diff --git a/snakemake/process_data/Snakefile b/snakemake/process_data/Snakefile index c23295793097ebc8a224123b30dc2388e5cd5aa2..c9a07d8556260e4a37810ea17cd6ac897d8627e5 100644 --- a/snakemake/process_data/Snakefile +++ b/snakemake/process_data/Snakefile @@ -39,7 +39,7 @@ rule clip_reads: flag = config["dir_created"], reads = os.path.join(config["input_dir"], "{sample}" + config["input_reads_pattern"]), output: - reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq.gz"), + reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq"), params: v = "-v", n = "-n", @@ -59,7 +59,6 @@ rule clip_reads: -l {params.l} \ {params.qual} \ -a {params.adapter} \ - {params.z} \ -i <(zcat {input.reads}) \ -o {output.reads}) &> {log}" @@ -69,9 +68,9 @@ rule clip_reads: rule trim_reads: input: - reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq.gz") + reads = os.path.join(config["output_dir"], "{sample}/pro.clipped.fastq") output: - reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq.gz"), + reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq"), params: v = "-v", l = "20", @@ -89,8 +88,7 @@ rule trim_reads: -l {params.l} \ -t {params.t} \ {params.qual} \ - {params.z} \ - -i <(zcat {input.reads}) \ + -i {input.reads} \ -o {output.reads}) &> {log}" ################################################################################# @@ -99,15 +97,14 @@ rule trim_reads: rule filter_reads: input: - reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq.gz"), + reads = os.path.join(config["output_dir"], "{sample}/pro.trimmed.fastq"), output: - reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq.gz"), + reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq"), params: v = "-v", q = "20", p = "90", qual = "-Q33", - z = "-z", cluster_log = os.path.join(config["cluster_log"], "filter_reads_{sample}.log") log: os.path.join(config["local_log"], "filter_reads_{sample}.log") @@ -119,8 +116,7 @@ rule filter_reads: -q {params.q} \ -p {params.p} \ {params.qual} \ - {params.z} \ - -i <(zcat {input.reads}) \ + -i {input.reads} \ -o {output.reads}) &> {log}" ################################################################################# @@ -129,7 +125,7 @@ rule filter_reads: rule fastq_to_fasta: input: - reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq.gz"), + reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fastq"), output: reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fasta"), params: @@ -149,7 +145,7 @@ rule fastq_to_fasta: {params.qual} \ {params.n} \ {params.r} \ - -i <(zcat {input.reads}) \ + -i {input.reads} \ -o {output.reads}) &> {log}" ################################################################################# @@ -190,7 +186,7 @@ rule map_to_other_genes: rule map_to_transcripts: input: - reads = os.path.join(config["output_dir"], "{sample}/pro.filtered.fasta"), + reads = os.path.join(config["output_dir"], "{sample}/other_genes.unmapped.fasta"), index = config["transcripts_index"], sequence = config["transcripts_sequence"] output: diff --git a/snakemake/process_data/cluster.json b/snakemake/process_data/cluster.json index 9af5fef199040ea6824264b1552313e3a38d4636..25fe29fd44b9fcb486624fc8bbf4b712d48ef2ce 100644 --- a/snakemake/process_data/cluster.json +++ b/snakemake/process_data/cluster.json @@ -4,7 +4,7 @@ "queue":"6hours", "time": "05:00:00", "threads":"1", -"mem":"4G" +"mem":"8G" }, "map_to_other_genes": {