example_complete.yaml

# Output and working directory (all other directories below, if not absolute, are relative to this one)
workdir: "/home/user/folder/results/" 

# Database output directory (Tip: create this folder in a common directory so it could be used for other runs as well as other users)
dbdir: "/home/user/folder/databases/"

# Samples (name and files)
samples:
  sample_name_1:
    fq1: "/home/user/folder/reads/file.1.fq.gz"
    fq2: "/home/user/folder/reads/file.2.fq.gz"
  sample_name_2:
    fq1: "/home/user/folder/reads/single.fq.gz"

# Tools ("p" -> profiling, "b" -> binning)
tools:
    clark: b
    dudes: p
    gottcha: p
    kaiju: b
    kraken: b
    motus: p

# Databases ("archaea_bacteria_201503" is the default.)
databases:
  - archaea_bacteria_201503
  - custom_database

# Path for reference sequences to build the "custom_database"
custom_database:
    clark: "/path/reference/sequences/fna/"
    dudes: "/path/reference/sequences/fna/"
    kaiju: "/path/reference/sequences/gbff/"
    kraken: "/path/reference/sequences/fna_gi/"

### MetaMeta Pipeline ### 
# Number of threads for each tool (distributed among the number of cores defined by main parameter --cores). Default: 1
threads: 1
# Gzipped input files (0: not gzipped / 1: gzipped). Default: 0
gzipped: 0
# Keep intermediate files (database, reads and output) (0: do not keep files / 1: keep all files). Default: 0
keepfiles: 0

### Trimming ### 
# Trimmomatic (0: off / 1: on). Default: 0
trimming: 0
# Trimmomatic parameter desiredminlen (minimun desired length). Default: 70
desiredminlen: 70
# Trimmomatic parameter strictness (range from 0-1 -> 0: not strict / 1: very scrict). Default: 0.8
strictness: 0.8

### Error correction ###
# BayesHammer (0: off / 1: on). Default: 0
errorcorr: 0

### Sub-sampling ###
# Sub-sampling (0: off / 1: on). Default: 0
subsample: 0
# Sub-sampe size (Integer: specific read number / Float: percentage of reads / 1: equally divide the whole set among the tools). Default: 1
samplesize: 1
# Sub-sample with replacement (0: without replacement / 1: with replacement). Default: 0
replacement: 0

### MetaMetaMerge ###
# MetaMetaMerge mode (precise, very-precise, linear, sensitive, very-sensitive). Default: linear
mode: linear
# MetaMetaMerge minimum abundance or Maximum results for each taxonomic level (0: off / 0-1: minimum relative abundance / >=1: maximum number of identifications). Default: 0.0001
cutoff: 0.0001
# MetaMetaMerge number of bins. Default: 4
bins: 4
# MetaMetaMerge ranks option. Generates the merged output based only on specified ranks and estimate upper levels. Default: species
ranks: species
# MetaMetaMerge detailed output. Generates detailed output for each taxon/tool and its normalized relative abundance estimation. It outputs 0 for tools which did not identified the taxon and -1 for tools without a taxon in the database. (0: off / 1: on). Default: 0
detailed: 0
# MetaMetaMerge verbose log output. (0: off / 1: on). Default: 0
verbose: 0

# Alternative path for the tools (uses it instead of the default path)
tool_alt_path:
    clark: ""
    dudes: ""
    gottcha: ""
    kaiju: ""
    kraken: ""
    motus: ""
    trimmomatic: ""
    spades: ""
    bowtie2: ""
    krona: ""
    metametamerge: ""