petermchale

petermchale

# purpose: use Basic Access Authentication to download data from a web server
# example usage: python <this file>.py --url https://cancer.sanger.ac.uk/cosmic/file_download/GRCh37/cosmic/v85/VCF/CosmicCodingMuts.vcf.gz --username email@example.com --password mycosmicpassword
# for more on Basic access authentication see: https://en.wikipedia.org/wiki/Basic_access_authentication

import requests
import argparse

parser = argparse.ArgumentParser()
parser.add_argument('--url')
parser.add_argument('--username')

petermchale

# purpose
# -------
# strip directory and suffix (argument 3) from path (argument 1) forming a prefix
# return the concatenation of prefix, argument 2, and suffix

# usage
# -----
# ./insert.sh "dir/file.vcf" ".normalized" ".vcf"
# file.normalized.vcf

petermchale

petermchale

#!/bin/bash

# python solution at: https://stackoverflow.com/a/39225039/6674256
# another solution is "rclone", but it requires setup and OAuth
# another solution is Google Drive API, but it requires setup and OAuth too
# another solution is https://github.com/odeke-em/drive, but it requires setup and OAuth too

fileid=$1 # use "Get shareable link" in your Google Drive to access the file ID
filename=$2
curl --cookie-jar ./cookie --location "https://drive.google.com/uc?export=download&id=${fileid}" > /dev/null

petermchale

#!/usr/bin/env bash

# download segmental duplications
seg_dups='genomicSuperDups'
seg_dups_final=$seg_dups.sorted.bed.gz
if [[ ! -e $seg_dups_final ]]; then
    echo "downloading, unzipping, bed-ifying segmental duplication data..."

    # database schema
    wget http://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/$seg_dups.sql

petermchale

petermchale

petermchale

#!/usr/bin/env python

import requests
import argparse
import sys
import gzip
import os

parser = argparse.ArgumentParser(description='fetch and parse self chain data from UCSC database')
parser.add_argument('--genome_build', type=str, help='e.g., "hg19" or "hg38"')

petermchale