johnbowes

## positional_duplicates.py
#!/usr/bin/python

import sys
import pandas as pd
import numpy as np

# arguments are fixed in the following format:
lmiss_file = sys.argv[1]
bim_file = sys.argv[2]
output_file = sys.argv[3]

## king.py
#!/usr/bin/python

# Run KING to generate sample QC and IBD summary stats
# ./king_1.9 -b <data>.bed --bysample --prefix <prefix_for_output>
# ./king_1.9 -b <data>.bed --kinship --related --degree 2 --prefix <prefix_for_output>
#
# Run this script to create a list of exclusions (member of pair with least data will be excluded)
# python king.py --prefix <prefix_for_output> --out <output_file_name>

# Add error if no samples in kinship file.

## effect_estimate_comp.R
setwd("C:/Users/mdeasjdb/Dropbox/PsA_immunochip/effect_comparison")

# format known associtions table - this contains a link between the two results sets and r2
xref <- read.csv(file="psoriasis_known_loci.txt", header=TRUE)
colnames(xref)[6] <- 'xref_study_snp'
colnames(xref)[1] <- 'xref_tsoi_snp'
xref <- subset(xref, select=c('xref_study_snp', 'xref_tsoi_snp', 'ld_rs', 'gene'))
xref$ld_rs[is.na(xref$ld_rs)] <- 1
xref$ld <- as.numeric(as.character(xref$ld_rs))

## snp2hla_formatter.py
#!/usr/bin/python

import sys
import os
import glob
import pandas as pd
import numpy as np
import argparse

# Future improvements

## HumanCoreExome_array_qc.sh
#!/bin/bash

module load apps/binapps/anaconda/2.1.0
module load apps/gcc/R/3.1.0

# clean data threshold variables.
SNP_MISS_THRESH=0.02            # threshold for SNP missing rate
SNP_MAF_THRESH=0.01             # threshold for minor allele
SNP_HWE_THRESH=1e-3             # threshold for HWE
SNP_HWE_GROUP='ALL'           # define within which group to calculate HWE

## shapeit2_phasing_array.sh
#!/bin/bash
## Inherit user environment from the login node
#$ -V
## Use the current directory as the working directory for SGE output and determining paths to files
#$ -cwd
## Request parallel environment and a number cores
#$ -pe smp.pe 12
##
## create an array
#$ -t 1-22

## impute2_job_array.sh
#!/bin/bash

#$ -S /bin/bash
##
## Inherit user environment from the login node
#$ -V
##
## Use the current directory as the working directory for SGE output and determining paths to files
#$ -cwd
##

## impute2_job.sh
#!/bin/bash

CHR=$1
INTERVAL_START=`printf "%.0f" $2`
INTERVAL_END=`printf "%.0f" $3`
INTERVAL=`printf "%03d" $4`

# directories
NAME="impute_test_data_hg19"
OUTPUT_DIR="/mnt/iusers01/jw01/mdeasjdb/scratch/impute_practice/"

## hg19_5mb_interval.list
1 10583 5010583	1
1 5010584 10010584	2
1 10010585 15010585	3
1 15010586 20010586	4
1 20010587 25010587	5
1 25010588 30010588	6
1 30010589 35010589	7
1 35010590 40010590	8
1 40010591 45010591	9
1 45010592 50010592	10

## align_to_reference.sh
#!/bin/bash

# study data details
STUDY=''
DATA_DIR='prepare_data/dataset/'
DATA=${DATA_DIR}${STUDY}"_chr"

# reference data details
REF_DIR='/mnt/iusers01/jw01/jw01-shared-resources/impute2/ref_panel/ALL_1000G_phase1integrated_v3_impute_macGT1/'
	#!/usr/bin/python

	import sys
	import pandas as pd
	import numpy as np

	# arguments are fixed in the following format:
	lmiss_file = sys.argv[1]
	bim_file = sys.argv[2]
	output_file = sys.argv[3]
	#!/usr/bin/python

	# Run KING to generate sample QC and IBD summary stats
	# ./king_1.9 -b <data>.bed --bysample --prefix <prefix_for_output>
	# ./king_1.9 -b <data>.bed --kinship --related --degree 2 --prefix <prefix_for_output>
	#
	# Run this script to create a list of exclusions (member of pair with least data will be excluded)
	# python king.py --prefix <prefix_for_output> --out <output_file_name>

	# Add error if no samples in kinship file.
	setwd("C:/Users/mdeasjdb/Dropbox/PsA_immunochip/effect_comparison")

	# format known associtions table - this contains a link between the two results sets and r2
	xref <- read.csv(file="psoriasis_known_loci.txt", header=TRUE)
	colnames(xref)[6] <- 'xref_study_snp'
	colnames(xref)[1] <- 'xref_tsoi_snp'
	xref <- subset(xref, select=c('xref_study_snp', 'xref_tsoi_snp', 'ld_rs', 'gene'))
	xref$ld_rs[is.na(xref$ld_rs)] <- 1
	xref$ld <- as.numeric(as.character(xref$ld_rs))
	#!/usr/bin/python

	import sys
	import os
	import glob
	import pandas as pd
	import numpy as np
	import argparse

	# Future improvements
	#!/bin/bash

	module load apps/binapps/anaconda/2.1.0
	module load apps/gcc/R/3.1.0

	# clean data threshold variables.
	SNP_MISS_THRESH=0.02 # threshold for SNP missing rate
	SNP_MAF_THRESH=0.01 # threshold for minor allele
	SNP_HWE_THRESH=1e-3 # threshold for HWE
	SNP_HWE_GROUP='ALL' # define within which group to calculate HWE
	#!/bin/bash
	## Inherit user environment from the login node
	#$ -V
	## Use the current directory as the working directory for SGE output and determining paths to files
	#$ -cwd
	## Request parallel environment and a number cores
	#$ -pe smp.pe 12
	##
	## create an array
	#$ -t 1-22
	#!/bin/bash

	#$ -S /bin/bash
	##
	## Inherit user environment from the login node
	#$ -V
	##
	## Use the current directory as the working directory for SGE output and determining paths to files
	#$ -cwd
	##
	#!/bin/bash

	CHR=$1
	INTERVAL_START=`printf "%.0f" $2`
	INTERVAL_END=`printf "%.0f" $3`
	INTERVAL=`printf "%03d" $4`

	# directories
	NAME="impute_test_data_hg19"
	OUTPUT_DIR="/mnt/iusers01/jw01/mdeasjdb/scratch/impute_practice/"
	1 10583 5010583 1
	1 5010584 10010584 2
	1 10010585 15010585 3
	1 15010586 20010586 4
	1 20010587 25010587 5
	1 25010588 30010588 6
	1 30010589 35010589 7
	1 35010590 40010590 8
	1 40010591 45010591 9
	1 45010592 50010592 10
	#!/bin/bash

	# study data details
	STUDY=''
	DATA_DIR='prepare_data/dataset/'
	DATA=${DATA_DIR}${STUDY}"_chr"

	# reference data details
	REF_DIR='/mnt/iusers01/jw01/jw01-shared-resources/impute2/ref_panel/ALL_1000G_phase1integrated_v3_impute_macGT1/'