nuada

#!/bin/bash

# Unzip files
for file in *.zip; do
        unzip "$file"
done

# Extract fastqs
for file in *.ab1; do
        seqret -sformat abi -osformat fastq  -auto -stdout -sequence "$file" > "$(basename "$file" .ab1).fastq"

nuada

#!/bin/bash
# usage: $0 <MiSeq output dir> <output dir>

dir=$1/Thumbnail_Images/L001
output=$2
number_of_tiles=$(grep FlowcellLayout ${1}/RunInfo.xml | cut -d = -f 5 | sed -e 's/[^0-9]*//g')

if [[ ! -d ${output} ]]; then
        mkdir ${output}
fi

nuada

#!/usr/share/gemini/anaconda/bin/python -E
# -*- coding: utf-8 -*-
# usage: gemini_summarize.py <query> <gemini.db>

import sys
import locale
from gemini import GeminiQuery

DP_THRESHOLD = 8
GQ_THRESHOLD = 20

nuada

#!/usr/bin/python

import pandas as pd
import sys

df = pd.read_csv(sys.argv[1], sep='\t', index_col=0)

for col in df.columns:
	if col[3] == 'B':
		df = df.drop(col, 1)

nuada

#!/bin/bash

bcftools norm -Ou -m -any $1 | # Split multi-allelic alleles
        bcftools norm -Ou -f /resources/hg19/ucsc.hg19.fasta | # Normalize
        bcftools annotate -Ob -x ID -I +'%CHROM:%POS:%REF:%ALT' | # Replace IDs with unique ID                                                                                                    
        plink --bcf /dev/stdin --keep-allele-order --double-id --allow-extra-chr 0 --make-bed --out variants                                                                                      
                                                                                                                                                                                                  
king -b variants.bed --kinship --prefix kinship                                                                                                                                                   
king -b variants.bed --individual

nuada

#!/bin/bash

max_jobs=4

for i in $(seq 10); do
        while [[ $(jobs | wc --lines) -ge ${max_jobs} ]]; do
                sleep 1
        done

        # Do the job

nuada

#!/bin/bash

if [[ -z $* ]]; then
        echo "Usage: $0 <bam file> <bed file>"
        exit 1
fi

# Header start
echo '@HD VN:1.0 SO:coordinate' | tr " " "\t"

nuada

#!/bin/bash

DATA='/data/project'
for sample in $(cd ${DATA}; ls -1 *.r1.fastq.gz | cut -d . -f 1); do
        bowtie2 -x /resources/phix/bowtie2/phix -1 ${DATA}/${sample}.r1.fastq.gz -2 ${DATA}/${sample}.r2.fastq.gz -S /dev/null --al-conc-gz phix-${sample}.r%.fastq.gz -p 4 2>&1 | tee -a phix.log
done

nuada

bedtools sort -i foo.bed | bedtools merge -i - -nms | sed -e 's/\r//g' | awk -F '\t' '{ split($4, name, "."); print $1 FS $2 FS $3 FS name[1] }'

nuada

#!/bin/bash

echo -e "#CHR\tBP1\tBP2\tID"
awk -F '\t' '{ print $1 FS $2+1 FS $3 FS NR }' | sed -e 's/^\([0-9]\+\)/chr\1/g'