YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 04:00:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updating headers and example commands in wrapper_submit.sh

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2025-01-22 12:56:11 -05:00 committed by GitHub
parent 4f033e8ab2
commit 5284a71ce8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 22 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
PTL1/Transcriptomes/Scripts/wrapper_submit.sh
View File

@ -1,17 +1,23 @@
## Last updated Jan 2025 by Auden Cote-L'Heureux
## This script is intended to be used to process genomic CDS with EukPhylo part 1 on an HPC that uses the Slurm workload manager.
## The first part of the script are Slurm-specific parameters that should be adjusted by users to fit their resource allocation
## needs and restrictions, followed by some example commands taken from the GitHub Wiki, more detail for which can be found
## here: https://github.com/Katzlab/EukPhylo/wiki/EukPhylo-Part-1:-GF-assignment
#!/bin/bash
#
#SBATCH --job-name=PTL1_GBF
#SBATCH --output=PTL1.%j.out # Stdout (%j expands to jobId)
## Slurm specific code
#SBATCH --job-name=EukPhylo
#SBATCH --output=EukPhylo.%j.out # Stdout (%j expands to jobId)
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --ntasks-per-node=64 # #change to number of srun when running multiple instances
#SBATCH --mem=160G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=YOUREMAIL@smith.edu
module purge #Cleans up any loaded modules
module use /gridapps/modules/all #make sure module locations is loaded
module load slurm
module load tqdm/4.62.3-GCCcore-11.2.0
module load Biopython/1.79-foss-2021b
@ -19,11 +25,12 @@ module load BLAST+/2.12.0-gompi-2021b
module load DIAMOND/2.0.13-GCC-11.2.0
module load VSEARCH/2.22.1-GCC-11.3.0
parent='/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams/'
parent='/Your/Home/Folder'
srun -D ${parent}Scripts python3 ${parent}Scripts/wrapper.py -1 1 -2 7 -x --assembled_transcripts ${parent}AssembledTranscripts -o ${parent} -n ${parent}Conspecific.txt --genetic_code Universal &
#srun -D ${parent}Scripts python3 ${parent}Scripts/wrapper.py -1 1 -2 7 -x --assembled_transcripts ${parent}Assembled_Transcripts -o ${parent} -n ${parent}Conspecific.txt --genetic_code ${parent}Gcodes.txt > log.out &
#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 2 -2 7 -x --assembled_transcripts ${parent}Plate7/Assembled_Transcripts -o ${parent}Plate7 -n ${parent}Plate7/Conspecific.txt --genetic_code ${parent}Plate7/Gcodes.txt &
#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 1 -2 7 -x --assembled_transcripts ${parent}Plate11/Assembled_Transcripts -o ${parent}Plate11 -n ${parent}Plate11/Conspecific.txt --genetic_code ${parent}Plate11/Gcodes.txt &
#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 2 -2 7 -x --assembled_transcripts ${parent}Plate18/Assembled_Transcripts -o ${parent}Plate18 -n ${parent}Plate18/Conspecific.txt --genetic_code ${parent}Plate18/Gcodes.txt &
wait
## Example commands
# A simple run that goes from script 1 to script 7 (the last script) using the Universal genetic code
srun -D ${parent}Scripts python3 ${parent}Scripts/wrapper.py --first_script 1 --last_script 7 --assembled_transcripts ${parent}AssembledTranscripts --genetic_code ${parent}Gcode.txt --databases ${parent}Databases > log.txt
# Including the cross-plate contamination step, using conspecific names
srun -D ${parent} python3 ${parent}Scripts/wrapper.py --first_script 1 --last_script 7 --assembled_transcripts ${parent}AssembledTranscripts --output . --genetic_code ${parent}Gcode.txt --databases ${parent}Databases --xplate_contam --conspecific_names ${parent}Conspecific.txt > log.txt