INSPIIRED.yml

#    This source code file is a component of the large INSPIIRED genomic analysis software package.
#    Copyright (C) 2016 Frederic Bushman
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation, either version 3 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    You should have received a copy of the GNU General Public License
#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
#
# Log file path.
# This file will be written to the analysis directory.
logFile : intSiteCaller.log

# Database configuration.
# If the database parameter is set to 'sqlite' then the provided sqliteIntSitesDB and sqliteSampleManagement databases will be used.
# If the parameter is set to 'mysql' the [mysqlConnectionGroup] connection credentials defined in your ~/.my.cnf file will be used.  
dataBase : sqlite
sqliteIntSitesDB : ~/INSPIIRED/databases/SQLite/intSites.db
sqliteSampleManagement : ~/INSPIIRED/databases/SQLite/specimenManagement.db
mysqlConnectionGroup :  intsites_miseq.read
mysqlSpecimenManagementGroup : specimen_management

# The parallelize parameter instructs INSPIRRED how to distribute jobs over the available processors.
# Allowed values are: no, qsub, bsub
# If 'no' is selected then all jobs will be ran serially. 
# If using qsub on a single, multi-core machine, then set the forceQsubPath to 'Yes'.
parallelize : qsub
forceQsubPath : Yes

# Debuging
# If this parameter is set to Yes than a number of intermediate temp files will be retained. 
debug : No

# Run id
# This id is used to distinguish the sequencing run from other previous runs.
runId : demoRun

# Maximum size for each sequence file chunk
chunkSize : 30000

# Epigenetic heat map data source
epigeneticDataDirectory : ~/INSPIIRED/components/EpigeneticHeatmapMaker/Epigenetic

# Heatmap ROC parameters
rocControls : unmatched

# Log in to system hosting vector and sequencing data files
remoteUser : everett@microb120.med.upenn.edu

# Directory that holds the vector information file defiled in the vectorSeq column of the provided sampleInfo.csv file
vectorDataPath : ~/INSPIIRED/inputs/demoDataSet

# Directory that holds the R1, R2, and I1 sequencing run gzipped FASTQ files.
# Defined paths should be absolute or relative to the analysis directory.
SequencingFiles:
  I1 :  Data/Undetermined_S0_L001_I1_001.fastq.gz
  R1 :  Data/Undetermined_S0_L001_R1_001.fastq.gz
  R2 :  Data/Undetermined_S0_L001_R2_001.fastq.gz

# Processing parameters
ProcessingParameters:
  qualityThreshold     : '?'
  badQualityBases      : 5
  qualitySlidingWindow : 10
  mingDNA              : 20
  minPctIdent          : 95
  maxAlignStart        : 5
  maxFragLength        : 2500