Add mermaid diagrams for all workflows

workflows/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/Assembly-Hifi-HiC-phasing-VGP4_diagrams.md

@@ -0,0 +1,116 @@
+```mermaid
+graph LR
+0["Pacbio Reads Collection"]@{ shape: docs }
+1["HiC forward reads"]@{ shape: doc }
+2["HiC reverse reads"]@{ shape: doc }
+3["Genomescope Summary"]@{ shape: doc }
+4["Meryl Database"]@{ shape: doc }
+5["Database for Busco Lineage"]@{ shape: lean-l }
+6["Lineage"]@{ shape: lean-l }
+7["Name for Haplotype 1"]@{ shape: lean-l }
+8["Name for Haplotype 2"]@{ shape: lean-l }
+9["Bits for bloom filter"]@{ shape: lean-l }
+10["SAK input file"]@{ shape: doc }
+11["Homozygous Read Coverage"]@{ shape: lean-l }
+12["Genomescope Model Parameters"]@{ shape: doc }
+13["Cutadapt"]@{ shape: process }
+0 --> 13
+14["Search in textfiles"]@{ shape: process }
+3 --> 14
+15["Compute"]@{ shape: process }
+12 --> 15
+16["MultiQC"]@{ shape: process }
+13 --> 16
+17["Replace Text"]@{ shape: process }
+14 --> 17
+18["Cut"]@{ shape: process }
+15 --> 18
+19["Convert"]@{ shape: process }
+17 --> 19
+20["Estimated homozygous read coverage"]@{ shape: process }
+18 --> 20
+21["Cut"]@{ shape: process }
+19 --> 21
+22["Homozygous read coverage for Hifiasm"]@{ shape: process }
+11 --> 22
+20 --> 22
+23["Estimated genome size"]@{ shape: process }
+21 --> 23
+24["Hifiasm"]@{ shape: process }
+22 --> 24
+9 --> 24
+1 --> 24
+2 --> 24
+13 --> 24
+25["Raw Unitig Image"]@{ shape: process }
+24 --> 25
+26["gfastats"]@{ shape: process }
+24 --> 26
+23 --> 26
+27["gfastats"]@{ shape: process }
+24 --> 27
+23 --> 27
+28["gfastats"]@{ shape: process }
+24 --> 28
+29["gfastats"]@{ shape: process }
+24 --> 29
+30["gfastats"]@{ shape: process }
+24 --> 30
+31["gfastats"]@{ shape: process }
+24 --> 31
+32["gfastats"]@{ shape: process }
+24 --> 32
+10 --> 32
+33["gfastats"]@{ shape: process }
+24 --> 33
+10 --> 33
+34["Text reformatting"]@{ shape: process }
+26 --> 34
+35["Text reformatting"]@{ shape: process }
+27 --> 35
+36["Data Prep Hap2"]@{ shape: subprocess }
+28 --> 36
+37["Data Prep Hap1"]@{ shape: subprocess }
+30 --> 37
+38["Text transformation"]@{ shape: process }
+32 --> 38
+39["Text transformation"]@{ shape: process }
+33 --> 39
+40["Join two Datasets"]@{ shape: process }
+35 --> 40
+34 --> 40
+41["Plot Data"]@{ shape: subprocess }
+36 --> 41
+8 --> 41
+7 --> 41
+37 --> 41
+42["Busco"]@{ shape: process }
+38 --> 42
+5 --> 42
+6 --> 42
+43["Merqury"]@{ shape: process }
+39 --> 43
+38 --> 43
+4 --> 43
+44["Busco"]@{ shape: process }
+39 --> 44
+5 --> 44
+6 --> 44
+45["Advanced Cut"]@{ shape: process }
+40 --> 45
+46["output_merqury.spectra-cn.fl"]@{ shape: process }
+43 --> 46
+47["output_merqury.spectra-asm.fl"]@{ shape: process }
+43 --> 47
+48["merqury_qv"]@{ shape: process }
+43 --> 48
+49["output_merqury.assembly_01.spectra-cn.fl"]@{ shape: process }
+43 --> 49
+50["merqury_stats"]@{ shape: process }
+43 --> 50
+51["output_merqury.assembly_02.spectra-cn.fl"]@{ shape: process }
+43 --> 51
+52["Replace"]@{ shape: process }
+45 --> 52
+
+```

workflows/VGP-assembly-v2/Assembly-Hifi-Trio-phasing-VGP5/Assembly-Hifi-Trio-phasing-VGP5_diagrams.md

@@ -0,0 +1,120 @@
+```mermaid
+graph LR
+0["Pacbio Reads Collection : child"]@{ shape: docs }
+1["Paternal Illumina reads (hap1)"]@{ shape: docs }
+2["Maternal Illumina reads (hap2)"]@{ shape: docs }
+3["Meryl Database : Child"]@{ shape: doc }
+4["Hapmer Database : Paternal"]@{ shape: doc }
+5["Hapmer Database : Maternal"]@{ shape: doc }
+6["Bits for bloom filter"]@{ shape: lean-l }
+7["Database for Busco Lineage"]@{ shape: lean-l }
+8["Lineage"]@{ shape: lean-l }
+9["Homozygous Read Coverage"]@{ shape: lean-l }
+10["Genomescope Model Parameters"]@{ shape: doc }
+11["Genomescope Summary"]@{ shape: doc }
+12["Utilize homology information to correct trio-phasing errors"]@{ shape: lean-l }
+13["SAK input file (Optional)"]@{ shape: doc }
+14["Name for Haplotype 1"]@{ shape: lean-l }
+15["Name for Haplotype 2"]@{ shape: lean-l }
+16["Cutadapt"]@{ shape: process }
+0 --> 16
+17["Compute"]@{ shape: process }
+10 --> 17
+18["Search in textfiles"]@{ shape: process }
+11 --> 18
+19["MultiQC"]@{ shape: process }
+16 --> 19
+20["Cut"]@{ shape: process }
+17 --> 20
+21["Replace Text"]@{ shape: process }
+18 --> 21
+22["Parse parameter value"]@{ shape: process }
+20 --> 22
+23["Convert"]@{ shape: process }
+21 --> 23
+24["Homozygous read coverage for Hifiasm"]@{ shape: process }
+9 --> 24
+22 --> 24
+25["Cut"]@{ shape: process }
+23 --> 25
+26["Hifiasm"]@{ shape: process }
+24 --> 26
+6 --> 26
+16 --> 26
+12 --> 26
+1 --> 26
+2 --> 26
+27["Estimated genome size"]@{ shape: process }
+25 --> 27
+28["gfastats"]@{ shape: process }
+26 --> 28
+13 --> 28
+29["gfastats"]@{ shape: process }
+26 --> 29
+13 --> 29
+30["Raw Unitig Image"]@{ shape: process }
+26 --> 30
+31["gfastats"]@{ shape: process }
+26 --> 31
+13 --> 31
+32["gfastats"]@{ shape: process }
+26 --> 32
+13 --> 32
+33["gfastats"]@{ shape: process }
+26 --> 33
+34["gfastats"]@{ shape: process }
+26 --> 34
+35["gfastats"]@{ shape: process }
+26 --> 35
+27 --> 35
+36["gfastats"]@{ shape: process }
+26 --> 36
+27 --> 36
+37["Busco"]@{ shape: process }
+31 --> 37
+7 --> 37
+8 --> 37
+38["Busco"]@{ shape: process }
+32 --> 38
+7 --> 38
+8 --> 38
+39["Merqury"]@{ shape: process }
+31 --> 39
+32 --> 39
+3 --> 39
+5 --> 39
+4 --> 39
+40["Data prep Hap1"]@{ shape: subprocess }
+33 --> 40
+41["Data Prep Hap2"]@{ shape: subprocess }
+34 --> 41
+42["Text reformatting"]@{ shape: process }
+35 --> 42
+43["Text reformatting"]@{ shape: process }
+36 --> 43
+44["merqury_qv"]@{ shape: process }
+39 --> 44
+45["output_merqury.spectra-cn.fl"]@{ shape: process }
+39 --> 45
+46["output_merqury.spectra-asm.fl"]@{ shape: process }
+39 --> 46
+47["output_merqury.assembly_01.spectra-cn.fl"]@{ shape: process }
+39 --> 47
+48["output_merqury.assembly_02.spectra-cn.fl"]@{ shape: process }
+39 --> 48
+49["merqury_stats"]@{ shape: process }
+39 --> 49
+50["Plots"]@{ shape: subprocess }
+41 --> 50
+15 --> 50
+14 --> 50
+40 --> 50
+51["Join two Datasets"]@{ shape: process }
+43 --> 51
+42 --> 51
+52["Advanced Cut"]@{ shape: process }
+51 --> 52
+53["Replace"]@{ shape: process }
+52 --> 53
+
+```

workflows/VGP-assembly-v2/Assembly-Hifi-only-VGP3/Assembly-Hifi-only-VGP3_diagrams.md

@@ -0,0 +1,106 @@
+```mermaid
+graph LR
+0["Pacbio Reads Collection"]@{ shape: docs }
+1["Meryl Database"]@{ shape: doc }
+2["Genomescope Summary"]@{ shape: doc }
+3["Bits for Hifiasm bloom filter"]@{ shape: lean-l }
+4["Homozygous Read Coverage"]@{ shape: lean-l }
+5["Genomescope Model Parameters"]@{ shape: doc }
+6["Database for Busco Lineage"]@{ shape: lean-l }
+7["Lineage"]@{ shape: lean-l }
+8["SAK input file (Optional)"]@{ shape: doc }
+9["Name of primary assembly"]@{ shape: lean-l }
+10["Name of alternate assembly"]@{ shape: lean-l }
+11["Cutadapt"]@{ shape: process }
+0 --> 11
+12["Search in textfiles"]@{ shape: process }
+2 --> 12
+13["Pick parameter value"]@{ shape: process }
+3 --> 13
+14["Compute"]@{ shape: process }
+5 --> 14
+15["MultiQC"]@{ shape: process }
+11 --> 15
+16["Replace Text"]@{ shape: process }
+12 --> 16
+17["Cut"]@{ shape: process }
+14 --> 17
+18["Convert"]@{ shape: process }
+16 --> 18
+19["Parse parameter value"]@{ shape: process }
+17 --> 19
+20["Cut"]@{ shape: process }
+18 --> 20
+21["Homozygous read coverage for Hifiasm"]@{ shape: process }
+4 --> 21
+19 --> 21
+22["Estimated genome size"]@{ shape: process }
+20 --> 22
+23["Hifiasm"]@{ shape: process }
+21 --> 23
+13 --> 23
+11 --> 23
+24["Raw Unitig Image"]@{ shape: process }
+23 --> 24
+25["gfastats"]@{ shape: process }
+23 --> 25
+8 --> 25
+26["gfastats"]@{ shape: process }
+23 --> 26
+8 --> 26
+27["gfastats"]@{ shape: process }
+23 --> 27
+8 --> 27
+28["gfastats"]@{ shape: process }
+23 --> 28
+8 --> 28
+29["gfastats"]@{ shape: process }
+23 --> 29
+22 --> 29
+30["gfastats"]@{ shape: process }
+23 --> 30
+22 --> 30
+31["gfastats"]@{ shape: process }
+23 --> 31
+32["gfastats"]@{ shape: process }
+23 --> 32
+33["Busco"]@{ shape: process }
+27 --> 33
+6 --> 33
+7 --> 33
+34["Merqury"]@{ shape: process }
+27 --> 34
+28 --> 34
+1 --> 34
+35["Text reformatting"]@{ shape: process }
+29 --> 35
+36["Text reformatting"]@{ shape: process }
+30 --> 36
+37["Data Prep Primary"]@{ shape: subprocess }
+31 --> 37
+38["Data Prep Alternate"]@{ shape: subprocess }
+32 --> 38
+39["merqury_qv"]@{ shape: process }
+34 --> 39
+40["output_merqury.spectra-cn.fl"]@{ shape: process }
+34 --> 40
+41["output_merqury.spectra-asm.fl"]@{ shape: process }
+34 --> 41
+42["output_merqury.assembly_01.spectra-cn.fl"]@{ shape: process }
+34 --> 42
+43["merqury_stats"]@{ shape: process }
+34 --> 43
+44["Join two Datasets"]@{ shape: process }
+35 --> 44
+36 --> 44
+45["Plotting Nx and Sizes"]@{ shape: subprocess }
+38 --> 45
+10 --> 45
+9 --> 45
+37 --> 45
+46["Advanced Cut"]@{ shape: process }
+44 --> 46
+47["Replace"]@{ shape: process }
+46 --> 47
+
+```

workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9_diagrams.md

@@ -0,0 +1,27 @@
+```mermaid
+graph LR
+0["Scaffolded assembly (fasta)"]@{ shape: doc }
+1["Database for Kraken2"]@{ shape: lean-l }
+2["soft-masking "]@{ shape: process }
+0 --> 2
+3["hard-masking"]@{ shape: process }
+2 --> 3
+4["ID non-target contaminants"]@{ shape: process }
+1 --> 4
+3 --> 4
+5["blast mitochondria DB"]@{ shape: process }
+3 --> 5
+6["Cut"]@{ shape: process }
+4 --> 6
+7["parsing blast output"]@{ shape: process }
+5 --> 7
+8["Filter"]@{ shape: process }
+6 --> 8
+9["Cut"]@{ shape: process }
+8 --> 9
+10["concatenate scaffold lists"]@{ shape: process }
+11["removing scaffolds "]@{ shape: process }
+0 --> 11
+10 --> 11
+
+```

workflows/VGP-assembly-v2/Mitogenome-assembly-VGP0/Mitogenome-Assembly-VGP0_diagrams.md

@@ -0,0 +1,16 @@
+```mermaid
+graph LR
+0["Collection of Pacbio Data"]@{ shape: docs }
+1["Species name (latin name)"]@{ shape: lean-l }
+2["Email adress"]@{ shape: lean-l }
+3["MitoHiFi"]@{ shape: process }
+2 --> 3
+1 --> 3
+4["MitoHiFi"]@{ shape: process }
+0 --> 4
+3 --> 4
+3 --> 4
+5["Compress file(s)"]@{ shape: process }
+4 --> 5
+
+```