# ParseBiosciences-Pipeline.1.5.0 on Bianca

## Load conda

source /sw/apps/conda/latest/rackham_stage/etc/profile.d/conda.sh

## Delete old environment, if necessary

conda env list
conda env remove -n spipe

## Install complete environment
`environment.yml`

channels:
  - file:///sw/apps/conda/latest/rackham/local_repo/conda-forge
  - file:///sw/apps/conda/latest/rackham/local_repo/bioconda
dependencies:
  - samtools=1.21
  - star=2.7.11b
  - cython=3.0.12
  - gcc=14.2.0
  - libxcrypt=4.4.36
  - libxml2=2.13.6
  - pigz=2.8
  - pip=25.0.1
  - python=3.12.8
  - setuptools=75.8.2
  - unzip=6.0
  - numpy>=1.23,<2.0.0
  - pandas>=2.2
  - scipy
  - matplotlib
  - natsort
  - h5py
  - pysam>=0.20.0
  - scanpy>=1.8
  - anndata
  - leidenalg
  - python-igraph
  - jinja2
  - psutil
  - python-calamine

Copy/paste the content above in a file with name `environment.yml`

conda env create -n spipe150 -f environment.yml --offline
conda activate spipe150

cd project_dir
unzip ParseBiosciences-Pipeline.1.5.0.zip
cd ParseBiosciences-Pipeline.1.5.0

Edit `setup.py` in the folder and replace "python-igraph" with "igraph" on line 30.

pip install --no-cache-dir --no-build-isolation ./
...
Requirement already satisfied: stdlib-list in /proj/sens2017625/nobackup/pmitev/conda_envs/spipe/lib/python3.12/site-packages (from session-info->scanpy>=1.8->splitpipe==1.5.0) (0.11.1)
Building wheels for collected packages: splitpipe
  Building wheel for splitpipe (pyproject.toml) ... done
  Created wheel for splitpipe: filename=splitpipe-1.5.0-cp312-cp312-linux_x86_64.whl size=9070698 sha256=b6bad40cc172f67680b4272dd95737a5db33c0165178f2ff7980a50fb1006b73
  Stored in directory: /scratch/pip-ephem-wheel-cache-1tdx_tnn/wheels/ba/4b/eb/157bdf269b0e483efa6dfe454166ccac75a00ac63eccdc2ba0
Successfully built splitpipe
Installing collected packages: splitpipe
Successfully installed splitpipe-1.5.0

## Running

# load conda if necessary
source /sw/apps/conda/latest/rackham_stage/etc/profile.d/conda.sh
conda activate spipe150

split-pipe -h 
usage: split-pipe [-h] [-m MODE] [-c CHEMISTRY] [-k KIT] [-p PARFILE] [--run_name RUN_NAME] [-f FQ1] [--fq2 FQ2] [-o OUTPUT_DIR]
                  [-g GENOME_DIR] [--parent_dir PARENT_DIR] [--targeted_list TARGETED_LIST] [--sample SAMPLE_NAME WELLS]
                  [--samp_list SAMP_LIST] [--samp_sltab SAMP_SLTAB] [--yes_allwell] [--no_allsample] [--genome_name [GENOME_NAME ...]]
                  [--genes [GENES ...]] [--fasta [FASTA ...]] [--gfasta GENOME_NAME FASTA] [--sublibraries [SUBLIBRARIES ...]]
                  [--sublib_list SUBLIB_LIST] [--sublib_pref SUBLIB_PREF] [--sublib_suff SUBLIB_SUFF] [--tscp_use TSCP_USE]
                  [--tscp_min TSCP_MIN] [--tscp_max TSCP_MAX] [--cell_use CELL_USE] [--cell_est CELL_EST] [--cell_xf CELL_XF]
                  [--cell_min CELL_MIN] [--cell_max CELL_MAX] [--cell_list CELL_LIST] [--crispr] [--crsp_guides CRSP_GUIDES]
                  [--crsp_read_thresh CRSP_READ_THRESH] [--crsp_tscp_thresh CRSP_TSCP_THRESH] [--crsp_max_mm] [--crsp_use_star]
                  [--immune_check] [--bcr_analysis] [--tcr_analysis] [--immune_genome IMMUNE_GENOME] [--use_imgt_db]
                  [--immune_read_thresh IMMUNE_READ_THRESH] [--save_anndata] [--kit_list [KIT_LIST]] [--chem_list] [--bc_list]
                  [--bc_round_set ROUND NAME] [--sample_bc_rounds SAMPLE_BC_ROUNDS] [--rseed RSEED] [--nthreads NTHREADS]
                  [--no_keep_going] [--reuse] [--keep_temps] [--one_step] [--until_step UNTIL_STEP] [--star_extra_args STAR_EXTRA_ARGS]
                  [--clear_runproc] [--start_timeout START_TIMEOUT] [--chem_score_skip] [--kit_score_skip] [--dryrun] [-e] [-V]

SplitPipe data processing pipeline v1.5.0

options:
  -h, --help            show this help message and exit
  -m MODE, --mode MODE  Mode dictates process(s) to run; REQUIRED; See -explain
  -c CHEMISTRY, --chemistry CHEMISTRY
                        Set chemistry version for data
  -k KIT, --kit KIT     Set kit and kit-specific parameters
  -p PARFILE, --parfile PARFILE
                        Parameter file

## Installing TCR and BCR dependencies

- Login to transit.uppmax.uu.se, mount the wharf by running
`mount_wharf your_project`. Navigate to the wharf folder.
- Copy `ParseBiosciences-Pipeline.1.5.0.zip` there
- Run `unzip ParseBiosciences-Pipeline.1.5.0.zip`
- cd to the unzipped folder `cd ParseBiosciences-Pipeline.1.5.0`
- fix the Windows encoding of the install script
`dos2unix install_immune_dbs.sh`
- Run `./install_immune_dbs.sh -i -y`
- All reference data and databases are downloaded in `splitpipe/immune_dir/IgBlast` - this folder needs to be copied where is the previous installation in the project folder to match the structure (needs to be done from shell on Bianca). Something like this

  cp -r /path_to_wharf/splitpipe/immune_dir/IgBlast  /path_to/installation/splitpipe/immune_dir/

According to the manual, you need to rerun the installation of the pipeline.
- source conda, activate the environment as described earlier.
- Navigate to the folder with the pipeline and run
`pip install --no-cache-dir --no-build-isolation ./`
- That should be it!

## Bugs
To run `./install_immune_dbs.sh -I -y` there are few fixes that need to be done.
1. Edit `install_immune_dbs.sh` and change line 285 from `return 0` to `return 1`
2. Edit file `/splitpipe/scripts/install_IgBlast.sh`. Lines 267-271 have missing "s" in the address i.e. add them so the addresses for the corresponding files starts with `https://..` like

# Line 267
# From 
wget http://www.imgt.org/download/V-QUEST/IMGT_V-QUEST_reference_directory/Homo_sapiens/TR/TRAV.fasta
# To
wget https://www.imgt.org/download/V-QUEST/IMGT_V-QUEST_reference_directory/Homo_sapiens/TR/TRAV.fasta

3. Run the script as expected.

## Contacts:
- [Pavlin Mitev](https://katalog.uu.se/profile/?id=N3-1425)
- [UPPMAX](https://www.uu.se/en/centre/uppmax)
- [AE@UPPMAX - related documentation](/8sqXISVRRquPDSw9o1DizQ)
https://support.naiss.se/Ticket/Display.html?id=308687
###### tags: `UPPMAX`,`RT-283547`