# Directory where you have decompressed your dataset
dataset_dir                                 = /share/data4/amcpherson/fusions/release/datasetnew
dataset_prefix                              = (dataset_dir)/Homo_sapiens.NCBI36.54

# Local directory acessible by individual cluster jobs
cluster_dir                                 = /localdata/fusions_reference
cluster_prefix                              = (cluster_dir)/Homo_sapiens.NCBI36.54

# Dataset files
gene_models                                 = (dataset_prefix).gtf
genome_fasta                                = (dataset_prefix).dna.fa
intron_regions                              = (dataset_prefix).intron.regions
intronic_fasta                              = (dataset_prefix).intronic.fa
exons_fasta                                 = (dataset_prefix).exons.fa
cds_fasta                                   = (dataset_prefix).cds.fa
utr5p_fasta                                 = (dataset_prefix).utr5p.fa
utr3p_fasta                                 = (dataset_prefix).utr3p.fa
cdna_regions                                = (dataset_prefix).cdna.regions
cdna_fasta                                  = (dataset_prefix).cdna.fa
cdna_ext_fasta                              = (dataset_prefix).cdna.ext.fa
cdna_ext_regions                            = (dataset_prefix).cdna.ext.regions
gene_regions                                = (dataset_prefix).gene.regions
gene_fasta                                  = (dataset_prefix).gene.fa
cdna_gene_fasta                             = (dataset_prefix).cdna.gene.fa
cdna_gene_regions                           = (dataset_prefix).cdna.gene.regions
tss_regions                                 = (dataset_prefix).gene.tss.regions
tts_regions                                 = (dataset_prefix).gene.tts.regions
upstream_fasta                              = (dataset_prefix).upstream.fa
downstream_fasta                            = (dataset_prefix).downstream.fa
rrna_fasta                                  = (dataset_prefix).rrna.fa
ig_gene_list                                = (dataset_prefix).ig.gene.list
gene_info_list                              = (dataset_prefix).gene.info.list
gene_adj_list                               = (dataset_prefix).gene.adj.list
gene_tran_list                              = (dataset_prefix).genetran.list
est_fasta                                   = (dataset_dir)/Homo_sapiens.NCBI.est.fa
est_alignments                              = (dataset_dir)/Homo_sapiens.NCBI36.est.alignments.psl

# Fasta files with bowtie indices, accessible by individual alignment jobs, possibly locally stored on cluster nodes
#  If you wish to have files local to a cluster's execution nodes, these can be different than the 
#  non-cluster equivalents, otherwise they could be set the same as cdna_fasta and cdna_gene_fasta
cdna_fasta_cluster                          = (cluster_prefix).cdna.fa
cdna_gene_fasta_cluster                     = (cluster_prefix).cdna.gene.fa

# Fasta files with bowtie indices for prefiltering reads for concordantly mapping pairs
#  Accessed only by individual jobs, thus these files could be put in the local directory 
#  of each cluster node if a cluster is being used. 
prefilter1                                  = (cluster_dir)/Homo_sapiens.NCBI36.54.dna.fa
prefilter2                                  = (cluster_dir)/Hs.seq.uniq

# Paths to executables and scripts
bowtie_bin                                  = /share/data/apps/bowtie-0.10.0/bowtie
bowtie_threads                              = 1
samtools_bin                                = /home/amcpherson/install/bin/samtools
findfusions_directory                       = /share/data4/amcpherson/fusions/findfusions
estislands_directory                        = /share/data4/amcpherson/fusions/estislands
scripts_directory                           = /share/data4/amcpherson/fusions/scripts

# Parameters for building the dataset
gene_sources                                = IG_C_gene,IG_D_gene,IG_J_gene,IG_V_gene,processed_transcript,protein_coding
chromosomes                                 = 1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X,Y
ig_gene_sources                             = IG_C_gene,IG_D_gene,IG_J_gene,IG_V_gene
rrna_gene_sources                           = Mt_rRNA,rRNA,rRNA_pseudogene
utr_extend                                  = 2000
cdna_utr_extend                             = 500
rrna_extend                                 = 100

# Max insert size considered by bowtie
max_insert_size                             = 500

# Filtering parameters
span_count_threshold                        = 5
split_count_threshold                       = 3
split_pos_pvalue_threshold                  = 0.01
split_min_pvalue_threshold                  = 0.01
span_length_pvalue_threshold                = 0.01
percent_identity_threshold                  = 0.90
max_dist_pos                                = 600
num_dist_genes                              = 500
split_min_anchor                            = 4
min_discordant_ratio                        = 0.5

# Position density when calculating covariance
covariance_sampling_density                 = 0.01

# Number of reads for each job in split
reads_per_job                               = 1000000

# Command for running a list of jobs in parallel
#  They system will append to the end of this command the name of a file containing
#  a list of job commands to be executed in parallel, then run that command. Provided
#  are run_cluster for running the commands on a cluster and run_multicore for running the
#  commands multithreaded.  Alternately, you could use simply use bash to execute in serial
batch_run_cmd                               = (scripts_directory)/run_cluster.pl -s rocks1 -q "-q fusions.q -l mem_free=3G" -b

# If you have command line 'mail' and wish to be notified
mailto                                      = andrew.mcpherson@gmail.com

