From 7612fd4a8828c9e670a1c6e8ed8684de5e4952d6 Mon Sep 17 00:00:00 2001
From: Alexis Mergez <alexis.mergez@inrae.fr>
Date: Fri, 25 Oct 2024 13:49:06 +0200
Subject: [PATCH 1/5] Added Pan1c prefix instead of pan1c
---
Snakefile | 200 ++++++++++++++++++++++++++----------------------------
1 file changed, 97 insertions(+), 103 deletions(-)
diff --git a/Snakefile b/Snakefile
index fbbc6ef..12975d7 100644
--- a/Snakefile
+++ b/Snakefile
@@ -36,17 +36,17 @@ nHAP = len(SAMPLES)
with gzip.open("data/haplotypes/"+config['reference'], "r") as handle:
CHRLIST = [line.decode().split("#")[-1].split('\n')[0] for line in handle.readlines() if line.decode()[0] == ">"]
-graph_tools = ["pan1c"] + (config["get_MC"] == "True")*["MC"]
+graph_tools = ["PGGB"] + (config["get_MC"] == "True")*["MC"]
# Adding optionnal output based on config.yaml, using the following function
def which_analysis():
## Default analysis
analysis_inputs = [
- expand("output/stats/{gtool}."+config['name']+".core.stats.tsv", gtool=graph_tools), # core stats
- expand("output/panacus.reports/{gtool}."+config['name']+".{chromosome}.histgrowth.html", chromosome=CHRLIST, gtool=graph_tools), # panacus histgrowth
- expand("output/chrGraphs.figs/{gtool}."+config['name']+".{chromosome}.1Dviz.png", chromosome=CHRLIST, gtool=graph_tools), # visualizations from odgi on chromosome graphs
- expand("output/stats/{gtool}."+config['name']+".chrGraph.general.stats.tsv", gtool=graph_tools) # chromosomes graph statistics
+ expand("output/stats/Pan1c.{gtool}."+config['name']+".core.stats.tsv", gtool=graph_tools), # core stats
+ expand("output/panacus.reports/Pan1c.{gtool}."+config['name']+".{chromosome}.histgrowth.html", chromosome=CHRLIST, gtool=graph_tools), # panacus histgrowth
+ expand("output/chrGraphs.figs/Pan1c.{gtool}."+config['name']+".{chromosome}.1Dviz.png", chromosome=CHRLIST, gtool=graph_tools), # visualizations from odgi on chromosome graphs
+ expand("output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.general.stats.tsv", gtool=graph_tools) # chromosomes graph statistics
]
## Optionals analysis steps
@@ -55,41 +55,35 @@ def which_analysis():
if config["get_ASMs_SyRI"] == "True": # Creating SyRI for each input assembly
analysis_inputs.append(
- expand("output/asm.syri.figs/"+config['name']+".{haplotype}.syri.{tool}.png", haplotype=SAMPLES_NOREF, tool=["mm2"])
+ expand("output/asm.syri.figs/Pan1c."+config['name']+".{haplotype}.syri_{tool}.png", haplotype=SAMPLES_NOREF, tool=["mm2"])
)
if config["get_chrInputs_SyRI"] == "True": # Creating SyRI figures for each PGGB input
analysis_inputs.append(
- expand("output/chrInput.syri.figs/"+config['name']+".{chromosome}.syri.png", chromosome=CHRLIST)
+ expand("output/chrInput.syri.figs/Pan1c."+config['name']+".{chromosome}.syri_mm2.png", chromosome=CHRLIST)
)
if config["run_Quast"] == "True": # Running Quast on input haplotypes
analysis_inputs.append(
- "output/"+config['name']+".quast.report.html"
+ "output/Pan1c."+config['name']+".quast.report.html"
)
if config["get_contig_pos"] == "True": # Chromosome decomposition into its contig figure
analysis_inputs.append(
- expand("output/chr.contig/{haplotype}.contig.png", haplotype=CHRLIST)
+ expand("output/chr.contig/Pan1c."+config['name']+"{chromosome}.contig.png", chromosome=CHRLIST)
)
if config["create_report"] == "True": # Creating report (need contig)
analysis_inputs.append(
- expand("output/{gtool}."+config['name']+".report.md", gtool=graph_tools)
+ expand("output/Pan1c.{gtool}."+config['name']+".report.md", gtool=graph_tools)
)
- analysis_inputs.append("output/report_data/"+config['name']+".assembly.json")
- analysis_inputs.append("output/report_data/"+config['name']+".graph.json")
+ analysis_inputs.append("output/report_data/Pan1c."+config['name']+".assembly.json")
+ analysis_inputs.append("output/report_data/Pan1c."+config['name']+".graph.json")
if config["get_VCF"] == "True": # VCF from the final graph against the "reference"
analysis_inputs.append(
expand("output/{gtool}.vcf.figs", gtool=graph_tools)
)
- analysis_inputs.append("output/report_data/"+config['name']+".var.json")
+ analysis_inputs.append("output/report_data/Pan1c."+config['name']+".var.json")
return analysis_inputs
-"""
-Functions ---------------------------------------------------------------------------------------
-"""
-def get_mem_mb(wildcards, attempt, threads, multiplier=config["mem_multiplier"]):
- return attempt * multiplier * threads
-
"""
Rules -------------------------------------------------------------------------------------------
"""
@@ -97,8 +91,8 @@ Rules ------------------------------------------------------------------------
# Main target rule
rule all:
input:
- expand("output/{gtool}."+config['name']+".gfa.gz", gtool=graph_tools), # Final graph (main output)
- "output/pan1c."+config['name']+".gfa.metadata", # Metadata for the final (also in top of gfa files as # line)
+ expand("output/Pan1c.{gtool}."+config['name']+".gfa.gz", gtool=graph_tools), # Final graph (main output)
+ "output/Pan1c."+config['name']+".gfa.metadata", # Metadata for the final (also in top of gfa files as # line)
which_analysis()
"""
@@ -153,7 +147,7 @@ rule quast_stats:
fas=expand("data/haplotypes/{haplotype}.fa.gz", haplotype=SAMPLES_NOREF),
ref="data/haplotypes/"+config['reference']
output:
- report="output/"+config['name']+".quast.report.html"
+ report="output/Pan1c."+config['name']+".quast.report.html"
threads: 16
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 4000
@@ -213,13 +207,13 @@ rule assemblathon_stats:
mv data/haplotypes/{wildcards.haplotype}.csv {output.csv}
"""
-rule contig_position:
+rule contig_positions:
# Produce figures with contig positions
input:
fa="data/chrInputs/"+config["name"]+".{chromosome}.fa.gz",
fai="data/chrInputs/"+config["name"]+".{chromosome}.fa.gz.fai"
output:
- fig="output/chr.contig/{chromosome}.contig.png",
+ fig="output/chr.contig/Pan1c."+config['name']+"{chromosome}.contig.png",
outdir=temp(directory("output/chr.contig/{chromosome}"))
threads: 1
resources:
@@ -290,8 +284,8 @@ rule SyRI_on_ASM_mm2:
ref="data/hap.ragtagged/"+config['reference'][:-5]+"ragtagged.fa.gz",
qry="data/hap.ragtagged/{haplotype}.ragtagged.fa.gz"
output:
- fig="output/asm.syri.figs/"+config['name']+".{haplotype}.syri.mm2.png",
- vcf="data/asm.syri.mm2/"+config['name']+".{haplotype}.syri.mm2.vcf.gz"
+ fig="output/asm.syri.figs/Pan1c."+config['name']+".{haplotype}.syri_mm2.png",
+ vcf="data/asm.syri.mm2/Pan1c."+config['name']+".{haplotype}.syri.mm2.vcf.gz"
log:
cmd="logs/SyRI_ASM/{haplotype}.SyRI_ASM.mm2.cmd.log",
time="logs/SyRI_ASM/{haplotype}.SyRI_ASM.mm2.time.log"
@@ -335,8 +329,8 @@ rule SyRI_on_ASM_wfm:
ref="data/hap.ragtagged/"+config['reference'][:-5]+"ragtagged.fa.gz",
qry="data/hap.ragtagged/{haplotype}.ragtagged.fa.gz"
output:
- fig="output/asm.syri.figs/"+config['name']+".{haplotype}.syri.wfm.png",
- vcf="data/asm.syri.wfm/"+config['name']+".{haplotype}.syri.wfm.vcf.gz"
+ fig="output/asm.syri.figs/Pan1c."+config['name']+".{haplotype}.syri_wfm.png",
+ vcf="data/asm.syri.wfm/Pan1c."+config['name']+".{haplotype}.syri.wfm.vcf.gz"
log:
cmd="logs/SyRI_ASM/{haplotype}.SyRI_ASM.wfm.cmd.log",
time="logs/SyRI_ASM/{haplotype}.SyRI_ASM.wfm.time.log"
@@ -384,19 +378,19 @@ def asm_json_inputs(wildcards):
if config["get_contig_pos"] == "True":
sections["contig_pos"] = expand(
- "output/chr.contig/{chromosome}.contig.png",
+ "output/chr.contig/Pan1c."+config['name']+"{chromosome}.contig.png",
chromosome=CHRLIST
)
if config["get_ASMs_SyRI"] == "True":
sections["SyRI_on_ASMs_figs"] = expand(
- "output/asm.syri.figs/"+config['name']+".{haplotype}.syri.mm2.png",
+ "output/asm.syri.figs/Pan1c."+config['name']+".{haplotype}.syri_mm2.png",
haplotype=SAMPLES_NOREF
)
if config["get_chrInputs_SyRI"] == "True":
sections["SyRI_on_chrInputs_figs"] = expand(
- "output/chrInput.syri.figs/"+config['name']+".{chromosome}.syri.png",
+ "output/chrInput.syri.figs/Pan1c."+config['name']+".{chromosome}.syri_mm2.png",
chromosome=CHRLIST
)
@@ -407,8 +401,8 @@ rule asm_json:
input:
unpack(asm_json_inputs)
output:
- json="output/report_data/"+config['name']+".assembly.json",
- merged="output/report_data/"+config['name']+".assemblathon_stats.tsv"
+ json="output/report_data/Pan1c."+config['name']+".assembly.json",
+ merged="output/report_data/Pan1c."+config['name']+".assemblathon_stats.tsv"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 16000
@@ -444,7 +438,7 @@ rule SyRI_on_chrInput:
input:
fasta='data/chrInputs/'+config['name']+'.{chromosome}.fa.gz'
output:
- fig="output/chrInput.syri.figs/"+config['name']+".{chromosome}.syri.png"
+ fig="output/chrInput.syri.figs/Pan1c."+config['name']+".{chromosome}.syri_mm2.png"
threads: 8
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 12000
@@ -497,10 +491,10 @@ rule wfmash_on_chr:
fa='data/chrInputs/'+config['name']+'.{chromosome}.fa.gz',
fai='data/chrInputs/'+config['name']+'.{chromosome}.fa.gz.fai'
output:
- mapping=temp("data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.wfmash.mapping.paf"),
- aln=temp("data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.wfmash.aln.paf"),
- mapping_gz="data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.wfmash.mapping.paf.gz",
- aln_gz="data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.wfmash.aln.paf.gz"
+ mapping=temp("data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.wfmash.mapping.paf"),
+ aln=temp("data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.wfmash.aln.paf"),
+ mapping_gz="data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.wfmash.mapping.paf.gz",
+ aln_gz="data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.wfmash.aln.paf.gz"
threads: 16
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 2000
@@ -553,7 +547,7 @@ rule seqwish:
fa='data/chrInputs/'+config['name']+'.{chromosome}.fa.gz',
aln=rules.wfmash_on_chr.output.aln_gz
output:
- gfa_gz="data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.seqwish.gfa.gz"
+ gfa_gz="data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.seqwish.gfa.gz"
threads: 8
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 4000
@@ -585,8 +579,8 @@ rule gfaffix_on_chr:
input:
rules.seqwish.output.gfa_gz
output:
- gfa_gz="data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.seqwish.gfaffixD.gfa.gz",
- transform="data/chrGraphs/pan1c.{chromosome}/pan1c.{chromosome}.seqwish.gfaffixD.transform.txt"
+ gfa_gz="data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.seqwish.gfaffixD.gfa.gz",
+ transform="data/chrGraphs/PGGB.{chromosome}/Pan1c."+config['name']+".{chromosome}.seqwish.gfaffixD.transform.txt"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 24000
@@ -617,10 +611,10 @@ rule gfaffix_on_chr:
rule odgi_postprocessing:
# Running pggb's postprocessing (mainly odgi) steps with gfaffix graph
input:
- tags="output/pan1c."+config['name']+".gfa.metadata",
+ tags="output/Pan1c."+config['name']+".gfa.metadata",
gfa_gz=rules.gfaffix_on_chr.output.gfa_gz
output:
- gfa_gz='data/chrGraphs/pan1c.'+config['name']+'.{chromosome}.gfa.gz'
+ gfa_gz="data/chrGraphs/Pan1c.PGGB."+config['name']+".{chromosome}.gfa.gz"
threads: 8
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 4000
@@ -686,10 +680,10 @@ rule odgi_postprocessing:
rule MC_graph:
input:
- tags="output/pan1c."+config['name']+".gfa.metadata",
+ tags="output/Pan1c."+config['name']+".gfa.metadata",
fa='data/chrInputs/'+config['name']+'.{chromosome}.fa.gz'
output:
- gfa_gz='data/chrGraphs/MC.'+config['name']+'.{chromosome}.gfa.gz'
+ gfa_gz='data/chrGraphs/Pan1c.MC.'+config['name']+'.{chromosome}.gfa.gz'
threads: 16
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 32000
@@ -740,9 +734,9 @@ rule MC_graph:
rule generate_graph_list:
# Generate a text file containing all created graphs
input:
- gfas=expand('data/chrGraphs/{{gtool}}.'+config['name']+'.{chromosome}.tmp.gfa', chromosome=CHRLIST)
+ gfas=expand('data/chrGraphs/Pan1c.{{gtool}}.'+config['name']+'.{chromosome}.tmp.gfa', chromosome=CHRLIST)
output:
- "data/chrGraphs/graphsList.{gtool}.txt"
+ temp("data/chrGraphs/graphsList.{gtool}.txt")
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 4000
@@ -756,13 +750,13 @@ rule graph_squeeze:
# Using odgi to merge every subgraphs into a final one
input:
glist="data/chrGraphs/graphsList.{gtool}.txt",
- tags="output/pan1c."+config['name']+".gfa.metadata",
- graphs=expand('data/chrGraphs/{{gtool}}.'+config['name']+'.{chromosome}.tmp.gfa', chromosome=CHRLIST)
+ tags="output/Pan1c."+config['name']+".gfa.metadata",
+ graphs=expand('data/chrGraphs/Pan1c.{{gtool}}.'+config['name']+'.{chromosome}.tmp.gfa', chromosome=CHRLIST)
output:
- gfa_gz="output/{gtool}."+config['name']+".gfa.gz"
+ gfa_gz="output/Pan1c.{gtool}."+config['name']+".gfa.gz"
log:
- cmd="logs/squeeze/{gtool}."+config['name']+".squeeze.cmd.log",
- time="logs/squeeze/{gtool}."+config['name']+".squeeze.time.log",
+ cmd="logs/squeeze/Pan1c.{gtool}."+config['name']+".squeeze.cmd.log",
+ time="logs/squeeze/Pan1c.{gtool}."+config['name']+".squeeze.time.log",
threads: 16
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 2000
@@ -794,10 +788,10 @@ rule graph_squeeze:
rule graph_stats:
# Using GFAstats to produce stats on every chromosome graphs
input:
- graph='data/chrGraphs/{gtool}.'+config['name']+'.{chromosome}.gfa.gz'
+ graph='data/chrGraphs/Pan1c.{gtool}.'+config['name']+'.{chromosome}.gfa.gz'
output:
- genstats="output/stats/chrGraphs.{gtool}/{gtool}."+config['name']+".{chromosome}.general.stats.tsv",
- pathstats="output/stats/chrGraphs.{gtool}/{gtool}."+config['name']+".{chromosome}.path.stats.tsv"
+ genstats="output/stats/chrGraphs.{gtool}/Pan1c.{gtool}."+config['name']+".{chromosome}.general.stats.tsv",
+ pathstats="output/stats/chrGraphs.{gtool}/Pan1c.{gtool}."+config['name']+".{chromosome}.path.stats.tsv"
threads: 4
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 8000
@@ -815,10 +809,10 @@ rule graph_stats:
rule graph_figs:
# Creating figures using odgi viz
input:
- graph='data/chrGraphs/{gtool}.'+config['name']+'.{chromosome}.tmp.gfa'
+ graph='data/chrGraphs/Pan1c.{gtool}.'+config['name']+'.{chromosome}.tmp.gfa'
output:
- oneDviz="output/chrGraphs.figs/{gtool}."+config['name']+".{chromosome}.1Dviz.png",
- pcov="output/chrGraphs.figs/{gtool}."+config['name']+".{chromosome}.pcov.png"
+ oneDviz="output/chrGraphs.figs/Pan1c.{gtool}."+config['name']+".{chromosome}.1Dviz.png",
+ pcov="output/chrGraphs.figs/Pan1c.{gtool}."+config['name']+".{chromosome}.pcov.png"
threads: 4
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 4000
@@ -841,10 +835,10 @@ rule graph_figs:
rule aggregate_graphs_stats:
# Reading and merging all stats files from chromosome graphs into a .tsv.
input:
- genstats=expand("output/stats/chrGraphs.{{gtool}}/{{gtool}}."+config['name']+".{chromosome}.general.stats.tsv", chromosome=CHRLIST)
+ genstats=expand("output/stats/chrGraphs.{{gtool}}/Pan1c.{{gtool}}."+config['name']+".{chromosome}.general.stats.tsv", chromosome=CHRLIST)
output:
- genstats="output/stats/{gtool}."+config['name']+".chrGraph.general.stats.tsv",
- pathstats="output/stats/{gtool}."+config['name']+".chrGraph.path.stats.tsv"
+ genstats="output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.general.stats.tsv",
+ pathstats="output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.path.stats.tsv"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 2000
@@ -865,8 +859,8 @@ rule get_graph_tags:
input:
"config.yaml"
output:
- md="output/pan1c."+config['name']+".gfa.metadata",
- json="output/report_data/"+config['name']+".tags.json"
+ md="output/Pan1c."+config['name']+".gfa.metadata",
+ json="output/report_data/Pan1c."+config['name']+".tags.json"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 8000
@@ -883,9 +877,9 @@ rule get_graph_tags:
rule pggb_input_stats:
# Produces statistics on pggb input sequences
input:
- flag="output/stats/{gtool}."+config['name']+".chrGraph.general.stats.tsv"
+ flag="output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.general.stats.tsv"
output:
- "output/stats/{gtool}."+config['name']+".chrInput.stats.tsv"
+ "output/stats/Pan1c.{gtool}."+config['name']+".chrInput.stats.tsv"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 32000
@@ -901,10 +895,10 @@ rule pggb_input_stats:
rule core_statistics:
# Aggregate chrInput, chrGraph and pggb statistics into a single tsv
input:
- chrInputStats = "output/stats/{gtool}."+config['name']+".chrInput.stats.tsv",
- chrGraphStats = "output/stats/{gtool}."+config['name']+".chrGraph.general.stats.tsv"
+ chrInputStats = "output/stats/Pan1c.{gtool}."+config['name']+".chrInput.stats.tsv",
+ chrGraphStats = "output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.general.stats.tsv"
output:
- tsv = "output/stats/{gtool}."+config['name']+".core.stats.tsv"
+ tsv = "output/stats/Pan1c.{gtool}."+config['name']+".core.stats.tsv"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 2000
@@ -921,11 +915,11 @@ rule core_statistics:
rule graph_json:
# Produce the Graph JSON for Pan1c QC
input:
- genstats = expand("output/stats/{gtool}."+config['name']+".chrGraph.general.stats.tsv", gtool=graph_tools),
- pathstats = expand("output/stats/{gtool}."+config['name']+".chrGraph.path.stats.tsv", gtool=graph_tools),
- odgifigs = expand("output/report/{gtool}."+config['name']+".{chromosome}.report.fig.png", gtool=graph_tools, chromosome=CHRLIST)
+ genstats = expand("output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.general.stats.tsv", gtool=graph_tools),
+ pathstats = expand("output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.path.stats.tsv", gtool=graph_tools),
+ odgifigs = expand("output/report/Pan1c.{gtool}."+config['name']+".{chromosome}.report.fig.png", gtool=graph_tools, chromosome=CHRLIST)
output:
- json="output/report_data/"+config['name']+".graph.json"
+ json="output/report_data/Pan1c."+config['name']+".graph.json"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 16000
@@ -968,12 +962,12 @@ rule get_pav:
rule panacus_stats:
# Produces panacus reports for a chromosome graph
input:
- graph='data/chrGraphs/{gtool}.'+config['name']+'.{chromosome}.tmp.gfa'
+ graph='data/chrGraphs/Pan1c.{gtool}.'+config['name']+'.{chromosome}.tmp.gfa'
output:
- html='output/panacus.reports/{gtool}.'+config['name']+'.{chromosome}.histgrowth.html'
+ html='output/panacus.reports/Pan1c.{gtool}.'+config['name']+'.{chromosome}.histgrowth.html'
log:
- cmd="logs/panacus/{gtool}.{chromosome}.panacus.cmd.log",
- time="logs/panacus/{gtool}.{chromosome}.panacus.time.log"
+ cmd="logs/panacus/Pan1c.{gtool}.{chromosome}.panacus.cmd.log",
+ time="logs/panacus/Pan1c.{gtool}.{chromosome}.panacus.time.log"
params:
app_path=config['app.path'],
pan_name=config['name'],
@@ -997,9 +991,9 @@ rule panacus_stats:
rule vg_deconstruct:
# Produce a VCF based on the "reference" haplotype
input:
- graph="output/{gtool}."+config['name']+".xg",
+ graph="output/Pan1c.{gtool}."+config['name']+".xg",
output:
- vcf=temp("output/{gtool}."+config['name']+".vcf"),
+ vcf=temp("output/Pan1c.{gtool}."+config['name']+".vcf"),
threads: 8
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 32000
@@ -1007,8 +1001,8 @@ rule vg_deconstruct:
app_path=config['app.path'],
ref=config['reference']
log:
- cmd="logs/vg_deconstruct/{gtool}.vg_deconstruct.cmd.log",
- time="logs/vg_deconstruct/{gtool}.vg_deconstruct.time.log"
+ cmd="logs/vg_deconstruct/Pan1c.{gtool}.vg_deconstruct.cmd.log",
+ time="logs/vg_deconstruct/Pan1c.{gtool}.vg_deconstruct.time.log"
shell:
"""
/usr/bin/time -v -o {log.time} \
@@ -1024,8 +1018,8 @@ rule vg_deconstruct:
rule vcf_fig:
# Produce a figure describing INS/DEL length distribution from vg deconstruct and SyRI
input:
- vg="output/{gtool}."+config['name']+".vcf.gz",
- syris_mm2=expand("data/asm.syri.mm2/"+config['name']+".{haplotype}.syri.mm2.vcf.gz", haplotype=SAMPLES_NOREF)
+ vg="output/Pan1c.{gtool}."+config['name']+".vcf.gz",
+ syris_mm2=expand("data/asm.syri.mm2/Pan1c."+config['name']+".{haplotype}.syri.mm2.vcf.gz", haplotype=SAMPLES_NOREF)
output:
vcf_fig=directory("output/{gtool}.vcf.figs")
threads: 1
@@ -1077,7 +1071,7 @@ rule vcf_fig:
rule vg_vcf_2_tsv:
input:
- "output/{gtool}."+config['name']+".vcf.gz"
+ "output/Pan1c.{gtool}."+config['name']+".vcf.gz"
output:
temp("tmp/var_json/vg_{gtool}.tsv")
threads: 1
@@ -1090,7 +1084,7 @@ rule vg_vcf_2_tsv:
rule syri_vcf_2_tsv:
input:
- expand("data/asm.syri.mm2/"+config['name']+".{haplotype}.syri.mm2.vcf.gz", haplotype=SAMPLES_NOREF)
+ expand("data/asm.syri.mm2/Pan1c."+config['name']+".{haplotype}.syri.mm2.vcf.gz", haplotype=SAMPLES_NOREF)
output:
temp("tmp/var_json/syri_mm2.tsv")
threads: 1
@@ -1138,7 +1132,7 @@ rule var_json:
input:
unpack(var_json_inputs)
output:
- json="output/report_data/"+config['name']+".var.json"
+ json="output/report_data/Pan1c."+config['name']+".var.json"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 48000
@@ -1155,12 +1149,12 @@ rule var_json:
rule create_pan1c_report_fig:
# Produces a markdown report figure of chromosomes graphs
input:
- graph='data/chrGraphs/{gtool}.'+config['name']+'.{chromosome}.tmp.gfa',
- contigfig="output/chr.contig/{chromosome}.contig.png",
+ graph='data/chrGraphs/Pan1c.{gtool}.'+config['name']+'.{chromosome}.tmp.gfa',
+ contigfig="output/chr.contig/Pan1c."+config['name']+"{chromosome}.contig.png",
output:
- odgifig=temp("tmp/{gtool}.{chromosome}.odgi.png"),
- namefig=temp("tmp/{gtool}.{chromosome}.name.png"),
- reportfig="output/report/{gtool}."+config['name']+".{chromosome}.report.fig.png"
+ odgifig=temp("tmp/Pan1c.{gtool}.{chromosome}.odgi.png"),
+ namefig=temp("tmp/Pan1c.{gtool}.{chromosome}.name.png"),
+ reportfig="output/report/Pan1c.{gtool}."+config['name']+".{chromosome}.report.fig.png"
threads: 4
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 2000
@@ -1198,14 +1192,14 @@ rule create_pan1c_report_fig:
rule create_chrGraphs_figs:
# Produce figures based on aggregated path stats
input:
- pathstats="output/stats/{gtool}."+config['name']+".chrGraph.path.stats.tsv"
+ pathstats="output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.path.stats.tsv"
output:
barplots=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST),
scatters=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST),
heatmaps=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST),
- barplot_mean="output/chrGraphs.stats.figs/{gtool}."+config['name']+".path.decomp.mean.png",
- scatter_mean="output/chrGraphs.stats.figs/{gtool}."+config['name']+".2D.scatter.mean.png",
- heatmap_diff="output/chrGraphs.stats.figs/{gtool}."+config['name']+".shared.content.diff.png"
+ barplot_mean="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".path.decomp.mean.png",
+ scatter_mean="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".2D.scatter.mean.png",
+ heatmap_diff="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".shared.content.diff.png"
threads: 1
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 16000
@@ -1232,26 +1226,26 @@ def get_report_sections(wildcards):
"""
sections = dict()
- sections["metadata"] = "output/pan1c."+config['name']+".gfa.metadata"
- sections["odgifigs"] = expand("output/report/{gtool}."+config['name']+".{chromosome}.report.fig.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
+ sections["metadata"] = "output/Pan1c."+config['name']+".gfa.metadata"
+ sections["odgifigs"] = expand("output/report/Pan1c.{gtool}."+config['name']+".{chromosome}.report.fig.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
sections["genstats"] = f"output/stats/{wildcards.gtool}."+config['name']+".chrGraph.general.stats.tsv"
sections["pathstats"] = f"output/stats/{wildcards.gtool}."+config['name']+".chrGraph.path.stats.tsv"
- sections["barplots"] = expand("output/chrGraphs.stats.figs/{gtool}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
- sections["scatters"] = expand("output/chrGraphs.stats.figs/{gtool}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
- sections["heatmaps"] = expand("output/chrGraphs.stats.figs/{gtool}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
+ sections["barplots"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
+ sections["scatters"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
+ sections["heatmaps"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
sections["barplot_mean"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".path.decomp.mean.png"
sections["scatter_mean"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".2D.scatter.mean.png"
sections["heatmap_diff"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".shared.content.diff.png"
if config["get_ASMs_SyRI"] == "True":
sections["SyRI_on_ASMs_figs"] = expand(
- "output/asm.syri.figs/"+config['name']+".{haplotype}.syri.mm2.png",
+ "output/asm.syri.figs/Pan1c."+config['name']+".{haplotype}.syri_mm2.png",
haplotype=SAMPLES_NOREF
)
if config["get_chrInputs_SyRI"] == "True":
sections["SyRI_on_chrInputs_figs"] = expand(
- "output/chrInput.syri.figs/"+config['name']+".{chromosome}.syri.png",
+ "output/chrInput.syri.figs/Pan1c."+config['name']+".{chromosome}.syri_mm2.png",
chromosome=CHRLIST
)
@@ -1265,8 +1259,8 @@ rule create_pan1c_report:
input:
unpack(get_report_sections)
output:
- report="output/{gtool}."+config['name']+".report.md",
- html="output/{gtool}."+config['name']+".report.html"
+ report="output/Pan1c.{gtool}."+config['name']+".report.md",
+ html="output/Pan1c.{gtool}."+config['name']+".report.html"
threads: 4
resources:
mem_mb = lambda wildcards, threads: threads * config["mem_multiplier"] * 500
--
GitLab
From 230d9103fe5d6f4ae90a844ae887a2ccd160afd2 Mon Sep 17 00:00:00 2001
From: Alexis Mergez <alexis.mergez@inrae.fr>
Date: Fri, 25 Oct 2024 14:48:27 +0200
Subject: [PATCH 2/5] Testing
---
rules/tools.smk | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/rules/tools.smk b/rules/tools.smk
index db1f566..490e74a 100644
--- a/rules/tools.smk
+++ b/rules/tools.smk
@@ -27,9 +27,9 @@ rule samtools_index:
rule run_bgzip:
# Run BGZIP on the file
input:
- "{file}"
+ "{file}.fa"
output:
- "{file}.gz"
+ "{file}.fa.gz"
threads: 4
retries: 1
resources:
--
GitLab
From b23eea95d1796bc4e91631ff873951519181c79e Mon Sep 17 00:00:00 2001
From: Alexis Mergez <alexis.mergez@inrae.fr>
Date: Fri, 25 Oct 2024 14:50:58 +0200
Subject: [PATCH 3/5] Fixed missing Pan1c
---
Snakefile | 6 +++---
scripts/graph.pan1c_QC.py | 4 +++-
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/Snakefile b/Snakefile
index 12975d7..db81dc7 100644
--- a/Snakefile
+++ b/Snakefile
@@ -1194,9 +1194,9 @@ rule create_chrGraphs_figs:
input:
pathstats="output/stats/Pan1c.{gtool}."+config['name']+".chrGraph.path.stats.tsv"
output:
- barplots=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST),
- scatters=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST),
- heatmaps=expand("output/chrGraphs.stats.figs/{{gtool}}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST),
+ barplots=expand("output/chrGraphs.stats.figs/Pan1c.{{gtool}}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST),
+ scatters=expand("output/chrGraphs.stats.figs/Pan1c.{{gtool}}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST),
+ heatmaps=expand("output/chrGraphs.stats.figs/Pan1c.{{gtool}}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST),
barplot_mean="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".path.decomp.mean.png",
scatter_mean="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".2D.scatter.mean.png",
heatmap_diff="output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".shared.content.diff.png"
diff --git a/scripts/graph.pan1c_QC.py b/scripts/graph.pan1c_QC.py
index 3c1bb07..8c41d82 100644
--- a/scripts/graph.pan1c_QC.py
+++ b/scripts/graph.pan1c_QC.py
@@ -2,7 +2,7 @@
Graph JSON creator for Pan1c-QC
@author: alexis.mergez@inrae.fr
-@version: 1.0
+@version: 1.1
"""
import os
@@ -99,6 +99,8 @@ for tsv in args.path:
for query in chrdf["Query.name"].unique():
shared_table[gtool][chrid][query] = chrdf[chrdf["Query.name"] == query].drop(columns="Query.name").set_index("Target.name").to_dict(orient="index")
+
+
## Assembling output JSON
Graph_JSON = {
--
GitLab
From 2658cabfd90535217bc26488dcb60883ae7408ce Mon Sep 17 00:00:00 2001
From: Alexis Mergez <alexis.mergez@inrae.fr>
Date: Fri, 25 Oct 2024 14:57:47 +0200
Subject: [PATCH 4/5] Found other missing 'Pan1c.'
---
Snakefile | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/Snakefile b/Snakefile
index db81dc7..6684e67 100644
--- a/Snakefile
+++ b/Snakefile
@@ -1228,14 +1228,14 @@ def get_report_sections(wildcards):
sections["metadata"] = "output/Pan1c."+config['name']+".gfa.metadata"
sections["odgifigs"] = expand("output/report/Pan1c.{gtool}."+config['name']+".{chromosome}.report.fig.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
- sections["genstats"] = f"output/stats/{wildcards.gtool}."+config['name']+".chrGraph.general.stats.tsv"
- sections["pathstats"] = f"output/stats/{wildcards.gtool}."+config['name']+".chrGraph.path.stats.tsv"
+ sections["genstats"] = f"output/stats/Pan1c.{wildcards.gtool}."+config['name']+".chrGraph.general.stats.tsv"
+ sections["pathstats"] = f"output/stats/Pan1c.{wildcards.gtool}."+config['name']+".chrGraph.path.stats.tsv"
sections["barplots"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".path.decomp.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
sections["scatters"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".2D.scatter.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
sections["heatmaps"] = expand("output/chrGraphs.stats.figs/Pan1c.{gtool}."+config['name']+".sharred.content.{chromosome}.png", chromosome=CHRLIST, gtool=[wildcards.gtool])
- sections["barplot_mean"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".path.decomp.mean.png"
- sections["scatter_mean"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".2D.scatter.mean.png"
- sections["heatmap_diff"] = f"output/chrGraphs.stats.figs/{wildcards.gtool}."+config['name']+".shared.content.diff.png"
+ sections["barplot_mean"] = f"output/chrGraphs.stats.figs/Pan1c.{wildcards.gtool}."+config['name']+".path.decomp.mean.png"
+ sections["scatter_mean"] = f"output/chrGraphs.stats.figs/Pan1c.{wildcards.gtool}."+config['name']+".2D.scatter.mean.png"
+ sections["heatmap_diff"] = f"output/chrGraphs.stats.figs/Pan1c.{wildcards.gtool}."+config['name']+".shared.content.diff.png"
if config["get_ASMs_SyRI"] == "True":
sections["SyRI_on_ASMs_figs"] = expand(
--
GitLab
From a2bb964af3aecb66402509e10348f01a07e2e1d3 Mon Sep 17 00:00:00 2001
From: Alexis Mergez <alexis.mergez@inrae.fr>
Date: Fri, 25 Oct 2024 14:58:30 +0200
Subject: [PATCH 5/5] Undid modif to run_bgzip
---
rules/tools.smk | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/rules/tools.smk b/rules/tools.smk
index 490e74a..db1f566 100644
--- a/rules/tools.smk
+++ b/rules/tools.smk
@@ -27,9 +27,9 @@ rule samtools_index:
rule run_bgzip:
# Run BGZIP on the file
input:
- "{file}.fa"
+ "{file}"
output:
- "{file}.fa.gz"
+ "{file}.gz"
threads: 4
retries: 1
resources:
--
GitLab