[database]
# The path of uniref databases folder.
uniref_db = /opt/metawibele_dbs/
# The path of domain databases folder. [data_path] provide the absolute path of the domain databases folder; [none] use the default domain databases installed in the metawibele package [ Default: none ]
domain_db = none

[basic]
# Study name [ Default: MGX ]
study = demo
# The prefix name for output results [ Default: metawibele ]
basename = demo 

[computation]
# The number of cores that you’re requesting [ Default: 1 ]
threads = 4
# The amount of memory (in MB) that you will be using for your job [ Default: 20000 ] 
memory = 20000
# The amount of time (in minute) that you will be using for your job [ Default: 60 ]
time = 60

[abundance]
# The method for normalization [Choices: cpm, relab]. [cpm] copies per million units (sum to 1 million); [relab] relative abundance (sum to 1) [ Default: cpm ]  
normalize = cpm
# The minimum abundance for each feature [ Default: 0 ]   
abundance_detection_level = 0

[msp]
# The absolute path of the config file used by MSPminer. [config_file] provide the mspminer config file; [none] use the default config files installed in the metawibele package. [ Default: none ]
mspminer = none
# The minimum fraction of taxonomy classified genes in each MSP [0-1]. [Default: 0.10]
tshld_classified = 0.10 
# The minimum percent differences between the most and second dominant taxon for each MSP [0-1]. [Default: 0.50] 
tshld_diff = 0.50 

[interproscan]
# Interproscan executable file, e.g. /my/path/interproscan/interproscan.sh [ Default: interproscan.sh ]
interproscan_cmmd = /usr/local/bin/interproscan-5.31-70.0/interproscan.sh
# The appls used by interproscan: [appls] comma separated list of analyses, [ Choices: CDD,COILS,Gene3D,HAMAP,MobiDBLite,PANTHER,Pfam,PIRSF,PRINTS,PROSITEPATTERNS,PROSITEPROFILES,SFLD,SMART,SUPERFAMILY,TIGRFAM,Phobius,SignalP,TMHMM ]; [all] use all analyses for running [ Default: all ]
interproscan_appl = "Pfam,SignalP,TMHMM"
# The number of splitting files which can be annotated in parallel [ Default: 1 ]
split_number = 4

[maaslin2]
# Maaslin2 executable file, e.g. /my/path/Maaslin2/R/Maaslin2.R, [ Default: Maaslin2.R ]
maaslin2_cmmd = Maaslin2.R
# The minimum abundance for each feature [ Default: 0 ]  
min_abundance = 0 
# The minimum percent of samples for which a feature is detected at minimum abundance [ Default: 0.1 ]
min_prevalence = 0.1  
# Keep features with variance greater than [Default: 0.0]
min_variance = 0
# The q-value threshold for significance [ Default: 0.25 ]
max_significance = 0.25
# The normalization method to apply [ Choices: TSS, CLR, CSS, NONE, TMM ], [ Default: TSS ]
normalization = NONE
# The transform to apply [ Choices: LOG, LOGIT, AST, NONE ],  [ Default: LOG ]
transform = LOG
# The analysis method to apply [ Choices: LM, CPLM, ZICP, NEGBIN, ZINB ], [ Default: LM ]
analysis_method = LM
# The fixed effects for the model, comma-delimited for multiple effects [ Default: all ]
fixed_effects = diagnosis,consent_age,antibiotic,immunosuppressant,mesalamine,steroids
# The random effects for the model, comma-delimited for multiple effects [ Default: none ]
random_effects = none
# The correction method for computing the q-value [ Default: BH ]
correction = BH
# Apply z-score so continuous metadata are on the same scale [ Default: TRUE ] apply z-score so continuous metadata are on the same scale [ Default: TRUE ]
standardize = TRUE
# Generate a heatmap for the significant associations [ Default: FALSE ]
plot_heatmap = FALSE
# In heatmap, plot top N features with significant associations [ Default: FALSE ]
heatmap_first_n = FALSE
# Generate scatter plots for the significant associations [ Default: FALSE ]
plot_scatter = FALSE
# The number of R processes to run in parallel [ Default: 1 ]
maaslin2_cores = 4
# The factor to use as a reference for a variable with more than two levels provided as a string of 'variable,reference' semi-colon delimited for multiple variables [ Default: NA ] NOTE: A space between the variable and reference will not error but will cause an inaccurate result.
reference = diagnosis,nonIBD
# The minimum percent of case-control samples used for comparison in which a feature is detected [ Default: 0.1 ]
tshld_prevalence = 0.10
# The q-value threshold for significance used as DA annotations [ Default: 0.05 ]
tshld_qvalue = 0.05
# The statistic used as effect size [ Choices: coef, mean(log) ]. [coef] represents the coefficient from the model; [mean(log)] represents the difference of mean values between case and control conditions. [  Default: mean(log) ]
effect_size = mean(log)
# The main phenotype metadata used for prioritization, e.g. metadata1. [ Default: none ]: skip the association with environmental/phenotypic parameters
phenotype = diagnosis