Merge branch '21-metaphlan3' into 'master'

metaphlan3 and strainphlan

Closes #21

See merge request !5

tools/metaphlan3/metaphlan/paired/Snakefile

+__metaphlan3_exec_command = config.get('metaphlan3', {}).get('exec_command', 'metaphlan')
+__metaphlan3_modules = config.get('metaphlan3', {}).get('modules')
+__metaphlan3_input_type = config['metaphlan3'].get('input_type', 'fastq')
+__metaphlan3_options = config.get('metaphlan3', {}).get('options', "")
+__metaphlan3_threads = config.get('metaphlan3', {}).get('threads', 1)
+
+
+rule metaphlan3_paired:
+    """
+    MetaPhlAn 3 can also natively handle paired-end metagenomes (but does not use the paired-end information),
+    and, more generally, metagenomes stored in multiple files (but you need to specify the --bowtie2out parameter):
+
+    $ metaphlan metagenome_1.fastq,metagenome_2.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5
+                    --input_type fastq > profiled_metagenome.txt
+
+    """
+    input:
+        r1 = __metaphlan3_input_r1,
+        r2 = __metaphlan3_input_r2
+    output:
+        profile = __metaphlan3_output,
+        bowtie2out = __metaphlan3_output_bowtie2out,
+        sams = __metaphlan3_output_sams
+    params:
+        exec_command = __metaphlan3_exec_command,
+        modules = __metaphlan3_modules,
+        input_type = __metaphlan3_input_type,
+        options = __metaphlan3_options
+    threads:
+        __metaphlan3_threads
+    run:
+        command = []
+        if params.modules:
+            command.append("module load {params.modules}")
+        command.append("{params.exec_command} --nproc {threads} --input_type {params.input_type} -s {output.sams} --bowtie2out {output.bowtie2out} {params.options} {input.r1},{input.r2} {output.profile}")
+        shell(" && ".join(command))

tools/metaphlan3/metaphlan/paired/config_example.yaml

+input_dir: data
+
+metaphlan3:
+  threads: 1
+  input_type: fastq
+  options: ""
+  pair_suffix: ""
+  exec_command: metaphlan

tools/metaphlan3/metaphlan/single/Snakefile

+__metaphlan3_exec_command = config.get('metaphlan3', {}).get('exec_command', 'metaphlan')
+__metaphlan3_modules = config.get('metaphlan3', {}).get('modules')
+__metaphlan3_input_type = config['metaphlan3'].get('input_type', 'fastq')
+__metaphlan3_options = config.get('metaphlan3', {}).get('options', "")
+__metaphlan3_threads = config.get('metaphlan3', {}).get('threads', 1)
+
+
+rule metaphlan3:
+    input:
+        __metaphlan3_input
+    output:
+        profile = __metaphlan3_output_profile,
+        bowtie2out = __metaphlan3_output_bowtie2out,
+        sams = __metaphlan3_output_sams
+    params:
+        exec_command = __metaphlan3_exec_command,
+        modules = __metaphlan3_modules,
+        input_type = __metaphlan3_input_type,
+        options = __metaphlan3_options
+    threads:
+        __metaphlan3_threads
+    run:
+        command = []
+        if params.modules:
+            command.append("module load {params.modules}")
+        command.append("{params.exec_command} --nproc {threads} --input_type {params.input_type} -s {output.sams} --bowtie2out {output.bowtie2out} {params.options} {input} {output.profile}")
+        shell(" && ".join(command))

tools/metaphlan3/metaphlan/single/config_example.yaml

+input_dir: data
+
+metaphlan3:
+  threads: 1
+  input_type: fastq
+  options: "--bowtie2db /pasteur/projets/policy01/Atm/DBs/metaphlan/metaphlan3bowtie2db/"
+  exec_command: metaphlan

tools/strainphlan/sample2markers/README.md

+# sample2markers.py for strainphlan
+
+This step will reconstruct all species strains found in metaphlan output sam file and store them in a pickle file (*.pkl). Those strains are referred as sample-reconstructed strains.
+
+### Help section
+
+```
+usage: sample2markers.py [-h] [-i INPUT [INPUT ...]] [--sorted]
+                         [-f INPUT_FORMAT] [-o OUTPUT_DIR]
+                         [-b BREADTH_THRESHOLD] [-n NPROCS]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -i INPUT [INPUT ...], --input INPUT [INPUT ...]
+                        The input samples as SAM or BAM files
+  --sorted              Whether the BAM input files are sorted. Default false
+  -f INPUT_FORMAT, --input_format INPUT_FORMAT
+                        The input samples format {bam, sam, bz2}. Default bz2
+  -o OUTPUT_DIR, --output_dir OUTPUT_DIR
+                        The output directory
+  -b BREADTH_THRESHOLD, --breadth_threshold BREADTH_THRESHOLD
+                        The breadth of coverage threshold for the consensus
+                        markers. Default 80 (%)
+  -n NPROCS, --nprocs NPROCS
+                        The number of threads to execute the script
+```

tools/strainphlan/sample2markers/Snakefile

+__sample2markers_exec_command = config.get('sample2markers', {}).get('exec_command', 'sample2markers.py')
+__sample2markers_modules = config.get('sample2markers', {}).get('modules')
+__sample2markers_options = config.get('sample2markers', {}).get('options', "")
+__sample2markers_threads = config.get('sample2markers', {}).get('threads', 1)
+
+
+rule sample2markers:
+    input:
+        __sample2markers_input
+    output:
+        __sample2markers_output
+    params:
+        exec_command = __sample2markers_exec_command,
+        modules = __sample2markers_modules,
+        output_dir = __sample2markers_output_dir,
+        options = __sample2markers_options
+    threads:
+        __sample2markers_threads
+    run:
+        command = []
+        if params.modules:
+            command.append("module load {params.modules}")
+        command.append("{params.exec_command} -n {threads} {params.options} -i {input} -o {params.output_dir}")
+        shell(" && ".join(command))

tools/strainphlan/sample2markers/config.yaml

+input_dir: data
+
+sample2markers:
+  threads: 1
+  exec_command: sample2markers.py