grid start
+#SBATCH --job-name=EukPhylo # Job name
+#SBATCH --output=Run_EukPhylo.%j.out # Stdout (%j expands to jobId)
 #SBATCH --nodes=1
-#SBATCH --ntasks=10 ##change this to be double the number of task/batches you want to launch
+#SBATCH --ntasks=10 ## On the Smith College HPC (Grid), we have to change this to be double the number of task/batches you want to launch
+#SBATCH -c 24 # Number of Cores per Task
+#SBATCH --mem=125G # Requested Memory
+#SBATCH -q long # Partition. Only use this on certain HPCs (e.g., Unity at UMass).
+#SBATCH -t 336:00:00 # Job time limit
 
 module purge       #Cleans up any loaded modules
 module use /gridapps/modules/all    #make sure module locations is loaded
@@ -25,26 +30,23 @@ module load RAxML
 module load IQ-TREE/2.1.2-gompi-2021b
 module load tqdm/4.64.1-GCCcore-12.2.0
 module load Python/3.9.6-GCCcore-11.2.0
-export PATH=$PATH:/beegfs/fast/katzlab/grid_phylotol_setup/programs/standard-RAxML-master
-parent='/beegfs/fast/katzlab/' #add your path starting with the name of your folder, should begin with /beegfs/fast/katzlab/
-#if you are running batches, you need an srun line for each batch!
-srun --exact -n 1 -D ${parent} python3 ${parent}Scripts/eukphylo.py --similarity_filter --sim_cutoff 0.95 --sim_taxa sim_taxa.txt --blacklist GuidanceRemovedSeqs_allConservedRuns_ML_nov_dec_2023.txt --start raw --end trees --gf_list B1_listofOGs.txt --taxon_list taxon_list.txt --data OutgroupR2Gs --output ${parent}Output_folder_B1 > Output_folder_B1.out &
-wait
-###Grid end
+export PATH=$PATH:/Path/To/Executable/Files
+
+parent='/Your/Home/Folder/' # The folder where you are running EukPhylo (this should contain the Scripts and input data folders
+
+## RUN COMMANDS BELOW
+
+# A simple run of part 2, starting from ReadyToGo files and running through tree building
+srun --exact -n 1 -D ${parent} python3 ${parent}Scripts/eukphylo.py --start raw --end trees --gf_list  ${parent}listofOGs.txt --taxon_list ${parent}taxon_list.txt --data ${parent}Input_folder --output ${parent}Output_folder
+
+# Another example run starting from ReadyToGo files and running through tree building, with the commonly used similarity filter cutoff, blacklist, and  "sim_taxa_list" arguments (see Wiki)
+srun --exact -n 1 -D ${parent} python3 ${parent}Scripts/eukphylo.py --start raw --end trees --gf_list  ${parent}listofOGs.txt --taxon_list ${parent}taxon_list.txt --data ${parent}Input_folder --output ${parent}Output_folder --similarity_filter --blacklist ${parent}Blacklist.txt --sim_cutoff 0.99 --sim_taxa sim_taxa_list.txt
+
+# An example of running just the concatenation step of part 2, starting from trees
+srun --exact -n 1 -D ${parent} python eukphylo.py --start trees --concatenate --concat_target_taxa Sr_rh --data Output
+
+# See the Wiki (https://github.com/Katzlab/EukPhylo/wiki/EukPhylo-Part-2:-MSAs,-trees,-and-contamination-loop) for more details!
+
+
 
 
-###Unity start
-#SBATCH -c 24 # Number of Cores per Task
-#SBATCH --mem=125G # Requested Memory
-#SBATCH -q long # Partition
-#SBATCH -t 336:00:00 # Job time limit
-module purge       #Cleans up any loaded modules
-module load miniconda/22.11.1-1
-module load mafft/7.481
-module load conda/latest
-conda activate /work/pi_lkatz_smith_edu/Conda_PTL6p2/envs/PTL/
-parent='/work/pi_lkatz_smith_edu/' #add your path startin>
-#if you are running batches, you need an srun line for each batch!
-srun -D ${parent} python3 ${parent}Scripts/eukphylo.py --similarity_filter --sim_cutoff 0.99 ## This line is incomplete
-wait
-###Unity end