Bio_to_HiC workflow

workflow/Snakefile

 import pandas as pd
 import os
+import yaml
+from collections import Counter
 
 configfile: "config.yaml"
 
-samples = pd.read_table(config["samples"], index_col="sample")
+
+samples = pd.read_table(config["samples"], dtype=str)
+
 
 rule all:
     input:
-        expand(config["arima_mapping"] + "final/{sample}.bam", sample=list(samples.index)),
-        expand(config["arima_mapping"] + "final/metric_{sample}.txt", sample=list(samples.index))
+        expand(config["salsa_scaffolding"] + "scaffolds/{sample}_scaffolds_FINAL.fasta", zip, sample=samples["sample"]),
+        #expand(config["arima_mapping"] + "merge_bio_repl/{sample}.bam.stats", zip, sample=samples["sample"])
+        #config["results"] + "bionano"
 
 include: "rules/arima_mapping.smk"
+include: "rules/salsa.smk"
+include: "rules/bionano.smk"
\ No newline at end of file

workflow/config.yaml

@@ -2,11 +2,46 @@ samples: ./units.tsv
 
 arima_mapping: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/intermed/arima_mapping/
 
+salsa_scaffolding: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/intermed/salsa_scaffolding/
+
+results: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/results/
+
 logs: ../logs/
 
 HIC_reads: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/arima_HiC/
 
 PacBio_assembly: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/assemblies/pac_bio_assembly.fna
 
-index: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/assemblies/
+raw_Filename_asse:
+
+index: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/results/bionano/hybrid_scaffolds/
+
+# --------------- Arima Mapping ---------------
+
+
+# --------------- Bionano Scaffolding ---------------
+
+# -------- Data --------
+
+cmap: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/bionano/bCalAnn1_Saphyr_DLE1.cmap
+
+rawFilename_cmap: bCalAnn1_Saphyr_DLE1
+
+# -------- Scripts --------
+
+hybridScript: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/workflow/scripts/bionano/tools/pipeline/1.0/HybridScaffold/1.0/hybridScaffold.pl
+
+refAligner: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/workflow/scripts/bionano/tools/pipeline/1.0/RefAligner/1.0/RefAligner
+
+# -------- Parameters --------
+
+# DLE1: CTTAAG ; 
+enzyme_sites: "CTTAAG" 
+
+enzyme_xml: /buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/workflow/scripts/bionano/tools/pipeline/1.0/HybridScaffold/1.0/hybridScaffold_DLE1_config.xml
+
+#conflict filter level genome maps: 1, 2, or 3
+conflictLvlMap: 2
 
+#conflict filter level sequences: 1, 2, or 3
+conflictLvlSeq: 2

workflow/envs/bionano.yaml

+channels:
+  - bioconda
+  - conda-forge
+  - anaconda
+  - bioconda-legacy
+dependencies:
+  - pandas
+  - lxml = 4.9.1
+  - perl-threaded = 5.32.1
+  - gcc_linux-64 = 11.2.0
+  - expat = 2.5.0
+  - perl-app-cpanminus = 1.7044

workflow/envs/salsa1.yaml

+channels:
+  - bioconda
+  - conda-forge
+  - anaconda
+dependencies:
+  - bedtools = 2.30.0
+  - samtools = 1.15.1

workflow/envs/salsa2.yaml

+channels:
+  - conda-forge
+  - anaconda
+  - bioconda
+dependencies:
+  - salsa2 = 2.3.

workflow/rules/arima_mapping.smk

@@ -82,10 +82,10 @@ rule r2_filter5end:
 rule samtools_faidx:
     input:
         #samtools_faidx soll erst nach bwa indexing starten da sie sonst beide auf die selbe input Datei zugreifen sollen
-        linker = config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fasta.sa"
+        linker = config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fasta.sa",
         reference = config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fasta"
     output:
-        config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fai" 
+        config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fasta.fai" 
     #params:
         #IsFastq = "-f"
     conda:
@@ -99,8 +99,7 @@ rule pair_reads:
     input:
         read1 = config["arima_mapping"] + "filtered_bam/{sample}_{unit_bio}_{unit_tech}_R1.bam",
         read2 = config["arima_mapping"] + "filtered_bam/{sample}_{unit_bio}_{unit_tech}_R2.bam",
-        faidx = config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fai" 
-
+        faidx = config["results"] + "bionano/hybrid_scaffolds/bCalAnn1_Saphyr_DLE1_bppAdjust_cmap_pac_bio_assembly_fna_NGScontigs_HYBRID_SCAFFOLD.fasta.fai" 
     output:
         config["arima_mapping"] + "paired/{sample}_{unit_bio}_{unit_tech}.bam"
     params:
@@ -123,7 +122,7 @@ rule add_read_groups:
         platform = "ILLUMINA",
         sampleName = "{sample}",
         library = "{sample}",
-        platform_unit ="None"
+        platform_unit ="None",
     conda:
         "../envs/arima_mapping.yaml"
     log:
@@ -167,13 +166,14 @@ rule mark_duplicates:
     output:
         bam = config["arima_mapping"] + "final/{sample}_{unit_bio}.bam",
         metric = config["arima_mapping"] + "final/metric_{sample}_{unit_bio}.txt"
-    #params:
     conda:
         "../envs/arima_mapping.yaml"
     log:
         config["logs"] + "arima_mapping/mark_duplicates/{sample}_{unit_bio}.log"
+    #wrapper:
+        #"v1.19.0/bio/picard/markduplicates"
     shell:
-        "picard MarkDuplicates I={input} O={output.bam} M={output.metric} 2> {log}"
+        "picard MarkDuplicates -Xmx20g I={input} O={output.bam} M={output.metric} 2> {log}"
 
 
 def bio_input(wildcards):

workflow/units.tsv

-sample	fq1	fq2
-bCalAnn1_A9_USPD16081032_HGCKKALXX_L3	"/buffer/ag_bsc/Theses/harlos_assembly/data/arima_HiC/bCalAnn1_A9_USPD16081032_HGCKKALXX_L3_R1.fastq.gz"	"/buffer/ag_bsc/Theses/harlos_assembly/data/arima_HiC/bCalAnn1_A9_USPD16081032_HGCKKALXX_L3_R2.fastq.gz"
+sample	unit_bio	unit_tech	fq1	fq2
+bCalAnn1	1	1	"/buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/arima_HiC/bCalAnn1_R1.fastq.gz"	"/buffer/ag_bsc/Theses/harlos_assembly/assembly_downstream/data/arima_HiC/bCalAnn1_R2.fastq.gz"