#######################
# parameter file format
#######################
#
# The FIRST non-commmented line should include the following TAB delimited key-value parameter pairs:
# key-value pairs:
# min_seq_length, max_seq_length -> length range of regions
# region_max_score               -> region score threshold (discard peaks with higher score)
# region_min_score		 -> set to -10000 (not used in current implementation)
# sample_space                   -> ensemble_<number of top regions to be considered>
# twobit_annotation_file         -> '2bit' file containing the genome sequence in compressed form
# species		         -> 'human' or 'mouse'
# known_pssm_path		 -> path to the pssm files for the datasets to be pre-processed
# peaks_file_path		 -> path to the peaks files with the corresponding binding evidence scores
# comment character 		 -> #
#
# On a separate line for each input dataset specify the following parameters:
# dataset_id 		         -> user-specified id for each ChIP-seq dataset (should be part of the dataset peaks file name)
# known_consensus		 -> literature consensus for the TF (if missing, enter an arbitraty dummy placeholder IUPAC string)
#
# NOTE: if the 'ensemble' approach is used to define the space of putative regulatory regions multiple lines should specify the 
# datasets to be included in the analysis, otherwise a single line should specify the datasets to be pre-processed for cERMIT analysis.
######################
min_seq_length=100	max_seq_length=1000	sample_space=top_5000	species=human	region_max_score=10	known_pssm_path=./data/pssms/	twobit_annotation_file=/nfs/labs/ohlerlab/sata/data/sgeorg/gbdb/hg18.2bit	peaks_file_path=./data/	region_min_score=-10000		out_path=./
#dataset_id=Human_STAT1			known_consensus=TTCNNNGAA
#dataset_id=Human_CTCF			known_consensus=RCCASYAGRKGGCRS
#dataset_id=Human_FoxA1			known_consensus=TRTTKRYTY
#dataset_id=Human_GABP			known_consensus=VVMGGAAGNB
#dataset_id=Human_NRSF			known_consensus=CTSTCCNNGGTBCTGR
#dataset_id=Human_SRF			known_consensus=GMCCWWWWWWGG
dataset_id=DNase_Human_STAT1		known_consensus=TTCNNNGAA
#dataset_id=DNase_Human_CTCF		known_consensus=RCCASYAGRKGGCRS
#dataset_id=DNase_Human_FoxA1		known_consensus=TRTTKRYTY
#dataset_id=DNase_Human_GABP		known_consensus=VVMGGAAGNB
#dataset_id=DNase_Human_NRSF_Johnson	known_consensus=CTSTCCNNGGTBCTGR
#dataset_id=DNase_Human_SRF		known_consensus=GMCCWWWWWWGG