# Configuration file for genomicode library.

# The format of this file is relatively straighforward.  It is
# (usually) read with the python ConfigParser parser, so please see
# its documentation for a more precise specification.
# https://docs.python.org/2/library/configparser.html
# 
# Unfortunately, variable interpolation and continuations are not
# supported here.

# Most of the options here are to help the library find programs on
# the system.  Other types of options are documented.  Some options
# are labeled as "experimental" and can be ignored.



[GENERAL APPLICATIONS]

# Should point to a Python 2.7+ "python" binary.  Not compatible with
# Python 3.
python=/usr/local/bin/python
matlab=/usr/local/bin/matlab
povray=/usr/local/bin/povray
Rscript=/usr/local/bin/Rscript


[BIOINFORMATICS SOFTWARE]

primer3=/usr/local/bin/primer3_core
patser=/usr/local/bin/patser-v3b
# Cluster 3.0.
cluster=/usr/local/bin/cluster
# "blat"
blat=/usr/local/bin/x86_64/blat


[SIGNATURE]

# bfrm binary.  You can download bfrm from:
#   https://www2.stat.duke.edu/research/software/west/bfrm/
bfrm=/data/genomidata/bfrm64

binreg20_path=/data/genomidata/SIGNATURE/BinReg2.0
bfrm_normalize_path=/data/genomidata/SIGNATURE/BFRM_normalize
bfrm_project_path=/data/genomidata/SIGNATURE/BFRM_project
selap_path=/data/genomidata/SIGNATURE/SELAPver3

# Path to the directory that contains DWD files.  e.g.
# <BatchAdjust>/
#   ReadMe.txt
#   SubRoutines/
#   BatchAdjustSM.m
#   basm1.m
#   [...]
# You can download DWD/BatchAdjust from:
#   http://marron.web.unc.edu/sample-page/marrons-matlab-software/
BatchAdjust=/data/genomidata/SIGNATURE/BatchAdjust


# This path contains gene expression signatures.  To download this:
# 1.  Go to http://www.bioinformatics.org/signature/
# 2.  Download the "SIGDB_111025.tgz" file.
#     Ignore SIGNATURE_111025.tgz.  It is redundant with this distribution.
# 3.  Uncompress the file.
# 4.  <sigdb_path> should point to:
#     SIGDB_111025/sigdb/
sigdb_path=/data/genomidata/SIGDB/sigdb



[CHANG LAB]

# By default, these scripts are installed in:
#   <python>/site-packages/genomicode/bin/
# The R libraries are installed in:
#   <python>/site-packages/genomicode/Rlib/

# Matrix manipulation.
slice_matrix=/home/xchen/chencode/scripts/slice_matrix.py
annotate_matrix=/home/xchen/chencode/scripts/annotate_matrix.py
align_matrices=/Volumes/Users/jchang/changlab/scripts/align_matrices.py

# Gene expression analysis.
preprocess=/home/jchang/changlab/scripts/preprocess.py
bfrmnorm=/home/xchen/chencode/scripts/bfrmnorm.py
combatnorm=/home/xchen/chencode/scripts/combatnorm.py
analyze_clinical=/home/xchen/chencode/scripts/analyze_clinical_outcome.py
find_diffexp_genes=/home/xchen/chencode/scripts/find_diffexp_genes.py
analyze_phenotype=/home/xchen/chencode/scripts/analyze_phenotype.py

# Pathway analysis.
pybinreg=/home/jchang/changlab/scripts/pybinreg.py
scoresig=/home/xchen/chencode/scripts/scoresig.py
score_geneset=/home/xchen/chencode/scripts/score_geneset.py
gsea=/home/xchen/chencode/scripts/gsea.py

# Interfaces to other programs.
pyrseqc=/home/jchang/bin/pyrseqc.py
pypeakseq=/home/jchang/bin/pypeakseq.py
pyspp=/home/jchang/bin/pyspp.py

# Miscellaneous utilities.
xls2txt=/home/jchang/changlab/scripts/xls2txt
txt2xls=/home/jchang/changlab/scripts/txt2xls
genepattern=/home/xchen/chencode/scripts/run_genepattern.py
arrayplot=/home/jchang/changlab/scripts/arrayplot2.py

# TCGA.
download_tcga=/home/xchen/chencode/scripts/download_tcga.py

# R libraries.
# Path to "Rlib" that is part of this package.
changlab_Rlib=/home/xchen/chencode/Rlib
# <Rlib>/ComBat.R
combat=/Volumes/Users/jchang/changlab/Rlib/ComBat.R


[NGS SOFTWARE]

# Miscellaneous utilities.
samtools=/usr/local/bin/samtools
bcftools=/usr/local/bin/bcftools
vcfutils=/usr/local/bin/vcfutils.pl
vcftools=/usr/local/bin/vcftools
bgzip=/usr/local/bin/bgzip
tabix=/usr/local/bin/tabix
bedtools=/usr/local/bin/bedtools
gtfutils=/usr/local/bin/gtfutils
bam2fastx=/usr/local/bin/bam2fastx


[GATK and Picard]

# Path to the "GenomeAnalysisTK.jar" file.
gatk_jar=/usr/local/bin/GATK/GenomeAnalysisTK.jar

# Path to the directory that contains the picard files.  e.g.
# <picard>/
#   picard.jar
#   picard-lib.jar
#   [...]
picard=/usr/local/picard-tools-1.129


[NGS Alignment]

bowtie_build=/usr/local/bin/bowtie-build
bowtie=/usr/local/bin/bowtie
bowtie2_build=/usr/local/bin/bowtie2-build
bowtie2=/usr/local/bin/bowtie2
bwa=/usr/local/bin/bwa

# Path to the "trimmomatic.jar" file.
trimmomatic_jar=/usr/local/bin/trimmomatic.jar

# Path to the "fastqc" Perl script.
fastqc=/usr/local/FastQC/fastqc


[RNA-SEQ]

tophat=/usr/local/bin/tophat
rsem_prepare=/usr/local/rsem/rsem-prepare-reference
rsem_calculate=/usr/local/rsem/rsem-calculate-expression
STAR=/usr/local/bin/STAR
htseq_count=/usr/bin/htseq-count

# Path to the jar file for RNA-SeQC, e.g. "RNA-SeQC_v1.1.8.jar".
rna_seqc_jar=/usr/local/bin/RNA-SeQC_v1.1.8.jar

# Experimental.  Please ignore.
rseqc_path=/usr/bin
rseqc_hg19=/data/genomidata/rseqc_hg19



[NGS Variant Calling]

platypus=/usr/local/bin/Platypus/Platypus.py
somaticsniper=/usr/local/bin/bam-somaticsniper
muse=/usr/local/bin/MuSE

# Path to the jar file for mutect, e.g. "mutect-1.1.7.jar".
mutect_jar=/usr/local/bin/mutect-1.1.7.jar
# MuTect only works with specific java versions.  Set the java that is
# compatible with the version of MuTect used.
mutect_java=/usr/bin/java

# Path to the jar file for VarScan.
varscan_jar=/usr/local/bin/VarScan.jar

# Path to the directory that contains the mutationSeq files.  e.g.
# <museq>/
#   classify.py
#   model_v4.1.2.npz
#   metadata.config
#   [...]
museq=/usr/local/museq_4.3.6

# Path to the directory that contains the Radia files.  e.g.
# <radia>/
#   scripts/
#     radia.py
#     filterRadia.py
#     mergeChroms.py
#   data/
#     hg19/
#       snp135/
#       cosmic/
#   [...]
radia_path=/usr/local/radia

# Path to the directory that contains the snpEff files.  e.g.
# <snp_eff_path>/
#   snpEff.jar
#   [...]
snp_eff_path=/usr/local/snpEff


# Path to the directory that contains the strelka files.  e.g.
# <strelka>/
#   bin/configureStrelkaWorkflow.pl
#   etc/strelka_config_bwa_default.ini
#   [...]
strelka=/usr/local/strelka_workflow


table_annovar=/usr/local/bin/table_annovar.pl
# ANNOVAR requires database files downloaded with
# annotate_variation.pl.  This should point to the directory where the
# files are downloaded.  e.g. downloaded with:
#   annotate_variation.pl -buildver hg19 -downdb cytoBand <annovar_db>
annovar_db=/data/genomidata/humandb


[NGS ChIP-Seq]

macs14=/usr/bin/macs14
macs2=/usr/bin/macs2
peakseq=/usr/local/bin/PeakSeq

# Path to the directory that contains the homer files.  e.g.
# <homer_path>/
#   README.txt
#   bin/homer
#   [...]
homer_path=/usr/local/bin/homer


[GENOME SEQUENCE DATA]

# Experimental.  Can ignore these.
# Used for fast access to genome sequence.
RA_CHROM_HG18=/data/genomidata/ra_chrom_hg18
RA_CHROM_HG19=/data/genomidata/ra_chrom_hg19
RA_CHROM_MM10=/data/genomidata/ra_chrom_mm10
knowngene_hg18=/data/genomidata/hg18.knownGene.110312.txt
knowngene_hg19=/data/genomidata/hg19.knownGene.130104.txt
knowngene_mm10=/data/genomidata/mm10.knownGene.130207.txt


[MICROARRAY DATA]

# Experimental.  Please ignore.
annot_data_affy=/data/genomidata/affymetrix/annotation
annot_data_illu=/data/genomidata/illumina/annotation
psid2platform=/data/genomidata/psid2platform
convert_platform=/data/genomidata/convert_platform
HumanHT_12_to_HG_u133_Plus_2=/home/changlab/data/mapping/HumanHT-12_to_HG-U133_Plus_2.txt
illumina_HUMANHT12_CONTROL=/data/genomidata/illumina/HumanHT-12.control.txt



[TRANSCRIPTION FACTOR DATA]

# Experimental.  Please ignore.
patser_alphabet=/data/genomidata/alphabet.prom_500_100
JASPAR_DB=/data/genomidata/JASPAR_CORE_2008
TRANSFAC_DB=/data/genomidata/transfac.12_1.pfm
JASPAR_info=/data/genomidata/jasparid2info
TRANSFAC_info=/data/genomidata/matid2info
matid2length=/data/genomidata/matid2length


[GENE PATTERN]

# Some modules rely on GenePattern.  Please create an account on the
# Gene Pattern server below, and configure the username and password
# here.
gp_server=http://genepattern.broadinstitute.org/gp/pages/index.jsf
gp_user=
gp_passwd=


[GENE MAP]

# Experimental.  Please ignore.
gm_user=genemap
gm_passwd=g33m4p
gm_db=genemap
gm_host=localhost
gm_port=3306


[TCGA]

# Experimental.  Please ignore.
cghubkey=/data/biocore/cghub.key
