python/salus/cmplatform/makefile

   1 SAMPLEID := mbrain mkidney
   2 LANEID_Illumina := L001
   3 LANEID_Salus := L001 L002 L003 L004
   4 PLATFORMS := Illumina Salus
   5
   6 define platform_rule
   7 TAGS_$1 := $$(foreach s, $$(SAMPLEID), $1/$$(s)_S1_L001)
   8 endef
   9 $(foreach platform,$(PLATFORMS),$(eval $(call platform_rule,$(platform))))
  10 ALLTAGS := $(TAGS_Illumina) $(TAGS_Salus)
  11
  12 RAW_Salus := $(foreach a, $(SAMPLEID), $(foreach b, $(LANEID_Salus), $(foreach r,R1 R2,raw4_Salus/$(a)_S1_$(b)_$(r)_001.fastq.gz )))
  13 MERGE_Salus := $(foreach tag,$(TAGS_Salus),raw_$(tag) )
  14 MERGE_Illumina := $(foreach a, $(SAMPLEID), $(foreach r,R1 R2,raw_Illumina/$(a)_S1_L001 ))
  15 FASTP_TAGS := $(foreach tag,$(ALLTAGS),fastp_$(tag) )
  16 FQ_DIRS := $(foreach p,raw fastp sub,$(foreach pf,$(PLATFORMS),$(p)_$(pf)))
  17
  18 all:    $(MERGE_Salus) $(FASTP_TAGS) $(foreach d,$(FQ_DIRS),$(d).stats)
  19         @echo $^
  20
  21 define smp_rule
  22 raw_Salus/$1_S1_L001: $$(filter raw4_Salus/$1_S1_%,$$(RAW_Salus))
  23         mkdir -p $$(dir $$@)
  24         @cat $$(filter %_R1_001.fastq.gz,$$^) > $$@_R1_001.fastq.gz
  25         @cat $$(filter %_R2_001.fastq.gz,$$^) > $$@_R2_001.fastq.gz
  26         touch $$@
  27 .PHONY raw_Illumina/$1_S1_L001:
  28 #       touch $$@
  29 sub_Illumina/$1_S1_L001: $$(filter fastp_Illumina/$1_S1_L001,$$(FASTP_TAGS))
  30         mkdir -p $$(dir $$@)
  31         cp --reflink=auto -l $$^_R1_001.cut.gz $$@_R1_001.fastq.gz
  32         cp --reflink=auto -l $$^_R2_001.cut.gz $$@_R2_001.fastq.gz
  33         touch $$@
  34 endef
  35 $(foreach sample, $(SAMPLEID), $(eval $(call smp_rule,$(sample))))
  36
  37 define pf_smp_rule
  38 fastp_$1/$2_S1_L001: $$(filter raw_$1/$2_S1_L001,$$(MERGE_Salus) $$(MERGE_Illumina))
  39         mkdir -p $$(dir $$@)
  40         micromamba run -n salus fastp --thread 4 -z 4 -A --max_len1 28 --max_len2 0 --dont_eval_duplication -q 20 -u 82 -n 4 --average_qual 20 --length_required 28 -y -Y 30 -g -x \
  41     -i $$<_R1_001.fastq.gz -I $$<_R2_001.fastq.gz -o $$@_R1_001.fastp.gz -O $$@_R2_001.fastp.gz -j $$@.fastp.json -h $$@.fastp.html 2>$$@.fastp.log
  42         micromamba run -n salus cutadapt -Z -j8 --pair-filter=any --minimum-length 28:50 --length 100 --times 0 --report full --json=$$@.cut.json \
  43           -o $$@_R1_001.cut.gz -p $$@_R2_001.cut.gz $$@_R1_001.fastp.gz $$@_R2_001.fastp.gz >$$@.cut.log
  44         touch $$@
  45 endef
  46 $(foreach pf, $(PLATFORMS), $(foreach sample, $(SAMPLEID), $(eval $(call pf_smp_rule,$(pf),$(sample)))) )
  47
  48 define pf_rule
  49 endef
  50 $(foreach pf, $(PLATFORMS), $(eval $(call pf_rule,$(pf))))
  51
  52 sub_Salus/mbrain_S1_L001: $(filter fastp_Salus/mbrain_S1_L001,$(FASTP_TAGS))
  53         mkdir -p $(dir $@)
  54         micromamba run -n salus seqkit --compress-level 4 -o $@_R1_001.fastq.gz -w 200 -j 1 sample -p 0.72 -s 123456 $^_R1_001.cut.gz
  55         micromamba run -n salus seqkit --compress-level 4 -o $@_R2_001.fastq.gz -w 200 -j 1 sample -p 0.72 -s 123456 $^_R2_001.cut.gz
  56         touch $@
  57
  58 sub_Salus/mkidney_S1_L001: $(filter fastp_Salus/mkidney_S1_L001,$(FASTP_TAGS))
  59         mkdir -p $(dir $@)
  60         micromamba run -n salus seqkit --compress-level 4 -o $@_R1_001.fastq.gz -w 200 -j 1 sample -p 0.76 -s 123456 $^_R1_001.cut.gz
  61         micromamba run -n salus seqkit --compress-level 4 -o $@_R2_001.fastq.gz -w 200 -j 1 sample -p 0.76 -s 123456 $^_R2_001.cut.gz
  62         touch $@
  63
  64 %.stats: $(foreach sample, $(SAMPLEID), %/$(sample)_S1_L001)
  65         micromamba run -n salus seqkit stats -a -o $@ -j8 $(dir $<)*.gz
  66
  67 .PHONY scp:
  68         scp makefile s0:/share/result/spatial/data/BoAo_sp/sub/