YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 03:30:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update run_eukphylo.sh

Browse Source
This commit is contained in:
Adri K. Grow 2025-02-13 18:01:48 -05:00 committed by GitHub
parent 1aebef4725
commit d4f27a3032
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
PTL2/run_eukphylo.sh
View File

@ -1,4 +1,4 @@
## Last updated Jan 2025 by Auden Cote-L'Heureux
## Last updated Jan 2025 by Auden Cote-L'Heureux; modified Feb 2025 by Adri K. Grow
## 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
@ -6,7 +6,7 @@
## These run commands can also be copied and run in the terminal / command line separately, without a shell script.
#!/bin/bash
#!/bin/bash ## DELETE all lines before this to run
## SLURM-SPECIFIC SETUP BELOW
@ -14,11 +14,16 @@
#SBATCH --output=Run_EukPhylo.%j.out # Stdout (%j expands to jobId)
#SBATCH --nodes=1
#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 --mail-type=ALL
#SBATCH --mail-user=email@xxx.edu ##add your email address for job updates
## UMass HPC (Unity) requirements below (DELETE section if not applicable):
#SBATCH --mem=125G # Requested Memory
#SBATCH -q long # Partition. Only use this on certain HPCs (e.g., Unity at UMass).
#SBATCH -c 24 # Number of Cores per Task
#SBATCH -q long # Partition
#SBATCH -t 336:00:00 # Job time limit
#Load required modules
module purge #Cleans up any loaded modules
module use /gridapps/modules/all #make sure module locations is loaded
module load slurm
@ -30,20 +35,22 @@ 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=$PATH:/Path/To/Executable/Files
module load Guidance_mid #Smith College HPC specific
parent='/Your/Home/Folder/' # The folder where you are running EukPhylo (this should contain the Scripts and input data folders
#export PATH=$PATH:/Path/To/Executable/Files
## RUN COMMANDS BELOW
parent='/Your/Home/Folder/' # The folder where you are running EukPhylo (this should contain the Scripts and input data folders)
## EXAMPLE 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
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 > Output.out
# 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
# Another example 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 > Output.out
# 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
srun --exact -n 1 -D ${parent} python3 ${parent}Scripts/eukphylo.py --start trees --concatenate --concat_target_taxa Sr_rh --data ${parent}Output > log.out
# See the Wiki (https://github.com/Katzlab/EukPhylo/wiki/EukPhylo-Part-2:-MSAs,-trees,-and-contamination-loop) for more details!