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 SRBIN := /share/result/spatial/test_huxs/10x/space-ranger/spaceranger-2.1.1/bin/spaceranger
   7
   8 define platform_rule
   9 TAGS_$1 := $$(foreach s, $$(SAMPLEID), $1/$$(s)_S1_L001)
  10 endef
  11 $(foreach platform,$(PLATFORMS),$(eval $(call platform_rule,$(platform))))
  12 ALLTAGS := $(TAGS_Illumina) $(TAGS_Salus)
  13
  14 RAW_Salus := $(foreach a, $(SAMPLEID), $(foreach b, $(LANEID_Salus), $(foreach r,R1 R2,raw4_Salus/$(a)_S1_$(b)_$(r)_001.fastq.gz )))
  15 MERGE_Salus := $(foreach tag,$(TAGS_Salus),raw_$(tag) )
  16 MERGE_Illumina := $(foreach a, $(SAMPLEID), $(foreach r,R1 R2,raw_Illumina/$(a)_S1_L001 ))
  17 FASTP_TAGS := $(foreach tag,$(ALLTAGS),fastp_$(tag) )
  18 SUBFQ_TAGS := $(foreach tag,$(ALLTAGS),sub_$(tag) )
  19 FQ_DIRS := $(foreach p,raw fastp sub,$(foreach pf,$(PLATFORMS),$(p)_$(pf)))
  20 SRLOGS := $(foreach smp, $(SAMPLEID), $(foreach pf,$(PLATFORMS),sr_$(pf)/sub_$(pf)_$(smp).log ))
  21
  22 #all:   $(MERGE_Salus) $(FASTP_TAGS) $(foreach d,$(FQ_DIRS),$(d).stats) $(SRLOGS)
  23 all:    $(foreach d,$(FQ_DIRS),$(d).stats) $(SRLOGS)
  24         @echo $^
  25
  26 define smp_rule
  27 raw_Salus/$1_S1_L001: $$(filter raw4_Salus/$1_S1_%,$$(RAW_Salus))
  28         mkdir -p $$(dir $$@)
  29         @cat $$(filter %_R1_001.fastq.gz,$$^) > $$@_R1_001.fastq.gz
  30         @cat $$(filter %_R2_001.fastq.gz,$$^) > $$@_R2_001.fastq.gz
  31         touch $$@
  32 raw_Illumina/$1_S1_L001:
  33         touch $$@
  34 sub_Illumina/$1_S1_L001: $$(filter fastp_Illumina/$1_S1_L001,$$(FASTP_TAGS))
  35         mkdir -p $$(dir $$@)
  36         cp --reflink=auto -l $$^_R1_001.cut.gz $$@_R1_001.fastq.gz
  37         cp --reflink=auto -l $$^_R2_001.cut.gz $$@_R2_001.fastq.gz
  38         touch $$@
  39 endef
  40 $(foreach sample, $(SAMPLEID), $(eval $(call smp_rule,$(sample))))
  41
  42 define pf_smp_rule
  43 fastp_$1/$2_S1_L001: $$(filter raw_$1/$2_S1_L001,$$(MERGE_Salus) $$(MERGE_Illumina))
  44         mkdir -p $$(dir $$@)
  45         micromamba run -n salus fastp --thread 4 -z 4 -A --max_len1 28 --max_len2 0 --dont_eval_duplication -q 20 -u 82 -n 4 --average_qual 20 --length_required 28 -y -Y 30 -g -x \
  46     -i $$<_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
  47         micromamba run -n salus cutadapt -Z -j8 --pair-filter=any --minimum-length 28:50 --length 100 --times 0 --report full --json=$$@.cut.json \
  48           -o $$@_R1_001.cut.gz -p $$@_R2_001.cut.gz $$@_R1_001.fastp.gz $$@_R2_001.fastp.gz >$$@.cut.log
  49         touch $$@
  50 endef
  51 $(foreach pf, $(PLATFORMS), $(foreach sample, $(SAMPLEID), $(eval $(call pf_smp_rule,$(pf),$(sample)))) )
  52
  53 define pf_rule
  54 sr_$(1)/sub_$(1)_mbrain.log: $$(filter sub_$1/mbrain_S1_L001,$$(SUBFQ_TAGS))
  55         mkdir -p $$(dir $$@)
  56         micromamba run -n salus $$(SRBIN) count --id=srp_$(1)_mbrain --transcriptome=refdata-gex-mm10-2020-A --fastqs=sub_$1 --sample=mbrain \
  57     --slide=V12A25-031 --slidefile=V12A25-031.gpr --localcores=36 --localmem=64 --vdrmode=disable \
  58     --area=A1 --image=mbrain.tif >$$@
  59 sr_$(1)/sub_$(1)_mkidney.log: $$(filter sub_$1/mkidney_S1_L001,$$(SUBFQ_TAGS))
  60         mkdir -p $$(dir $$@)
  61         micromamba run -n salus $$(SRBIN) count --id=srp_$(1)_mkidney --transcriptome=refdata-gex-mm10-2020-A --fastqs=sub_$1 --sample=mkidney \
  62     --slide=V12A25-031 --slidefile=V12A25-031.gpr --localcores=36 --localmem=64 --vdrmode=disable \
  63     --area=A1 --image=mkidney.tif >$$@
  64 endef
  65 $(foreach pf, $(PLATFORMS), $(eval $(call pf_rule,$(pf))))
  66
  67 sub_Salus/mbrain_S1_L001: $(filter fastp_Salus/mbrain_S1_L001,$(FASTP_TAGS))
  68         mkdir -p $(dir $@)
  69         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
  70         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
  71         touch $@
  72
  73 sub_Salus/mkidney_S1_L001: $(filter fastp_Salus/mkidney_S1_L001,$(FASTP_TAGS))
  74         mkdir -p $(dir $@)
  75         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
  76         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
  77         touch $@
  78
  79 %.stats: $(foreach sample, $(SAMPLEID), %/$(sample)_S1_L001)
  80         micromamba run -n salus seqkit stats -a -o $@ -j8 $(dir $<)*.gz
  81
  82 .PHONY scp:
  83         scp makefile s0:/share/result/spatial/data/BoAo_sp/sub/