bonifazi

# grep a string in multiple file names and include subdirectories
grep --include 'file1.txt' --include 'file2.txt' -rn --ignore-case TITLE directory1 directory2

bonifazi

#!/usr/bin/env Rscript
#
# Purpose: what this script does.
# Author: Renzo Bonifazi - dd-mm-yyyy
# Usage:
# # Rscript --vanilla myscript.R --file my_path/myfile.csv --output myoutput.csv
#
# Example:
# # Rscript --vanilla Make_pedigree.R --file Renzo/Documents/file.csv --output Output.csv
#

bonifazi

#!/usr/bin/env bash
# initiate a project directory structure
mkdir -p Backups             # to store any backup
mkdir -p Data/Raw_data       # raw data
mkdir -p Data/Raw_data/geno  # genotypes are in a sub-dir (add more if needed)
mkdir -p Data/Proc_data      # processed, i.e. cleaned data at different steps. Use horizontal dirs for middle steps.
mkdir -p Masters             # Main wrappers to run the pipeline (usually bash)
mkdir -p Programs/Scripts    # Collection of scripts (any language)
mkdir -p Programs/Scripts/R_func # Collection of R functions (which can be re-used from other projects)
mkdir -p Programs/Software   # Binaries and executables with their licences 

bonifazi

# different (similar) ways to check and load pkgs in R
# method 1
check_pkgs <- function(pkg_list){
      for(pkg in pkg_list) {
        if(!require(pkg, character.only = T)){
          stop('Please install the ', pkg, ' package, using "install.packages(', pkg, ')"', call. = F)
        }
      }
    }
check_pkgs(pkg_list = c("asserththat", "ggplot2"))

bonifazi

pacman::p_load(Hmisc, rrapply)

# loop variables
scenarios <- c("scenario1", "scenario2")
groups <- c("grp1", "grp2", "grp3", "grp4")
 
# create two lists, one for the plots and one for the statistics only
ALL_stats <- list()
ALL_plots <- list()
for(scenario in scenarios){

bonifazi

# First compute PCA files using Plink2 from the command line
# Refer to https://www.cog-genomics.org/plink/2.0/strat#pca for how PCA approximation is done
# As suggested in the link above, --maf is applied for variants below 0.01
# Plink2 command line is:
# plink2 --cow --bfile <mybfile> --keep-allele-order --maf 0.01 --pca approx

######### plot in R  ################
# Output: a 4 pages pdf file with: pages 1 to 3 are scatterplots of PCx vs PCx (with PCx from 1 to 3), page 4 is a 3D scatterplot of the first 3 PCs.
pacman::p_load(dplyr, data.table, ggplot2, scatterplot3d)
pca_res <- fread(file = "plink2.eigenvec")

bonifazi

awk 'BEGIN {
  OFS = ","
  print "ID", 0, 1, 2, 5
}
{
  for (i = 2; i <= NF; i++) {
    count[$1,$i]++
  }
  vals[$1] = $1
}

bonifazi

alias ll='ls -lah --color=auto --classify --group-directories-first --time-style=long-iso'
# alias ll='ls -lah --color=auto --classify --group-directories-first --time-style=long-iso --sort=time -r'

alias diff-s='diff -s -wy --suppress-common-lines'

alias squeue_comment="squeue --format='%18i %9P %8j %8u %2t %10M %6D %R %k'"