config_simulate.yml

### GLOBAL VARS ###
rules_to_run: 'all_simulated' 
# one of the following: 'all_rw', 'all_simulated', 'preprocess', 'simulate', 'data_integration', 'evaluation', 'visualization'

data_source: 'MIDASim'
# it has to be 'microbiomeHD', 'CMD', or 'MIDASim'

sim_output_root: './trial_simulation'

### SIMULATION PHASE ###
# or_l: [1, 1.25, 1.5]
# cond_effect_val_l: [0, 0.25, 0.5, 0.75, 1]
# batch_effect_val_l: [0, 0.25, 0.5, 0.75, 1]
or_l: [1.25]
cond_effect_val_l: [0.5]
batch_effect_val_l: [0.5]
iter: 1

# list of covariates to be used in the final stage of data cleaning/complete confounding calculations + data saving
# in our case, only ['disease', 'gender', 'age_category'] for CMD/IBD datasets are used, otherwise all empty

### BENCHMARK PHASE ###
# used_R_methods_count: ["combat_seq", "limma", "MMUPHin", 'ConQuR', 'ConQuR_libsize']
used_R_methods_count: ["combat_seq", "limma", "MMUPHin"]
# used_R_methods_relab: ["combat", "limma", "MMUPHin", 'ConQuR_rel']
used_R_methods_relab: ["combat", "limma", "MMUPHin"]
used_Python_methods: ['harmony', "percentile_norm"]


### EVALUATION PHASE ###
binarizing_agent: 'cond_1' # for two microbiomeHD datasets or 'IBD' for ibd or 'adenoma' for the CRC dataset