config.yaml

PROJECT: test2
METADATA: metadata.tsv
GROUP: ID # column in METADATA file to pool samples
PATH: PATH # column in METADATA file for rawdata path

WORKDIR:  # same directory as Snakefile if not specified

#--------------------------------
# Parameters to change in xander
#--------------------------------

### detailed instructions can be found at https://github.com/rdpstaff/Xander_assembler

### memory for bloom filter [2**(FILTER_SIZE-2)] < HEAP < MAXMEM
### memory = 2**(FILTER_SIZE-2), 38 = 64 GB, 37 = 32 GB, 36 = 16 GB
### based on experience, a bloom filter should be at least twice the size of you data in fasta

#FILTER_SIZE: 37
#MAX_JVM_HEAP: '48G' # memory for java program, must be larger than the corresponding memory of the FILTER_SIZE
FILTER_SIZE: 24 # for test only
MAX_JVM_HEAP: '400M' #for test only

#GENES="rplB rpsC amoA_AOA amoA_AOB nifH nirK nirS norB_cNor norB_qNor nosZ nosZ_a2"
GENES: 'rplB'

### THIS SECTION MUST BE MODIFIED BASED ON THE INPUT DATASETS
### De Bruijn Graph Build Parameters
K_SIZE: 45  # kmer size, should be multiple of 3 = 4 GB, increase FILTER_SIZE if the bloom filter predicted false positive rate i s greater than 1%
MIN_COUNT: 2  # minimum kmer abundance in SEQFILE to be included in the final de Bruijn graph structure
THREADS: 1 # threads for xander_findStarts


### xander dependencies
HMMALIGN: hmmalign # NO need to change if you follow tutorial on github
UCHIME: uchime # dito
XANDER_DIR: Xander_assembler #dito
JAR_DIR: RDPTools #dito

#----------------------------
# params for otu analyses
#----------------------------
DISTANCE: 0.05

#------------------------------------------------
# params to be set dynamically in Snakemake file
#------------------------------------------------
SAMPLES:
REF_DIR: