config.yaml

# ------ Resssources ------ 
threads : 8 # single task nb threads
task_memory: 200 # nb of Go of Ram you expect bedtool and rpsblast to take
Percent_memory: 0.5 # maximum quantity of memory the snakemake can take
# ------ Output folder ------
execution_directory: ~/path/to/output/folder/ # path to output folder,   
# ------ Path to data folder ------ 
# - all samples are required to be stored in independant folders, the folder name will later define sample names in profiles.
# - only paired reads
# - there must be a unique R1 file and R2 file
# - "R1" and "R2" must be in the filenames
# -  only following extensions : .fq, .fq.gz, .fastq, .fastq.gz, .fa, .fa.gz, .fasta, .fasta.gz 
data: ~/path/to/data/folder/ # path to data folder,   
# ------ Samples preprocessing ------
filtering: /path/to/fasta.file # database for read filtering prior to pipeline
# ------ Assembly parameters ------
assembly: 
  parameters: --k-min 29 # additional parameters to be passed to megahit 
  per_sample: [folder_name|sample*] # a subfolder name where the anlysis is done | a regular expression to select which samples to runs  
  groups: # will create 3 directories PerAD/AD7/AD7_1_11, PerAD/AD1, AD2 :
      PerAD/AD7/AD7_1_11:  
        ['AD7_W@(?([0-9])|1[0-1])?(_Repeat?)'] # you can put here any regular expression that ls can support. Here, it will mach with AD7_W1 to AD7_W11 ending or not with repeat 
      PerAD/AD1:  
        ["*"] 
      AD2:
        ["sample1"]
# ------ Binning parameters------ 
binning :
  concoct :
    contig_size : 1000 # min contig size considered
  metabat2 :
    contig_size : 1500 # min contig size considered
# ------ Annotation parameters ------ 
annotation: # support only diamond for now
  diamond :
    CARD:
      db: [/mnt/gpfs/seb/Database/CARD/CARD_DB_0.9.24.dmnd]
      # Annotation is a tsv file, 1st column is gene name, 2nd is new name (ex KO,COG), all others are optional/additional info (function, definition, pathway...)
      annotation: [/mnt/gpfs/seb/Database/Kihyun_Lee_Databases/CARD_Annotation_V2.tsv] 
      # min_Bitscore , max_Evalue , min_Pid , min_subject_pid , min_coverage , min_Query_coverage
      filter: [0,1e-5,0.8,0,0.2,0.8]
    IntI:
      db: [/mnt/gpfs/seb/Database/Kihyun_Lee_Databases/IntI.db.dmnd]
      # Annotation can be none, in this case, only gene name appears    
      annotation: [none] 
      # min_Bitscore , max_Evalue , min_Pid , min_subject_pid , min_coverage , min_Query_coverage
      filter: [0,1e-5,0.8,0,0.2,0.8]
      color: "#ff0000" # orf graph
  cat_db: /mnt/gpfs/seb/Database/NR_Cat
  checkm: /mnt/gpfs/seb/Database/CheckM
  ip_db: /mnt/gpfs/seb/Database/ip
  kraken_db: /mnt/gpfs/seb/Database/Kraken_Standard
  kofamscan: 
    profiles: /mnt/gpfs/seb/Database/KEGG/kofamscan/ko_hmm.hmm
    ko_list: /mnt/gpfs/seb/Database/KEGG/kofamscan/ko_list