Wildcards_Iteration

https://snakemake.readthedocs.io/en/stable/snakefiles/rules.html#wildcards

expand

#normal
expand(["{dataset}/a.{ext}", "{dataset}/b.{ext}"], dataset=DATASETS, ext=FORMATS)
#leads to
["ds1/a.txt", "ds1/b.txt", "ds2/a.txt", "ds2/b.txt", "ds1/a.csv", "ds1/b.csv", "ds2/a.csv", "ds2/b.csv"]
#zip
expand(["{dataset}/a.{ext}", "{dataset}/b.{ext}"], zip, dataset=DATASETS, ext=FORMATS)
#leads to
["ds1/a.txt", "ds1/b.txt", "ds2/a.csv", "ds2/b.csv"]
#mask from rule all
expand("{{dataset}}/a.{ext}", ext=FORMATS)
#simplest format: multiext
rule plot:
    output:
        multiext("some/plot", ".pdf", ".svg", ".png")
##Error
###Not all output, log and benchmark files of rule bam_to_tbi_ribo contain the same wildcards. This is crucial though, in order to avoid that two or more jobs write to the same file
###解决方法多wildcards输入对更多wildcards输出的时候，要用expand把结果和mask把结果弄好，不然snakemake遍历之后会分不清你的输入所对应的输出结果是哪些。
###也要注意mask的变量是否写在后面，对输出数量的影响（循环的原理）。
rule bam_to_tbi_ribo:
  input: 
    ribo_bam = 'ribohmm/ribo_bam_tbi/{merge}_{mpsf}.bam',
    lengths = 'ribohmm/configs/{merge}_{mpsf}.txt'
  output: 
    fwd = expand('ribohmm/ribo_bam_tbi/{{merge}}_{{mpsf}}_fwd.{read_length}.gz.tbi', read_length=READ_LENGTHS),
    rev = expand('ribohmm/ribo_bam_tbi/{{merge}}_{{mpsf}}_rev.{read_length}.gz.tbi', read_length=READ_LENGTHS)
  benchmark: 'time_benchmarks/ribohmm/bam_to_tbi/RIBO_{merge}_{mpsf}.txt'
  shell:
    r''' {PYTHON3} {RIBOHMM_SRC_DIR}/bam_to_tbi.py --dtype riboseq --length {input.lengths} {input.ribo_bam}'''

Constrain wildcards

#First, a wildcard can be constrained within the file pattern, by appending a regular expression separated by a comma:
output: "{dataset,\d+}.{group}.txt"
#Second, a wildcard can be constrained within the rule via the keyword wildcard_constraints:
rule complex_conversion:
    input:
        "{dataset}/inputfile"
    output:
        "{dataset}/file.{group}.txt"
    wildcard_constraints:
        dataset="\d+"
    shell:
        "somecommand --group {wildcards.group}  < {input}  > {output}"
#global constraining wildcards
wildcard_constraints:
    dataset="\d+"
rule a:
    ...
rule b:
    ...