From 32c4aa8ec1443e5c8b00855ca20d09efca571783 Mon Sep 17 00:00:00 2001
From: Kedi Cao <kedic715@gmail.com>
Date: Fri, 14 Mar 2025 10:30:18 +0100
Subject: [PATCH] change .png extensions to .pdf, add empty samples list in
config
---
config/snake_config.yaml | 172 ++++++++++++++++-----------------
snakemodules/crop_remapped.smk | 6 +-
snakemodules/crop_unmapped.smk | 6 +-
3 files changed, 92 insertions(+), 92 deletions(-)
diff --git a/config/snake_config.yaml b/config/snake_config.yaml
index 087f754..89832bd 100644
--- a/config/snake_config.yaml
+++ b/config/snake_config.yaml
@@ -1,86 +1,86 @@
-### Define *full path* of references here
-REFERENCE:
- /home/user/popinSnake/example_data/ref/chr21_ins.fa
-
-### Provide *full path* of input sample folder here
-INPUT_DIR:
- /home/user/popinSnake/example_data/
-
-### Provide selected sample names from input sample folder (optional)
-### If not provide a list of samples, all samples found under input_dir will be analyzed
-SAMPLES:
- # - S0001
- # - S0002
- # - S0003
-
-### Provide *full path* of where your workflow is located
-# this path will be a prefix for submodules and log files within the workflow
-# e.g.: /home/user/popinSnake
-WORKFLOW_PATH:
- /home/user/popinSnake/
-
-### Provide *full path* of where you wish the analyzed output to be stored
-# this path is a prefix for WORK_DIR and RESULTS_DIR
-# e.g.: /home/user/../output
-OUTPUT_PATH:
- /home/user/output_path/
-
-### Choose workflow behaviour here
-SICKLE:
- "yes"
-ASSEMBLER:
- "minia"
-ANALYSIS:
- "yes"
-
-### Define contamination removal module
-remove_contamination:
- "yes"
-# Provid an alternative reference genome after contamination removal to ensure that cleaned reads are accurately realigned
-ALTREF:
- /home/user/popinSnake/example_data/altref/chr21_remap.fa
-# Define the *full path* of where the kraken database is installed
-kraken_db_path:
- /home/user/popinSnake/example_data/kraken_db/
-# deprecated parameters for snakefile download_krakendb
-# check readme file for more information on how to download krakendb
-# Pipeline to automatically download the chosen kraken database
-#install_kraken_db:
-# "no"
-#kraken_lib:
-# "https://genome-idx.s3.amazonaws.com/kraken/k2_standard_08gb_20240605.tar.gz"
-
-### Define other workflow parameter values here
-receive_email_notifications: "no" # choose between "yes" or "no" to receive email notifications or not
-email: "user@example.com" # specify your email address here to receive email notifications before each notebook execution.
-kmerlength: 29 # for velvet assembly
-k_merge: 63 # for rule popins2_merge_contigs
-readlen: 150 # for rules popins2_place_refalign and popins2_place_splitalign
-min-qual: 30 # for rule popins2_crop_unmapped, Minimum average quality value in windows for read quality trimming.
-min-read-len: 60 # for rule popins2_crop_unmapped, Minimum read length to keep the read after quality trimming.
-
-
-# Sub-directories for OUTPUT_PATH
-# These folders will be automatically created after snakemake execution
-# WORK_DIR includes intermediate output, processed data
-# RESUTLS_DIR includes analyzed output, final results
-WORK_DIR:
- workdir
-RESULTS_DIR:
- results
-
-# Define paths to binaries:
-# (Change only if you are not using the default installation locations.)
-POPINS2_BIN:
- submodules/popins4snake/popins4snake
-MINIA_BIN:
- submodules/gatb-minia-pipeline/gatb
-SICKLE_BIN:
- submodules/sickle/sickle
-VELVET_BIN:
- submodules/velvet
-# Part of the contamination removal module
-python_script:
- snakemodules/scripts/remap_classified_human.py
-
-
+### Define *full path* of references here
+REFERENCE:
+ /home/kedic/workflow_dev/popinSnake/example_data/ref/chr21_ins.fa
+
+### Provide *full path* of input sample folder here
+INPUT_DIR:
+ /home/kedic/workflow_dev/popinSnake/example_data/
+### Provide selected sample names from input sample folder (optional)
+# If sample names are not provided, workflow will automatically look for samples.bam and samples.bai under input_dir
+# all samples found under input_dir will be analyzed
+SAMPLES:
+ # - S0001
+ # - S0002
+ # - S0003
+
+### Provide *full path* of where your workflow is located
+# this path will be a prefix for submodules and log files within the workflow
+# e.g.: /home/user/popinSnake
+WORKFLOW_PATH:
+ /home/kedic/workflow_dev/popinSnake/
+
+### Provide *full path* of where you wish the analyzed output to be stored
+# this path is a prefix for WORK_DIR and RESULTS_DIR
+# e.g.: /home/user/../output
+OUTPUT_PATH:
+ /home/kedic/workflow_dev/test_output/
+
+### Select workflow behaviour here
+SICKLE:
+ "yes"
+ASSEMBLER:
+ "minia"
+ANALYSIS:
+ "yes"
+
+### Define contamination removal module
+remove_contamination:
+ "no"
+# Provid an alternative reference genome after contamination removal to ensure that cleaned reads are accurately realigned
+ALTREF:
+ /home/kedic/workflow_dev/popinSnake/example_data/altref/chr21_remap.fa
+# Define the *full path* of where the kraken database is installed
+kraken_db_path:
+ /home/kedic/workflow_dev/popinSnake/example_data/kraken_db
+# deprecated parameters for snakefile download_krakendb
+# check readme file for more information on how to download krakendb
+# Pipeline to automatically download the chosen kraken database
+#install_kraken_db:
+# "no"
+#kraken_lib:
+# "https://genome-idx.s3.amazonaws.com/kraken/k2_standard_08gb_20240605.tar.gz"
+
+### Define other workflow parameter values here
+receive_email_notifications: "no" # choose between "yes" or "no" to receive email notifications or not
+email: "user@example.com" # specify your email address here to receive email notifications before each notebook execution.
+kmerlength: 29 # for velvet assembly
+k_merge: 63 # for rule popins2_merge_contigs
+readlen: 150 # for rules popins2_place_refalign and popins2_place_splitalign
+min-qual: 30 # for rule popins2_crop_unmapped, Minimum average quality value in windows for read quality trimming.
+min-read-len: 60 # for rule popins2_crop_unmapped, Minimum read length to keep the read after quality trimming.
+
+
+# Sub-directories for OUTPUT_PATH
+# These folders will be automatically created after snakemake execution
+# WORK_DIR includes intermediate output, processed data
+# RESUTLS_DIR includes analyzed output, final results
+WORK_DIR:
+ workdir
+RESULTS_DIR:
+ results
+
+# Define paths to binaries:
+# (Change only if you are not using the default installation locations.)
+POPINS2_BIN:
+ submodules/popins4snake/popins4snake
+MINIA_BIN:
+ submodules/gatb-minia-pipeline/gatb
+SICKLE_BIN:
+ submodules/sickle/sickle
+VELVET_BIN:
+ submodules/velvet
+# Part of the contamination removal module
+python_script:
+ snakemodules/scripts/remap_classified_human.py
+
+
diff --git a/snakemodules/crop_remapped.smk b/snakemodules/crop_remapped.smk
index 87a3c96..813f91e 100644
--- a/snakemodules/crop_remapped.smk
+++ b/snakemodules/crop_remapped.smk
@@ -53,7 +53,7 @@ if config["SICKLE"]=="no":
rule popins2_sort:
input:
- os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
mates = WORK_DIR + "/{sample}/mates.bam"
output:
temp(WORK_DIR + "/{sample}/non_ref.bam")
@@ -106,7 +106,7 @@ elif config["SICKLE"]=="yes":
rule popins2_sort:
input:
- # os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ # os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
mates = WORK_DIR + "/{sample}/mates.bam"
output:
temp(WORK_DIR + "/{sample}/non_ref.bam")
@@ -127,7 +127,7 @@ elif config["SICKLE"]=="yes":
rule popins2_sickle:
input:
- # os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ # os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
single = WORK_DIR + "/{sample}/single_clean.fastq",
pair_1 = WORK_DIR + "/{sample}/paired_1_clean.fastq",
pair_2 = WORK_DIR + "/{sample}/paired_2_clean.fastq"
diff --git a/snakemodules/crop_unmapped.smk b/snakemodules/crop_unmapped.smk
index dc98159..dd0ef28 100644
--- a/snakemodules/crop_unmapped.smk
+++ b/snakemodules/crop_unmapped.smk
@@ -51,7 +51,7 @@ if config["SICKLE"]=="no":
rule popins2_sort:
input:
- os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
mates = WORK_DIR + "/{sample}/mates.bam"
output:
temp(WORK_DIR + "/{sample}/non_ref.bam")
@@ -104,7 +104,7 @@ elif config["SICKLE"]=="yes":
rule popins2_sort:
input:
- # os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ # os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
mates = WORK_DIR + "/{sample}/mates.bam"
output:
temp(WORK_DIR + "/{sample}/non_ref.bam")
@@ -125,7 +125,7 @@ elif config["SICKLE"]=="yes":
rule popins2_sickle:
input:
- # os.path.join(RESULTS_DIR, "read_numbers.png") if config["ANALYSIS"]=="yes" else [],
+ # os.path.join(RESULTS_DIR, "read_numbers.pdf") if config["ANALYSIS"]=="yes" else [],
single = WORK_DIR + "/{sample}/single.fastq",
pair_1 = WORK_DIR + "/{sample}/paired.1.fastq",
pair_2 = WORK_DIR + "/{sample}/paired.2.fastq"
--
GitLab