diff --git a/snakemake/process_data/Snakefile b/snakemake/process_data/Snakefile
index a1db0443509f0d41f70ab65a1750df71cdadec1c..0d869f4f1db37782a1e6725df2f733426c995041 100644
--- a/snakemake/process_data/Snakefile
+++ b/snakemake/process_data/Snakefile
@@ -1,7 +1,7 @@
configfile: "config.yaml"
#from snakemake.utils import listfiles
-localrules: create_output_and_log_directories, remove_multimappers, read_length_histogram, count_reads, determine_p_site_offset, filter_reads_based_on_read_lengths_and_offsets, bam_sort_and_index, finish
+localrules: finish
################################################################################
### Finish rule
@@ -12,24 +12,7 @@ rule finish:
pdf = expand(os.path.join(config["output_dir"], "{sample}/read_length/read_length_histogram.pdf"), sample=config["sample"]),
counts = expand(os.path.join(config["output_dir"], "{sample}/counts.tsv"), sample=config["sample"]),
bai = expand(os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.a_site_profile.sorted.bam.bai"), sample=config["sample"])
-################################################################################
-### Create output and log directories
-################################################################################
-rule create_output_and_log_directories:
- output:
- output_dir = config["output_dir"],
- cluster_log = config["cluster_log"],
- local_log = config["local_log"],
- sample_dir = expand(os.path.join(config["output_dir"], "{sample}"), sample=config["sample"]),
- flag = config["dir_created"]
- threads: 1
- shell:
- "mkdir -p {output.output_dir}; \
- mkdir -p {output.cluster_log}; \
- mkdir -p {output.local_log}; \
- mkdir -p {output.sample_dir}; \
- touch {output.flag};"
################################################################################
### Clipping reads
@@ -37,17 +20,15 @@ rule create_output_and_log_directories:
rule clip_reads:
input:
- flag = config["dir_created"],
- reads = os.path.join(config["input_dir"], "{sample}" + config["input_reads_pattern"]),
+ 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.gz")
params:
v = "-v",
n = "-n",
l = "20",
- adapter = lambda wildcards: config[wildcards.sample]['adapter'],
- z = "-z",
- cluster_log = os.path.join(config["cluster_log"], "clip_reads_{sample}.log")
+ adapter = "GATCGGAAGAGCACA", #lambda wildcards: config[wildcards.sample]['adapter'],
+ z = "-z"
log:
os.path.join(config["local_log"], "clip_reads_{sample}.log")
singularity:
@@ -76,8 +57,7 @@ rule trim_reads:
l = "20",
t = lambda wildcards: config[wildcards.sample]['minimum_quality'],
Q = lambda wildcards: config[wildcards.sample]['quality_type'],
- z = "-z",
- cluster_log = os.path.join(config["cluster_log"], "trim_reads_{sample}.log")
+ z = "-z"
log:
os.path.join(config["local_log"], "trim_reads_{sample}.log")
singularity:
@@ -106,8 +86,7 @@ rule filter_reads:
q = lambda wildcards: config[wildcards.sample]['minimum_quality'],
p = "90",
z = "-z",
- Q = lambda wildcards: config[wildcards.sample]['quality_type'],
- cluster_log = os.path.join(config["cluster_log"], "filter_reads_{sample}.log")
+ Q = lambda wildcards: config[wildcards.sample]['quality_type']
log:
os.path.join(config["local_log"], "filter_reads_{sample}.log")
singularity:
@@ -134,8 +113,7 @@ rule fastq_to_fasta:
params:
v = "-v",
n = "-n",
- r = "-r",
- cluster_log = os.path.join(config["cluster_log"], "fastq_to_fasta_{sample}.log")
+ r = "-r"
log:
os.path.join(config["local_log"], "fastq_to_fasta_{sample}.log")
singularity:
@@ -162,8 +140,7 @@ rule map_to_other_genes:
reads = os.path.join(config["output_dir"], "{sample}/other_genes.unmapped.fasta")
params:
silent = "--silent",
- accuracy = "90",
- cluster_log = os.path.join(config["cluster_log"], "map_to_other_genes_{sample}.log")
+ accuracy = "90"
log:
os.path.join(config["local_log"], "map_to_other_genes_{sample}.log")
threads: 8
@@ -194,8 +171,7 @@ rule map_to_transcripts:
reads = os.path.join(config["output_dir"], "{sample}/transcripts.unmapped.fasta")
params:
silent = "--silent",
- accuracy = "90",
- cluster_log = os.path.join(config["cluster_log"], "map_to_transcripts_{sample}.log")
+ accuracy = "90"
log:
os.path.join(config["local_log"], "map_to_transcripts_{sample}.log")
threads: 8
@@ -307,8 +283,7 @@ rule determine_p_site_offset:
p_site_offset = os.path.join(config["output_dir"],
"{sample}/p_site_offsets")
params:
- outdir = os.path.join(config["output_dir"], "{sample}/p_site_offsets"),
- cluster_log = os.path.join(config["cluster_log"], "determine_p_site_offset_{sample}.log")
+ outdir = os.path.join(config["output_dir"], "{sample}/p_site_offsets")
log:
os.path.join(config["local_log"], "determine_p_site_offset_{sample}.log")
threads: 1
@@ -334,8 +309,6 @@ rule filter_reads_based_on_read_lengths_and_offsets:
)
output:
bam = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.a_site_profile.bam"),
- params:
- cluster_log = os.path.join(config["cluster_log"], "filter_reads_based_on_read_lengths_and_offsets_{sample}.log")
log:
os.path.join(config["local_log"], "filter_reads_based_on_read_lengths_and_offsets_{sample}.log")
threads: 1
@@ -357,8 +330,6 @@ rule bam_sort_and_index:
output:
bam = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.a_site_profile.sorted.bam"),
bai = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.a_site_profile.sorted.bam.bai"),
- params:
- cluster_log = os.path.join(config["cluster_log"], "bam_sort_and_index_{sample}.log")
log:
os.path.join(config["local_log"], "bam_sort_and_index_{sample}.log")
threads: 1
diff --git a/snakemake/process_data/cluster.json b/snakemake/process_data/cluster.json
index 79460b66581f15141f995a41de93fd9fa2d9a852..5ab3acc35e7f9fa1bedb4add01859c1d55e50e27 100644
--- a/snakemake/process_data/cluster.json
+++ b/snakemake/process_data/cluster.json
@@ -1,30 +1,29 @@
{
-"__default__":
-{
-"queue":"6hours",
-"time": "05:00:00",
-"threads":"1",
-"mem":"8G"
-},
-"map_to_other_genes":
-{
-"queue":"6hours",
-"time": "06:00:00",
-"threads":"8",
-"mem":"50G"
-},
-"map_to_transcripts":
-{
-"queue":"6hours",
-"time": "06:00:00",
-"threads":"8",
-"mem":"50G"
-},
-"sam2bam_sort_and_index":
-{
-"queue":"6hours",
-"time": "06:00:00",
-"threads":"1",
-"mem":"10G"
-}
+ "__default__" :
+ {
+ "queue": "6hours",
+ "time": "05:00:00",
+ "threads": "1",
+ "mem": "4G",
+ "name": "{rule}.{wildcards}",
+ "out": "$PWD/logs/cluster_log/{rule}.{wildcards}-%j-%N.out"
+ },
+ "map_to_other_genes":
+ {
+ "time": "06:00:00",
+ "threads":"8",
+ "mem":"50G"
+ },
+ "map_to_transcripts":
+ {
+ "time": "06:00:00",
+ "threads":"8",
+ "mem":"50G"
+ },
+ "sam2bam_sort_and_index":
+ {
+ "time": "06:00:00",
+ "threads":"1",
+ "mem":"10G"
+ }
}
diff --git a/snakemake/process_data/config.yaml b/snakemake/process_data/config.yaml
index c2b5488d5f1a79ada0e7b9d41ce32dca7571e0d5..f3b40e9ab620f617b5e8ec6d585c84767ef498ec 100644
--- a/snakemake/process_data/config.yaml
+++ b/snakemake/process_data/config.yaml
@@ -11,17 +11,16 @@
### Output and log directory
##############################################################################
output_dir: "results"
- local_log: "results/local_log"
- cluster_log: "results/cluster_log"
- dir_created: "results/dir_created"
+ local_log: "logs/local_log"
+ cluster_log: "logs/cluster_log"
##############################################################################
### sample info
##############################################################################
input_dir: "samples"
input_reads_pattern: ".fastq.gz"
- sample: ["example", "example2", "SRR1536304", "SRR1536305"]
- example: {adapter: GATCGGAAGAGCACA, minimum_quality: 20, quality_type: 33}
- example2: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 64}
- SRR1536304: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 33}
- SRR1536305: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 33}
+ sample: ["example"] #, "example2", "SRR1536304", "SRR1536305"]
+ example: {adapter: "GATCGGAAGAGCACA", minimum_quality: 20, quality_type: 33}
+# example2: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 64}
+# SRR1536304: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 33}
+# SRR1536305: {adapter: CTGTAGGCACCATCA, minimum_quality: 20, quality_type: 33}
...
diff --git a/snakemake/process_data/run_snakefile.sh b/snakemake/process_data/run_snakefile.sh
index 6791403020a28256d19de15e0efa43447fe8ee58..536a8d02fea353f99177d5aeddeeea00b2a3766b 100755
--- a/snakemake/process_data/run_snakefile.sh
+++ b/snakemake/process_data/run_snakefile.sh
@@ -1,10 +1,13 @@
# set -e
+mkdir -p logs/cluster_log
+mkdir -p logs/local_log
+
snakemake \
--cluster-config cluster.json \
---cluster "sbatch --cpus-per-task={cluster.threads} --mem={cluster.mem} --qos={cluster.queue} --time={cluster.time} --output={params.cluster_log}-%j-%N -p scicore" \
+--cluster "sbatch --cpus-per-task={cluster.threads} --mem={cluster.mem} --qos={cluster.queue} --time={cluster.time} --job-name={cluster.name} -o {cluster.out} -p scicore" \
--cores 256 \
-p \
--rerun-incomplete \
--use-singularity \
---singularity-args "--bind ${PWD}"
\ No newline at end of file
+--singularity-args "--bind ${PWD},${PWD}/../"