In cmatKhan/mislabels: Biostrings Algorithms Final Project

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  eval = FALSE,
  echo = TRUE
)

library(finalProject)

Introduction

This script runs the RNAseq pile up vs all genome distance calculation which generates the data for analysis

SGE script

#!/bin/bash

#$ -N conduct_expr
#$ -cwd
#$ -t 1-2
#$ -l mem_free=10G
#$ -q power
#$ -o /dsgmnt/llfs_external/$USER/logs
#$ -e /dsgmnt/llfs_external/$USER/logs

root=/dsgmnt/llfs_external/cmateusiak

# activate environment
source activate $root/conda_envs/r_env

# lookup path
lookup=$root/lookups/final_project_lookup.txt

# assign each line of lookup to variable
read pileup_database_dirpath < <(sed -n ${SGE_TASK_ID}p $lookup )

sample_genotype_db_path=$root/sample_genotype_db.sqlite

experiment_output=$pileup_database_dirpath/experiment_res.rds

Rscript $root/scripts/conduct_mislabel_experiment.R $sample_genotype_db_path $pileup_database_dirpath $experiment_output

Rscript

#!/usr/bin/env Rscript

.libPaths(.libPaths()[2])

library(finalProject)
library(tidyverse)

args = commandArgs(trailingOnly=TRUE)

sample_genotype_db_path  = args[1]
pileup_database_dirpath = args[2]
experiment_output  = args[3]

sample_list = paste0("sample", seq(1,4))

experiment_res = 
  map(sample_list, 
      ~conduct_experiment(sample_genotype_db_path,
                         pileup_database_dirpath,
                         .,
                         filename_id_subject_mislabel_map))

write_rds(experiment_res, experiment_output)