mohammedkhalfan

#!/bin/sh
#
#SBATCH --verbose
#SBATCH --job-name=rnaseq
#SBATCH --output=rnaseq.o%j
#SBATCH --error=rnaseq.e%j
#SBATCH --time=72:00:00
#SBATCH --nodes=1
#SBATCH --tasks-per-node=1
#SBATCH --cpus-per-task=4

mohammedkhalfan

import os
import random
import gzip
import sys
from multiprocessing import Pool

# Parameters
input_dir = sys.argv[1]
output_dir = os.path.join(input_dir, "small")
downsample_ratio = 0.01  # Replace with the desired downsample ratio

mohammedkhalfan

group,replicate,fastq_1,fastq_2,strandedness
control,1,/path/to/S1_L002_R1_001.fastq.gz,/path/to/S1_L002_R2_001.fastq.gz,unstranded
control,2,/path/to/S2_L002_R1_001.fastq.gz,/path/to/S2_L002_R2_001.fastq.gz,unstranded
control,3,/path/to/S3_L002_R1_001.fastq.gz,/path/to/S3_L002_R2_001.fastq.gz,unstranded
treatment,1,/path/to/S4_L003_R1_001.fastq.gz,,unstranded
treatment,2,/path/to/S5_L003_R1_001.fastq.gz,,unstranded
treatment,3,/path/to/S6_L003_R1_001.fastq.gz,,unstranded
treatment,3,/path/to/S6_L004_R1_001.fastq.gz,,unstranded

mohammedkhalfan

// Set these five params at a minimum
params.input = 'samplesheet.csv'
params.fasta = '/scratch/work/cgsb/genomes/Public/Vertebrate_mammalian/Homo_sapiens/Ensembl/GRCh38.p10/Homo_sapiens.GRCh38.dna.toplevel.fa'
params.gtf = '/scratch/work/cgsb/genomes/Public/Vertebrate_mammalian/Homo_sapiens/Ensembl/GRCh38.p10/Homo_sapiens.GRCh38.88.gtf'
out_root = '/scratch/netID/rnaseq_project'
params.email = 'netID@nyu.edu'

// Only make changes below if required
params.outdir = out_root + '/results'
workDir = out_root + '/nextflow_work'

mohammedkhalfan

## Usage: python3 count-barcode-freq.py <fastq_file.gz>
## Example: python3 count-barcode-freq.py sample.fastq.gz
from operator import itemgetter
import sys, gzip

barcodes = {}
with gzip.open(sys.argv[1]) as fastq:
        for line in fastq:
                if not line.startswith(b'@'): continue
                bc = line.decode("utf-8").split(':')[-1].strip()

mohammedkhalfan

{
	"fasta": [{
		"name": "Bowtie2 Index",
		"extensions": [".1.bt2", ".2.bt2", ".3.bt2", ".4.bt2", ".rev.2.bt2", ".rev.1.bt2"],
		"tags": "alignment, tophat, rnaseq",
		"modules": ["bowtie2/intel/2.2.9"],
		"command": "bowtie2-build $IN $IN",
		"mem": 64
	},
	{

mohammedkhalfan

{
	"Plant": {
		"Arabidopsis_thaliana": {
			"Ensembl": [{
				"TAIR10": {
					"dna": "ftp://ftp.ensemblgenomes.org/pub/plants/release-34/fasta/arabidopsis_thaliana/dna/Arabidopsis_thaliana.TAIR10.dna.toplevel.fa.gz",
					"gff": "ftp://ftp.ensemblgenomes.org/pub/plants/release-34/gff3/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.34.gff3.gz",
					"gtf": "ftp://ftp.ensemblgenomes.org/pub/plants/release-34/gtf/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.34.gtf.gz"
				},
				"TAIR9-example-other-version--remove-later": {

mohammedkhalfan

## Load required module
from jira.client import JIRA

## Step 1
def jira():
    JIRA_SERVER="https://cbi.abudhabi.nyu.edu/jira"
    
    key_cert='/path/to/private/key.pem'
    with open(key_cert, 'r') as key_cert_file:
        key_cert_data = key_cert_file.read()