diff --git a/modules/jabba/1.0/config/default.yaml b/modules/jabba/1.0/config/default.yaml new file mode 100644 index 00000000..e4185d49 --- /dev/null +++ b/modules/jabba/1.0/config/default.yaml @@ -0,0 +1,56 @@ +lcr-modules: + + jabba: + + inputs: + # Available wildcards: {seq_type} {genome_build} {sample_id} + sample_bam: "__UPDATE__" + sample_bai: "__UPDATE__" + + # SV caller VCF v4.2 file. Available wildcards: + # {seq_type} {genome_build} {tumour_id} {normal_id} {pair_status} + manta_junc: "__UPDATE__" + gridss_junc: "__UPDATE__" + + merge_svs: "{MODSDIR}/src/R/merge_svs.R" + make_pon: "{MODSDIR}/src/R/make_pon.R" + make_germline: "{MODSDIR}/src/R/make_germline_filter.R" + run_custom_fc: "{MODSDIR}/src/R/run_custom_fragcounter.R" + run_jabba_main: "{MODSDIR}/src/R/run_jabba_main.R" + + scratch_subdirectories: [] + + # CPLEX_DIR is path to local CPLEX installation. See + # https://github.com/mskilab/JaBbA#installation for + # instructions. + CPLEX_DIR: "__UPDATE__" + + conda_envs: + jabba: "{MODSDIR}/envs/jabba.yaml" + + options: + jabba: + --ppmethod sequenza + --slack 20 + + threads: + merge_svs: 1 + fragcounter: 1 + make_pon: 10 + dryclean: 12 + make_germline: 1 + jabba: 10 + + mem_mb: + merge_svs: 4096 + fragcounter: 4096 + make_pon: 30000 + dryclean: 30000 + make_germline: 30000 + jabba: 30000 + + pairing_config: + genome: + run_paired_tumours: True + run_unpaired_tumours_with: null + run_paired_tumours_as_unpaired: False diff --git a/modules/jabba/1.0/envs/jabba.yaml b/modules/jabba/1.0/envs/jabba.yaml new file mode 100644 index 00000000..edad732e --- /dev/null +++ b/modules/jabba/1.0/envs/jabba.yaml @@ -0,0 +1,382 @@ +name: lcr-jabba +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - _libgcc_mutex=0.1 + - _openmp_mutex=4.5 + - _r-mutex=1.0.1 + - argon2-cffi=20.1.0 + - async_generator=1.10 + - attrs=21.2.0 + - backcall=0.2.0 + - backports=1.0 + - backports.functools_lru_cache=1.6.4 + - binutils_impl_linux-64=2.35.1 + - binutils_linux-64=2.35 + - bioconductor-annotationdbi=1.54.0 + - bioconductor-biobase=2.52.0 + - bioconductor-biocfilecache=2.0.0 + - bioconductor-biocgenerics=0.38.0 + - bioconductor-biocio=1.2.0 + - bioconductor-biocparallel=1.26.0 + - bioconductor-biomart=2.48.0 + - bioconductor-biostrings=2.60.0 + - bioconductor-bsgenome=1.60.0 + - bioconductor-copynumber=1.32.0 + - bioconductor-delayedarray=0.18.0 + - bioconductor-genomeinfodb=1.28.0 + - bioconductor-genomeinfodbdata=1.2.6 + - bioconductor-genomicalignments=1.28.0 + - bioconductor-genomicfeatures=1.44.0 + - bioconductor-genomicranges=1.44.0 + - bioconductor-iranges=2.26.0 + - bioconductor-keggrest=1.32.0 + - bioconductor-matrixgenerics=1.4.0 + - bioconductor-rhtslib=1.24.0 + - bioconductor-rsamtools=2.8.0 + - bioconductor-rtracklayer=1.52.0 + - bioconductor-s4vectors=0.30.0 + - bioconductor-structuralvariantannotation=1.8.0 + - bioconductor-summarizedexperiment=1.22.0 + - bioconductor-variantannotation=1.38.0 + - bioconductor-xvector=0.32.0 + - bioconductor-zlibbioc=1.38.0 + - bleach=3.3.0 + - bwidget=1.9.14 + - bzip2=1.0.8 + - c-ares=1.17.1 + - ca-certificates=2021.7.5 + - cairo=1.16.0 + - certifi=2021.5.30 + - cffi=1.14.5 + - curl=7.77.0 + - decorator=5.0.9 + - defusedxml=0.7.1 + - entrypoints=0.3 + - font-ttf-dejavu-sans-mono=2.37 + - font-ttf-inconsolata=3.000 + - font-ttf-source-code-pro=2.038 + - font-ttf-ubuntu=0.83 + - fontconfig=2.13.1 + - fonts-conda-ecosystem=1 + - fonts-conda-forge=1 + - freetype=2.10.4 + - fribidi=1.0.10 + - gcc_impl_linux-64=9.3.0 + - gcc_linux-64=9.3.0 + - gettext=0.21.0 + - gfortran_impl_linux-64=9.3.0 + - gfortran_linux-64=9.3.0 + - graphite2=1.3.14 + - gsl=2.6 + - gxx_impl_linux-64=9.3.0 + - gxx_linux-64=9.3.0 + - harfbuzz=2.8.1 + - icu=68.1 + - importlib-metadata=4.6.0 + - ipykernel=5.5.5 + - ipython=7.25.0 + - ipython_genutils=0.2.0 + - jbig=2.1 + - jedi=0.18.0 + - jinja2=3.0.1 + - jpeg=9d + - jsonschema=3.2.0 + - jupyter_client=6.1.12 + - jupyter_core=4.7.1 + - jupyterlab_pygments=0.1.2 + - kernel-headers_linux-64=2.6.32 + - krb5=1.19.1 + - ld_impl_linux-64=2.35.1 + - lerc=2.2.1 + - libblas=3.9.0 + - libcblas=3.9.0 + - libcurl=7.77.0 + - libdeflate=1.7 + - libedit=3.1.20210216 + - libev=4.33 + - libffi=3.3 + - libgcc-devel_linux-64=9.3.0 + - libgcc-ng=11.1.0 + - libgfortran-ng=9.3.0 + - libgfortran5=9.3.0 + - libglib=2.68.3 + - libgomp=11.1.0 + - libiconv=1.16 + - liblapack=3.9.0 + - libnghttp2=1.43.0 + - libopenblas=0.3.15 + - libpng=1.6.37 + - libsodium=1.0.18 + - libssh2=1.9.0 + - libstdcxx-devel_linux-64=9.3.0 + - libstdcxx-ng=11.1.0 + - libtiff=4.3.0 + - libuuid=2.32.1 + - libwebp-base=1.2.0 + - libxcb=1.14 + - libxml2=2.9.12 + - lz4-c=1.9.3 + - make=4.3 + - markupsafe=2.0.1 + - matplotlib-inline=0.1.2 + - mistune=0.8.4 + - nbclient=0.5.3 + - nbconvert=6.1.0 + - nbformat=5.1.3 + - ncurses=6.2 + - nest-asyncio=1.5.1 + - notebook=6.4.0 + - openssl=1.1.1k + - packaging=20.9 + - pandoc=2.14.0.3 + - pandocfilters=1.4.3 + - pango=1.48.6 + - parso=0.8.2 + - pcre=8.45 + - pcre2=10.36 + - pexpect=4.8.0 + - pickleshare=0.7.5 + - pip=21.1.3 + - pixman=0.40.0 + - prometheus_client=0.11.0 + - prompt-toolkit=3.0.19 + - ptyprocess=0.7.0 + - pycparser=2.20 + - pygments=2.9.0 + - pyparsing=2.4.7 + - pyrsistent=0.17.3 + - python=3.9.5 + - python-dateutil=2.8.1 + - python_abi=3.9 + - pyzmq=22.1.0 + - r-argparse=2.0.4 + - r-askpass=1.1 + - r-assertthat=0.2.1 + - r-backports=1.2.1 + - r-base=4.1.0 + - r-base64enc=0.1_3 + - r-bh=1.75.0_0 + - r-bit=4.0.4 + - r-bit64=4.0.5 + - r-bitops=1.0_7 + - r-blob=1.2.1 + - r-boot=1.3_28 + - r-brio=1.1.2 + - r-broom=0.7.8 + - r-bslib=0.2.5.1 + - r-cachem=1.0.5 + - r-callr=3.7.0 + - r-caret=6.0_88 + - r-cellranger=1.1.0 + - r-class=7.3_19 + - r-cli=3.0.0 + - r-clipr=0.7.1 + - r-cluster=2.1.2 + - r-codetools=0.2_18 + - r-colorspace=2.0_2 + - r-commonmark=1.7 + - r-cpp11=0.3.1 + - r-crayon=1.4.1 + - r-crul=1.1.0 + - r-curl=4.3.2 + - r-data.table=1.14.0 + - r-dbi=1.1.1 + - r-dbplyr=2.1.1 + - r-desc=1.3.0 + - r-diffobj=0.3.4 + - r-digest=0.6.27 + - r-dplyr=1.0.7 + - r-dtplyr=1.1.0 + - r-ellipsis=0.3.2 + - r-essentials=4.1 + - r-evaluate=0.14 + - r-fansi=0.4.2 + - r-farver=2.1.0 + - r-fastmap=1.1.0 + - r-filelock=1.0.2 + - r-findpython=1.0.7 + - r-forcats=0.5.1 + - r-foreach=1.5.1 + - r-foreign=0.8_81 + - r-formatr=1.11 + - r-fs=1.5.0 + - r-futile.logger=1.4.3 + - r-futile.options=1.0.1 + - r-gargle=1.1.0 + - r-generics=0.1.0 + - r-getopt=1.20.3 + - r-ggplot2=3.3.5 + - r-gistr=0.9.0 + - r-glmnet=4.1_2 + - r-glue=1.4.2 + - r-googledrive=1.0.1 + - r-googlesheets4=0.3.0 + - r-gower=0.2.2 + - r-gtable=0.3.0 + - r-haven=2.4.1 + - r-hexbin=1.28.2 + - r-highr=0.9 + - r-hms=1.1.0 + - r-htmltools=0.5.1.1 + - r-htmlwidgets=1.5.3 + - r-httpcode=0.3.0 + - r-httpuv=1.6.1 + - r-httr=1.4.2 + - r-ids=1.0.1 + - r-iotools=0.3_1 + - r-ipred=0.9_11 + - r-irdisplay=1.0 + - r-irkernel=1.2 + - r-isoband=0.2.4 + - r-iterators=1.0.13 + - r-jquerylib=0.1.4 + - r-jsonlite=1.7.2 + - r-kernsmooth=2.23_20 + - r-knitr=1.33 + - r-labeling=0.4.2 + - r-lambda.r=1.2.4 + - r-later=1.2.0 + - r-lattice=0.20_44 + - r-lava=1.6.9 + - r-lazyeval=0.2.2 + - r-lifecycle=1.0.0 + - r-lubridate=1.7.10 + - r-magrittr=2.0.1 + - r-maps=3.3.0 + - r-markdown=1.1 + - r-mass=7.3_54 + - r-matrix=1.3_4 + - r-matrixstats=0.59.0 + - r-memoise=2.0.0 + - r-mgcv=1.8_36 + - r-mime=0.11 + - r-modelmetrics=1.2.2.2 + - r-modelr=0.1.8 + - r-munsell=0.5.0 + - r-nlme=3.1_152 + - r-nnet=7.3_16 + - r-numderiv=2016.8_1.1 + - r-openssl=1.4.4 + - r-optparse=1.6.6 + - r-pbapply=1.4_3 + - r-pbdzmq=0.3_5 + - r-pillar=1.6.1 + - r-pkgconfig=2.0.3 + - r-pkgload=1.2.1 + - r-plogr=0.2.0 + - r-plyr=1.8.6 + - r-png=0.1_7 + - r-praise=1.0.0 + - r-prettyunits=1.1.1 + - r-proc=1.17.0.1 + - r-processx=3.5.2 + - r-prodlim=2019.11.13 + - r-progress=1.2.2 + - r-promises=1.2.0.1 + - r-pryr=0.1.4 + - r-ps=1.6.0 + - r-purrr=0.3.4 + - r-quantmod=0.4.18 + - r-r6=2.5.0 + - r-randomforest=4.6_14 + - r-rappdirs=0.3.3 + - r-rbokeh=0.5.1 + - r-rcolorbrewer=1.1_2 + - r-rcpp=1.0.6 + - r-rcurl=1.98_1.3 + - r-readr=1.4.0 + - r-readxl=1.3.1 + - r-recipes=0.1.16 + - r-recommended=4.1 + - r-rematch=1.0.1 + - r-rematch2=2.1.2 + - r-remotes=2.4.0 + - r-repr=1.1.3 + - r-reprex=2.0.0 + - r-reshape2=1.4.4 + - r-restfulr=0.0.13 + - r-rjson=0.2.20 + - r-rlang=0.4.11 + - r-rmarkdown=2.9 + - r-rpart=4.1_15 + - r-rprojroot=2.0.2 + - r-rsqlite=2.2.5 + - r-rstudioapi=0.13 + - r-rvest=1.0.0 + - r-sass=0.4.0 + - r-scales=1.1.1 + - r-selectr=0.4_2 + - r-seqminer=8.0 + - r-sequenza=3.0.0 + - r-shape=1.4.6 + - r-shiny=1.6.0 + - r-snow=0.4_3 + - r-sourcetools=0.1.7 + - r-spatial=7.3_14 + - r-squarem=2021.1 + - r-squash=1.0.9 + - r-stringi=1.6.2 + - r-stringr=1.4.0 + - r-survival=3.2_11 + - r-sys=3.4 + - r-testthat=3.0.3 + - r-tibble=3.1.2 + - r-tidyr=1.1.3 + - r-tidyselect=1.1.1 + - r-tidyverse=1.3.1 + - r-timedate=3043.102 + - r-tinytex=0.32 + - r-triebeard=0.3.0 + - r-ttr=0.24.2 + - r-tzdb=0.1.2 + - r-urltools=1.7.3 + - r-utf8=1.2.1 + - r-uuid=0.1_4 + - r-vctrs=0.3.8 + - r-viridislite=0.4.0 + - r-vroom=1.5.4 + - r-waldo=0.2.5 + - r-withr=2.4.2 + - r-xfun=0.24 + - r-xml=3.99_0.6 + - r-xml2=1.3.2 + - r-xtable=1.8_4 + - r-xts=0.12.1 + - r-yaml=2.2.1 + - r-zoo=1.8_9 + - readline=8.1 + - sed=4.8 + - send2trash=1.7.1 + - setuptools=52.0.0 + - six=1.16.0 + - sqlite=3.36.0 + - sysroot_linux-64=2.12 + - terminado=0.10.1 + - testpath=0.5.0 + - tk=8.6.10 + - tktable=2.10 + - tornado=6.1 + - traitlets=5.0.5 + - tzdata=2021a + - wcwidth=0.2.5 + - webencodings=0.5.1 + - wheel=0.36.2 + - xorg-kbproto=1.0.7 + - xorg-libice=1.0.10 + - xorg-libsm=1.2.3 + - xorg-libx11=1.7.2 + - xorg-libxext=1.3.4 + - xorg-libxrender=0.9.10 + - xorg-libxt=1.2.1 + - xorg-renderproto=0.11.1 + - xorg-xextproto=7.3.0 + - xorg-xproto=7.0.31 + - xz=5.2.5 + - zeromq=4.3.4 + - zipp=3.4.1 + - zlib=1.2.11 + - zstd=1.5.0 +prefix: /home/prasathp/miniconda3/envs/lcr-jabba diff --git a/modules/jabba/1.0/jabba.smk b/modules/jabba/1.0/jabba.smk new file mode 100644 index 00000000..d5a121ef --- /dev/null +++ b/modules/jabba/1.0/jabba.smk @@ -0,0 +1,298 @@ +#!/usr/bin/env snakemake + + +##### ATTRIBUTION ##### + + +# Original Author: N/A +# Module Author: Prasath Pararajalingam +# Contributors: N/A + + +##### SETUP ##### + + +# Import package with useful functions for developing analysis modules +import oncopipe as op +import os + +# Check that the oncopipe dependency is up-to-date. Add all the following lines to any module that uses new features in oncopipe +min_oncopipe_version="1.0.11" +import pkg_resources +try: + from packaging import version +except ModuleNotFoundError: + sys.exit("The packaging module dependency is missing. Please install it ('pip install packaging') and ensure you are using the most up-to-date oncopipe version") + +# To avoid this we need to add the "packaging" module as a dependency for LCR-modules or oncopipe + +current_version = pkg_resources.get_distribution("oncopipe").version +if version.parse(current_version) < version.parse(min_oncopipe_version): + print('\x1b[0;31;40m' + f'ERROR: oncopipe version installed: {current_version}' + '\x1b[0m') + print('\x1b[0;31;40m' + f"ERROR: This module requires oncopipe version >= {min_oncopipe_version}. Please update oncopipe in your environment" + '\x1b[0m') + sys.exit("Instructions for updating to the current version of oncopipe are available at https://lcr-modules.readthedocs.io/en/latest/ (use option 2)") + +# End of dependency checking section + +# Setup module and store module-specific configuration in `CFG` +# `CFG` is a shortcut to `config["lcr-modules"]["jabba"]` +CFG = op.setup_module( + name = "jabba", + version = "1.0", + subdirectories = ["inputs", "fragcounter", "dryclean", "jabba", "outputs"], +) + +os.environ["CPLEX_DIR"] = str(CFG["CPLEX_DIR"]) + + +# Define rules to be run locally when using a compute cluster +localrules: + _jabba_install_jabba, + _jabba_input_bam, + _jabba_link_graph_rds, + _jabba_all + + +##### RULES ##### + +### Adjust coverage for GC and mappability ### + +# Install JaBba suite from github +rule _jabba_install_fragcounter: + output: + complete = CFG["dirs"]["fragcounter"] + "fragcounter.installed" + conda: CFG["conda_envs"]["jabba"] + shell: + op.as_one_line(""" + Rscript -e 'Sys.setenv(R_REMOTES_NO_ERRORS_FROM_WARNINGS = TRUE)' + -e 'Sys.unsetenv("GITHUB_PAT")' + -e 'if ("fragCounter" %in% installed.packages()==FALSE) {{remotes::install_github("morinlab/fragCounter", upgrade = TRUE, force = TRUE)}}' + -e 'library(fragCounter)' + && + touch {output.complete} + """) + + +rule _jabba_install_dryclean: + input: + installed1 = str(rules._jabba_install_fragcounter.output.complete) + output: + complete = CFG["dirs"]["dryclean"] + "dryclean.installed" + conda: CFG["conda_envs"]["jabba"] + shell: + op.as_one_line(""" + Rscript -e 'Sys.setenv(R_REMOTES_NO_ERRORS_FROM_WARNINGS = TRUE)' + -e 'Sys.unsetenv("GITHUB_PAT")' + -e 'if ("dryclean" %in% installed.packages()==FALSE) {{remotes::install_github("morinlab/dryclean", upgrade = TRUE, force = TRUE)}}' + -e 'library(dryclean)' + && + touch {output.complete} + """) + + +rule _jabba_install_jabba: + input: + installed1 = str(rules._jabba_install_dryclean.output.complete), + installed2 = str(rules._jabba_install_fragcounter.output.complete) + output: + complete = CFG["dirs"]["jabba"] + "jabba.installed" + conda: CFG["conda_envs"]["jabba"] + params: + cplex_dir = CFG["CPLEX_DIR"] + shell: + op.as_one_line(""" + Rscript -e 'Sys.setenv(R_REMOTES_NO_ERRORS_FROM_WARNINGS = TRUE)' + -e 'Sys.setenv(CPLEX_DIR = "{params.cplex_dir}")' + -e 'Sys.unsetenv("GITHUB_PAT")' + -e 'if ("copynumber" %in% installed.packages()==FALSE) {{BiocManager::install("copynumber")}}' + -e 'if (is.null(packageDescription("copynumber")$GithubUsername)) {{remotes::install_github("ShixiangWang/copynumber", dependencies = TRUE)}}' + -e 'if ("JaBbA" %in% installed.packages()==FALSE) {{remotes::install_github("mskilab/JaBbA", upgrade = TRUE, force = TRUE)}}' + -e 'library(JaBbA)' + && + touch {output.complete} + """) + + +# Symlinks the input files into the module results directory (under '00-inputs/') +rule _jabba_input_bam: + input: + bam = CFG["inputs"]["sample_bam"], + bai = CFG["inputs"]["sample_bai"] + output: + bam = CFG["dirs"]["inputs"] + "bam/{seq_type}--{genome_build}/{sample_id}.bam", + bai = CFG["dirs"]["inputs"] + "bam/{seq_type}--{genome_build}/{sample_id}.bai", + crai = CFG["dirs"]["inputs"]+ "bam/{seq_type}--{genome_build}/{sample_id}.crai" + run: + op.relative_symlink(input.bam, output.bam) + op.relative_symlink(input.bai, output.bai) + op.relative_symlink(input.bai, output.crai) + + +rule _jabba_input_gridss_vcf: + input: + junc = CFG["inputs"]["gridss_junc"] + output: + junc = CFG["dirs"]["inputs"] + "junc/gridss/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.vcf" + run: + op.relative_symlink(input.junc, output.junc) + +rule _jabba_process_gridss_vcf: + input: + junc = str(rules._jabba_input_gridss_vcf.output.junc) + output: + junc = CFG["dirs"]["inputs"] + "junc/gridss/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.bnd.vcf" + shell: + op.as_one_line(""" + zcat {input.junc} || cat {input.junc} | awk 'BEGIN {{OFS=FS=\"\t\"}} $0 ~ /^#/ || $3 !~ /b$/' > {output.junc} + """) + +rule _jabba_input_manta_vcf: + input: + junc = CFG["inputs"]["manta_junc"] + output: + junc = CFG["dirs"]["inputs"] + "junc/manta/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.vcf" + run: + op.relative_symlink(input.junc, output.junc) + + +rule _jabba_merge_svs: + input: + installed = str(rules._jabba_install_jabba.output.complete), + manta = str(rules._jabba_input_manta_vcf.output.junc), + gridss = str(rules._jabba_process_gridss_vcf.output.junc) + output: + junc = CFG["dirs"]["inputs"] + "junc/merged/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.rds" + log: + stdout = CFG["logs"]["inputs"] + "run/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/merge_svs.stdout.log", + stderr = CFG["logs"]["inputs"] + "run/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/merge_svs.stderr.log" + conda: CFG["conda_envs"]["jabba"] + threads: CFG["threads"]["merge_svs"] + params: + merge_svs = CFG["inputs"]["merge_svs"] + resources: + mem_mb = CFG["mem_mb"]["merge_svs"] + shell: + op.as_one_line(""" + Rscript {params.merge_svs} --manta {input.manta} --gridss {input.gridss} --genome {wildcards.genome_build} --rds {output} > {log.stdout} 2> {log.stderr} + """) + + +# Runs fragcounter on individual samples +rule _jabba_run_fragcounter: + input: + installed = str(rules._jabba_install_fragcounter.output.complete), + bam = str(rules._jabba_input_bam.output.bam), + gc = reference_files("genomes/{genome_build}/annotations/jabba/gc1000.rds"), + map = reference_files("genomes/{genome_build}/annotations/jabba/map1000.rds"), + ref = reference_files("genomes/{genome_build}/genome_fasta/genome.fa") + output: + rds = CFG["dirs"]["fragcounter"] + "run/{seq_type}--{genome_build}/{sample_id}/cov.rds" + log: + stdout = CFG["logs"]["fragcounter"] + "run/{seq_type}--{genome_build}/{sample_id}/fc.stdout.log", + stderr = CFG["logs"]["fragcounter"] + "run/{seq_type}--{genome_build}/{sample_id}/fc.stderr.log" + conda: CFG["conda_envs"]["jabba"] + threads: CFG["threads"]["fragcounter"] + resources: + mem_mb = CFG["mem_mb"]["fragcounter"] + shell: + op.as_one_line(""" + FRAG=$(Rscript -e 'cat(paste0(installed.packages()["fragCounter", "LibPath"], "/fragCounter/extdata/"))'); $FRAG/frag -b {input.bam} -r {input.ref} -w 1000 -d `dirname {input.gc}` -o `dirname {output.rds}` > {log.stdout} 2> {log.stderr} + """) + + +### Run dryclean on tumours to remove background and germline variation ### + + +rule _jabba_run_dryclean_tumour: + input: + installed = str(rules._jabba_install_dryclean.output.complete), + rds = CFG["dirs"]["fragcounter"] + "run/{seq_type}--{genome_build}/{tumour_id}/cov.rds", + pon = reference_files("genomes/{genome_build}/jabba/pon/detergent.rds"), + germline = reference_files("genomes/{genome_build}/jabba/pon/germline.markers.rds") + output: + rds = CFG["dirs"]["dryclean"] + "run/{seq_type}--{genome_build}/{tumour_id}/drycleaned.cov.rds" + log: + stdout = CFG["logs"]["dryclean"] + "run/{seq_type}--{genome_build}/{tumour_id}.stdout.log", + stderr = CFG["logs"]["dryclean"] + "run/{seq_type}--{genome_build}/{tumour_id}.stderr.log" + conda: CFG["conda_envs"]["jabba"] + threads: CFG["threads"]["dryclean"] + resources: + mem_mb = CFG["mem_mb"]["dryclean"] + wildcard_constraints: + tumour_id = "|".join(CFG["runs"]["tumour_sample_id"]) + shell: + op.as_one_line(""" + Rscript -e 'library(dryclean); library(parallel)' + -e 'samp <- readRDS("{input.rds}")' + -e 'decomp <- start_wash_cycle(cov = samp, detergent.pon.path = "{input.pon}", whole_genome = TRUE, mc.cores = {threads}, germline.file = "{input.germline}", germline.filter = TRUE)' + -e 'saveRDS(decomp, "{output.rds}")' > {log.stdout} 2> {log.stderr} + """) + +def get_pp(wildcards): + pp = config['lcr-modules']['jabba']['pp'] + + purity = pp[wildcards.genome_build][wildcards.tumour_id]['purity'] + purity_range = [round(purity - 0.1, 2), round(purity + 0.1, 2)] + purity_range = [str(1) if x > 1 else str(0) if x < 0 else str(x) for x in purity_range] + + ploidy = pp[wildcards.genome_build][wildcards.tumour_id]['ploidy'] + + return({'purity': ','.join(purity_range), 'ploidy': ploidy}) + +rule _jabba_run_jabba: + input: + installed = str(rules._jabba_install_jabba.output.complete), + rds = str(rules._jabba_run_dryclean_tumour.output.rds), + junc = str(rules._jabba_merge_svs.output.junc) + output: + rds = CFG["dirs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/jabba.simple.gg.rds", + karyograph = CFG["dirs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/karyograph.rds", + simple = CFG["dirs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/jabba.simple.rds" + log: + stdout = CFG["logs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.stdout.log", + stderr = CFG["logs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.stderr.log" + params: + opts = CFG["options"]["jabba"], + purity = lambda w: get_pp(w)['purity'], + ploidy = lambda w: get_pp(w)['ploidy'], + CPLEX = CFG["CPLEX_DIR"] + conda: CFG["conda_envs"]["jabba"] + threads: CFG["threads"]["jabba"] + resources: + mem_mb = CFG["mem_mb"]["jabba"] + shell: + op.as_one_line(""" + JABBA_PATH=$(Rscript -e 'cat(paste0(installed.packages()["JaBbA", "LibPath"], "/JaBbA/extdata/"))'); $JABBA_PATH/jba `readlink -e {input.junc}` `readlink -e {input.rds}` --field foreground --cfield tier --outdir `dirname {output.rds}` --purity {params.purity} --cores {threads} {params.opts} > {log.stdout} 2> {log.stderr} + """) + + +rule _jabba_link_graph_rds: + input: + rds = CFG["dirs"]["jabba"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/jabba.simple.gg.rds" + output: + rds = CFG["dirs"]["outputs"] + "rds/{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.jabba.simple.gg.rds" + run: + op.relative_symlink(input.rds, output.rds) + + +# Generates the target sentinels for each run, which generate the symlinks +rule _jabba_all: + input: + expand( + [ + str(rules._jabba_link_graph_rds.output.rds), + ], + zip, # Run expand() with zip(), not product() + seq_type=CFG["runs"]["tumour_seq_type"], + genome_build=CFG["runs"]["tumour_genome_build"], + tumour_id=CFG["runs"]["tumour_sample_id"], + normal_id=CFG["runs"]["normal_sample_id"], + pair_status=CFG["runs"]["pair_status"]) + + +##### CLEANUP ##### + + +# Perform some clean-up tasks, including storing the module-specific +# configuration on disk and deleting the `CFG` variable +op.cleanup_module(CFG) diff --git a/modules/jabba/1.0/schemas/base-1.0.yaml b/modules/jabba/1.0/schemas/base-1.0.yaml new file mode 120000 index 00000000..0a69d1ce --- /dev/null +++ b/modules/jabba/1.0/schemas/base-1.0.yaml @@ -0,0 +1 @@ +../../../../schemas/base/base-1.0.yaml \ No newline at end of file diff --git a/modules/jabba/1.0/src/R/merge_svs.R b/modules/jabba/1.0/src/R/merge_svs.R new file mode 100644 index 00000000..3829d1f0 --- /dev/null +++ b/modules/jabba/1.0/src/R/merge_svs.R @@ -0,0 +1,79 @@ +suppressPackageStartupMessages({ + library(argparse) + library(data.table) + library(dplyr) + library(tidyr) + library(magrittr) + library(purrr) + library(gGnome) +}) + +##### PARSER ##### + +parser <- ArgumentParser() +parser$add_argument('--manta', help = 'Path to Manta VCF.') +parser$add_argument('--gridss', help = 'Path to GRIDSS VCF.') +parser$add_argument('--genome', help = 'Genome build.') +parser$add_argument('--pad', default = 100, help = 'Padding for SV merging. [Default %(default)s].') +parser$add_argument('--rds', help = 'Output RDS') +args <- parser$parse_args() + +##### TESTING ##### + +# args <- list() +# args$manta <- 'results/gambl/jabba-1.0/00-inputs/junc/manta/genome--hg38/05-18796T--05-18796N--matched.vcf' +# args$gridss <- 'results/gambl/jabba-1.0/00-inputs/junc/gridss/genome--hg38/05-18796T--05-18796N--matched.vcf' +# args$genome <- 'hg38' +# args$pad <- 50 + +##### MERGING ##### + +br <- list() + +sl <- NULL +if (args$genome == 'grch37') { + sl <- hg_seqlengths('BSgenome.Hsapiens.UCSC.hg19::Hsapiens', chr = FALSE) +} else if (args$genome == 'hg38') { + sl <- hg_seqlengths('BSgenome.Hsapiens.UCSC.hg38::Hsapiens', chr = TRUE) +} + +# FIX: jJ fails when no breakpoints are present +# i.e., only del, dup, ins are present +# Should only be a problem with Manta +br$manta <- + tryCatch({ + jJ(args$manta, seqlengths = sl) + }, error = function(e){ + GRanges() + }) +br$gridss <- jJ(args$gridss, seqlengths = sl) + +any.empty <- any(map_int(br, length)==0) + +# Handle empty SV inputs +if (length(br$manta) == 0) { + br.merged <- merge(gridss = br$gridss, pad = args$pad) +} else if (length(br$gridss) == 0) { + br.merged <- merge(manta = br$manta, pad = args$pad) +} else if (length(br$gridss) == 0 && length(br$manta) == 0) { + warning("GRIDSS and Manta VCFs are both empty.\n") +} else { + br.merged <- merge(manta = br$manta, gridss = br$gridss, pad = args$pad) +} + +br.merged.val <- as.data.table(values(br.merged$grl)) +br.merged.grl <- GRangesList(br.merged$grl) + +# Categorize variants into tiers if SVs are available from both tools +if (!any.empty) { + br.merged.val$tier <- br.merged.val$seen.by.manta * br.merged.val$seen.by.gridss + br.merged.val[, tier := ifelse(tier == 0, 2, 1)] + br.merged.val[FILTER.manta != "PASS" | FILTER.gridss != "PASS", tier := 3] +} + +values(br.merged.grl) <- br.merged.val + +##### OUTPUT ##### + +saveRDS(br.merged.grl, file = args$rds) + diff --git a/modules/jabba/CHANGELOG.md b/modules/jabba/CHANGELOG.md new file mode 100644 index 00000000..9980e858 --- /dev/null +++ b/modules/jabba/CHANGELOG.md @@ -0,0 +1,13 @@ +# Changelog + +All notable changes to the `jabba` module will be documented in this file. + +The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), +and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). + +## [1.0] - 2021-04-01 + +This release was authored by Prasath Pararajalingam. + +- Used custom versions of fragcounter and dryclean functions for running chr-prefixed + samples. diff --git a/workflows/reference_files/2.4/config/default.yaml b/workflows/reference_files/2.4/config/default.yaml index 1ad75c50..f65a7026 100644 --- a/workflows/reference_files/2.4/config/default.yaml +++ b/workflows/reference_files/2.4/config/default.yaml @@ -138,12 +138,30 @@ tools: gsutil: conda_env: "envs/gsutil-4.53.yaml" version: "4.53" + wiggletools: + conda_env: "envs/wiggletools-1.2.10.yaml" + version: "1.2.10" + rtracklayer: + conda_env: "envs/rtracklayer-1.50.0.yaml" + version: "1.50.0" + jabba: + conda_env: "envs/jabba.yaml" + version: "1.0.0" sigprofiler: conda_env: "envs/sigprofiler-1.1.yaml" version: "1.1" bcftools: conda_env: "envs/bcftools-1.10.2.yaml" version: "1.10.2" +pon: + hg38: "etc/hg38.normals.tbl" + grch37: "etc/grch37.normals.tbl" + +jabba: + fragcounter: "src/jabba/run_custom_fragcounter.R" + make_pon: "src/jabba/make_pon.R" + make_germline: "src/jabba/make_germline_filter.R" + cvbio_config: gtf: diff --git a/workflows/reference_files/2.4/envs/jabba.yaml b/workflows/reference_files/2.4/envs/jabba.yaml new file mode 120000 index 00000000..e49e6e77 --- /dev/null +++ b/workflows/reference_files/2.4/envs/jabba.yaml @@ -0,0 +1 @@ +../../../../modules/jabba/1.0/envs/jabba.yaml \ No newline at end of file diff --git a/workflows/reference_files/2.4/envs/rtracklayer-1.50.0.yaml b/workflows/reference_files/2.4/envs/rtracklayer-1.50.0.yaml new file mode 100644 index 00000000..d5adb591 --- /dev/null +++ b/workflows/reference_files/2.4/envs/rtracklayer-1.50.0.yaml @@ -0,0 +1,123 @@ +name: rtracklayer-1.50.0 +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - _libgcc_mutex=0.1=conda_forge + - _openmp_mutex=4.5=1_gnu + - _r-mutex=1.0.1=anacondar_1 + - binutils_impl_linux-64=2.35.1=h193b22a_2 + - binutils_linux-64=2.35=h67ddf6f_30 + - bioconductor-biobase=2.50.0=r40hd029910_1 + - bioconductor-biocgenerics=0.36.0=r40hdfd78af_1 + - bioconductor-biocparallel=1.24.1=r40h399db7b_0 + - bioconductor-biostrings=2.58.0=r40hd029910_1 + - bioconductor-delayedarray=0.16.3=r40hd029910_0 + - bioconductor-genomeinfodb=1.26.4=r40hdfd78af_0 + - bioconductor-genomeinfodbdata=1.2.4=r40hdfd78af_1 + - bioconductor-genomicalignments=1.26.0=r40hd029910_1 + - bioconductor-genomicranges=1.42.0=r40hd029910_1 + - bioconductor-iranges=2.24.1=r40hd029910_0 + - bioconductor-matrixgenerics=1.2.1=r40hdfd78af_0 + - bioconductor-rhtslib=1.22.0=r40hd029910_1 + - bioconductor-rsamtools=2.6.0=r40h399db7b_1 + - bioconductor-rtracklayer=1.50.0=r40h9bb0e53_1 + - bioconductor-s4vectors=0.28.1=r40hd029910_0 + - bioconductor-summarizedexperiment=1.20.0=r40hdfd78af_1 + - bioconductor-xvector=0.30.0=r40hd029910_1 + - bioconductor-zlibbioc=1.36.0=r40hd029910_1 + - bwidget=1.9.14=ha770c72_0 + - bzip2=1.0.8=h7f98852_4 + - c-ares=1.17.1=h7f98852_1 + - ca-certificates=2020.12.5=ha878542_0 + - cairo=1.16.0=h6cf1ce9_1008 + - curl=7.75.0=h979ede3_0 + - fontconfig=2.13.1=hba837de_1004 + - freetype=2.10.4=h0708190_1 + - fribidi=1.0.10=h36c2ea0_0 + - gcc_impl_linux-64=9.3.0=h70c0ae5_18 + - gcc_linux-64=9.3.0=hf25ea35_30 + - gettext=0.19.8.1=h0b5b191_1005 + - gfortran_impl_linux-64=9.3.0=hc4a2995_18 + - gfortran_linux-64=9.3.0=hdc58fab_30 + - graphite2=1.3.13=h58526e2_1001 + - gsl=2.6=he838d99_2 + - gxx_impl_linux-64=9.3.0=hd87eabc_18 + - gxx_linux-64=9.3.0=h3fbe746_30 + - harfbuzz=2.8.0=h83ec7ef_1 + - icu=68.1=h58526e2_0 + - jpeg=9d=h36c2ea0_0 + - kernel-headers_linux-64=2.6.32=h77966d4_13 + - krb5=1.17.2=h926e7f8_0 + - ld_impl_linux-64=2.35.1=hea4e1c9_2 + - libblas=3.9.0=8_openblas + - libcblas=3.9.0=8_openblas + - libcurl=7.75.0=hc4aaa36_0 + - libedit=3.1.20191231=he28a2e2_2 + - libev=4.33=h516909a_1 + - libffi=3.3=h58526e2_2 + - libgcc-devel_linux-64=9.3.0=h7864c58_18 + - libgcc-ng=9.3.0=h2828fa1_18 + - libgfortran-ng=9.3.0=hff62375_18 + - libgfortran5=9.3.0=hff62375_18 + - libglib=2.68.0=h3e27bee_2 + - libgomp=9.3.0=h2828fa1_18 + - libiconv=1.16=h516909a_0 + - liblapack=3.9.0=8_openblas + - libnghttp2=1.43.0=h812cca2_0 + - libopenblas=0.3.12=pthreads_h4812303_1 + - libpng=1.6.37=h21135ba_2 + - libssh2=1.9.0=ha56f1ee_6 + - libstdcxx-devel_linux-64=9.3.0=hb016644_18 + - libstdcxx-ng=9.3.0=h6de172a_18 + - libtiff=4.2.0=hdc55705_0 + - libuuid=2.32.1=h7f98852_1000 + - libwebp-base=1.2.0=h7f98852_2 + - libxcb=1.13=h7f98852_1003 + - libxml2=2.9.10=h72842e0_3 + - lz4-c=1.9.3=h9c3ff4c_0 + - make=4.3=hd18ef5c_1 + - ncurses=6.2=h58526e2_4 + - openssl=1.1.1k=h7f98852_0 + - pango=1.48.4=hb8ff022_0 + - pcre=8.44=he1b5a44_0 + - pcre2=10.36=h032f7d1_1 + - pixman=0.40.0=h36c2ea0_0 + - pthread-stubs=0.4=h36c2ea0_1001 + - r-base=4.0.3=h349a78a_8 + - r-bh=1.75.0_0=r40hc72bb7e_0 + - r-bitops=1.0_6=r40hcdcec82_1004 + - r-crayon=1.4.1=r40hc72bb7e_0 + - r-data.table=1.14.0=r40hcfec24a_0 + - r-formatr=1.8=r40hc72bb7e_0 + - r-futile.logger=1.4.3=r40h6115d3f_1003 + - r-futile.options=1.0.1=r40h6115d3f_1002 + - r-lambda.r=1.2.4=r40h6115d3f_1 + - r-lattice=0.20_41=r40hcfec24a_3 + - r-matrix=1.3_2=r40he454529_0 + - r-matrixstats=0.58.0=r40hcfec24a_0 + - r-rcurl=1.98_1.3=r40hcfec24a_0 + - r-snow=0.4_3=r40h6115d3f_1002 + - r-xml=3.99_0.6=r40hcfec24a_0 + - readline=8.0=he28a2e2_2 + - sed=4.8=he412f7d_0 + - sysroot_linux-64=2.12=h77966d4_13 + - tk=8.6.10=h21135ba_1 + - tktable=2.10=hb7b940f_3 + - xorg-kbproto=1.0.7=h7f98852_1002 + - xorg-libice=1.0.10=h7f98852_0 + - xorg-libsm=1.2.3=hd9c2040_1000 + - xorg-libx11=1.7.0=h7f98852_0 + - xorg-libxau=1.0.9=h7f98852_0 + - xorg-libxdmcp=1.1.3=h7f98852_0 + - xorg-libxext=1.3.4=h7f98852_1 + - xorg-libxrender=0.9.10=h7f98852_1003 + - xorg-libxt=1.2.1=h7f98852_2 + - xorg-renderproto=0.11.1=h7f98852_1002 + - xorg-xextproto=7.3.0=h7f98852_1002 + - xorg-xproto=7.0.31=h7f98852_1007 + - xz=5.2.5=h516909a_1 + - zlib=1.2.11=h516909a_1010 + - zstd=1.4.9=ha95c52a_0 +prefix: /home/prasathp/miniconda3/envs/rtracklayer-1.50.0 diff --git a/workflows/reference_files/2.4/envs/wiggletools-1.2.10.yaml b/workflows/reference_files/2.4/envs/wiggletools-1.2.10.yaml new file mode 100644 index 00000000..ec2443dc --- /dev/null +++ b/workflows/reference_files/2.4/envs/wiggletools-1.2.10.yaml @@ -0,0 +1,41 @@ +name: wiggletools-1.2.10 +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - _libgcc_mutex=0.1=conda_forge + - _openmp_mutex=4.5=1_gnu + - bzip2=1.0.8=h7f98852_4 + - c-ares=1.17.1=h7f98852_1 + - ca-certificates=2020.12.5=ha878542_0 + - curl=7.76.0=h979ede3_0 + - gsl=2.6=he838d99_2 + - htslib=1.12=h9093b5e_1 + - krb5=1.17.2=h926e7f8_0 + - libbigwig=0.4.6=h1b8c3c0_1 + - libblas=3.9.0=8_openblas + - libcblas=3.9.0=8_openblas + - libcurl=7.76.0=hc4aaa36_0 + - libdeflate=1.7=h7f98852_5 + - libedit=3.1.20191231=he28a2e2_2 + - libev=4.33=h516909a_1 + - libgcc-ng=9.3.0=h2828fa1_18 + - libgfortran-ng=9.3.0=hff62375_18 + - libgfortran5=9.3.0=hff62375_18 + - libgomp=9.3.0=h2828fa1_18 + - libnghttp2=1.43.0=h812cca2_0 + - libopenblas=0.3.12=pthreads_h4812303_1 + - libpng=1.6.37=h21135ba_2 + - libssh2=1.9.0=ha56f1ee_6 + - libstdcxx-ng=9.3.0=h6de172a_18 + - libuuid=2.32.1=h7f98852_1000 + - mysql-connector-c=6.1.11=h6eb9d5d_1007 + - ncurses=6.2=h58526e2_4 + - openssl=1.1.1k=h7f98852_0 + - tk=8.6.10=h21135ba_1 + - ucsc-wigtobigwig=377=h0b8a92a_2 + - wiggletools=1.2.10=he98db58_1 + - xz=5.2.5=h516909a_1 + - zlib=1.2.11=h516909a_1010 +prefix: /home/prasathp/miniconda3/envs/wiggletools-1.2.10 diff --git a/workflows/reference_files/2.4/etc/grch37.normals.tbl b/workflows/reference_files/2.4/etc/grch37.normals.tbl new file mode 100644 index 00000000..ea50e4ad --- /dev/null +++ b/workflows/reference_files/2.4/etc/grch37.normals.tbl @@ -0,0 +1,201 @@ +compression bam_available patient_id sample_id seq_type genome_build tissue_status cohort library_id pathology time_point protocol ffpe_or_frozen read_length strandedness seq_source_type sex EBV_status_inf link_name data_path unix_group biopsy_id +cram TRUE 03-31934 FL1001N genome grch37 normal FL_Kridel A13798 Genome frozen 100 frozen F data/genome_bams/FL1001N.grch37.bam /projects/analysis/analysis22/A13798/merge_bwa-0.5.7/100nt/hg19a/A13798_4_lanes_dupsFlagged.cram gambl +cram TRUE 00-27081 FL1002N genome grch37 normal FL_Kridel A32588 Genome frozen 100 frozen M data/genome_bams/FL1002N.grch37.bam /projects/rmorin/data/FL_Kridel/FL1002/FL1002N.cram gambl +cram TRUE 05-16784 FL1003N genome grch37 normal FL_Kridel A29909 Genome frozen 100 frozen F data/genome_bams/FL1003N.grch37.bam /projects/analysis/analysis11/A29909/merge_bwa/hg19a/A29909_3_lanes_dupsFlagged.cram gambl +cram TRUE 98-21877 FL1004N genome grch37 normal FL_Kridel A29907 Genome frozen 100 frozen M data/genome_bams/FL1004N.grch37.bam /projects/analysis/analysis11/A29907/merge_bwa/hg19a/A29907_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-40818 FL1005N genome grch37 normal FL_Kridel A29908 Genome frozen 100 frozen F data/genome_bams/FL1005N.grch37.bam /projects/analysis/analysis11/A29908/merge_bwa/hg19a/A29908_3_lanes_dupsFlagged.cram gambl +cram TRUE 00-28588 FL1006N genome grch37 normal FL_Kridel A29906 Genome frozen 100 frozen M data/genome_bams/FL1006N.grch37.bam /projects/analysis/analysis11/A29906/merge_bwa/hg19a/A29906_3_lanes_dupsFlagged.cram gambl +cram TRUE 02-14557 FL1008N genome grch37 normal FL_Kridel A30564 Genome frozen 100 frozen M data/genome_bams/FL1008N.grch37.bam /projects/analysis/analysis11/A30564/merge_bwa/hg19a/A30564_3_lanes_dupsFlagged.cram gambl +cram TRUE 03-28399 FL1009N genome grch37 normal FL_Kridel A41085 Genome frozen 100 frozen F data/genome_bams/FL1009N.grch37.bam /projects/analysis/analysis13/A41085/merge_bwa/100nt/hg19a/A41085_3_lanes_dupsFlagged.cram gambl +cram TRUE 99-30068 FL1010N genome grch37 normal FL_Kridel A32573 Genome frozen 100 frozen M data/genome_bams/FL1010N.grch37.bam /projects/analysis/analysis13/A32573/merge_bwa/100nt/hg19a/A32573_3_lanes_dupsFlagged.cram gambl +cram TRUE 00-12637 FL1011N genome grch37 normal FL_Kridel A32585 Genome frozen 100 frozen M data/genome_bams/FL1011N.grch37.bam /projects/analysis/analysis13/A32585/merge_bwa/100nt/hg19a/A32585_3_lanes_dupsFlagged.cram gambl +cram TRUE 06-14752 FL1012N genome grch37 normal FL_Kridel A32595 Genome frozen 100 frozen F data/genome_bams/FL1012N.grch37.bam /projects/analysis/analysis13/A32595/merge_bwa/100nt/hg19a/A32595_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-21038 FL1013N genome grch37 normal FL_Kridel A32578 Genome frozen 100 frozen M data/genome_bams/FL1013N.grch37.bam /projects/analysis/analysis14/A32578/merge_bwa/100nt/hg19a/A32578_3_lanes_dupsFlagged.cram gambl +cram TRUE 04-26932 FL1014N genome grch37 normal FL_Kridel A45934 Genome frozen 100 frozen M data/genome_bams/FL1014N.grch37.bam /projects/analysis/analysis14/A45934/merge_bwa/100nt/hg19a/A45934_3_lanes_dupsFlagged.cram gambl +cram TRUE 00-17988 FL1015N genome grch37 normal FL_Kridel A32583 Genome frozen 100 frozen F data/genome_bams/FL1015N.grch37.bam /projects/analysis/analysis13/A32583/merge_bwa/100nt/hg19a/A32583_3_lanes_dupsFlagged.cram gambl +cram TRUE 10-18768 FL1016N genome grch37 normal FL_Kridel A42955 Genome frozen 100 frozen F data/genome_bams/FL1016N.grch37.bam /projects/analysis/analysis14/A42955/merge_bwa/100nt/hg19a/A42955_3_lanes_dupsFlagged.cram gambl +cram TRUE 13-30325 FL1017N genome grch37 normal FL_Kridel A45789 Genome frozen 100 frozen M data/genome_bams/FL1017N.grch37.bam /projects/analysis/analysis14/A45789/merge_bwa/100nt/hg19a/A45789_3_lanes_dupsFlagged.cram gambl +bam TRUE 06-11184 FL1018N genome grch37 normal FL_Kridel A46201 Genome frozen 100 frozen F data/genome_bams/FL1018N.grch37.bam /projects/analysis/analysis15/A46201/merge_bwa/100nt/hg19a/A46201_3_lanes_dupsFlagged.bam gambl +bam TRUE 09-17636 FL1019N genome grch37 normal FL_Kridel A46202 Genome frozen 100 frozen M data/genome_bams/FL1019N.grch37.bam /projects/analysis/analysis15/A46202/merge_bwa/100nt/hg19a/A46202_3_lanes_dupsFlagged.bam gambl +bam TRUE 09-31458 FL1020N genome grch37 normal FL_Kridel A47937 Genome frozen 125 frozen M data/genome_bams/FL1020N.grch37.bam /projects/analysis/analysis16/A47937/merge_bwa/125nt/hg19a/A47937_2_lanes_dupsFlagged.bam gambl +cram TRUE 96-13639 FL2001N genome grch37 normal FL_Kridel A17754 Genome frozen 100 frozen M data/genome_bams/FL2001N.grch37.bam /projects/rmorin/data/FL_Kridel/FL2001/FL2001N.cram gambl +cram TRUE 06-28477 FL2002N genome grch37 normal FL_Kridel A17755 Genome frozen 100 frozen M data/genome_bams/FL2002N.grch37.bam /projects/rmorin/data/FL_Kridel/FL2002/FL2002N.cram gambl +cram TRUE 06-12968 FL2003N genome grch37 normal FL_Kridel A32594 Genome frozen 100 frozen F data/genome_bams/FL2003N.grch37.bam /projects/analysis/analysis13/A32594/merge_bwa/100nt/hg19a/A32594_3_lanes_dupsFlagged.cram gambl +cram TRUE 06-25647 FL2004N genome grch37 normal FL_Kridel A30565 Genome frozen 100 frozen F data/genome_bams/FL2004N.grch37.bam /projects/analysis/analysis12/A30565/merge_bwa/100nt/hg19a/A30565_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-37759 FL2005N genome grch37 normal FL_Kridel A32576 Genome frozen 100 frozen M data/genome_bams/FL2005N.grch37.bam /projects/analysis/analysis13/A32576/merge_bwa/100nt/hg19a/A32576_3_lanes_dupsFlagged.cram gambl +cram TRUE 05-32284 FL2006N genome grch37 normal FL_Kridel A43003 Genome frozen 100 frozen M data/genome_bams/FL2006N.grch37.bam /projects/analysis/analysis14/A43003/merge_bwa/100nt/hg19a/A43003_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-33580 FL2007N genome grch37 normal FL_Kridel A42960 Genome frozen 100 frozen F data/genome_bams/FL2007N.grch37.bam /projects/analysis/analysis14/A42960/merge_bwa/100nt/hg19a/A42960_3_lanes_dupsFlagged.cram gambl +bam TRUE 12-35317 FL2008N genome grch37 normal FL_Kridel A46203 Genome frozen 100 frozen M data/genome_bams/FL2008N.grch37.bam /projects/analysis/analysis15/A46203/merge_bwa/100nt/hg19a/A46203_3_lanes_dupsFlagged.bam gambl +cram TRUE 00-16220 FL3001N genome grch37 normal FL_Kridel A42963 Genome frozen 100 frozen F data/genome_bams/FL3001N.grch37.bam /projects/analysis/analysis14/A42963/merge_bwa/100nt/hg19a/A42963_3_lanes_dupsFlagged.cram gambl +cram TRUE 96-29962 FL3002N genome grch37 normal FL_Kridel A42965 Genome frozen 100 frozen F data/genome_bams/FL3002N.grch37.bam /projects/analysis/analysis14/A42965/merge_bwa/100nt/hg19a/A42965_3_lanes_dupsFlagged.cram gambl +cram TRUE 04-24504 FL3003N genome grch37 normal FL_Kridel A42967 Genome frozen 100 frozen M data/genome_bams/FL3003N.grch37.bam /projects/analysis/analysis14/A42967/merge_bwa/100nt/hg19a/A42967_3_lanes_dupsFlagged.cram gambl +cram TRUE 03-23652 FL3004N genome grch37 normal FL_Kridel A42969 Genome frozen 100 frozen F data/genome_bams/FL3004N.grch37.bam /projects/analysis/analysis14/A42969/merge_bwa/100nt/hg19a/A42969_3_lanes_dupsFlagged.cram gambl +bam TRUE 04-40070 FL3005N genome grch37 normal FL_Kridel A42971 Genome frozen 100 frozen F data/genome_bams/FL3005N.grch37.bam /projects/analysis/analysis14/A42971/merge_bwa/100nt/hg19a/A42971_3_lanes_dupsFlagged.bam gambl +cram TRUE 97-28459 FL3006N genome grch37 normal FL_Kridel A42973 Genome frozen 100 frozen M data/genome_bams/FL3006N.grch37.bam /projects/analysis/analysis14/A42973/merge_bwa/100nt/hg19a/A42973_3_lanes_dupsFlagged.cram gambl +cram TRUE 04-35917 FL3007N genome grch37 normal FL_Kridel A42975 Genome frozen 100 frozen F data/genome_bams/FL3007N.grch37.bam /projects/analysis/analysis14/A42975/merge_bwa/100nt/hg19a/A42975_3_lanes_dupsFlagged.cram gambl +cram TRUE 04-25276 FL3008N genome grch37 normal FL_Kridel A42977 Genome frozen 100 frozen M data/genome_bams/FL3008N.grch37.bam /projects/analysis/analysis14/A42977/merge_bwa/100nt/hg19a/A42977_3_lanes_dupsFlagged.cram gambl +cram TRUE 01-14271 FL3009N genome grch37 normal FL_Kridel A42979 Genome frozen 100 frozen F data/genome_bams/FL3009N.grch37.bam /projects/analysis/analysis14/A42979/merge_bwa/100nt/hg19a/A42979_3_lanes_dupsFlagged.cram gambl +cram TRUE 99-30885 FL3010N genome grch37 normal FL_Kridel A42981 Genome frozen 100 frozen M data/genome_bams/FL3010N.grch37.bam /projects/analysis/analysis14/A42981/merge_bwa/100nt/hg19a/A42981_3_lanes_dupsFlagged.cram gambl +cram TRUE 02-10151 FL3011N genome grch37 normal FL_Kridel A42983 Genome frozen 100 frozen F data/genome_bams/FL3011N.grch37.bam /projects/analysis/analysis14/A42983/merge_bwa/100nt/hg19a/A42983_3_lanes_dupsFlagged.cram gambl +cram TRUE 03-20737 FL3012N genome grch37 normal FL_Kridel A42985 Genome frozen 100 frozen M data/genome_bams/FL3012N.grch37.bam /projects/analysis/analysis14/A42985/merge_bwa/100nt/hg19a/A42985_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-11291 FL3013N genome grch37 normal FL_Kridel A42987 Genome frozen 100 frozen M data/genome_bams/FL3013N.grch37.bam /projects/analysis/analysis14/A42987/merge_bwa/100nt/hg19a/A42987_3_lanes_dupsFlagged.cram gambl +cram TRUE 01-22904 FL3014N genome grch37 normal FL_Kridel A42989 Genome frozen 100 frozen M data/genome_bams/FL3014N.grch37.bam /projects/analysis/analysis14/A42989/merge_bwa/100nt/hg19a/A42989_3_lanes_dupsFlagged.cram gambl +cram TRUE 06-19817 FL3015N genome grch37 normal FL_Kridel A42991 Genome frozen 100 frozen M data/genome_bams/FL3015N.grch37.bam /projects/analysis/analysis14/A42991/merge_bwa/100nt/hg19a/A42991_3_lanes_dupsFlagged.cram gambl +cram TRUE 06-24121 FL3016N genome grch37 normal FL_Kridel A42993 Genome frozen 100 frozen M data/genome_bams/FL3016N.grch37.bam /projects/analysis/analysis14/A42993/merge_bwa/100nt/hg19a/A42993_3_lanes_dupsFlagged.cram gambl +cram TRUE 07-10201 FL3017N genome grch37 normal FL_Kridel A42995 Genome frozen 100 frozen M data/genome_bams/FL3017N.grch37.bam /projects/analysis/analysis14/A42995/merge_bwa/100nt/hg19a/A42995_3_lanes_dupsFlagged.cram gambl +cram TRUE 05-18781 FL3018N genome grch37 normal FL_Kridel A42997 Genome frozen 100 frozen F data/genome_bams/FL3018N.grch37.bam /projects/analysis/analysis14/A42997/merge_bwa/100nt/hg19a/A42997_3_lanes_dupsFlagged.cram gambl +cram TRUE 06-30263 FL3019N genome grch37 normal FL_Kridel A42999 Genome frozen 100 frozen F data/genome_bams/FL3019N.grch37.bam /projects/analysis/analysis14/A42999/merge_bwa/100nt/hg19a/A42999_3_lanes_dupsFlagged.cram gambl +bam TRUE 06-30342 FL3020N genome grch37 normal FL_Kridel A43001 Genome frozen 100 frozen F data/genome_bams/FL3020N.grch37.bam /projects/analysis/analysis14/A43001/merge_bwa/100nt/hg19a/A43001_3_lanes_dupsFlagged.bam gambl +bam TRUE 05-32150 05-32150N genome grch37 normal DLBCL_Gascoyne A48265 Genome frozen 125 blood F data/genome_bams/05-32150N.grch37.bam /projects/analysis/analysis16/A48265/merge_bwa/125nt/hg19a/A48265_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-22818 13-22818N genome grch37 normal DLBCL_GenomeCanada A46939 Genome frozen 125 blood F data/genome_bams/13-22818N.grch37.bam /projects/analysis/analysis17/A46939/merge_bwa/125nt/hg19a/A46939_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-19570 13-19570N genome grch37 normal FL_GenomeCanada A46932 Genome frozen 125 blood M data/genome_bams/13-19570N.grch37.bam /projects/analysis/analysis15/A46932/merge_bwa/125nt/hg19a/A46932_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-26597 13-26597N genome grch37 normal FL_GenomeCanada A48276 Genome frozen 125 blood F data/genome_bams/13-26597N.grch37.bam /projects/analysis/analysis17/A48276/merge_bwa/125nt/hg19a/A48276_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-26601 13-26601N genome grch37 normal DLBCL_GenomeCanada A34733 Genome frozen 100 blood M data/genome_bams/13-26601N.grch37.bam /projects/analysis/analysis12/A34733/merge_bwa/hg19a/A34733_3_lanes_dupsFlagged.bam gambl +bam TRUE 13-29091 13-29091N genome grch37 normal FL_GenomeCanada A48277 Genome frozen 125 blood M data/genome_bams/13-29091N.grch37.bam /projects/analysis/analysis17/A48277/merge_bwa/125nt/hg19a/A48277_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-27960 13-27960N genome grch37 normal FL_GenomeCanada A46933 Genome frozen 125 blood F data/genome_bams/13-27960N.grch37.bam /projects/analysis/analysis15/A46933/merge_bwa/125nt/hg19a/A46933_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-30451 13-30451N genome grch37 normal DLBCL_GenomeCanada A46940 Genome frozen 125 blood M data/genome_bams/13-30451N.grch37.bam /projects/analysis/analysis15/A46940/merge_bwa/125nt/hg19a/A46940_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-31210 13-31210N genome grch37 normal DLBCL_GenomeCanada A34734 Genome frozen 100 blood M data/genome_bams/13-31210N.grch37.bam /projects/analysis/analysis12/A34734/merge_bwa/hg19a/A34734_3_lanes_dupsFlagged.bam gambl +bam TRUE 13-34919 13-34919N genome grch37 normal FL_GenomeCanada A48283 Genome frozen 125 blood M data/genome_bams/13-34919N.grch37.bam /projects/analysis/analysis18/A48283/merge_bwa/125nt/hg19a/A48283_2_lanes_dupsFlagged.bam gambl +bam TRUE 99-13520 99-13520N genome grch37 normal FL_GenomeCanada A46934 Genome frozen 125 blood F data/genome_bams/99-13520N.grch37.bam /projects/analysis/analysis15/A46934/merge_bwa/125nt/hg19a/A46934_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-40593 13-40593N genome grch37 normal FL_GenomeCanada A46935 Genome frozen 125 blood M data/genome_bams/13-40593N.grch37.bam /projects/analysis/analysis15/A46935/merge_bwa/125nt/hg19a/A46935_2_lanes_dupsFlagged.bam gambl +bam TRUE 04-38964 04-38964N genome grch37 normal FL_GenomeCanada A48274 Genome frozen 125 blood F data/genome_bams/04-38964N.grch37.bam /projects/analysis/analysis18/A48274/merge_bwa/125nt/hg19a/A48274_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-40370 13-40370N genome grch37 normal FL_GenomeCanada A48290 Genome frozen 125 blood F data/genome_bams/13-40370N.grch37.bam /projects/analysis/analysis18/A48290/merge_bwa/125nt/hg19a/A48290_2_lanes_dupsFlagged.bam gambl +bam TRUE 13-43956 13-43956N genome grch37 normal FL_GenomeCanada A46936 Genome frozen 125 blood F data/genome_bams/13-43956N.grch37.bam /projects/analysis/analysis15/A46936/merge_bwa/125nt/hg19a/A46936_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-11777 14-11777N genome grch37 normal FL_GenomeCanada A48295 Genome frozen 125 blood F data/genome_bams/14-11777N.grch37.bam /projects/analysis/analysis18/A48295/merge_bwa/125nt/hg19a/A48295_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-11009 14-11009N genome grch37 normal FL_GenomeCanada A48287 Genome frozen 125 blood M data/genome_bams/14-11009N.grch37.bam /projects/analysis/analysis18/A48287/merge_bwa/125nt/hg19a/A48287_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-11247 14-11247N genome grch37 normal DLBCL_GenomeCanada A48294 Genome frozen 125 blood M data/genome_bams/14-11247N.grch37.bam /projects/analysis/analysis18/A48294/merge_bwa/125nt/hg19a/A48294_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-13480 14-13480N genome grch37 normal FL_GenomeCanada A46937 Genome frozen 125 blood F data/genome_bams/14-13480N.grch37.bam /projects/analysis/analysis15/A46937/merge_bwa/125nt/hg19a/A46937_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-11427 14-11427N genome grch37 normal FL_GenomeCanada A46945 Genome frozen 125 blood F data/genome_bams/14-11427N.grch37.bam /projects/analysis/analysis15/A46945/merge_bwa/125nt/hg19a/A46945_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-13938 14-13938N genome grch37 normal FL_GenomeCanada A47179 Genome frozen 125 blood M data/genome_bams/14-13938N.grch37.bam /projects/analysis/analysis15/A47179/merge_bwa/125nt/hg19a/A47179_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-16707 14-16707N genome grch37 normal DLBCL_GenomeCanada A46942 Genome frozen 125 blood F data/genome_bams/14-16707N.grch37.bam /projects/analysis/analysis15/A46942/merge_bwa/125nt/hg19a/A46942_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-13213 14-13213N genome grch37 normal FL_GenomeCanada A47178 Genome frozen 125 blood M data/genome_bams/14-13213N.grch37.bam /projects/analysis/analysis15/A47178/merge_bwa/125nt/hg19a/A47178_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-13959 14-13959N genome grch37 normal DLBCL_GenomeCanada A46943 Genome frozen 125 blood F data/genome_bams/14-13959N.grch37.bam /projects/analysis/analysis15/A46943/merge_bwa/125nt/hg19a/A46943_2_lanes_dupsFlagged.bam gambl +bam TRUE 01-20260 01-20260N genome grch37 normal FL_GenomeCanada A48280 Genome frozen 125 blood M data/genome_bams/01-20260N.grch37.bam /projects/analysis/analysis17/A48280/merge_bwa/125nt/hg19a/A48280_2_lanes_dupsFlagged.bam gambl +bam TRUE 03-34157 03-34157N genome grch37 normal FL_GenomeCanada A46938 Genome frozen 125 blood F data/genome_bams/03-34157N.grch37.bam /projects/analysis/analysis15/A46938/merge_bwa/125nt/hg19a/A46938_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-15505 14-15505N genome grch37 normal FL_GenomeCanada A48279 Genome frozen 125 blood M data/genome_bams/14-15505N.grch37.bam /projects/analysis/analysis17/A48279/merge_bwa/125nt/hg19a/A48279_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-20962 14-20962N genome grch37 normal DLBCL_GenomeCanada A51624 Genome frozen 125 blood M data/genome_bams/14-20962N.grch37.bam /projects/analysis/analysis21/A51624/merge_bwa-0.5.7/125nt/hg19a/A51624_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-16281 14-16281N genome grch37 normal DLBCL_GenomeCanada A48281 Genome frozen 125 blood F data/genome_bams/14-16281N.grch37.bam /projects/analysis/analysis19/A48281/merge_bwa/125nt/hg19a/A48281_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-25466 14-25466N genome grch37 normal DLBCL_GenomeCanada A48282 Genome frozen 125 blood M data/genome_bams/14-25466N.grch37.bam /projects/analysis/analysis17/A48282/merge_bwa/125nt/hg19a/A48282_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-25416 14-25416N genome grch37 normal FL_GenomeCanada A48296 Genome frozen 125 blood M data/genome_bams/14-25416N.grch37.bam /projects/analysis/analysis18/A48296/merge_bwa/125nt/hg19a/A48296_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-23891 14-23891N genome grch37 normal DLBCL_GenomeCanada A48293 Genome frozen 125 blood M data/genome_bams/14-23891N.grch37.bam /projects/analysis/analysis18/A48293/merge_bwa/125nt/hg19a/A48293_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-26632 14-26632N genome grch37 normal FL_GenomeCanada A55756 Genome frozen 125 blood F data/genome_bams/14-26632N.grch37.bam /projects/analysis/analysis22/A55756/merge_bwa-0.5.7/125nt/hg19a/A55756_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-24907 14-24907N genome grch37 normal FL_GenomeCanada A48289 Genome frozen 125 blood F data/genome_bams/14-24907N.grch37.bam /projects/analysis/analysis18/A48289/merge_bwa/125nt/hg19a/A48289_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-28286 14-28286N genome grch37 normal FL_GenomeCanada A55757 Genome frozen 125 blood F data/genome_bams/14-28286N.grch37.bam /projects/analysis/analysis22/A55757/merge_bwa-0.5.7/125nt/hg19a/A55757_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-27873 14-27873N genome grch37 normal DLBCL_GenomeCanada A47177 Genome frozen 125 blood M data/genome_bams/14-27873N.grch37.bam /projects/analysis/analysis15/A47177/merge_bwa/125nt/hg19a/A47177_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-29644 14-29644N genome grch37 normal FL_GenomeCanada A48288 Genome frozen 125 blood M data/genome_bams/14-29644N.grch37.bam /projects/analysis/analysis18/A48288/merge_bwa/125nt/hg19a/A48288_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-29140 14-29140N genome grch37 normal FL_GenomeCanada A55758 Genome frozen 125 blood M data/genome_bams/14-29140N.grch37.bam /projects/analysis/analysis22/A55758/merge_bwa-0.5.7/125nt/hg19a/A55758_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-32185 14-32185N genome grch37 normal FL_GenomeCanada A48275 Genome frozen 125 blood M data/genome_bams/14-32185N.grch37.bam /projects/analysis/analysis18/A48275/merge_bwa/125nt/hg19a/A48275_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-32442 14-32442N genome grch37 normal DLBCL_GenomeCanada A48286 Genome frozen 125 blood M data/genome_bams/14-32442N.grch37.bam /projects/analysis/analysis18/A48286/merge_bwa/125nt/hg19a/A48286_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-32899 14-32899N genome grch37 normal FL_GenomeCanada A51633 Genome frozen 125 blood F data/genome_bams/14-32899N.grch37.bam /projects/analysis/analysis21/A51633/merge_bwa-0.5.7/125nt/hg19a/A51633_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-32922 14-32922N genome grch37 normal FL_GenomeCanada A48285 Genome frozen 125 blood M data/genome_bams/14-32922N.grch37.bam /projects/analysis/analysis18/A48285/merge_bwa/125nt/hg19a/A48285_2_lanes_dupsFlagged.bam gambl +bam TRUE 10-24757 10-24757N genome grch37 normal CLL_GenomeCanada A61236 Genome frozen 150 sorted_cells F data/genome_bams/10-24757N.grch37.bam /projects/analysis/analysis26/A61236/merge_bwa-0.5.7/150nt/hg19a/A61236_4_lanes_dupsFlagged.bam gambl +bam TRUE 14-33436 14-33436N genome grch37 normal DLBCL_GenomeCanada A70268 Genome frozen 150 blood M data/genome_bams/14-33436N.grch37.bam /projects/analysis/analysis28/A70268/H25LTCCXY_3/A70268/150nt/hg19a/bwa-mem-0.7.6a-sb/A70268_1_lane_dupsFlagged.bam gambl +bam TRUE 14-30670 14-30670N genome grch37 normal FL_GenomeCanada A48291 Genome frozen 125 blood M data/genome_bams/14-30670N.grch37.bam /projects/analysis/analysis18/A48291/merge_bwa/125nt/hg19a/A48291_2_lanes_dupsFlagged.bam gambl +bam TRUE 96-31596 96-31596N genome grch37 normal DLBCL_GenomeCanada A48688 Genome frozen 125 blood M data/genome_bams/96-31596N.grch37.bam /projects/analysis/analysis18/A48688/merge_bwa/125nt/hg19a/A48688_2_lanes_dupsFlagged.bam gambl +bam TRUE 04-33507 04-33507N genome grch37 normal CLL_GenomeCanada A51661 Genome frozen 125 sorted_cells F data/genome_bams/04-33507N.grch37.bam /projects/analysis/analysis21/A51661/merge_bwa-0.5.7/125nt/hg19a/A51661_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-34508 14-34508N genome grch37 normal FL_GenomeCanada A51642 Genome frozen 125 blood F data/genome_bams/14-34508N.grch37.bam /projects/analysis/analysis21/A51642/merge_bwa-0.5.7/125nt/hg19a/A51642_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-34800 14-34800N genome grch37 normal FL_GenomeCanada A70269 Genome frozen 150 blood M data/genome_bams/14-34800N.grch37.bam /projects/analysis/analysis28/A70269/H25LTCCXY_4/A70269/150nt/hg19a/bwa-mem-0.7.6a-sb/A70269_1_lane_dupsFlagged.bam gambl +bam TRUE 12-32967 12-32967N genome grch37 normal FL_GenomeCanada A51651 Genome frozen 125 blood F data/genome_bams/12-32967N.grch37.bam /projects/analysis/analysis21/A51651/merge_bwa-0.5.7/125nt/hg19a/A51651_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-35030 14-35030N genome grch37 normal FL_GenomeCanada A51659 Genome frozen 125 blood M data/genome_bams/14-35030N.grch37.bam /projects/analysis/analysis21/A51659/merge_bwa-0.5.7/125nt/hg19a/A51659_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-33262 14-33262N genome grch37 normal DLBCL_GenomeCanada A51667 Genome frozen 125 blood F data/genome_bams/14-33262N.grch37.bam /projects/analysis/analysis21/A51667/merge_bwa-0.5.7/125nt/hg19a/A51667_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-34590 14-34590N genome grch37 normal FL_GenomeCanada A48284 Genome frozen 125 blood M data/genome_bams/14-34590N.grch37.bam /projects/analysis/analysis18/A48284/merge_bwa/125nt/hg19a/A48284_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-35632 14-35632N genome grch37 normal DLBCL_GenomeCanada A51675 Genome frozen 125 blood M data/genome_bams/14-35632N.grch37.bam /projects/analysis/analysis21/A51675/merge_bwa-0.5.7/125nt/hg19a/A51675_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-34708 14-34708N genome grch37 normal FL_GenomeCanada A51677 Genome frozen 125 blood M data/genome_bams/14-34708N.grch37.bam /projects/analysis/analysis21/A51677/merge_bwa-0.5.7/125nt/hg19a/A51677_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-37722 14-37722N genome grch37 normal DLBCL_GenomeCanada A51625 Genome frozen 125 blood M data/genome_bams/14-37722N.grch37.bam /projects/analysis/analysis21/A51625/merge_bwa-0.5.7/125nt/hg19a/A51625_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-36022 14-36022N genome grch37 normal DLBCL_GenomeCanada A51634 Genome frozen 125 blood F data/genome_bams/14-36022N.grch37.bam /projects/analysis/analysis21/A51634/merge_bwa-0.5.7/125nt/hg19a/A51634_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-38639 14-38639N genome grch37 normal FL_GenomeCanada A51643 Genome frozen 125 blood M data/genome_bams/14-38639N.grch37.bam /projects/analysis/analysis21/A51643/merge_bwa-0.5.7/125nt/hg19a/A51643_2_lanes_dupsFlagged.bam gambl +bam TRUE 07-34776 07-34776N genome grch37 normal FL_GenomeCanada A51652 Genome frozen 125 blood F data/genome_bams/07-34776N.grch37.bam /projects/analysis/analysis21/A51652/merge_bwa-0.5.7/125nt/hg19a/A51652_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-37865 14-37865N genome grch37 normal FL_GenomeCanada A51660 Genome frozen 125 blood M data/genome_bams/14-37865N.grch37.bam /projects/analysis/analysis21/A51660/merge_bwa-0.5.7/125nt/hg19a/A51660_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-10535 15-10535N genome grch37 normal DLBCL_GenomeCanada A51668 Genome frozen 125 blood M data/genome_bams/15-10535N.grch37.bam /projects/analysis/analysis21/A51668/merge_bwa-0.5.7/125nt/hg19a/A51668_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-10675 15-10675N genome grch37 normal FL_GenomeCanada A51676 Genome frozen 125 blood M data/genome_bams/15-10675N.grch37.bam /projects/analysis/analysis21/A51676/merge_bwa-0.5.7/125nt/hg19a/A51676_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-41461 14-41461N genome grch37 normal DLBCL_GenomeCanada A51617 Genome frozen 125 blood F data/genome_bams/14-41461N.grch37.bam /projects/analysis/analysis21/A51617/merge_bwa-0.5.7/125nt/hg19a/A51617_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-11617 15-11617N genome grch37 normal DLBCL_GenomeCanada A55759 Genome frozen 125 blood F data/genome_bams/15-11617N.grch37.bam /projects/analysis/analysis22/A55759/merge_bwa-0.5.7/125nt/hg19a/A55759_2_lanes_dupsFlagged.bam gambl +bam TRUE 09-31233 09-31233N genome grch37 normal DLBCL_GenomeCanada A55760 Genome frozen 125 blood M data/genome_bams/09-31233N.grch37.bam /projects/analysis/analysis22/A55760/merge_bwa-0.5.7/125nt/hg19a/A55760_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-12532 15-12532N genome grch37 normal FL_GenomeCanada A51626 Genome frozen 125 blood M data/genome_bams/15-12532N.grch37.bam /projects/analysis/analysis21/A51626/merge_bwa-0.5.7/125nt/hg19a/A51626_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-13365 15-13365N genome grch37 normal DLBCL_GenomeCanada A51635 Genome frozen 125 blood F data/genome_bams/15-13365N.grch37.bam /projects/analysis/analysis21/A51635/merge_bwa-0.5.7/125nt/hg19a/A51635_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-13383 15-13383N genome grch37 normal DLBCL_GenomeCanada A55761 Genome frozen 125 blood F data/genome_bams/15-13383N.grch37.bam /projects/analysis/analysis22/A55761/merge_bwa-0.5.7/125nt/hg19a/A55761_2_lanes_dupsFlagged.bam gambl +bam TRUE 07-41844 07-41844N genome grch37 normal CLL_GenomeCanada A51669 Genome frozen 125 sorted_cells M data/genome_bams/07-41844N.grch37.bam /projects/analysis/analysis21/A51669/merge_bwa-0.5.7/125nt/hg19a/A51669_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-14583 15-14583N genome grch37 normal FL_GenomeCanada A51644 Genome frozen 125 blood F data/genome_bams/15-14583N.grch37.bam /projects/analysis/analysis21/A51644/merge_bwa-0.5.7/125nt/hg19a/A51644_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-15253 15-15253N genome grch37 normal FL_GenomeCanada A55762 Genome frozen 125 blood M data/genome_bams/15-15253N.grch37.bam /projects/analysis/analysis22/A55762/merge_bwa-0.5.7/125nt/hg19a/A55762_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-14453 15-14453N genome grch37 normal FL_GenomeCanada A51653 Genome frozen 125 blood M data/genome_bams/15-14453N.grch37.bam /projects/analysis/analysis21/A51653/merge_bwa-0.5.7/125nt/hg19a/A51653_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-15757 15-15757N genome grch37 normal DLBCL_GenomeCanada A55763 Genome frozen 125 blood M data/genome_bams/15-15757N.grch37.bam /projects/analysis/analysis22/A55763/merge_bwa-0.5.7/125nt/hg19a/A55763_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-14813 15-14813N genome grch37 normal FL_GenomeCanada A70270 Genome frozen 150 blood F data/genome_bams/15-14813N.grch37.bam /projects/analysis/analysis28/A70270/H25LTCCXY_5/A70270/150nt/hg19a/bwa-mem-0.7.6a-sb/A70270_1_lane_dupsFlagged.bam gambl +cram TRUE 15-16852 15-16852N genome grch37 normal FL_GenomeCanada A85280 Genome frozen 150 blood M data/genome_bams/15-16852N.grch37.bam /projects/analysis/analysis30/A85280/merge26242_bwa-mem-0.7.6a-sb/150nt/hg19a/A85280_27_lanes_dupsFlagged.cram gambl +bam TRUE 15-16885 15-16885N genome grch37 normal FL_GenomeCanada A55764 Genome frozen 125 blood F data/genome_bams/15-16885N.grch37.bam /projects/analysis/analysis22/A55764/merge_bwa-0.5.7/125nt/hg19a/A55764_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-27524 14-27524N genome grch37 normal FL_GenomeCanada A70271 Genome frozen 150 blood F data/genome_bams/14-27524N.grch37.bam /projects/analysis/analysis28/A70271/H25LTCCXY_6/A70271/150nt/hg19a/bwa-mem-0.7.6a-sb/A70271_1_lane_dupsFlagged.bam gambl +bam TRUE 15-18916 15-18916N genome grch37 normal FL_GenomeCanada A55765 Genome frozen 125 blood M data/genome_bams/15-18916N.grch37.bam /projects/analysis/analysis22/A55765/merge_bwa-0.5.7/125nt/hg19a/A55765_2_lanes_dupsFlagged.bam gambl +bam TRUE 09-22014 09-22014N genome grch37 normal CLL_GenomeCanada A51616 Genome frozen 125 sorted_cells M data/genome_bams/09-22014N.grch37.bam /projects/analysis/analysis21/A51616/merge_bwa-0.5.7/125nt/hg19a/A51616_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-17849 15-17849N genome grch37 normal FL_GenomeCanada A70272 Genome frozen 150 blood M data/genome_bams/15-17849N.grch37.bam /projects/analysis/analysis28/A70272/H25LTCCXY_7/A70272/150nt/hg19a/bwa-mem-0.7.6a-sb/A70272_1_lane_dupsFlagged.bam gambl +bam TRUE 14-41250 14-41250N genome grch37 normal FL_GenomeCanada A55766 Genome frozen 125 blood F data/genome_bams/14-41250N.grch37.bam /projects/analysis/analysis22/A55766/merge_bwa-0.5.7/125nt/hg19a/A55766_2_lanes_dupsFlagged.bam gambl +bam TRUE 96-11779 96-11779N genome grch37 normal FL_GenomeCanada A55767 Genome frozen 125 blood M data/genome_bams/96-11779N.grch37.bam /projects/analysis/analysis22/A55767/merge_bwa-0.5.7/125nt/hg19a/A55767_2_lanes_dupsFlagged.bam gambl +bam TRUE 98-20105 98-20105N genome grch37 normal CLL_GenomeCanada A51618 Genome frozen 125 sorted_cells F data/genome_bams/98-20105N.grch37.bam /projects/analysis/analysis21/A51618/merge_bwa-0.5.7/125nt/hg19a/A51618_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-18723 15-18723N genome grch37 normal DLBCL_GenomeCanada A55768 Genome frozen 125 blood M data/genome_bams/15-18723N.grch37.bam /projects/analysis/analysis22/A55768/merge_bwa-0.5.7/125nt/hg19a/A55768_2_lanes_dupsFlagged.bam gambl +bam TRUE 10-39333 10-39333N genome grch37 normal FL_GenomeCanada A55769 Genome frozen 125 blood M data/genome_bams/10-39333N.grch37.bam /projects/analysis/analysis22/A55769/merge_bwa-0.5.7/125nt/hg19a/A55769_2_lanes_dupsFlagged.bam gambl +bam TRUE 05-15969 05-15969N genome grch37 normal CLL_GenomeCanada A55770 Genome frozen 125 sorted_cells M data/genome_bams/05-15969N.grch37.bam /projects/analysis/analysis22/A55770/merge_bwa-0.5.7/125nt/hg19a/A55770_2_lanes_dupsFlagged.bam gambl +bam TRUE 12-15808 12-15808N genome grch37 normal CLL_GenomeCanada A55771 Genome frozen 125 sorted_cells M data/genome_bams/12-15808N.grch37.bam /projects/analysis/analysis22/A55771/merge_bwa-0.5.7/125nt/hg19a/A55771_2_lanes_dupsFlagged.bam gambl +bam TRUE 14-35026 14-35026N genome grch37 normal DLBCL_GenomeCanada A55772 Genome frozen 125 blood M data/genome_bams/14-35026N.grch37.bam /projects/analysis/analysis22/A55772/merge_bwa-0.5.7/125nt/hg19a/A55772_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-21654 15-21654N genome grch37 normal DLBCL_GenomeCanada A70273 Genome frozen 150 blood M data/genome_bams/15-21654N.grch37.bam /projects/analysis/analysis28/A70273/H25LTCCXY_8/A70273/150nt/hg19a/bwa-mem-0.7.6a-sb/A70273_1_lane_dupsFlagged.bam gambl +bam TRUE 15-24306 15-24306N genome grch37 normal DLBCL_GenomeCanada A55773 Genome frozen 125 blood F data/genome_bams/15-24306N.grch37.bam /projects/analysis/analysis22/A55773/merge_bwa-0.5.7/125nt/hg19a/A55773_2_lanes_dupsFlagged.bam gambl +bam TRUE 09-34898 09-34898N genome grch37 normal CLL_GenomeCanada A55774 Genome frozen 125 sorted_cells M data/genome_bams/09-34898N.grch37.bam /projects/analysis/analysis22/A55774/merge_bwa-0.5.7/125nt/hg19a/A55774_2_lanes_dupsFlagged.bam gambl +bam TRUE 11-28845 11-28845N genome grch37 normal FL_GenomeCanada A55775 Genome frozen 125 blood F data/genome_bams/11-28845N.grch37.bam /projects/analysis/analysis22/A55775/merge_bwa-0.5.7/125nt/hg19a/A55775_2_lanes_dupsFlagged.bam gambl +bam TRUE 04-24029 04-24029N genome grch37 normal FL_GenomeCanada A70274 Genome frozen 150 blood F data/genome_bams/04-24029N.grch37.bam /projects/analysis/analysis28/A70274/H2F33CCXY_1/A70274/150nt/hg19a/bwa-mem-0.7.6a-sb/A70274_1_lane_dupsFlagged.bam gambl +bam TRUE 15-24058 15-24058N genome grch37 normal DLBCL_GenomeCanada A55776 Genome frozen 125 blood M data/genome_bams/15-24058N.grch37.bam /projects/analysis/analysis22/A55776/merge_bwa-0.5.7/125nt/hg19a/A55776_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-29305 15-29305N genome grch37 normal FL_GenomeCanada A70275 Genome frozen 150 blood F data/genome_bams/15-29305N.grch37.bam /projects/analysis/analysis28/A70275/H2F33CCXY_2/A70275/150nt/hg19a/bwa-mem-0.7.6a-sb/A70275_1_lane_dupsFlagged.bam gambl +bam TRUE 15-30123 15-30123N genome grch37 normal FL_GenomeCanada A70276 Genome frozen 150 blood M data/genome_bams/15-30123N.grch37.bam /projects/analysis/analysis28/A70276/H2F33CCXY_3/A70276/150nt/hg19a/bwa-mem-0.7.6a-sb/A70276_1_lane_dupsFlagged.bam gambl +bam TRUE 11-12907 11-12907N genome grch37 normal CLL_GenomeCanada A55777 Genome frozen 125 sorted_cells M data/genome_bams/11-12907N.grch37.bam /projects/analysis/analysis22/A55777/merge_bwa-0.5.7/125nt/hg19a/A55777_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-29858 15-29858N genome grch37 normal DLBCL_GenomeCanada A70277 Genome frozen 150 blood F data/genome_bams/15-29858N.grch37.bam /projects/analysis/analysis28/A70277/H2F33CCXY_4/A70277/150nt/hg19a/bwa-mem-0.7.6a-sb/A70277_1_lane_dupsFlagged.bam gambl +bam TRUE 15-29370 15-29370N genome grch37 normal CLL_GenomeCanada A55778 Genome frozen 125 sorted_cells M data/genome_bams/15-29370N.grch37.bam /projects/analysis/analysis23/A55778/merge_bwa-0.5.7/125nt/hg19a/A55778_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-31924 15-31924N genome grch37 normal DLBCL_GenomeCanada A70278 Genome frozen 150 blood M data/genome_bams/15-31924N.grch37.bam /projects/analysis/analysis28/A70278/H2F33CCXY_5/A70278/150nt/hg19a/bwa-mem-0.7.6a-sb/A70278_1_lane_dupsFlagged.bam gambl +bam TRUE 15-26544 15-26544N genome grch37 normal CLL_GenomeCanada A55779 Genome frozen 125 sorted_cells F data/genome_bams/15-26544N.grch37.bam /projects/analysis/analysis23/A55779/merge_bwa-0.5.7/125nt/hg19a/A55779_2_lanes_dupsFlagged.bam gambl +bam TRUE 15-30563 15-30563N genome grch37 normal FL_GenomeCanada A70279 Genome frozen 150 blood M data/genome_bams/15-30563N.grch37.bam /projects/analysis/analysis28/A70279/H2F33CCXY_6/A70279/150nt/hg19a/bwa-mem-0.7.6a-sb/A70279_1_lane_dupsFlagged.bam gambl +bam TRUE 15-24979 15-24979N genome grch37 normal CLL_GenomeCanada A61237 Genome frozen 150 sorted_cells M data/genome_bams/15-24979N.grch37.bam /projects/analysis/analysis26/A61237/merge_bwa-0.5.7/150nt/hg19a/A61237_4_lanes_dupsFlagged.bam gambl +bam TRUE 15-34472 15-34472N genome grch37 normal DLBCL_GenomeCanada A70280 Genome frozen 150 blood F data/genome_bams/15-34472N.grch37.bam /projects/analysis/analysis28/A70280/H2F33CCXY_7/A70280/150nt/hg19a/bwa-mem-0.7.6a-sb/A70280_1_lane_dupsFlagged.bam gambl +bam TRUE 92-34897 92-34897N genome grch37 normal CLL_GenomeCanada A61238 Genome frozen 150 sorted_cells M data/genome_bams/92-34897N.grch37.bam /projects/analysis/analysis26/A61238/merge_bwa-0.5.7/150nt/hg19a/A61238_4_lanes_dupsFlagged.bam gambl +bam TRUE 15-37079 15-37079N genome grch37 normal FL_GenomeCanada A70281 Genome frozen 150 blood F data/genome_bams/15-37079N.grch37.bam /projects/analysis/analysis28/A70281/H2CMCCCXY_1/A70281/150nt/hg19a/bwa-mem-0.7.6a-sb/A70281_1_lane_dupsFlagged.bam gambl +bam TRUE 15-36416 15-36416N genome grch37 normal FL_GenomeCanada A70282 Genome frozen 150 blood M data/genome_bams/15-36416N.grch37.bam /projects/analysis/analysis28/A70282/H2CMCCCXY_2/A70282/150nt/hg19a/bwa-mem-0.7.6a-sb/A70282_1_lane_dupsFlagged.bam gambl +bam TRUE 15-36675 15-36675N genome grch37 normal FL_GenomeCanada A70283 Genome frozen 150 blood M data/genome_bams/15-36675N.grch37.bam /projects/analysis/analysis28/A70283/H2CMCCCXY_3/A70283/150nt/hg19a/bwa-mem-0.7.6a-sb/A70283_1_lane_dupsFlagged.bam gambl +bam TRUE 15-37466 15-37466N genome grch37 normal FL_GenomeCanada A70284 Genome frozen 150 blood M data/genome_bams/15-37466N.grch37.bam /projects/analysis/analysis28/A70284/H2CLYCCXY_1/A70284/150nt/hg19a/bwa-mem-0.7.6a-sb/A70284_1_lane_dupsFlagged.bam gambl +bam TRUE 15-39657 15-39657N genome grch37 normal FL_GenomeCanada A70285 Genome frozen 150 blood M data/genome_bams/15-39657N.grch37.bam /projects/analysis/analysis28/A70285/H2CLYCCXY_2/A70285/150nt/hg19a/bwa-mem-0.7.6a-sb/A70285_1_lane_dupsFlagged.bam gambl +bam TRUE 15-33862 15-33862N genome grch37 normal FL_GenomeCanada A70286 Genome frozen 150 blood F data/genome_bams/15-33862N.grch37.bam /projects/analysis/analysis28/A70286/H2CLYCCXY_3/A70286/150nt/hg19a/bwa-mem-0.7.6a-sb/A70286_1_lane_dupsFlagged.bam gambl +bam TRUE 15-41277 15-41277N genome grch37 normal FL_GenomeCanada A70287 Genome frozen 150 blood F data/genome_bams/15-41277N.grch37.bam /projects/analysis/analysis28/A70287/H2CLYCCXY_4/A70287/150nt/hg19a/bwa-mem-0.7.6a-sb/A70287_1_lane_dupsFlagged.bam gambl +bam TRUE 15-39521 15-39521N genome grch37 normal FL_GenomeCanada A70288 Genome frozen 150 blood M data/genome_bams/15-39521N.grch37.bam /projects/analysis/analysis28/A70288/H2CLYCCXY_5/A70288/150nt/hg19a/bwa-mem-0.7.6a-sb/A70288_1_lane_dupsFlagged.bam gambl +bam TRUE 15-40296 15-40296N genome grch37 normal FL_GenomeCanada A70289 Genome frozen 150 blood M data/genome_bams/15-40296N.grch37.bam /projects/analysis/analysis28/A70289/H2CMCCCXY_4/A70289/150nt/hg19a/bwa-mem-0.7.6a-sb/A70289_1_lane_dupsFlagged.bam gambl +bam TRUE 15-31595 15-31595N genome grch37 normal CLL_GenomeCanada A61239 Genome frozen 150 sorted_cells M data/genome_bams/15-31595N.grch37.bam /projects/analysis/analysis26/A61239/merge_bwa-0.5.7/150nt/hg19a/A61239_4_lanes_dupsFlagged.bam gambl +bam TRUE 15-42543 15-42543N genome grch37 normal FL_GenomeCanada A70290 Genome frozen 150 blood F data/genome_bams/15-42543N.grch37.bam /projects/analysis/analysis28/A70290/H2CMCCCXY_5/A70290/150nt/hg19a/bwa-mem-0.7.6a-sb/A70290_1_lane_dupsFlagged.bam gambl +bam TRUE 10-35696 10-35696N genome grch37 normal CLL_GenomeCanada A61240 Genome frozen 150 sorted_cells M data/genome_bams/10-35696N.grch37.bam /projects/analysis/analysis26/A61240/merge_bwa-0.5.7/150nt/hg19a/A61240_4_lanes_dupsFlagged.bam gambl +bam TRUE 11-34915 11-34915N genome grch37 normal FL_GenomeCanada A70291 Genome frozen 150 blood M data/genome_bams/11-34915N.grch37.bam /projects/analysis/analysis28/A70291/H25MNCCXY_1/A70291/150nt/hg19a/bwa-mem-0.7.6a-sb/A70291_1_lane_dupsFlagged.bam gambl +bam TRUE 11-35935 11-35935N genome grch37 normal DLBCL_GenomeCanada A70292 Genome frozen 150 blood M data/genome_bams/11-35935N.grch37.bam /projects/analysis/analysis28/A70292/H2CLYCCXY_6/A70292/150nt/hg19a/bwa-mem-0.7.6a-sb/A70292_1_lane_dupsFlagged.bam gambl +bam TRUE 15-26538 15-26538N genome grch37 normal DLBCL_GenomeCanada A85281 Genome frozen 150 blood M data/genome_bams/15-26538N.grch37.bam /projects/analysis/analysis30/A85281/merge26251_bwa-mem-0.7.6a-sb/150nt/hg19a/A85281_27_lanes_dupsFlagged.bam gambl +bam TRUE 15-37429 15-37429N genome grch37 normal CLL_GenomeCanada A61241 Genome frozen 150 sorted_cells M data/genome_bams/15-37429N.grch37.bam /projects/analysis/analysis26/A61241/merge_bwa-0.5.7/150nt/hg19a/A61241_4_lanes_dupsFlagged.bam gambl +bam TRUE 15-38154 15-38154N genome grch37 normal DLBCL_GenomeCanada A70293 Genome frozen 150 blood M data/genome_bams/15-38154N.grch37.bam /projects/analysis/analysis28/A70293/H2CLYCCXY_7/A70293/150nt/hg19a/bwa-mem-0.7.6a-sb/A70293_1_lane_dupsFlagged.bam gambl +bam TRUE 09-37629 09-37629N genome grch37 normal DLBCL_GenomeCanada A70294 Genome frozen 150 blood M data/genome_bams/09-37629N.grch37.bam /projects/analysis/analysis28/A70294/H2CLYCCXY_8/A70294/150nt/hg19a/bwa-mem-0.7.6a-sb/A70294_1_lane_dupsFlagged.bam gambl +bam TRUE 16-10805 16-10805N genome grch37 normal FL_GenomeCanada A70295 Genome frozen 150 blood M data/genome_bams/16-10805N.grch37.bam /projects/analysis/analysis28/A70295/H2CNTCCXY_1/A70295/150nt/hg19a/bwa-mem-0.7.6a-sb/A70295_1_lane_dupsFlagged.bam gambl +bam TRUE 15-43891 15-43891N genome grch37 normal DLBCL_GenomeCanada A70296 Genome frozen 150 blood M data/genome_bams/15-43891N.grch37.bam /projects/analysis/analysis28/A70296/H2CNTCCXY_2/A70296/150nt/hg19a/bwa-mem-0.7.6a-sb/A70296_1_lane_dupsFlagged.bam gambl +bam TRUE 07-11993 07-11993N genome grch37 normal CLL_GenomeCanada A61242 Genome frozen 150 sorted_cells M data/genome_bams/07-11993N.grch37.bam /projects/analysis/analysis26/A61242/merge_bwa-0.5.7/150nt/hg19a/A61242_4_lanes_dupsFlagged.bam gambl +bam TRUE 04-24937 04-24937N genome grch37 normal DLBCL_GenomeCanada A70297 Genome frozen 150 blood F data/genome_bams/04-24937N.grch37.bam /projects/analysis/analysis28/A70297/H2CNTCCXY_3/A70297/150nt/hg19a/bwa-mem-0.7.6a-sb/A70297_1_lane_dupsFlagged.bam gambl +bam TRUE 09-25670 09-25670N genome grch37 normal CLL_GenomeCanada A61243 Genome frozen 150 sorted_cells M data/genome_bams/09-25670N.grch37.bam /projects/analysis/analysis26/A61243/merge_bwa-0.5.7/150nt/hg19a/A61243_4_lanes_dupsFlagged.bam gambl +bam TRUE 16-13504 16-13504N genome grch37 normal FL_GenomeCanada A70298 Genome frozen 150 blood F data/genome_bams/16-13504N.grch37.bam /projects/analysis/analysis28/A70298/H2CNTCCXY_4/A70298/150nt/hg19a/bwa-mem-0.7.6a-sb/A70298_1_lane_dupsFlagged.bam gambl +bam TRUE 03-21390 03-21390N genome grch37 normal CLL_GenomeCanada A61244 Genome frozen 150 sorted_cells M data/genome_bams/03-21390N.grch37.bam /projects/analysis/analysis26/A61244/merge_bwa-0.5.7/150nt/hg19a/A61244_4_lanes_dupsFlagged.bam gambl +bam TRUE 08-32802 08-32802N genome grch37 normal CLL_GenomeCanada A61245 Genome frozen 150 sorted_cells F data/genome_bams/08-32802N.grch37.bam /projects/analysis/analysis26/A61245/merge_bwa-0.5.7/150nt/hg19a/A61245_4_lanes_dupsFlagged.bam gambl +bam TRUE 10-31625 10-31625N genome grch37 normal DLBCL_GenomeCanada A70299 Genome frozen 150 blood F data/genome_bams/10-31625N.grch37.bam /projects/analysis/analysis28/A70299/H2CNTCCXY_5/A70299/150nt/hg19a/bwa-mem-0.7.6a-sb/A70299_1_lane_dupsFlagged.bam gambl +bam TRUE 15-43113 15-43113N genome grch37 normal CLL_GenomeCanada A61246 Genome frozen 150 sorted_cells M data/genome_bams/15-43113N.grch37.bam /projects/analysis/analysis26/A61246/merge_bwa-0.5.7/150nt/hg19a/A61246_4_lanes_dupsFlagged.bam gambl +bam TRUE 16-14439 16-14439N genome grch37 normal CLL_GenomeCanada A61247 Genome frozen 150 sorted_cells M data/genome_bams/16-14439N.grch37.bam /projects/analysis/analysis26/A61247/merge_bwa-0.5.7/150nt/hg19a/A61247_4_lanes_dupsFlagged.bam gambl +bam TRUE 11-30570 11-30570N genome grch37 normal CLL_GenomeCanada A61248 Genome frozen 150 sorted_cells M data/genome_bams/11-30570N.grch37.bam /projects/analysis/analysis26/A61248/merge_bwa-0.5.7/150nt/hg19a/A61248_4_lanes_dupsFlagged.bam gambl +bam TRUE 16-16723 16-16723N genome grch37 normal DLBCL_GenomeCanada A70300 Genome frozen 150 blood F data/genome_bams/16-16723N.grch37.bam /projects/analysis/analysis28/A70300/H2CNTCCXY_6/A70300/150nt/hg19a/bwa-mem-0.7.6a-sb/A70300_1_lane_dupsFlagged.bam gambl +bam TRUE 16-13732 16-13732N genome grch37 normal DLBCL_GenomeCanada A70301 Genome frozen 150 blood M data/genome_bams/16-13732N.grch37.bam /projects/analysis/analysis28/A70301/H2CNTCCXY_7/A70301/150nt/hg19a/bwa-mem-0.7.6a-sb/A70301_1_lane_dupsFlagged.bam gambl +bam TRUE 16-16192 16-16192N genome grch37 normal DLBCL_GenomeCanada A70302 Genome frozen 150 blood F data/genome_bams/16-16192N.grch37.bam /projects/analysis/analysis28/A70302/H2CNTCCXY_8/A70302/150nt/hg19a/bwa-mem-0.7.6a-sb/A70302_1_lane_dupsFlagged.bam gambl +bam TRUE 06-27098 06-27098N genome grch37 normal CLL_GenomeCanada A61249 Genome frozen 150 sorted_cells M data/genome_bams/06-27098N.grch37.bam /projects/analysis/analysis26/A61249/merge_bwa-0.5.7/150nt/hg19a/A61249_4_lanes_dupsFlagged.bam gambl +bam TRUE 16-17861 16-17861N genome grch37 normal DLBCL_GenomeCanada A70303 Genome frozen 150 blood F data/genome_bams/16-17861N.grch37.bam /projects/analysis/analysis28/A70303/H2CN2CCXY_1/A70303/150nt/hg19a/bwa-mem-0.7.6a-sb/A70303_1_lane_dupsFlagged.bam gambl +bam TRUE 07-31636 07-31636N genome grch37 normal CLL_GenomeCanada A61250 Genome frozen 150 sorted_cells F data/genome_bams/07-31636N.grch37.bam /projects/analysis/analysis26/A61250/merge_bwa-0.5.7/150nt/hg19a/A61250_4_lanes_dupsFlagged.bam gambl +bam TRUE 16-18623 16-18623N genome grch37 normal DLBCL_GenomeCanada A70304 Genome frozen 150 blood F data/genome_bams/16-18623N.grch37.bam /projects/analysis/analysis28/A70304/H2CN2CCXY_2/A70304/150nt/hg19a/bwa-mem-0.7.6a-sb/A70304_1_lane_dupsFlagged.bam gambl +bam TRUE 16-18029 16-18029N genome grch37 normal DLBCL_GenomeCanada A70305 Genome frozen 150 blood M data/genome_bams/16-18029N.grch37.bam /projects/analysis/analysis28/A70305/H2CN2CCXY_3/A70305/150nt/hg19a/bwa-mem-0.7.6a-sb/A70305_1_lane_dupsFlagged.bam gambl +bam TRUE 09-26109 09-26109N genome grch37 normal CLL_GenomeCanada A61497 Genome frozen 150 sorted_cells M data/genome_bams/09-26109N.grch37.bam /projects/analysis/analysis26/A61497/merge_bwa-0.5.7/150nt/hg19a/A61497_4_lanes_dupsFlagged.bam gambl +bam TRUE 96-17434 96-17434N genome grch37 normal CLL_GenomeCanada A61253 Genome frozen 150 sorted_cells M data/genome_bams/96-17434N.grch37.bam /projects/analysis/analysis26/A61253/merge_bwa-0.5.7/150nt/hg19a/A61253_4_lanes_dupsFlagged.bam gambl +bam TRUE 04-41840 04-41840N genome grch37 normal CLL_GenomeCanada A70341 Genome frozen 150 sorted_cells M data/genome_bams/04-41840N.grch37.bam /projects/analysis/analysis28/A70341/H273HCCXY_1/A70341/150nt/hg19a/bwa-mem-0.7.6a-sb/A70341_1_lane_dupsFlagged.bam gambl +bam TRUE 16-20119 16-20119N genome grch37 normal FL_GenomeCanada A70306 Genome frozen 150 blood F data/genome_bams/16-20119N.grch37.bam /projects/analysis/analysis28/A70306/H2CN2CCXY_4/A70306/150nt/hg19a/bwa-mem-0.7.6a-sb/A70306_1_lane_dupsFlagged.bam gambl +bam TRUE 93-73569 93-73569N genome grch37 normal CLL_GenomeCanada A70342 Genome frozen 150 sorted_cells M data/genome_bams/93-73569N.grch37.bam /projects/analysis/analysis28/A70342/HKTKYALXX_4/A70342/150nt/hg19a/bwa-mem-0.7.6a-sb/A70342_1_lane_dupsFlagged.bam gambl +bam TRUE 16-11636 16-11636N genome grch37 normal DLBCL_GenomeCanada A70307 Genome frozen 150 blood F data/genome_bams/16-11636N.grch37.bam /projects/analysis/analysis28/A70307/H2CN2CCXY_5/A70307/150nt/hg19a/bwa-mem-0.7.6a-sb/A70307_1_lane_dupsFlagged.bam gambl +bam TRUE 15-43657 15-43657N genome grch37 normal DLBCL_GenomeCanada A70308 Genome frozen 150 blood M data/genome_bams/15-43657N.grch37.bam /projects/analysis/analysis28/A70308/H2CN2CCXY_6/A70308/150nt/hg19a/bwa-mem-0.7.6a-sb/A70308_1_lane_dupsFlagged.bam gambl +bam TRUE 13-21628 13-21628N genome grch37 normal CLL_GenomeCanada A70343 Genome frozen 150 sorted_cells F data/genome_bams/13-21628N.grch37.bam /projects/analysis/analysis28/A70343/HKTKYALXX_5/A70343/150nt/hg19a/bwa-mem-0.7.6a-sb/A70343_1_lane_dupsFlagged.bam gambl +bam TRUE 16-19402 16-19402N genome grch37 normal FL_GenomeCanada A70309 Genome frozen 150 blood M data/genome_bams/16-19402N.grch37.bam /projects/analysis/analysis28/A70309/H2CN2CCXY_7/A70309/150nt/hg19a/bwa-mem-0.7.6a-sb/A70309_1_lane_dupsFlagged.bam gambl +bam TRUE 07-10659 07-10659N genome grch37 normal CLL_GenomeCanada A70344 Genome frozen 150 sorted_cells F data/genome_bams/07-10659N.grch37.bam /projects/analysis/analysis28/A70344/HKTKYALXX_6/A70344/150nt/hg19a/bwa-mem-0.7.6a-sb/A70344_1_lane_dupsFlagged.bam gambl diff --git a/workflows/reference_files/2.4/etc/hg38.normals.tbl b/workflows/reference_files/2.4/etc/hg38.normals.tbl new file mode 100644 index 00000000..fdd2aa0a --- /dev/null +++ b/workflows/reference_files/2.4/etc/hg38.normals.tbl @@ -0,0 +1,201 @@ +compression bam_available patient_id sample_id seq_type genome_build tissue_status cohort library_id pathology time_point protocol ffpe_or_frozen read_length strandedness seq_source_type sex EBV_status_inf link_name data_path unix_group biopsy_id +bam TRUE BLGSP-71-06-00001 BLGSP-71-06-00001-99A-01D genome hg38 normal BL_Pediatric A47818 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00001-99A-01D.hg38.bam /projects/analysis/analysis23/A47818/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47818_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00005 BLGSP-71-06-00005-99A-01D genome hg38 normal BL_Pediatric A47820 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00005-99A-01D.hg38.bam /projects/analysis/analysis23/A47820/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47820_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00004 BLGSP-71-06-00004-99A-01D genome hg38 normal BL_Pediatric A47822 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00004-99A-01D.hg38.bam /projects/analysis/analysis23/A47822/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47822_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00007 BLGSP-71-06-00007-99A-01D genome hg38 normal BL_Pediatric A47824 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00007-99A-01D.hg38.bam /projects/analysis/analysis23/A47824/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47824_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00013 BLGSP-71-06-00013-99A-01D genome hg38 normal BL_Pediatric A47826 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00013-99A-01D.hg38.bam /projects/analysis/analysis23/A47826/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47826_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00080 BLGSP-71-06-00080-99A-01D genome hg38 normal BL_Pediatric A47828 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00080-99A-01D.hg38.bam /projects/analysis/analysis23/A47828/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47828_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00019 BLGSP-71-06-00019-99A-01D genome hg38 normal BL_Pediatric A47830 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00019-99A-01D.hg38.bam /projects/analysis/analysis23/A47830/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47830_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00008 BLGSP-71-06-00008-99A-01D genome hg38 normal BL_Pediatric A47832 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00008-99A-01D.hg38.bam /projects/analysis/analysis23/A47832/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47832_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00071 BLGSP-71-06-00071-99A-01D genome hg38 normal BL_Pediatric A47834 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00071-99A-01D.hg38.bam /projects/analysis/analysis23/A47834/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47834_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00012 BLGSP-71-06-00012-12A-01D genome hg38 normal BL_Pediatric A47836 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00012-12A-01D.hg38.bam /projects/analysis/analysis23/A47836/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47836_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00074 BLGSP-71-06-00074-99A-01D genome hg38 normal BL_Pediatric A47838 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00074-99A-01D.hg38.bam /projects/analysis/analysis23/A47838/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47838_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00072 BLGSP-71-06-00072-12A-01D genome hg38 normal BL_Pediatric A47840 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00072-12A-01D.hg38.bam /projects/analysis/analysis23/A47840/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47840_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00078 BLGSP-71-06-00078-99A-01D genome hg38 normal BL_Pediatric A47842 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00078-99A-01D.hg38.bam /projects/analysis/analysis23/A47842/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47842_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00075 BLGSP-71-06-00075-99A-01D genome hg38 normal BL_Pediatric A47844 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00075-99A-01D.hg38.bam /projects/analysis/analysis23/A47844/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47844_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00081 BLGSP-71-06-00081-10A-01D genome hg38 normal BL_Pediatric A47846 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00081-10A-01D.hg38.bam /projects/analysis/analysis23/A47846/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A47846_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00002 BLGSP-71-06-00002-99A-01D genome hg38 normal BL_Pediatric A55951 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00002-99A-01D.hg38.bam /projects/analysis/analysis23/A55951/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55951_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00115 BLGSP-71-19-00115-16A-01D genome hg38 normal BL_Pediatric A55953 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-19-00115-16A-01D.hg38.bam /projects/analysis/analysis23/A55953/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55953_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00088 BLGSP-71-06-00088-99A-01D genome hg38 normal BL_Pediatric A55955 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00088-99A-01D.hg38.bam /projects/analysis/analysis23/A55955/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55955_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00085 BLGSP-71-06-00085-99A-01D genome hg38 normal BL_Pediatric A55957 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00085-99A-01D.hg38.bam /projects/analysis/analysis23/A55957/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55957_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00125 BLGSP-71-19-00125-16A-01D genome hg38 normal BL_Pediatric A55959 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00125-16A-01D.hg38.bam /projects/analysis/analysis23/A55959/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55959_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00116 BLGSP-71-19-00116-10A-01D genome hg38 normal BL_Pediatric A55961 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00116-10A-01D.hg38.bam /projects/analysis/analysis23/A55961/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55961_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00089 BLGSP-71-06-00089-99A-01D genome hg38 normal BL_Pediatric A55963 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00089-99A-01D.hg38.bam /projects/analysis/analysis23/A55963/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55963_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00126 BLGSP-71-19-00126-16A-01D genome hg38 normal BL_Pediatric A55965 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00126-16A-01D.hg38.bam /projects/analysis/analysis23/A55965/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55965_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00093 BLGSP-71-06-00093-99A-01D genome hg38 normal BL_Pediatric A55967 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00093-99A-01D.hg38.bam /projects/analysis/analysis23/A55967/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55967_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00016 BLGSP-71-06-00016-12A-01D genome hg38 normal BL_Pediatric A55969 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00016-12A-01D.hg38.bam /projects/analysis/analysis23/A55969/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55969_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00095 BLGSP-71-06-00095-99A-01D genome hg38 normal BL_Pediatric A55971 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00095-99A-01D.hg38.bam /projects/analysis/analysis23/A55971/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55971_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00020 BLGSP-71-06-00020-12A-01D genome hg38 normal BL_Pediatric A55973 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00020-12A-01D.hg38.bam /projects/analysis/analysis23/A55973/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55973_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00104 BLGSP-71-19-00104-10A-01D genome hg38 normal BL_Pediatric A55975 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-19-00104-10A-01D.hg38.bam /projects/analysis/analysis23/A55975/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55975_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00076 BLGSP-71-06-00076-12A-01D genome hg38 normal BL_Pediatric A55977 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00076-12A-01D.hg38.bam /projects/analysis/analysis23/A55977/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55977_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00105 BLGSP-71-19-00105-10A-01D genome hg38 normal BL_Pediatric A55979 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00105-10A-01D.hg38.bam /projects/analysis/analysis23/A55979/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55979_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00086 BLGSP-71-06-00086-99A-01D genome hg38 normal BL_Pediatric A55981 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00086-99A-01D.hg38.bam /projects/analysis/analysis23/A55981/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55981_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00113 BLGSP-71-19-00113-10A-01D genome hg38 normal BL_Pediatric A55983 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00113-10A-01D.hg38.bam /projects/analysis/analysis23/A55983/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55983_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00084 BLGSP-71-06-00084-99A-01D genome hg38 normal BL_Pediatric A55985 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00084-99A-01D.hg38.bam /projects/analysis/analysis23/A55985/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A55985_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00036 BLGSP-71-08-00036-10A-01D genome hg38 normal BL_Pediatric A59853 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-08-00036-10A-01D.hg38.bam /projects/analysis/analysis25/A59853/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59853_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-21-00185 BLGSP-71-21-00185-10B-01D genome hg38 normal BL_Adult A59854 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-21-00185-10B-01D.hg38.bam /projects/analysis/analysis25/A59854/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59854_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00087 BLGSP-71-06-00087-99A-01D genome hg38 normal BL_Pediatric A59855 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00087-99A-01D.hg38.bam /projects/analysis/analysis25/A59855/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59855_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00122 BLGSP-71-19-00122-10A-01D genome hg38 normal BL_Pediatric A59856 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-19-00122-10A-01D.hg38.bam /projects/analysis/analysis25/A59856/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59856_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00033 BLGSP-71-08-00033-10A-01D genome hg38 normal BL_Pediatric A59862 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-08-00033-10A-01D.hg38.bam /projects/analysis/analysis25/A59862/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59862_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-21-00186 BLGSP-71-21-00186-10A-01D genome hg38 normal BL_Adult A59864 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-21-00186-10A-01D.hg38.bam /projects/analysis/analysis25/A59864/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59864_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00094 BLGSP-71-06-00094-99A-01D genome hg38 normal BL_Pediatric A59865 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00094-99A-01D.hg38.bam /projects/analysis/analysis25/A59865/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59865_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00127 BLGSP-71-19-00127-16A-01D genome hg38 normal BL_Pediatric A59866 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-19-00127-16A-01D.hg38.bam /projects/analysis/analysis25/A59866/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59866_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00041 BLGSP-71-08-00041-10A-01D genome hg38 normal BL_Pediatric A59868 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-08-00041-10A-01D.hg38.bam /projects/analysis/analysis25/A59868/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59868_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00038 BLGSP-71-08-00038-10A-01D genome hg38 normal BL_Pediatric A59871 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-08-00038-10A-01D.hg38.bam /projects/analysis/analysis25/A59871/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59871_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00035 BLGSP-71-08-00035-10A-01D genome hg38 normal BL_Pediatric A59872 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-08-00035-10A-01D.hg38.bam /projects/analysis/analysis25/A59872/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59872_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00110 BLGSP-71-19-00110-16A-01D genome hg38 normal BL_Pediatric A59875 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-19-00110-16A-01D.hg38.bam /projects/analysis/analysis25/A59875/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A59875_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00144 BLGSP-71-06-00144-99A-01D genome hg38 normal BL_Pediatric A62433 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00144-99A-01D.hg38.bam /projects/analysis/analysis26/A62433/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62433_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00154 BLGSP-71-06-00154-99A-01D genome hg38 normal BL_Pediatric A62434 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00154-99A-01D.hg38.bam /projects/analysis/analysis26/A62434/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62434_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00162 BLGSP-71-06-00162-99A-01D genome hg38 normal BL_Pediatric A62435 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00162-99A-01D.hg38.bam /projects/analysis/analysis26/A62435/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62435_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00098 BLGSP-71-06-00098-10A-01D genome hg38 normal BL_Pediatric A62436 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00098-10A-01D.hg38.bam /projects/analysis/analysis26/A62436/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62436_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00432 BLGSP-71-08-00432-10A-01D genome hg38 normal BL_Pediatric A62443 Genome frozen 125 unsorted data/genome_bams/BLGSP-71-08-00432-10A-01D.hg38.bam /projects/analysis/analysis26/A62443/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62443_2_lanes_dupsFlagged_reheadered.bam gambl +bam TRUE BLGSP-71-06-00142 BLGSP-71-06-00142-99A-01D genome hg38 normal BL_Pediatric A62444 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00142-99A-01D.hg38.bam /projects/analysis/analysis26/A62444/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62444_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00148 BLGSP-71-06-00148-99A-01D genome hg38 normal BL_Pediatric A62445 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00148-99A-01D.hg38.bam /projects/analysis/analysis26/A62445/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62445_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00158 BLGSP-71-06-00158-99A-01D genome hg38 normal BL_Pediatric A62446 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00158-99A-01D.hg38.bam /projects/analysis/analysis26/A62446/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62446_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00042 BLGSP-71-08-00042-10A-01D genome hg38 normal BL_Pediatric A62451 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-08-00042-10A-01D.hg38.bam /projects/analysis/analysis26/A62451/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62451_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00143 BLGSP-71-06-00143-12A-01D genome hg38 normal BL_Pediatric A62452 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00143-12A-01D.hg38.bam /projects/analysis/analysis26/A62452/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62452_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00149 BLGSP-71-06-00149-99A-01D genome hg38 normal BL_Pediatric A62453 Genome frozen 125 unsorted F data/genome_bams/BLGSP-71-06-00149-99A-01D.hg38.bam /projects/analysis/analysis26/A62453/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62453_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00161 BLGSP-71-06-00161-12A-01D genome hg38 normal BL_Pediatric A62454 Genome frozen 125 unsorted M data/genome_bams/BLGSP-71-06-00161-12A-01D.hg38.bam /projects/analysis/analysis26/A62454/merge_bwa-mem-0.7.6a/125nt/hg38_no_alt/A62454_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00160 BLGSP-71-06-00160-12A-01D genome hg38 normal BL_Pediatric A64107 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00160-12A-01D.hg38.bam /projects/analysis/analysis26/A64107/H37H5ALXX_3/A64107/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64107_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00123 BLGSP-71-19-00123-16A-01D genome hg38 normal BL_Pediatric A64108 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-19-00123-16A-01D.hg38.bam /projects/analysis/analysis26/A64108/H37H5ALXX_4/A64108/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64108_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00137 BLGSP-71-06-00137-99A-01D genome hg38 normal BL_Pediatric A64109 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00137-99A-01D.hg38.bam /projects/analysis/analysis26/A64109/H37H5ALXX_5/A64109/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64109_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00128 BLGSP-71-19-00128-16A.1-01D genome hg38 normal BL_Pediatric A64111 Genome frozen 150 sorted M data/genome_bams/BLGSP-71-19-00128-16A.1-01D.hg38.bam /projects/analysis/analysis26/A64111/H37H5ALXX_8/A64111/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64111_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00022 BLGSP-71-08-00022-12A-01D genome hg38 normal BL_Pediatric A64115 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00022-12A-01D.hg38.bam /projects/analysis/analysis26/A64115/H33W3ALXX_3/A64115/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64115_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00133 BLGSP-71-19-00133-16A-01D genome hg38 normal BL_Pediatric A64116 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00133-16A-01D.hg38.bam /projects/analysis/analysis26/A64116/H33TYALXX_5/A64116/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64116_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00155 BLGSP-71-06-00155-99A-01D genome hg38 normal BL_Pediatric A64120 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00155-99A-01D.hg38.bam /projects/analysis/analysis26/A64120/H33TYALXX_8/A64120/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64120_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00023 BLGSP-71-08-00023-12A-01D genome hg38 normal BL_Pediatric A64121 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00023-12A-01D.hg38.bam /projects/analysis/analysis26/A64121/H3CL2ALXX_1/A64121/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64121_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-21-00187 BLGSP-71-21-00187-10A-01D genome hg38 normal BL_Adult A64122 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-21-00187-10A-01D.hg38.bam /projects/analysis/analysis26/A64122/H3CL2ALXX_2/A64122/150nt/hg38_no_alt/bwa-mem-0.7.6a/A64122_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00146 BLGSP-71-06-00146-10A-01D genome hg38 normal BL_Pediatric A66494 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00146-10A-01D.hg38.bam /projects/analysis/analysis27/A66494/H73TYALXX_3/A66494/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A66494_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00159 BLGSP-71-06-00159-12A-01D genome hg38 normal BL_Pediatric A66496 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00159-12A-01D.hg38.bam /projects/analysis/analysis27/A66496/H5WLTALXX_5/A66496/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A66496_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00255 BLGSP-71-06-00255-12A-01D genome hg38 normal BL_Pediatric A66498 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00255-12A-01D.hg38.bam /projects/analysis/analysis27/A66498/H5WLTALXX_6/A66498/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A66498_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00165 BLGSP-71-06-00165-99A-01D genome hg38 normal BL_Pediatric A68621 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00165-99A-01D.hg38.bam /projects/analysis/analysis28/A68621/HG35NALXX_6/A68621/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68621_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00166 BLGSP-71-06-00166-99A-01D genome hg38 normal BL_Pediatric A68623 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00166-99A-01D.hg38.bam /projects/analysis/analysis28/A68623/HG3TGALXX_1/A68623/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68623_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00169 BLGSP-71-06-00169-99A-01D genome hg38 normal BL_Pediatric A68625 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00169-99A-01D.hg38.bam /projects/analysis/analysis28/A68625/HG3TGALXX_2/A68625/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68625_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00050 BLGSP-71-08-00050-10A-01D genome hg38 normal BL_Pediatric A68627 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00050-10A-01D.hg38.bam /projects/analysis/analysis28/A68627/HG3TGALXX_5/A68627/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68627_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00191 BLGSP-71-08-00191-10A-01D genome hg38 normal BL_Pediatric A68629 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00191-10A-01D.hg38.bam /projects/analysis/analysis28/A68629/HG3L5ALXX_1/A68629/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68629_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00194 BLGSP-71-08-00194-10A-01D genome hg38 normal BL_Pediatric A68631 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00194-10A-01D.hg38.bam /projects/analysis/analysis28/A68631/HG3TGALXX_8/A68631/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68631_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00197 BLGSP-71-08-00197-10A-01D genome hg38 normal BL_Pediatric A68633 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00197-10A-01D.hg38.bam /projects/analysis/analysis28/A68633/HG5JYALXX_5/A68633/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68633_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00199 BLGSP-71-08-00199-10A-01D genome hg38 normal BL_Pediatric A68635 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00199-10A-01D.hg38.bam /projects/analysis/analysis28/A68635/HG5JYALXX_8/A68635/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68635_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00200 BLGSP-71-08-00200-10A-01D genome hg38 normal BL_Pediatric A68637 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00200-10A-01D.hg38.bam /projects/analysis/analysis28/A68637/HG3NLALXX_3/A68637/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68637_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00204 BLGSP-71-08-00204-10A-01D genome hg38 normal BL_Pediatric A68639 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00204-10A-01D.hg38.bam /projects/analysis/analysis28/A68639/HG3NLALXX_6/A68639/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68639_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00205 BLGSP-71-08-00205-10A-01D genome hg38 normal BL_Pediatric A68641 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00205-10A-01D.hg38.bam /projects/analysis/analysis28/A68641/HG3T5ALXX_1/A68641/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68641_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00206 BLGSP-71-08-00206-10A-01D genome hg38 normal BL_Pediatric A68643 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00206-10A-01D.hg38.bam /projects/analysis/analysis28/A68643/HG3T5ALXX_4/A68643/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68643_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00210 BLGSP-71-08-00210-10A-01D genome hg38 normal BL_Pediatric A68645 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00210-10A-01D.hg38.bam /projects/analysis/analysis28/A68645/HG3T5ALXX_7/A68645/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A68645_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00171 BLGSP-71-06-00171-99A-01D genome hg38 normal BL_Pediatric A70931 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00171-99A-01D.hg38.bam /projects/analysis/analysis28/A70931/HKNVJALXX_8/A70931/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70931_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00174 BLGSP-71-06-00174-99A-01D genome hg38 normal BL_Pediatric A70933 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00174-99A-01D.hg38.bam /projects/analysis/analysis28/A70933/HKNCHALXX_1/A70933/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70933_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00177 BLGSP-71-06-00177-99A-01D genome hg38 normal BL_Pediatric A70935 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00177-99A-01D.hg38.bam /projects/analysis/analysis28/A70935/HKN5MALXX_1/A70935/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70935_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00180 BLGSP-71-06-00180-99A-01D genome hg38 normal BL_Pediatric A70937 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00180-99A-01D.hg38.bam /projects/analysis/analysis28/A70937/HKMVJALXX_1/A70937/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70937_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00251 BLGSP-71-06-00251-12A-01D genome hg38 normal BL_Pediatric A70939 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00251-12A-01D.hg38.bam /projects/analysis/analysis28/A70939/HKNHKALXX_1/A70939/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70939_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00280 BLGSP-71-06-00280-99A-01D genome hg38 normal BL_Pediatric A70942 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00280-99A-01D.hg38.bam /projects/analysis/analysis28/A70942/HKNHKALXX_4/A70942/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70942_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00281 BLGSP-71-06-00281-99A-01D genome hg38 normal BL_Pediatric A70944 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00281-99A-01D.hg38.bam /projects/analysis/analysis28/A70944/HKNHKALXX_7/A70944/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70944_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00253 BLGSP-71-06-00253-10A-01D genome hg38 normal BL_Pediatric A70946 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00253-10A-01D.hg38.bam /projects/analysis/analysis28/A70946/HKNHKALXX_8/A70946/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70946_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00172 BLGSP-71-06-00172-99A-01D genome hg38 normal BL_Pediatric A70948 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00172-99A-01D.hg38.bam /projects/analysis/analysis28/A70948/HKMMJALXX_3/A70948/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70948_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00190 BLGSP-71-06-00190-10A-01D genome hg38 normal BL_Pediatric A70950 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00190-10A-01D.hg38.bam /projects/analysis/analysis28/A70950/HKMMJALXX_6/A70950/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70950_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00129 BLGSP-71-19-00129-16A-01D genome hg38 normal BL_Pediatric A70952 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00129-16A-01D.hg38.bam /projects/analysis/analysis28/A70952/HKMMJALXX_7/A70952/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70952_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00252 BLGSP-71-06-00252-10A-01D genome hg38 normal BL_Pediatric A70954 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00252-10A-01D.hg38.bam /projects/analysis/analysis28/A70954/HKMMJALXX_8/A70954/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70954_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00277 BLGSP-71-06-00277-12A-01D genome hg38 normal BL_Pediatric A70956 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00277-12A-01D.hg38.bam /projects/analysis/analysis29/A70956/HKNCLALXX_3/A70956/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A70956_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00156 BLGSP-71-06-00156-99A-01D genome hg38 normal BLGSP_Bcell_UNC A77531 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00156-99A-01D.hg38.bam /projects/analysis/analysis30/A77531/H3JKLCCXY_4/A77531/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77531_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00163 BLGSP-71-06-00163-10A-01D genome hg38 normal BLGSP_Bcell_UNC A77533 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00163-10A-01D.hg38.bam /projects/analysis/analysis30/A77533/H2WFFCCXY_3/A77533/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77533_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00164 BLGSP-71-06-00164-99A-01D genome hg38 normal BL_Pediatric A77535 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00164-99A-01D.hg38.bam /projects/analysis/analysis30/A77535/H2WF5CCXY_1/A77535/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77535_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00167 BLGSP-71-06-00167-99A-01D genome hg38 normal BLGSP_Bcell_UNC A77537 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00167-99A-01D.hg38.bam /projects/analysis/analysis30/A77537/H2WF5CCXY_2/A77537/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77537_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-06-00178 BLGSP-71-06-00178-99A-01D genome hg38 normal BL_Pediatric A77539 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00178-99A-01D.hg38.bam /projects/analysis/analysis30/A77539/H2WFFCCXY_7/A77539/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77539_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00121 BLGSP-71-19-00121-16A-01D genome hg38 normal BLGSP_Bcell_UNC A77541 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-19-00121-16A-01D.hg38.bam /projects/analysis/analysis30/A77541/H2WF5CCXY_3/A77541/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A77541_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-22-00332 BLGSP-71-22-00332-10A-01D genome hg38 normal BL_Pediatric A78681 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-22-00332-10A-01D.hg38.bam /projects/analysis/analysis30/A78681/HCV35CCXY_6/A78681/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A78681_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-22-00337 BLGSP-71-22-00337-10A-01D genome hg38 normal BL_Pediatric A78685 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-22-00337-10A-01D.hg38.bam /projects/analysis/analysis30/A78685/HCV7WCCXY_2/A78685/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A78685_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-22-00339 BLGSP-71-22-00339-10A-01D genome hg38 normal BL_Pediatric A78688 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-22-00339-10A-01D.hg38.bam /projects/analysis/analysis30/A78688/HCV7WCCXY_5/A78688/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A78688_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-22-00347 BLGSP-71-22-00347-10A-01D genome hg38 normal BL_Pediatric A78690 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-22-00347-10A-01D.hg38.bam /projects/analysis/analysis30/A78690/HCV7WCCXY_8/A78690/150nt/hg38_no_alt/bwa-mem-0.7.6a-sb/A78690_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00025 BLGSP-71-08-00025-10A-01D genome hg38 normal BL_Pediatric A82291 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00025-10A-01D.hg38.bam /projects/analysis/analysis30/A82291/merge24636_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82291_14_lanes_dupsFlagged.bam gambl +cram TRUE BLGSP-71-06-00283 BLGSP-71-06-00283-99A-01D genome hg38 normal BL_Pediatric A82293 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00283-99A-01D.hg38.bam /projects/analysis/analysis30/A82293/merge24649_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82293_14_lanes_dupsFlagged.cram gambl +cram TRUE BLGSP-71-06-00286 BLGSP-71-06-00286-99A-01D genome hg38 normal BL_Pediatric A82297 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-06-00286-99A-01D.hg38.bam /projects/analysis/analysis30/A82297/merge25088_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82297_16_lanes_dupsFlagged.cram gambl +cram TRUE BLGSP-71-06-00288 BLGSP-71-06-00288-99A-01D genome hg38 normal BL_Pediatric A82299 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-06-00288-99A-01D.hg38.bam /projects/analysis/analysis30/A82299/merge25089_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82299_16_lanes_dupsFlagged.cram gambl +bam TRUE BLGSP-71-21-00188 BLGSP-71-21-00188-10A-01D genome hg38 normal BL_Adult A87335 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-21-00188-10A-01D.hg38.bam /projects/analysis/analysis30/A87335/merge27390_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A87335_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00207 BLGSP-71-08-00207-10A-01D genome hg38 normal BL_Pediatric A93863 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00207-10A-01D.hg38.bam /projects/analysis/analysis30/A93863/merge32375_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93863_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00212 BLGSP-71-08-00212-10A-01D genome hg38 normal BL_Pediatric A93865 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00212-10A-01D.hg38.bam /projects/analysis/analysis30/A93865/merge32373_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93865_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00213 BLGSP-71-08-00213-10A-01D genome hg38 normal BL_Pediatric A93867 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-08-00213-10A-01D.hg38.bam /projects/analysis/analysis30/A93867/merge32371_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93867_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00217 BLGSP-71-08-00217-10A-01D genome hg38 normal BL_Pediatric A93869 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00217-10A-01D.hg38.bam /projects/analysis/analysis30/A93869/merge32369_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93869_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-08-00219 BLGSP-71-08-00219-10A-01D genome hg38 normal BL_Pediatric A93871 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-08-00219-10A-01D.hg38.bam /projects/analysis/analysis30/A93871/merge32367_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93871_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-21-00243 BLGSP-71-21-00243-10A-01D genome hg38 normal BL_Adult A93873 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-21-00243-10A-01D.hg38.bam /projects/analysis/analysis30/A93873/merge32366_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93873_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00415 BLGSP-71-27-00415-10A-01D genome hg38 normal BL_Adult A93879 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00415-10A-01D.hg38.bam /projects/analysis/analysis30/A93879/merge32365_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93879_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00429 BLGSP-71-27-00429-10A-01D genome hg38 normal BL_Adult A93881 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00429-10A-01D.hg38.bam /projects/analysis/analysis30/A93881/merge32364_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93881_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00512 BLGSP-71-27-00512-10A-01D genome hg38 normal BL_Adult A93883 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00512-10A-01D.hg38.bam /projects/analysis/analysis30/A93883/merge32363_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A93883_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00522 BLGSP-71-19-00522-10A-01D genome hg38 normal BL_Pediatric A94777 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00522-10A-01D.hg38.bam /projects/analysis/analysis31/A94777/merge33369_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A94777_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00411 BLGSP-71-27-00411-10A-01D genome hg38 normal BL_Adult A94789 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00411-10A-01D.hg38.bam /projects/analysis/analysis31/A94789/merge33367_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A94789_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00425 BLGSP-71-27-00425-10A-01D genome hg38 normal BL_Adult A94791 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00425-10A-01D.hg38.bam /projects/analysis/analysis31/A94791/merge33406_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A94791_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-17-00356 BLGSP-71-17-00356-99A-01D genome hg38 normal BL_Adult A95253 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-17-00356-99A-01D.hg38.bam /projects/analysis/analysis31/A95253/merge34309_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95253_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-17-00237 BLGSP-71-17-00237-99A-01D genome hg38 normal BL_Adult A95255 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-17-00237-99A-01D.hg38.bam /projects/analysis/analysis31/A95255/merge34308_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95255_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-17-00231 BLGSP-71-17-00231-99A-01D genome hg38 normal BL_Adult A95257 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-17-00231-99A-01D.hg38.bam /projects/analysis/analysis31/A95257/merge34307_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95257_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-17-00238 BLGSP-71-17-00238-99A-01D genome hg38 normal BL_Adult A95260 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-17-00238-99A-01D.hg38.bam /projects/analysis/analysis31/A95260/merge34306_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95260_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00520 BLGSP-71-19-00520-10A-01D genome hg38 normal BL_Pediatric A95262 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00520-10A-01D.hg38.bam /projects/analysis/analysis31/A95262/merge34315_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95262_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00519 BLGSP-71-19-00519-10A-01D genome hg38 normal BL_Pediatric A95264 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-19-00519-10A-01D.hg38.bam /projects/analysis/analysis31/A95264/merge34316_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95264_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00521 BLGSP-71-19-00521-10A-01D genome hg38 normal BL_Pediatric A95266 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00521-10A-01D.hg38.bam /projects/analysis/analysis31/A95266/merge34319_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95266_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-19-00523 BLGSP-71-19-00523-16A-01D genome hg38 normal BL_Pediatric A95268 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-19-00523-16A-01D.hg38.bam /projects/analysis/analysis31/A95268/merge34318_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95268_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00414 BLGSP-71-27-00414-10A-01D genome hg38 normal BL_Adult A95272 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00414-10A-01D.hg38.bam /projects/analysis/analysis32/A95272/merge34348_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95272_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00430 BLGSP-71-27-00430-10A-01D genome hg38 normal BL_Adult A95274 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00430-10A-01D.hg38.bam /projects/analysis/analysis32/A95274/merge34346_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95274_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00420 BLGSP-71-27-00420-10A-01D genome hg38 normal BL_Adult A95278 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00420-10A-01D.hg38.bam /projects/analysis/analysis32/A95278/merge34347_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A95278_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-27-00513 BLGSP-71-27-00513-10A-01D genome hg38 normal BL_Adult B00424 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-27-00513-10A-01D.hg38.bam /projects/analysis/analysis32/B00424/merge38248_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B00424_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-17-00235 BLGSP-71-17-00235-99A-01D genome hg38 normal BL_Adult B35153 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-17-00235-99A-01D.hg38.bam /projects/analysis/analysis33/B35153/merge48824_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B35153_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-30-00641 BLGSP-71-30-00641-10A-01D genome hg38 normal BL_Pediatric B54457 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-30-00641-10A-01D.hg38.bam /projects/analysis/analysis32/B54457/merge45987_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B54457_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-30-00660 BLGSP-71-30-00660-10A-01D genome hg38 normal BL_Adult B54458 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-30-00660-10A-01D.hg38.bam /projects/analysis/analysis32/B54458/merge45986_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B54458_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-30-00665 BLGSP-71-30-00665-10A-01D genome hg38 normal BL_Adult B54459 Genome frozen 150 unsorted F data/genome_bams/BLGSP-71-30-00665-10A-01D.hg38.bam /projects/analysis/analysis32/B54459/merge45985_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B54459_1_lane_dupsFlagged.bam gambl +bam TRUE BLGSP-71-30-00666 BLGSP-71-30-00666-10A-01D genome hg38 normal BL_Adult B54460 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-30-00666-10A-01D.hg38.bam /projects/analysis/analysis33/B54460/merge49105_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B54460_2_lanes_dupsFlagged.bam gambl +bam TRUE BLGSP-71-30-00682 BLGSP-71-30-00682-10A-01D genome hg38 normal BL_Adult B54461 Genome frozen 150 unsorted M data/genome_bams/BLGSP-71-30-00682-10A-01D.hg38.bam /projects/analysis/analysis33/B54461/merge49106_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/B54461_2_lanes_dupsFlagged.bam gambl +cram TRUE 78-15566 78-15566N genome hg38 normal MCL_Morin A82259 Genome frozen 150 blood M data/genome_bams/78-15566N.hg38.bam /projects/analysis/analysis30/A82259/merge25083_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82259_16_lanes_dupsFlagged.cram gambl +cram TRUE 11-19987 11-19987N genome hg38 normal MCL_Morin A82256 Genome frozen 150 blood M data/genome_bams/11-19987N.hg38.bam /projects/analysis/analysis30/A82256/merge25086_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82256_16_lanes_dupsFlagged.cram gambl +cram TRUE 12-20363 12-20363N genome hg38 normal MCL_Morin A82257 Genome frozen 150 blood F data/genome_bams/12-20363N.hg38.bam /projects/analysis/analysis30/A82257/merge24643_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82257_14_lanes_dupsFlagged.cram gambl +cram TRUE 07-11855 07-11855N genome hg38 normal MCL_Morin A82252 Genome frozen 150 blood M data/genome_bams/07-11855N.hg38.bam /projects/analysis/analysis30/A82252/merge25085_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82252_16_lanes_dupsFlagged.cram gambl +cram TRUE 07-20432 07-20432N genome hg38 normal MCL_Morin A82254 Genome frozen 150 blood M data/genome_bams/07-20432N.hg38.bam /projects/analysis/analysis30/A82254/merge24638_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82254_14_lanes_dupsFlagged.cram gambl +cram TRUE 09-36389 09-36389N genome hg38 normal MCL_Morin A82255 Genome frozen 150 blood M data/genome_bams/09-36389N.hg38.bam /projects/analysis/analysis30/A82255/merge24648_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82255_14_lanes_dupsFlagged.cram gambl +cram TRUE 05-11733 05-11733N genome hg38 normal MCL_Morin A82251 Genome frozen 150 blood F data/genome_bams/05-11733N.hg38.bam /projects/analysis/analysis30/A82251/merge25082_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82251_16_lanes_dupsFlagged.cram gambl +bam TRUE 07-20025 07-20025N genome hg38 normal MCL_Morin A82253 Genome frozen 150 blood M data/genome_bams/07-20025N.hg38.bam /projects/analysis/analysis30/A82253/merge25087_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82253_16_lanes_dupsFlagged.bam gambl +cram TRUE 04-38353 04-38353N genome hg38 normal MCL_Morin A82250 Genome frozen 150 blood F data/genome_bams/04-38353N.hg38.bam /projects/analysis/analysis30/A82250/merge25090_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82250_16_lanes_dupsFlagged.cram gambl +cram TRUE 13-14456 13-14456N genome hg38 normal MCL_Morin A82258 Genome frozen 150 blood M data/genome_bams/13-14456N.hg38.bam /projects/analysis/analysis30/A82258/merge25084_bwa-mem-0.7.6a-sb/150nt/hg38_no_alt/A82258_16_lanes_dupsFlagged.cram gambl +bam TRUE 08-20595 08-20595N genome hg38 normal MCL_Morin A68657 Genome frozen 150 blood M data/genome_bams/08-20595N.hg38.bam /projects/analysis/analysis27/A68657/HG3LFALXX_4/A68657/150nt/hg38_no_alt/bwa-0.5.7/A68657_1_lane_dupsFlagged.bam gambl +bam TRUE 01-15563 01-15563N genome hg38 normal MCL_Morin A92122 Genome frozen 150 blood M data/genome_bams/01-15563N.hg38.bam /projects/analysis/analysis30/A92122/merge32121_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92122_24_lanes_dupsFlagged.bam gambl +bam TRUE 03-29738 03-29738N genome hg38 normal MCL_Morin A92123 Genome frozen 150 blood M data/genome_bams/03-29738N.hg38.bam /projects/analysis/analysis30/A92123/merge32111_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92123_24_lanes_dupsFlagged.bam gambl +bam TRUE 08-34293 08-34293N genome hg38 normal MCL_Morin A92136 Genome frozen 150 blood M data/genome_bams/08-34293N.hg38.bam /projects/analysis/analysis30/A92136/merge32128_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92136_24_lanes_dupsFlagged.bam gambl +cram TRUE 10-40390 10-40390N genome hg38 normal MCL_Morin A92125 Genome frozen 150 blood M data/genome_bams/10-40390N.hg38.bam /projects/analysis/analysis30/A92125/merge32114_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92125_24_lanes_dupsFlagged.cram gambl +bam TRUE 14-16889 14-16889N genome hg38 normal MCL_Morin A92127 Genome frozen 150 blood M data/genome_bams/14-16889N.hg38.bam /projects/analysis/analysis30/A92127/merge32108_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92127_24_lanes_dupsFlagged.bam gambl +bam TRUE 09-27079 09-27079N genome hg38 normal MCL_Morin A92124 Genome frozen 150 blood M data/genome_bams/09-27079N.hg38.bam /projects/analysis/analysis30/A92124/merge32109_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92124_24_lanes_dupsFlagged.bam gambl +bam TRUE 14-28333 14-28333N genome hg38 normal MCL_Morin A92128 Genome frozen 150 blood M data/genome_bams/14-28333N.hg38.bam /projects/analysis/analysis30/A92128/merge32117_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92128_24_lanes_dupsFlagged.bam gambl +bam TRUE 14-36901 14-36901N genome hg38 normal MCL_Morin A92129 Genome frozen 150 blood M data/genome_bams/14-36901N.hg38.bam /projects/analysis/analysis30/A92129/merge32125_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92129_24_lanes_dupsFlagged.bam gambl +bam TRUE 15-30071 15-30071N genome hg38 normal MCL_Morin A92140 Genome frozen 150 blood M data/genome_bams/15-30071N.hg38.bam /projects/analysis/analysis30/A92140/merge32112_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92140_24_lanes_dupsFlagged.bam gambl +bam TRUE 15-24585 15-24585N genome hg38 normal MCL_Morin A92139 Genome frozen 150 blood M data/genome_bams/15-24585N.hg38.bam /projects/analysis/analysis30/A92139/merge32122_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92139_24_lanes_dupsFlagged.bam gambl +bam TRUE 10-17030 10-17030N genome hg38 normal MCL_Morin A92133 Genome frozen 150 blood M data/genome_bams/10-17030N.hg38.bam /projects/analysis/analysis30/A92133/merge32110_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92133_24_lanes_dupsFlagged.bam gambl +bam TRUE 12-18218 12-18218N genome hg38 normal MCL_Morin A92137 Genome frozen 150 blood M data/genome_bams/12-18218N.hg38.bam /projects/analysis/analysis30/A92137/merge32124_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92137_24_lanes_dupsFlagged.bam gambl +bam TRUE 10-17031 10-17031N genome hg38 normal MCL_Morin A92134 Genome frozen 150 blood M data/genome_bams/10-17031N.hg38.bam /projects/analysis/analysis30/A92134/merge32120_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92134_24_lanes_dupsFlagged.bam gambl +cram TRUE 79-15007 79-15007N genome hg38 normal MCL_Morin A92141 Genome frozen 150 blood F data/genome_bams/79-15007N.hg38.bam /projects/analysis/analysis30/A92141/merge32116_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92141_24_lanes_dupsFlagged.cram gambl +bam TRUE 16-15192 16-15192N genome hg38 normal MCL_Morin A92142 Genome frozen 150 blood F data/genome_bams/16-15192N.hg38.bam /projects/analysis/analysis30/A92142/merge32118_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92142_24_lanes_dupsFlagged.bam gambl +bam TRUE 10-17838 10-17838N genome hg38 normal MCL_Morin A92135 Genome frozen 150 blood M data/genome_bams/10-17838N.hg38.bam /projects/analysis/analysis30/A92135/merge32129_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92135_24_lanes_dupsFlagged.bam gambl +bam TRUE 16-32881 16-32881N genome hg38 normal MCL_Morin A92144 Genome frozen 150 blood M data/genome_bams/16-32881N.hg38.bam /projects/analysis/analysis30/A92144/merge32131_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92144_24_lanes_dupsFlagged.bam gambl +bam TRUE 01-20357 01-20357N genome hg38 normal MCL_Morin A92143 Genome frozen 150 blood F data/genome_bams/01-20357N.hg38.bam /projects/analysis/analysis30/A92143/merge32130_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92143_24_lanes_dupsFlagged.bam gambl +bam TRUE 16-40003 16-40003N genome hg38 normal MCL_Morin A92146 Genome frozen 150 blood M data/genome_bams/16-40003N.hg38.bam /projects/analysis/analysis30/A92146/merge32123_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92146_24_lanes_dupsFlagged.bam gambl +bam TRUE 13-29643 13-29643N genome hg38 normal MCL_Morin A92126 Genome frozen 150 blood M data/genome_bams/13-29643N.hg38.bam /projects/analysis/analysis30/A92126/merge32127_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92126_24_lanes_dupsFlagged.bam gambl +bam TRUE 13-33873 13-33873N genome hg38 normal MCL_Morin A92138 Genome frozen 150 blood M data/genome_bams/13-33873N.hg38.bam /projects/analysis/analysis30/A92138/merge32115_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92138_24_lanes_dupsFlagged.bam gambl +bam TRUE 16-31255 16-31255N genome hg38 normal MCL_Morin A92145 Genome frozen 150 blood M data/genome_bams/16-31255N.hg38.bam /projects/analysis/analysis30/A92145/merge32113_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92145_24_lanes_dupsFlagged.bam gambl +bam TRUE 16-15506 16-15506N genome hg38 normal MCL_Morin A92131 Genome frozen 150 blood M data/genome_bams/16-15506N.hg38.bam /projects/analysis/analysis30/A92131/merge32119_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92131_24_lanes_dupsFlagged.bam gambl +bam TRUE 15-34596 15-34596N genome hg38 normal MCL_Morin A92130 Genome frozen 150 blood M data/genome_bams/15-34596N.hg38.bam /projects/analysis/analysis30/A92130/merge31571_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A92130_15_lanes_dupsFlagged.bam gambl +bam TRUE 03-13711 03-13711N genome hg38 normal MCL_Morin A99563 Genome frozen 150 blood F data/genome_bams/03-13711N.hg38.bam /projects/analysis/analysis32/A99563/merge37753_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99563_1_lane_dupsFlagged.bam gambl +bam TRUE 03-16786 03-16786N genome hg38 normal MCL_Morin A99564 Genome frozen 150 blood M data/genome_bams/03-16786N.hg38.bam /projects/analysis/analysis32/A99564/merge37752_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99564_1_lane_dupsFlagged.bam gambl +bam TRUE 06-19179 06-19179N genome hg38 normal MCL_Morin A99565 Genome frozen 150 blood F data/genome_bams/06-19179N.hg38.bam /projects/analysis/analysis32/A99565/merge37736_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99565_1_lane_dupsFlagged.bam gambl +bam TRUE 06-23090 06-23090N genome hg38 normal MCL_Morin A99566 Genome frozen 150 blood F data/genome_bams/06-23090N.hg38.bam /projects/analysis/analysis32/A99566/merge37735_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99566_1_lane_dupsFlagged.bam gambl +bam TRUE 10-26934 10-26934N genome hg38 normal MCL_Morin A99567 Genome frozen 150 blood F data/genome_bams/10-26934N.hg38.bam /projects/analysis/analysis32/A99567/merge37738_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99567_1_lane_dupsFlagged.bam gambl +bam TRUE 97-17126 97-17126N genome hg38 normal MCL_Morin A99568 Genome frozen 150 blood M data/genome_bams/97-17126N.hg38.bam /projects/analysis/analysis32/A99568/merge37737_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99568_1_lane_dupsFlagged.bam gambl +bam TRUE 01-26545 01-26545N genome hg38 normal MCL_Morin A99569 Genome frozen 150 blood M data/genome_bams/01-26545N.hg38.bam /projects/analysis/analysis32/A99569/merge37751_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99569_1_lane_dupsFlagged.bam gambl +bam TRUE 01-26790 01-26790N genome hg38 normal MCL_Morin A99570 Genome frozen 150 blood M data/genome_bams/01-26790N.hg38.bam /projects/analysis/analysis32/A99570/merge37750_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99570_1_lane_dupsFlagged.bam gambl +bam TRUE 94-13463 94-13463N genome hg38 normal MCL_Morin A99571 Genome frozen 150 blood M data/genome_bams/94-13463N.hg38.bam /projects/analysis/analysis32/A99571/merge37859_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99571_1_lane_dupsFlagged.bam gambl +bam TRUE 77-56018 77-56018N genome hg38 normal MCL_Morin A99572 Genome frozen 150 blood F data/genome_bams/77-56018N.hg38.bam /projects/analysis/analysis32/A99572/merge37749_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99572_1_lane_dupsFlagged.bam gambl +bam TRUE 07-28085 07-28085N genome hg38 normal MCL_Morin A99573 Genome frozen 150 blood M data/genome_bams/07-28085N.hg38.bam /projects/analysis/analysis32/A99573/merge37748_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99573_1_lane_dupsFlagged.bam gambl +bam TRUE 08-19397 08-19397N genome hg38 normal MCL_Morin A99574 Genome frozen 150 blood F data/genome_bams/08-19397N.hg38.bam /projects/analysis/analysis32/A99574/merge37747_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99574_1_lane_dupsFlagged.bam gambl +bam TRUE 05-13982 05-13982N genome hg38 normal MCL_Morin A99575 Genome frozen 150 blood F data/genome_bams/05-13982N.hg38.bam /projects/analysis/analysis32/A99575/merge37746_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99575_1_lane_dupsFlagged.bam gambl +bam TRUE 10-20030 10-20030N genome hg38 normal MCL_Morin A99576 Genome frozen 150 blood M data/genome_bams/10-20030N.hg38.bam /projects/analysis/analysis32/A99576/merge37745_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99576_1_lane_dupsFlagged.bam gambl +bam TRUE 11-10748 11-10748N genome hg38 normal MCL_Morin A99577 Genome frozen 150 blood M data/genome_bams/11-10748N.hg38.bam /projects/analysis/analysis32/A99577/merge37744_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99577_1_lane_dupsFlagged.bam gambl +bam TRUE 13-10635 13-10635N genome hg38 normal MCL_Morin A99578 Genome frozen 150 blood F data/genome_bams/13-10635N.hg38.bam /projects/analysis/analysis32/A99578/merge37743_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99578_1_lane_dupsFlagged.bam gambl +bam TRUE 14-40961 14-40961N genome hg38 normal MCL_Morin A99579 Genome frozen 150 blood M data/genome_bams/14-40961N.hg38.bam /projects/analysis/analysis32/A99579/merge37742_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99579_1_lane_dupsFlagged.bam gambl +bam TRUE 15-19582 15-19582N genome hg38 normal MCL_Morin A99580 Genome frozen 150 blood M data/genome_bams/15-19582N.hg38.bam /projects/analysis/analysis32/A99580/merge37741_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99580_1_lane_dupsFlagged.bam gambl +bam TRUE 16-44147 16-44147N genome hg38 normal MCL_Morin A99581 Genome frozen 150 blood F data/genome_bams/16-44147N.hg38.bam /projects/analysis/analysis32/A99581/merge37740_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99581_1_lane_dupsFlagged.bam gambl +bam TRUE 12-22919 12-22919N genome hg38 normal MCL_Morin A99582 Genome frozen 150 blood M data/genome_bams/12-22919N.hg38.bam /projects/analysis/analysis32/A99582/merge37739_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99582_1_lane_dupsFlagged.bam gambl +bam TRUE 16-11370 16-11370N genome hg38 normal MCL_Morin A99583 Genome frozen 150 blood M data/genome_bams/16-11370N.hg38.bam /projects/analysis/analysis32/A99583/merge37798_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99583_1_lane_dupsFlagged.bam gambl +bam TRUE 11-37681 11-37681N genome hg38 normal MCL_Morin A99584 Genome frozen 150 blood M data/genome_bams/11-37681N.hg38.bam /projects/analysis/analysis32/A99584/merge37797_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99584_1_lane_dupsFlagged.bam gambl +bam TRUE 93-53574 93-53574N genome hg38 normal MCL_Morin A99585 Genome frozen 150 blood M data/genome_bams/93-53574N.hg38.bam /projects/analysis/analysis32/A99585/merge37796_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99585_1_lane_dupsFlagged.bam gambl +bam TRUE 01-20985 01-20985N genome hg38 normal MCL_Morin A99586 Genome frozen 150 blood F data/genome_bams/01-20985N.hg38.bam /projects/analysis/analysis32/A99586/merge38134_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99586_1_lane_dupsFlagged.bam gambl +bam TRUE 12-10626 12-10626N genome hg38 normal MCL_Morin A99587 Genome frozen 150 blood M data/genome_bams/12-10626N.hg38.bam /projects/analysis/analysis32/A99587/merge38132_bwa-mem-0.7.6a-sb/150bp/hg38_no_alt/A99587_1_lane_dupsFlagged.bam gambl diff --git a/workflows/reference_files/2.4/prepare_reference_files.smk b/workflows/reference_files/2.4/prepare_reference_files.smk index 7f8005ab..e348f836 100644 --- a/workflows/reference_files/2.4/prepare_reference_files.smk +++ b/workflows/reference_files/2.4/prepare_reference_files.smk @@ -24,6 +24,7 @@ original_dir = os.getcwd() reference_dir = config["reference_directory"] os.chdir(reference_dir) + # Include the `reference_files` module include: os.path.join(original_dir, "reference_files.smk") @@ -56,7 +57,12 @@ rule all: rules.get_blacklist_download.output.bed, rules.get_repeatmasker_download.output.bed, rules.get_mutect2_pon.output.vcf, - rules.get_af_only_gnomad_vcf.output.vcf + rules.get_af_only_gnomad_vcf.output.vcf, + rules.get_jabba_gc_rds.output.rds, + rules.get_jabba_map_rds.output.rds, + rules.get_par_rds.output.rds, + rules.jabba_pon_make_germline_filter.output.germline, + rules.jabba_pon_make_pon.output.pon ], genome_build=config["genome_builds"].keys(), bwa_version=config["tools"]["bwa"]["version"], diff --git a/workflows/reference_files/2.4/reference_files.smk b/workflows/reference_files/2.4/reference_files.smk index f3e3a831..e6e59b04 100644 --- a/workflows/reference_files/2.4/reference_files.smk +++ b/workflows/reference_files/2.4/reference_files.smk @@ -4,6 +4,16 @@ include: "reference_files_header.smk" +##### SRC/ETC DIRECTORY ##### + + +for k,v in config['pon'].items(): + config['pon'][k] = os.path.join(workflow.basedir, v) + +for k,v in config['jabba'].items(): + config['jabba'][k] = os.path.join(workflow.basedir, v) + + ##### SEQUENCE AND INDICES ##### @@ -227,6 +237,213 @@ rule calc_gc_content: gzip -c > {output.wig} """) +rule get_jabba_gc_rds: + input: + bed = get_download_file(rules.download_ucsc_gc.output.bed), + txt = get_download_file(rules.download_ucsc_chrom_sizes.output.txt) + output: + rds = "genomes/{genome_build}/annotations/jabba/gc1000.rds" + conda: CONDA_ENVS["rtracklayer"] + shell: + op.as_one_line(""" + Rscript + -e 'library(rtracklayer); gr <- import("{input.bed}")' + -e 'names(mcols(gr))[1] <- "score"; gr[gr$score == "nan",]$score <- 0' + -e 'gr$score <- as.numeric(gr$score)' + -e 'sizes <- read.delim("{input.txt}", stringsAsFactors = FALSE, col.names = c("chrom", "length"), header = FALSE)' + -e 'sizes <- unlist(split(as.numeric(sizes$length), sizes$chrom))[levels(seqnames(gr))]' + -e 'seqlengths(gr) <- sizes' + -e 'saveRDS(gr, "{output.rds}")' + """) + +rule get_jabba_map_rds: + input: + bed = get_download_file(rules.download_ucsc_map.output.bed), + txt = get_download_file(rules.download_ucsc_chrom_sizes.output.txt) + output: + rds = "genomes/{genome_build}/annotations/jabba/map1000.rds" + conda: CONDA_ENVS["rtracklayer"] + shell: + op.as_one_line(""" + Rscript + -e 'library(rtracklayer); gr <- import("{input.bed}")' + -e 'names(mcols(gr))[1] <- "score"; gr[gr$score == "nan",]$score <- 0' + -e 'gr$score <- as.numeric(gr$score)' + -e 'sizes <- read.delim("{input.txt}", stringsAsFactors = FALSE, col.names = c("chrom", "length"), header = FALSE)' + -e 'sizes <- unlist(split(as.numeric(sizes$length), sizes$chrom))[levels(seqnames(gr))]' + -e 'seqlengths(gr) <- sizes' + -e 'saveRDS(gr, "{output.rds}")' + """) + +rule get_par_rds: + input: + bed = get_download_file(rules.download_par_bed.output.bed), + txt = get_download_file(rules.download_ucsc_chrom_sizes.output.txt) + output: + rds = "genomes/{genome_build}/annotations/jabba/PAR_{genome_build}.rds" + conda: CONDA_ENVS["rtracklayer"] + shell: + op.as_one_line(""" + Rscript + -e 'library(rtracklayer); gr <- import("{input.bed}")' + -e 'sizes <- read.delim("{input.txt}", stringsAsFactors = FALSE, col.names = c("chrom", "length"), header = FALSE)' + -e 'sizes <- unlist(split(as.numeric(sizes$length), sizes$chrom))[levels(seqnames(gr))]' + -e 'seqlengths(gr) <- sizes' + -e 'saveRDS(gr, "{output.rds}")' + """) + + +##### JaBbA PON generation ###### + + +rule install_fragcounter: + output: + complete = "downloads/jabba_prereqs/fragcounter.installed" + conda: CONDA_ENVS["jabba"] + shell: + op.as_one_line(""" + Rscript -e 'Sys.setenv(R_REMOTES_NO_ERRORS_FROM_WARNINGS = TRUE)' + -e 'if (!"fragCounter" %in% rownames(installed.packages())) {{remotes::install_github("morinlab/fragCounter", upgrade = TRUE, force = TRUE)}}' + -e 'library(fragCounter)' + && + touch {output.complete} + """) + + +rule install_dryclean: + input: + installed = "downloads/jabba_prereqs/fragcounter.installed" + output: + complete = "downloads/jabba_prereqs/dryclean.installed" + conda: CONDA_ENVS["jabba"] + shell: + op.as_one_line(""" + Rscript -e 'Sys.setenv(R_REMOTES_NO_ERRORS_FROM_WARNINGS = TRUE)' + -e 'if (!"gUtils" %in% rownames(installed.packages())) {{remotes::install_github("mskilab/gUtils", upgrade = FALSE)}}' + -e 'if (!"dryclean" %in% rownames(installed.packages())) {{remotes::install_github("morinlab/dryclean", upgrade = FALSE)}}' + -e 'library(dryclean)' + && + touch {output.complete} + """) + +# Use normal samples specified in config['pon'] table +NORMALS = {k : op.load_samples(v) for k,v in config['pon'].items()} +NORMALS = {k : dict(zip(v.sample_id, v.data_path)) for k,v in NORMALS.items()} + + +rule jabba_pon_symlink_normal_bams: + output: + bam = "genomes/{genome_build}/jabba/pon/00-normal_bams/{sample_id}.bam", + bai = "genomes/{genome_build}/jabba/pon/00-normal_bams/{sample_id}.bam.bai" + params: + bam = lambda wc: NORMALS[wc.genome_build][wc.sample_id] + run: + shell("ln -sf {params.bam} {output.bam}") + if params.bam.endswith('.cram'): + shell("ln -sf {params.bam}.crai {output.bai}") + else: + shell("ln -sf {params.bam}.bai {output.bai}") + +# Run fragcounter on normals to get GC/mappability corrected coverage values +rule jabba_pon_run_fragcounter: + input: + installed = str(rules.install_fragcounter.output.complete), + bam = str(rules.jabba_pon_symlink_normal_bams.output.bam), + gc = str(rules.get_jabba_gc_rds.output.rds), + map = str(rules.get_jabba_map_rds.output.rds), + ref = str(rules.get_genome_fasta_download.output.fasta) + output: + rds = "genomes/{genome_build}/jabba/pon/01-fragcounter/run/{sample_id}/cov.rds" + conda: CONDA_ENVS["jabba"] + threads: 1 + resources: + mem_mb = 4096 + shell: + op.as_one_line(""" + FRAG=$(Rscript -e 'cat(paste0(installed.packages()["fragCounter", "LibPath"], "/fragCounter/extdata/"))'); $FRAG/frag -b {input.bam} -r {input.ref} -w 1000 -d `dirname {input.gc}` -o `dirname {output.rds}` + """) + + +rule jabba_pon_symlink_fragcounter: + input: + rds = str(rules.jabba_pon_run_fragcounter.output.rds) + output: + rds = "genomes/{genome_build}/jabba/pon/01-fragcounter/cov/{sample_id}.cov.rds" + run: + op.relative_symlink(input.rds, output.rds) + +# Use dryclean to create panel-of-normal (PON) from fragcounter coverages +rule jabba_pon_make_pon: + input: + installed = str(rules.install_dryclean.output.complete), + par = str(rules.get_par_rds.output.rds), + rds = lambda wc: expand("genomes/{{genome_build}}/jabba/pon/01-fragcounter/cov/{sample_id}.cov.rds", + sample_id = NORMALS[wc.genome_build].keys()), + make_pon = config['jabba']['make_pon'] + output: + tbl = "genomes/{genome_build}/jabba/pon/normal_table.rds", + pon = "genomes/{genome_build}/jabba/pon/detergent.rds" + params: + choose_samples = 'cluster' + conda: CONDA_ENVS["jabba"] + threads: 100 + resources: + mem_mb = 30000 + shell: + op.as_one_line(""" + Rscript {input.make_pon} {threads} `dirname {input.rds[0]}` {output.tbl} {output.pon} {input.par} {wildcards.genome_build} {params.choose_samples} + """) + +# Improve coverage signal fidelity by running each normal against PON +# Serves to identify and separate background variations (noise) from foreground variation (signal) +rule jabba_pon_run_dryclean_normal: + input: + installed = str(rules.install_dryclean.output.complete), + rds = str(rules.jabba_pon_run_fragcounter.output.rds), + pon = str(rules.jabba_pon_make_pon.output.pon) + output: + rds = "genomes/{genome_build}/jabba/pon/02-dryclean/run/{sample_id}/drycleaned.cov.rds" + conda: CONDA_ENVS["jabba"] + threads: 12 + resources: + mem_mb = 30000 + shell: + op.as_one_line(""" + Rscript -e 'library(dryclean); library(parallel)' + -e 'samp <- readRDS("{input.rds}")' + -e 'decomp <- start_wash_cycle(cov = samp, detergent.pon.path = "{input.pon}", whole_genome = TRUE, mc.cores = {threads}, germline.filter = FALSE)' + -e 'saveRDS(decomp, "{output.rds}")' + """) + + +rule jabba_pon_link_dryclean_normal_rds: + input: + rds = "genomes/{genome_build}/jabba/pon/02-dryclean/run/{sample_id}/drycleaned.cov.rds" + output: + rds = "genomes/{genome_build}/jabba/pon/02-dryclean/cov/{sample_id}.drycleaned.cov.rds" + run: + op.relative_symlink(input.rds, output.rds) + +# Use dryclean normals to identify germline regions which will be used +# on tumour data to find germline regions. +rule jabba_pon_make_germline_filter: + input: + installed = str(rules.install_dryclean.output.complete), + tbl = str(rules.jabba_pon_make_pon.output.tbl), + rds = lambda wc: expand("genomes/{{genome_build}}/jabba/pon/02-dryclean/cov/{sample_id}.drycleaned.cov.rds", sample_id = NORMALS[wc.genome_build].keys()), + make_germline = config["jabba"]["make_germline"] + output: + germline = "genomes/{genome_build}/jabba/pon/germline.markers.rds" + conda: CONDA_ENVS["jabba"] + threads: 25 + resources: + mem_mb = 30000 + shell: + op.as_one_line(""" + Rscript {input.make_germline} {input.tbl} `dirname {input.rds[0]}` {output.germline} 0.5 0.1 {threads} + """) + + ##### VARIATION ##### diff --git a/workflows/reference_files/2.4/reference_files_header.smk b/workflows/reference_files/2.4/reference_files_header.smk index d2326396..00ee2a8f 100644 --- a/workflows/reference_files/2.4/reference_files_header.smk +++ b/workflows/reference_files/2.4/reference_files_header.smk @@ -411,6 +411,110 @@ rule download_sdf: mv $(dirname {output.sdf})/{params.build}/* {output.sdf} """) +rule download_ucsc_chrom_sizes: + output: + txt = 'downloads/chrom_sizes/sizes.{version}.txt' + params: + provider = 'ucsc', + url = lambda w: { + 'grch37': 'hg19', + 'grch38': 'hg38' + }[w.version] + shell: + "wget -qO {output.txt} http://hgdownload.cse.ucsc.edu/goldenpath/{params.url}/bigZips/{params.url}.chrom.sizes" + +rule make_1kb_genome_bed: + input: + txt = rules.download_ucsc_chrom_sizes.output.txt + output: + bed = 'downloads/genome_beds_1kb/1kb.{version}.bed' + params: + provider = 'ucsc', + url = lambda w: { + 'grch37': 'hg19', + 'grch38': 'hg38' + }[w.version] + conda: CONDA_ENVS['bedtools'] + shell: + op.as_one_line(""" + grep -P '^chr[12]?[0-9XY]\t' {input.txt} + | + bedtools makewindows -g - -w 1000 + | + bedtools sort + > + {output.bed} + """) + +rule download_ucsc_gc: + input: + sizes = rules.download_ucsc_chrom_sizes.output.txt, + bed = rules.make_1kb_genome_bed.output.bed + output: + bed = 'downloads/gc1000_beds/gc1000.{version}.bed' + params: + provider = 'ucsc', + url = lambda w: { + 'grch37': 'hg19', + 'grch38': 'hg38' + }[w.version] + conda: CONDA_ENVS["wiggletools"] + resources: + mem_mb = 18000 + shell: + op.as_one_line(""" + wget -qO downloads/gc1000_beds/{wildcards.version}.gc5Base.wig.gz http://hgdownload.cse.ucsc.edu/goldenpath/{params.url}/bigZips/{params.url}.gc5Base.wigVarStep.gz + && + wigToBigWig -clip downloads/gc1000_beds/{wildcards.version}.gc5Base.wig.gz {input.sizes} downloads/gc1000_beds/{wildcards.version}.gc5Base.bw + && + wiggletools apply_paste {output.bed} meanI {input.bed} downloads/gc1000_beds/{wildcards.version}.gc5Base.bw + """) + +rule download_ucsc_map: + input: + bed = rules.make_1kb_genome_bed.output.bed + output: + bed = 'downloads/map1000_beds/map1000.{version}.bed' + params: + provider = 'ucsc', + url = lambda w: { + 'grch37': 'http://hgdownload.soe.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeMapability/wgEncodeCrgMapabilityAlign100mer.bigWig', + 'grch38': 'http://hgdownload.soe.ucsc.edu/gbdb/hg38/hoffmanMappability/k100.Umap.MultiTrackMappability.bw' + }[w.version] + conda: CONDA_ENVS['wiggletools'] + resources: + mem_mb = 8000 + shell: + op.as_one_line(""" + wget -qO downloads/map1000_beds/{wildcards.version}.map.bw {params.url} + && + wiggletools apply_paste {output.bed} meanI {input.bed} downloads/map1000_beds/{wildcards.version}.map.bw + """) + + +rule download_par_bed: + output: + bed = 'downloads/par_region/PAR.{version}.bed' + params: + provider = 'ucsc' + run: + file = open(output.bed, 'w') + par_region = [] + if wildcards.version == 'grch37': + par_region.append(['chrX','60001','2699520']) + par_region.append(['chrX','154931044','155260560']) + par_region.append(['chrY','10001','2649520']) + par_region.append(['chrY','59034050','59363566']) + elif wildcards.version == 'grch38': + par_region.append(['chrX','10000','2781479']) + par_region.append(['chrX','155701382','156030895']) + par_region.append(['chrY','10000','2781479']) + par_region.append(['chrY','56887902','57217415']) + with open(output.bed, 'w') as f: + for i in par_region: + f.write('\t'.join(i) + '\n') + + ##### FUNCTIONS ##### diff --git a/workflows/reference_files/2.4/src/jabba/make_germline_filter.R b/workflows/reference_files/2.4/src/jabba/make_germline_filter.R new file mode 100644 index 00000000..ca183488 --- /dev/null +++ b/workflows/reference_files/2.4/src/jabba/make_germline_filter.R @@ -0,0 +1,37 @@ +#!/usr/bin/env Rscript + +args <- commandArgs(trailingOnly = TRUE) + +nrml.tbl.path <- args[1] +drcln.dir <- args[2] +outdir <- args[3] +signal.thresh <- args[4] +pct.thresh <- args[5] +cores <- args[6] + +library(dryclean) +library(parallel) + +drcln.dir.abs <- normalizePath(drcln.dir) +drcln.rds <- Sys.glob(file.path(drcln.dir.abs, "*.rds")) +drcln.smp <- gsub('.drycleaned.cov.rds', '', basename(drcln.rds)) + +drcln.tbl <- data.table( + sample = drcln.smp, + decomposed_cov = drcln.rds +) + +nrml.tbl <- readRDS(nrml.tbl.path) +nrml.tbl <- nrml.tbl[drcln.tbl,,on = 'sample'] + +saveRDS(nrml.tbl, file.path(dirname(outdir), 'normal_table.rds')) + +grm = identify_germline( + normal.table.path = file.path(dirname(outdir), 'normal_table.rds'), + path.to.save = dirname(outdir), + signal.thresh = signal.thresh, + pct.thresh = pct.thresh, + save.grm = TRUE, + num.cores = cores +) + diff --git a/workflows/reference_files/2.4/src/jabba/make_pon.R b/workflows/reference_files/2.4/src/jabba/make_pon.R new file mode 100644 index 00000000..a5006bdc --- /dev/null +++ b/workflows/reference_files/2.4/src/jabba/make_pon.R @@ -0,0 +1,69 @@ +#! /usr/bin/env Rscript + +args <- commandArgs(trailingOnly = TRUE) + +threads <- args[1] +nrml.dir <- args[2] +tbl.out <- args[3] +pon.path <- args[4] +par.path <- args[5] +build <- args[6] +choose.samples <- args[7] + +library(data.table) +library(dryclean) +library(parallel) +library(IRanges) +library(GenomicRanges) + +if (!choose.samples %in% c('rand', 'all', 'cluster')){ + stop('Argument 7 must be one of "rand", "all", or "cluster"') +} + +nrml.dir.abs <- normalizePath(nrml.dir) +nrml.rds <- Sys.glob(file.path(nrml.dir.abs, "*.rds")) +nrml.smp <- gsub('.cov.rds', '', basename(nrml.rds)) + +nrml.tbl <- data.table( + sample = nrml.smp, + normal_cov = nrml.rds +) + +saveRDS(nrml.tbl, tbl.out) + +if (choose.samples == 'all') { + detergent = prepare_detergent( + normal.table.path = tbl.out, + path.to.save = dirname(pon.path), + num.cores = threads, + build = build, + PAR.file = par.path, + save.pon = TRUE, + use.all = TRUE + ) +} else if (choose.samples == 'rand') { + detergent = prepare_detergent( + normal.table.path = tbl.out, + path.to.save = dirname(pon.path), + num.cores = threads, + build = build, + PAR.file = par.path, + save.pon = TRUE, + use.all = FALSE, + choose.randomly = TRUE + ) +} else if (choose.samples == 'cluster') { + detergent = prepare_detergent( + normal.table.path = tbl.out, + path.to.save = dirname(pon.path), + num.cores = threads, + build = build, + PAR.file = par.path, + save.pon = TRUE, + number.of.samples = min(100,length(nrml.smp)), + use.all = FALSE, + choose.by.clustering = TRUE + ) +} + +