diff --git a/tools/cd-hit-est/Snakefile b/tools/cd-hit-est/Snakefile
new file mode 100644
index 0000000000000000000000000000000000000000..5b08bdd95da031c56c69c1cd487305251e2278d5
--- /dev/null
+++ b/tools/cd-hit-est/Snakefile
@@ -0,0 +1,129 @@
+"""
+CD-HIT-EST manual
+
+ ====== CD-HIT version 4.8.1 (built on May 23 2020) ======
+
+Usage: cd-hit-est [Options]
+
+Options
+
+ -i input filename in fasta format, required, can be in .gz format
+ -j input filename in fasta/fastq format for R2 reads if input are paired end (PE) files
+ -i R1.fq -j R2.fq -o output_R1 -op output_R2 or
+ -i R1.fa -j R2.fa -o output_R1 -op output_R2
+ -o output filename, required
+ -op output filename for R2 reads if input are paired end (PE) files
+ -c sequence identity threshold, default 0.9
+ this is the default cd-hit's "global sequence identity" calculated as:
+ number of identical amino acids or bases in alignment
+ divided by the full length of the shorter sequence
+ -G use global sequence identity, default 1
+ if set to 0, then use local sequence identity, calculated as :
+ number of identical amino acids or bases in alignment
+ divided by the length of the alignment
+ NOTE!!! don't use -G 0 unless you use alignment coverage controls
+ see options -aL, -AL, -aS, -AS
+ -b band_width of alignment, default 20
+ -M memory limit (in MB) for the program, default 800; 0 for unlimitted;
+ -T number of threads, default 1; with 0, all CPUs will be used
+ -n word_length, default 10, see user's guide for choosing it
+ -l length of throw_away_sequences, default 10
+ -d length of description in .clstr file, default 20
+ if set to 0, it takes the fasta defline and stops at first space
+ -s length difference cutoff, default 0.0
+ if set to 0.9, the shorter sequences need to be
+ at least 90% length of the representative of the cluster
+ -S length difference cutoff in amino acid, default 999999
+ if set to 60, the length difference between the shorter sequences
+ and the representative of the cluster can not be bigger than 60
+ -aL alignment coverage for the longer sequence, default 0.0
+ if set to 0.9, the alignment must covers 90% of the sequence
+ -AL alignment coverage control for the longer sequence, default 99999999
+ if set to 60, and the length of the sequence is 400,
+ then the alignment must be >= 340 (400-60) residues
+ -aS alignment coverage for the shorter sequence, default 0.0
+ if set to 0.9, the alignment must covers 90% of the sequence
+ -AS alignment coverage control for the shorter sequence, default 99999999
+ if set to 60, and the length of the sequence is 400,
+ then the alignment must be >= 340 (400-60) residues
+ -A minimal alignment coverage control for the both sequences, default 0
+ alignment must cover >= this value for both sequences
+ -uL maximum unmatched percentage for the longer sequence, default 1.0
+ if set to 0.1, the unmatched region (excluding leading and tailing gaps)
+ must not be more than 10% of the sequence
+ -uS maximum unmatched percentage for the shorter sequence, default 1.0
+ if set to 0.1, the unmatched region (excluding leading and tailing gaps)
+ must not be more than 10% of the sequence
+ -U maximum unmatched length, default 99999999
+ if set to 10, the unmatched region (excluding leading and tailing gaps)
+ must not be more than 10 bases
+ -B 1 or 0, default 0, by default, sequences are stored in RAM
+ if set to 1, sequence are stored on hard drive
+ !! No longer supported !!
+ -P input paired end (PE) reads, default 0, single file
+ if set to 1, please use -i R1 -j R2 to input both PE files
+ -cx length to keep after trimming the tail of sequence, default 0, not trimming
+ if set to 50, the program only uses the first 50 letters of input sequence
+ -cy length to keep after trimming the tail of R2 sequence, default 0, not trimming
+ if set to 50, the program only uses the first 50 letters of input R2 sequence
+ e.g. -cx 100 -cy 80 for paired end reads
+ -ap alignment position constrains, default 0, no constrain
+ if set to 1, the program will force sequences to align at beginings
+ when set to 1, the program only does +/+ alignment
+ -p 1 or 0, default 0
+ if set to 1, print alignment overlap in .clstr file
+ -g 1 or 0, default 0
+ by cd-hit's default algorithm, a sequence is clustered to the first
+ cluster that meet the threshold (fast cluster). If set to 1, the program
+ will cluster it into the most similar cluster that meet the threshold
+ (accurate but slow mode)
+ but either 1 or 0 won't change the representatives of final clusters
+ -r 1 or 0, default 1, by default do both +/+ & +/- alignments
+ if set to 0, only +/+ strand alignment
+ -mask masking letters (e.g. -mask NX, to mask out both 'N' and 'X')
+ -match matching score, default 2 (1 for T-U and N-N)
+ -mismatch mismatching score, default -2
+ -gap gap opening score, default -6
+ -gap-ext gap extension score, default -1
+ -bak write backup cluster file (1 or 0, default 0)
+ -sc sort clusters by size (number of sequences), default 0, output clusters by decreasing length
+ if set to 1, output clusters by decreasing size
+ -sf sort fasta/fastq by cluster size (number of sequences), default 0, no sorting
+ if set to 1, output sequences by decreasing cluster size
+ this can be very slow if the input is in .gz format
+ -h print this help
+
+ Questions, bugs, contact Weizhong Li at liwz@sdsc.edu
+ For updated versions and information, please visit: http://cd-hit.org
+ or https://github.com/weizhongli/cdhit
+
+ cd-hit web server is also available from http://cd-hit.org
+
+ If you find cd-hit useful, please kindly cite:
+
+ "CD-HIT: a fast program for clustering and comparing large sets of protein or nucleotide sequences", Weizhong Li & Adam Godzik. Bioinformatics, (2006) 22:1658-1659
+ "CD-HIT: accelerated for clustering the next generation sequencing data", Limin Fu, Beifang Niu, Zhengwei Zhu, Sitao Wu & Weizhong Li. Bioinformatics, (2012) 28:3150-3152
+"""
+
+__cd_hit_est_exec_command = config.get('cd_hit_est', {}).get('exec_command', 'cd_hit_est')
+__cd_hit_est_modules = config.get('cd_hit_est', {}).get('modules')
+__cd_hit_est_options = config.get('cd_hit_est', {}).get('options', '')
+__cd_hit_est_threads = config.get('cd_hit_est', {}).get('threads', 1)
+
+rule cd_hit_est:
+ input:
+ __cd_hit_est_input
+ output:
+ __cd_hit_est_output
+ params:
+ exec_command = __cd_hit_est_exec_command,
+ modules = __cd_hit_est_modules,
+ options = __cd_hit_est_options
+ threads:
+ __cd_hit_est_threads
+ run:
+ command = []
+ if params.modules:
+ command.append("module load {params.modules}")
+ command.append("{params.exec_command} {params.options} -i {input} -T {threads} -M 0 -o {output}")
+ shell(" && ".join(command))
diff --git a/tools/cd-hit-est/example_usage/Snakefile b/tools/cd-hit-est/example_usage/Snakefile
new file mode 100644
index 0000000000000000000000000000000000000000..b037c44c16567054a7ce10cefa1c944bfcd1594a
--- /dev/null
+++ b/tools/cd-hit-est/example_usage/Snakefile
@@ -0,0 +1,20 @@
+configfile: "config.yaml"
+
+# ==== Snakefile path ====
+__cd-hit_rules = config.get("snakefiles", {}).get("cd_hit_est")
+
+__main_output_dir = config.get('output_dir', 'output')
+
+# ==== Main config ====
+SAMPLES = config.get('samples')
+__input_dir = config.get('input_dir', 'data')
+
+# ==== Run cd-hit ====
+__cd-hit_output_dir = f"{__main_output_dir}/cd-hit"
+__cd-hit_input = "{dir}/{{sample}}.fa".format(dir=__input_dir, sample="{sample}")
+__cd-hit_output = "{dir}/{{sample}}.fa".format(dir=__cd-hit_output_dir, sample="{sample}")
+include: __cd-hit_rules
+
+rule all:
+ input:
+ expand("{dir}/{{sample}}.fa".format(dir=__cd-hit_output_dir), sample=SAMPLES)
diff --git a/tools/cd-hit-est/example_usage/config.yaml b/tools/cd-hit-est/example_usage/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..765e44d0eac0c009dd42b323b78bc91b0e44eb36
--- /dev/null
+++ b/tools/cd-hit-est/example_usage/config.yaml
@@ -0,0 +1,15 @@
+snakefiles:
+ cd_hit_est: /pasteur/zeus/projets/p02/metasig/gitlab/snakemake/tools/cd-hit/Snakefile
+
+input_dir: /some/input/directory
+output_dir: /some/output/directory
+
+samples:
+- test_00000
+- test_00001
+- test_00002
+
+cd_hit_est:
+ exec_command: cd-hit-est
+ modules: blast+/2.10.0 cd-hit
+ threads: 16
diff --git a/tools/prodigal/Snakefile b/tools/prodigal/Snakefile
new file mode 100644
index 0000000000000000000000000000000000000000..b304adea1f7348077ed365d3741a143d33f6e2e9
--- /dev/null
+++ b/tools/prodigal/Snakefile
@@ -0,0 +1,45 @@
+"""
+Prodigal manual
+
+Usage: prodigal [-a trans_file] [-c] [-d nuc_file] [-f output_type]
+ [-g tr_table] [-h] [-i input_file] [-m] [-n] [-o output_file]
+ [-p mode] [-q] [-s start_file] [-t training_file] [-v]
+
+ -a: Write protein translations to the selected file.
+ -c: Closed ends. Do not allow genes to run off edges.
+ -d: Write nucleotide sequences of genes to the selected file.
+ -f: Select output format (gbk, gff, or sco). Default is gbk.
+ -g: Specify a translation table to use (default 11).
+ -h: Print help menu and exit.
+ -i: Specify FASTA/Genbank input file (default reads from stdin).
+ -m: Treat runs of N as masked sequence; don't build genes across them.
+ -n: Bypass Shine-Dalgarno trainer and force a full motif scan.
+ -o: Specify output file (default writes to stdout).
+ -p: Select procedure (single or meta). Default is single.
+ -q: Run quietly (suppress normal stderr output).
+ -s: Write all potential genes (with scores) to the selected file.
+ -t: Write a training file (if none exists); otherwise, read and use
+ the specified training file.
+ -v: Print version number and exit.
+"""
+
+__prodigal_exec_command = config.get('prodigal', {}).get('exec_command', 'prodigal')
+__prodigal_modules = config.get('prodigal', {}).get('modules')
+__prodigal_options = config.get('prodigal', {}).get('options', '')
+
+rule prodigal:
+ input:
+ __prodigal_input
+ output:
+ fasta_genes = __prodigal_fasta_genes,
+ genes = __prodigal_genes
+ params:
+ exec_command = __prodigal_exec_command,
+ modules = __prodigal_modules,
+ options = __prodigal_options
+ run:
+ command = []
+ if params.modules:
+ command.append("module load {params.modules}")
+ command.append("{params.exec_command} {params.options} -i {input} -d {output.fasta_genes} -o {output.genes}")
+ shell(" && ".join(command))
diff --git a/tools/prodigal/example_usage/Snakefile b/tools/prodigal/example_usage/Snakefile
new file mode 100644
index 0000000000000000000000000000000000000000..4b32331d84ec33fa11ea1b3299fcdbd9cfe12f3c
--- /dev/null
+++ b/tools/prodigal/example_usage/Snakefile
@@ -0,0 +1,22 @@
+configfile: "config.yaml"
+
+# ==== Snakefile path ====
+__prodigal_rules = config.get("snakefiles", {}).get("prodigal")
+
+__main_output_dir = config.get('output_dir', 'output')
+
+# ==== Main config ====
+SAMPLES = config.get('samples')
+__input_dir = config.get('input_dir', 'data')
+
+# ==== Run prodigal ====
+__prodigal_output_dir = f"{__main_output_dir}/prodigal"
+__prodigal_input = "{dir}/{{sample}}.fa".format(dir=__input_dir, sample="{sample}")
+__prodigal_fasta_genes = "{dir}/{{sample}}.fa".format(dir=__prodigal_output_dir, sample="{sample}")
+__prodigal_genes = "{dir}/{{sample}}.gbk".format(dir=__prodigal_output_dir, sample="{sample}")
+include: __prodigal_rules
+
+rule all:
+ input:
+ fasta_genes = expand("{dir}/{{sample}}.fa".format(dir=__prodigal_output_dir), sample=SAMPLES),
+ genes = expand("{dir}/{{sample}}.gbk".format(dir=__prodigal_output_dir), sample=SAMPLES)
diff --git a/tools/prodigal/example_usage/config.yaml b/tools/prodigal/example_usage/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3314b2d9914f22ea2a1f2ee845374147bdf236ac
--- /dev/null
+++ b/tools/prodigal/example_usage/config.yaml
@@ -0,0 +1,14 @@
+snakefiles:
+ prodigal: /pasteur/zeus/projets/p02/metasig/gitlab/snakemake/tools/prodigal/Snakefile
+
+input_dir: /some/input/directory
+output_dir: /some/output/directory
+
+samples:
+- test_00000
+- test_00001
+- test_00002
+
+prodigal:
+ exec_command: prodigal
+ modules: prodigal