From 8c7edff76fc7763873a45dc578add7baa0fcc4dd Mon Sep 17 00:00:00 2001
From: Kenzo-Hugo Hillion <kenzo-hugo.hillion1@pasteur.fr>
Date: Tue, 11 Feb 2020 12:37:33 +0100
Subject: [PATCH] finish Snakefile for splitting Fasta
---
tools/utils/split_fasta/Snakefile | 6 +---
.../utils/split_fasta/example_usage/Snakefile | 28 +++++++++++++++++++
.../split_fasta/example_usage/config.yaml | 9 ++++++
3 files changed, 38 insertions(+), 5 deletions(-)
create mode 100644 tools/utils/split_fasta/example_usage/Snakefile
create mode 100644 tools/utils/split_fasta/example_usage/config.yaml
diff --git a/tools/utils/split_fasta/Snakefile b/tools/utils/split_fasta/Snakefile
index d4bd950..1c4401a 100644
--- a/tools/utils/split_fasta/Snakefile
+++ b/tools/utils/split_fasta/Snakefile
@@ -1,8 +1,3 @@
-__split_fasta_number_sequences = config.get('split_fasta', {}).get('number_sequences', 1000000)
-__split_fasta_prefix = config.get('split_fasta', {}).get('prefix', 'seq_chunk_')
-
-EXPECTED_EXT = [f"{i:05d}" for i in range(0, int(9898412/__split_fasta_number_sequences) + 1)]
-
rule split_fasta:
"""
Split a FASTA file with the desired number of sequences per chunk
@@ -17,4 +12,5 @@ rule split_fasta:
shell:
"""
cat {input} | awk '/^>/ {{if(N>0) printf("\\n"); printf("%s\\n",$0);++N;next;}} {{ printf("%s",$0);}} END {{printf("\\n");}}' | split -l {params.n_lines} -a 5 -d - {params.prefix}
+ for i in `ls {params.prefix}*`; do mv $i ${{i}}.fa;done
"""
diff --git a/tools/utils/split_fasta/example_usage/Snakefile b/tools/utils/split_fasta/example_usage/Snakefile
new file mode 100644
index 0000000..4e6be41
--- /dev/null
+++ b/tools/utils/split_fasta/example_usage/Snakefile
@@ -0,0 +1,28 @@
+configfile: "config.yaml"
+
+def count_sequences(fasta_file):
+ with open(fasta_file, 'r') as file:
+ seq = 0
+ for line in file:
+ if '>' in line:
+ seq += 1
+ return seq
+
+# ==== Snakefile path ====
+__split_fasta_rules = config.get("snakefiles", {}).get("split_fasta")
+
+__main_output_dir = config.get('output_dir', 'output')
+
+# ==== Split FASTA ====
+__split_fasta_output_dir = __main_output_dir + "/split_fasta"
+
+__split_fasta_input = config['input_fasta']
+__split_fasta_number_sequences = config.get('split_fasta', {}).get('number_sequences', 1000000)
+total_number_sequences = count_sequences(__split_fasta_input)
+EXTENSIONS = [f"{i:05d}" for i in range(0, int(total_number_sequences/__split_fasta_number_sequences) + 1)]
+__split_fasta_prefix = "/".join([__split_fasta_output_dir, config['split_fasta']['prefix']])
+__split_fasta_output = expand(__split_fasta_prefix + "{ext}.fa", ext=EXTENSIONS)
+include: __split_fasta_rules
+
+rule all:
+ input: __split_fasta_output
diff --git a/tools/utils/split_fasta/example_usage/config.yaml b/tools/utils/split_fasta/example_usage/config.yaml
new file mode 100644
index 0000000..559a789
--- /dev/null
+++ b/tools/utils/split_fasta/example_usage/config.yaml
@@ -0,0 +1,9 @@
+snakefiles:
+ split_fasta: /pasteur/projets/policy01/Atm/snakemake/tools/utils/split_fasta/Snakefile
+
+input_fasta: /pasteur/projets/policy01/DBs/IGC/2014-9.9M/IGC.fa
+output_dir: /pasteur/projets/policy01/sandbox/20200210_test_snakemake/output
+
+split_fasta:
+ prefix: IGC_
+ number_sequences: 1000000
--
GitLab