miniconda update

zUMIs-env/

zUMIs-miniconda.tar.bz2

# Welcome to zUMIs :wrench: :red_car::dash: :wrench:

## Quickstart

Nobody likes reading long README files so here is how you get going:

Fetch zUMIs by cloning the repository:

```

git clone https://github.com/sdparekh/zUMIs.git`

```

Start anaylysing your data:

```

zUMIs/zUMIs-master.sh -c -y my_config.yaml

```

zUMIs now comes with its own [miniconda](https://docs.conda.io/en/latest/miniconda.html) environment, so you do not need to deal with dependencies or installations (use the -c flag to use conda).

If you wish to use your own dependencies, head to the [zUMIs wiki](https://github.com/sdparekh/zUMIs/wiki/Installation#dependencies) to see what is required. 

## Intro

zUMIs is a fast and flexible pipeline to process RNA-seq data with (or without) UMIs.

The input to this pipeline is simply fastq files. In the most common cases, you will have a read containing the cDNA sequence and other read(s) containing UMI and Cell Barcode information. Furthermore, you will need a STAR index for your genome and GTF annotation file.

## Loom output

The loom format is increasing in popularity and compatible with downstream analysis using python out of the box.

We provide a script to convert zUMIs output into loom file automatically based on the [loomR package from the Satija lab](https://satijalab.org/loomR/loomR_tutorial.html). Please make sure you have loomR installed.

To convert zUMIs output to loom, simply run `Rscript rds2loom.R myRun.yaml`.

zUMIs will try to automatically do this, otherwise convert zUMIs output to loom by simply running `Rscript rds2loom.R myRun.yaml`.

## Changelog

19 Feb 2020: [zUMIs2.7.0 released](https://github.com/sdparekh/zUMIs/releases/tag/2.7.0): Simplify installation greatly by a cond-pack of miniconda with all dependencies. The conda environment is used with `zUMIs-master.sh -c`, with the old behavior staying as the default. 

13 Feb 2020: zUMIs2.6.3: Faster demultiplexing using python/pysam. Made forking of UMI collapse worker threads more robust.

06 Feb 2020: zUMIs2.6.2: Changes to the hamming distance UMI collapse to avoid overcollapsing of highly expressed genes.

    dir.create( paste0(opt$out_dir,"/zUMIs_output/demultiplexed/") )

  }

  installed_py <- system("pip3 freeze", intern = TRUE)

  installed_py <- system("pip freeze", intern = TRUE)

  if(any(grepl("pysam==",installed_py))){

    print("Using python implementation to demultiplex.")

  for(type in names(rds)){

    for(quant in names(rds[[type]])){

      outfile <- paste0(opt$out_dir,"/zUMIs_output/expression/",opt$project,".",type,".",quant,".all.loom")

      loomR::create(filename = outfile, data = as.matrix(rds[[type]][[quant]][["all"]]), transpose = TRUE,overwrite = TRUE)

      loomR::create(filename = outfile, data = as.matrix(rds[[type]][[quant]][["all"]]), do.transpose = TRUE,overwrite = TRUE)

      for(d in names(rds[[type]][[quant]][["downsampling"]])){

        outfile <- paste0(opt$out_dir,"/zUMIs_output/expression/",opt$project,".",type,".",quant,".",d,".loom")

        loomR::create(filename = outfile, data = as.matrix(rds[[type]][[quant]][["downsampling"]][[d]]), transpose = TRUE,overwrite = TRUE)

        loomR::create(filename = outfile, data = as.matrix(rds[[type]][[quant]][["downsampling"]][[d]]), do.transpose = TRUE,overwrite = TRUE)

      }

    }

# Pipeline to run UMI-seq analysis from fastq to read count tables.

# Authors: Swati Parekh, Christoph Ziegenhain, Beate Vieth & Ines Hellmann

# Contact: sparekh@age.mpg.de or christoph.ziegenhain@ki.se

vers=2.6.3b

vers=2.7.0

currentv=`curl -s https://raw.githubusercontent.com/sdparekh/zUMIs/master/zUMIs-master.sh | grep '^vers=' | cut -f2 -d "="`

if [ "$currentv" != "$vers" ]; then echo -e "------------- \n\n Good news! A newer version of zUMIs is available at https://github.com/sdparekh/zUMIs \n\n-------------"; fi

## Program path ##

	-d  <zUMIs-dir>   	 : Directory containing zUMIs scripts.  Default: path to this script.

## Miniconda environment

  -c : Use zUMIs dependencies in the preinstalled conda enviroment.

zUMIs version $vers

EOF

# Define the default variables #

zumisdir=$(dirname `readlink -f $0`)

while getopts ":y:d:h" options; do #Putting <:> between keys implies that they can not be called without an argument.

while getopts ":y:d:ch" options; do #Putting <:> between keys implies that they can not be called without an argument.

  case $options in

  y ) yaml=$OPTARG;;

  d ) zumisdir=$OPTARG;;

  c ) conda=true;;

  h ) usage

          exit 1;;

  \? ) echo -e "\n This key is not available! Please check the usage again: -$OPTARG"

    echo "Rscript_exec: $Rexc" >> $yaml

fi

#check for conda usage!

if [[ $conda = true ]]; then

  echo "Using miniconda environment for zUMIs!"

  samtoolsexc=samtools

  if grep -q 'samtools_exec:' $yaml; then

      sed -i '/samtools_exec:/d' $yaml

  fi

  echo "samtools_exec: $samtoolsexc" >> $yaml

  pigzexc=pigz

  if grep -q 'pigz_exec:' $yaml; then

      sed -i '/pigz_exec:/d' $yaml

  fi

  echo "pigz_exec: $pigzexc" >> $yaml

  starexc=STAR

  if grep -q 'STAR_exec:' $yaml; then

      sed -i '/STAR_exec:/d' $yaml

  fi

  echo "STAR_exec: $starexc" >> $yaml

  Rexc=Rscript

  if grep -q 'Rscript_exec:' $yaml; then

      sed -i '/Rscript_exec:/d' $yaml

  fi

  echo "Rscript_exec: $Rexc" >> $yaml

  zumisenv=$zumisdir/zUMIs-env

  miniconda=$zumisdir/zUMIs-miniconda.tar.bz2

  #check if zUMIs environment has been unpacked from tar

  if [[ ! -d $zumisenv ]] || [[ $zumisdir/zUMIs-miniconda.partaa -nt $zumisenv ]] ; then

    [ -d $zumisenv ] || mkdir -p $zumisenv

    cat $zumisdir/zUMIs-miniconda.parta* > $miniconda

    tar -xj --overwrite -f $miniconda -C $zumisenv

  fi

  #activate zUMIs environment!

  source $zumisenv/bin/activate

  conda-unpack

fi

if grep -q 'zUMIs_directory:' $yaml

  then

    sed -i "s|zUMIs_directory:.*|zUMIs_directory: $zumisdir|" $yaml

  fi

  date

fi

#close conda enviroment if necessary

if [ $conda = true ]; then

  source $zumisenv/bin/deactivate

fi