seandavi

Insert Workshop Title

Instructor(s) name(s) and contact information

Provide names and contact information for all instructors.

Workshop Description

Along with the topic of your workshop, include how students can expect to spend their time. For the description may also include information

seandavi

seandavi

# salmon wdl
#
# Assumes gencode here!!!!
#
#############################

task salmon_index {

  File transcript_file
  Int kmer 

seandavi

import groovy.json.JsonSlurper

def jsonSlurper = new JsonSlurper()

res = jsonSlurper.parse(new URL('https://api-omicidx.cancerdatasci.org/sra/1.0/search/run?q=experiment_accession:' + params.experiment + '&size=500'))

l = res.hits.hits.collect {
    [ it._source.experiment_accession, it._source.accession ]
}

seandavi

seandavi

library(dplyr)


library(RMySQL)
con = dbConnect(MySQL(),user='USERNAME',password='PASSWORD',host='solexadb.XXXXXXXXXX.us-east-1.rds.amazonaws.com',port=3306,dbname='solexa')
res = dbGetQuery(con,
                 "select study_id,source.name as source_name, sample.name as sample_name, fcb.type as software,
                 fcb.dateStamp as basecalldate, fcb.softwareVersion as version, study_id,
                 sr.date as run_date, sr.sequencer as sequencer, sm.model, ssr.library_id as library_id,
                 sr.ID as run_id, sample.ID as sample_id, nt.value as sample_source,

seandavi

import boto3

# set the profile name based on ~/.aws/credentials entry
boto3.setup_default_session(profile_name='s3')

from snakemake.remote.S3 import RemoteProvider as S3RemoteProvider
s3 = S3RemoteProvider()

# This simply copies the file from local storage to s3
rule all:

seandavi

library(aws.s3)
aws.signature::use_credentials(profile='s3')
disco_maf = s3read_using(readr::read_tsv,object="s3://target-osteosarcoma/TargetOsteoDiscovery/summary/strelka.maf.filtered.tab")
disco_gistic = s3read_using(readr::read_tsv,object="s3://target-osteosarcoma/TargetOsteoDiscovery/all_thresholded.by_genes.txt")
library(tidyr)
library(dplyr)
library(ComplexHeatmap)
x = disco_gistic %>% 
  gather(key = 'Sample', value='CN', -c('Gene Symbol', "Locus ID", "Cytoband")) %>%
  dplyr::select(Sample, Hugo_Symbol = `Gene Symbol`, CN) %>%

seandavi

library(GenomicDataCommons)
library(magrittr)

TCGAtranslateID = function(file_ids) {
    info = files() %>%
        GenomicDataCommons::filter( ~ file_id %in% file_ids) %>%
        GenomicDataCommons::select('cases.samples.submitter_id') %>%
        results_all()
    # The mess of code below is to extract TCGA barcodes
    # id_list will contain a list (one item for each file_id)

seandavi

#!/usr/bin/env python
import argparse
import lxml.etree
import os, sys
import bz2

parser = argparse.ArgumentParser()
parser.add_argument('tag')
parser.add_argument('n',default=100000)
parser.add_argument('wrapper', default=None)