[General]
# Required: Specify the three letter abbreviation of the species your samples
# are taken from.  For example, mouse is 'mmu', zebrafish is 'dre'.
species: mmu

# The file containing the list of samples files.
# samples_filelist: samples_filelist

# The maximum number of threads (processors) to use for various operations.
# max_threads: 4

# The maximum amount of memory (in GB) to allocate to the aligner.
# If left unset, Prost will allocate 85% of your system memory.
# max_memory: 128

# The prefix to use for Prost! output filenames.
# output_file_prefix: prost_output

# The minimum number times a sequence must appear as a read in the samples
# datasets in order to be included.
# min_seq_count: 30

# A sequence must have at least min_seq_length basepairs in order to be
# included by Prost!
# min_seq_length: 14

# A sequence must have at most max_seq_length basepairs in order to be
# included by Prost!
# max_seq_length: 28

# The maximum genetic wiggle.
# wiggle: 5

# The maximum number of genomic locations to report per sequence (if exceeded,
# it is simply reported as TML (too many locations).
# max_locations_to_report: 20

# The maximum number of genomic locations allowed per sequence.  If exceeded
# for a given sequence, only the number of genomic locations is preserved,
# while the actual locations are erased, and the sequence is not binned (i.e.
# it is only included in the isomiRs or no_genomic_hits tab).  Reported as
# "MLAE" (maximum locations allowed exceeded).  This may help reduce Prost!
# memory consumption in some data sets. Note that any sequence marked as
# MLAE will *not* be included when calculating normalization in the
# by_genomic_location tab.
# max_locations_allowed: 2000000000

# Skip all sequence alignments.
# skip_sequence_alignments: no

# Skip the genome sequence alignment.
# skip_genome_alignment: no

# Skip the annotation sequence alignments.
# skip_annotation_alignments: no

# If the mature miR annotation file is given, then an extra column
# "MainSeqMatchesAnnotationFile" is added to the compressed_by_annotation tab
# in the Prost! output.  For a given AnnotationBin:
#   a) if the Bin has multiple in-species mature miR annotations, then the
#      column is marked "Multiple"
#   b) if the Bin's MainSequence exactly matches the annotation file's
#      annotated sequence, then the column is marked "Yes".
#   c) if the Bin's MainSequence does not exactly match the annotation file's
#      annotated sequence, then the column is marked "No".
# This column helps users assess the quality of the annotation file used.
# NOTE: This field will not be optional in the future.  This should be
# set to be the same as the "db" field in the [AnnotationAlignment1] section.
# mature_mir_annotation_fasta: /some/path/to/mature_miR.annotation.fa


# Note: This alignment exists for documentation purposes only.  It describes
# how to configure the several [*Alignments] below.
# ---
# [GenericAlignment]
# name: A human readable name for this alignment.
# tool: (bbmap|bbmapskimmer)
# db: Path to the aligner's reference.
# max_3p_mismatches: Maximum number of mismatches on the 3p end.
# max_non_3p_mismatches: Maximum number of mismatches on the 5p end and the
#   core of the alignment.  Effectively, this determines the maximum
#   designation of any sequence/bin in all Prost! output.
# allow_indels: (yes|no)
# type: Applicable only for AnnotationAlignments.
#   (MirbaseMirAnnotation|MirbaseHairpinAnnotation|BiomartOtherRNAAnnotation)
# indelnt_penalty_multiplier: Inserted/deleted nucleotides penalty multiplier (X).
#       Multiply the number of inserted or deleted nucleotides by X and add to
#       the number of non-3-prime mismatches in the alignment (Y); if Y is
#       greater than max_non_3p_mismatches, the hit will be rejected. 


# For the genome alignment, we recommend keeping the number of non-3-prime
# mismatches to '2' (i.e. 5-prime mismatches and "core" mismatches).
# Required.
[GenomeAlignment]
name: genome
tool: bbmap
db: /some/path/to/Mus_musculus.genome.db
max_3p_mismatches: 3
max_non_3p_mismatches: 2
allow_indels: no
indelnt_penalty_multiplier: 3

# Required.
[AnnotationAlignment1]
type: MirbaseMirAnnotation
name: matures
tool: bbmap
db: /some/path/to/mature_miR.annotation.fasta
max_3p_mismatches: 0
max_non_3p_mismatches: 0
allow_indels: no

# Required.
[AnnotationAlignment2]
type: MirbaseHairpinAnnotation
name: hairpins
tool: bbmap
db: /some/path/to/hairpin.annotation.fasta
max_3p_mismatches: 0
max_non_3p_mismatches: 0
allow_indels: no

# Required. 
# If you wish, you can use the fake BioMart file found here:
# https://raw.githubusercontent.com/uoregon-postlethwait/prost/master/fake_biomart_file.fa
[AnnotationAlignment3]
type: BiomartOtherRNAAnnotation
name: other
tool: bbmap
db: /some/path/to/otherRNAs.annotation.fasta
max_3p_mismatches: 0
max_non_3p_mismatches: 0
allow_indels: no