diff --git a/raw_inputs/raw_snap_index.py b/raw_inputs/raw_snap_index.py
new file mode 100755
index 0000000000000000000000000000000000000000..1105c40775b3b659394489549dbe19e36ce0269f
--- /dev/null
+++ b/raw_inputs/raw_snap_index.py
@@ -0,0 +1,14 @@
+import os
+import re
+import sys
+
+def raw_snap_index(results_dir, snap_index):
+ out = dict()
+ from os import listdir
+ from os.path import isfile, join
+ onlyfiles = [join(snap_index, f) for f in listdir(snap_index) if isfile(join(snap_index, f))]
+ out["snap_index"] = onlyfiles
+
+ return(out)
+
+#print(raw_snap_index(sys.argv[1],sys.argv[2]) )
\ No newline at end of file
diff --git a/raw_inputs/raw_snap_index.yaml b/raw_inputs/raw_snap_index.yaml
new file mode 100755
index 0000000000000000000000000000000000000000..d84786aa7deb90d844e870b022c7012ca608dd36
--- /dev/null
+++ b/raw_inputs/raw_snap_index.yaml
@@ -0,0 +1,13 @@
+{
+ name: raw_snap_index,
+ function_call: "raw_snap_index(config['results_dir'], config['snap_index'])",
+ options: [
+ {
+ name: "snap_index",
+ type: "input_dir",
+ value: "/Data",
+ label: "Directory containing the snap index files: ",
+ volumes: [Data: "/Data", Results: "/Results"]
+ }
+ ]
+}
\ No newline at end of file
diff --git a/tools/global.yaml b/tools/global.yaml
index 3e3ea8e47bbd504edea1a3d6c30c59d80f22cef1..162af1d2969b27eb51584476482b1e66c57385fb 100755
--- a/tools/global.yaml
+++ b/tools/global.yaml
@@ -54,6 +54,7 @@ data: [
{name: "illumina_dir", category: "sequences"},
{name: "accel_align_index", category: "index"},
+ {name: "snap_index", category: "index"},
{name: "bowtie_index", category: "index"},
{name: "bowtie2_index", category: "index"},
{name: "bwa_mem_index", category: "index"},
diff --git a/tools/snap/snap.rule.snakefile b/tools/snap/snap.rule.snakefile
new file mode 100755
index 0000000000000000000000000000000000000000..212ea9161828666ff32b0502b405c707ab20b7ff
--- /dev/null
+++ b/tools/snap/snap.rule.snakefile
@@ -0,0 +1,61 @@
+if config["SeOrPe"] == "PE":
+
+ rule <step_name>__snap_PE:
+ input:
+ **<step_name>__snap_PE_inputs()
+ output:
+ bam = config["results_dir"]+"/"+config["<step_name>__snap_PE_output_dir"]+"/{sample}.bam"
+ log:
+ config["results_dir"]+"/logs/" + config["<step_name>__snap_PE_output_dir"] + "/{sample}_snap_log.txt"
+ threads:
+ config["<step_name>__snap_threads"]
+ params:
+ command = config["<step_name>__snap_PE_command"],
+ #indexPrefix = config["<step_name>__snap_index_output_dir"]+"/index",
+ #/patho_index/indexName.fna.hash
+ indexDir = lambda w, input: os.path.dirname([x for x in input.index if 'GenomeIndexHash' in x]),
+ snap_seed_number = config["<step_name>__snap_seed_number"],
+ snap_min_insert_size = config["<step_name>__snap_min_insert_size"],
+ snap_max_insert_size = config["<step_name>__snap_max_insert_size"],
+ snap_disable_alt_awareness = "-A-" if config["<step_name>__snap_disable_alt_awareness"] else "",
+ snap_max_score_gap = config["<step_name>__snap_max_score_gap"]
+ shell:
+ "{params.command} "
+ "{params.indexDir} "
+ "{input.read} {input.read2} "
+ "-t {threads} "
+ "-n {params.snap_seed_number} "
+ "-s {params.snap_min_insert_size} {params.snap_max_insert_size} "
+ "{params.snap_disable_alt_awareness} "
+ "-asg {params.snap_max_score_gap} "
+ "-so "
+ "-o {output.bam} 2> {log}; "
+
+
+elif config["SeOrPe"] == "SE":
+
+ rule <step_name>__snap_SE:
+ input:
+ **<step_name>__snap_SE_inputs()
+ output:
+ bam = config["results_dir"]+"/"+config["<step_name>__snap_SE_output_dir"]+"/{sample}.bam"
+ log:
+ config["results_dir"]+"/logs/" + config["<step_name>__snap_SE_output_dir"] + "/{sample}_snap_log.txt"
+ threads:
+ config["<step_name>__snap_threads"]
+ params:
+ command = config["<step_name>__snap_PE_command"],
+ snap_seed_number = config["<step_name>__snap_seed_number"],
+ snap_disable_alt_awareness = "-A-" if config["<step_name>__snap_disable_alt_awareness"] else "",
+ snap_max_score_gap = config["<step_name>__snap_max_score_gap"]
+ indexDir = lambda w, input: os.path.dirname([x for x in input.index if 'GenomeIndexHash' in x]),
+ shell:
+ "{params.command} "
+ "{params.indexDir} "
+ "{input.read} "
+ "-t {threads} "
+ "-n {params.snap_seed_number} "
+ "{params.snap_disable_alt_awareness} "
+ "-asg {params.snap_max_score_gap} "
+ "-so "
+ "-o {output.bam} 2> {log}; "
diff --git a/tools/snap/snap.yaml b/tools/snap/snap.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..33b2097da7bee19ac94b26cabfcb10b4dd6b9b91
--- /dev/null
+++ b/tools/snap/snap.yaml
@@ -0,0 +1,153 @@
+{
+ id: snap,
+ name: Scalable Nucleotide Alignment Program,
+ article: arXiv:1111.5572v1,
+ website: "https://www.microsoft.com/en-us/research/project/snap/",
+ git: "https://github.com/amplab/snap",
+ description: "fast and accurate aligner for short DNA reads. It is optimized for modern read lengths of 100 bases or higher, and align them quickly through a hash-based indexing scheme.",
+ version: "2.0",
+ documentation: "https://github.com/amplab/snap/tree/master/docs",
+ multiqc: "custom",
+ commands:
+ [
+ {
+ name: snap_PE,
+ cname: "snap PE",
+ command: snap-aligner paired,
+ category: "mapping",
+ output_dir: snap/PE,
+ inputs: [{ name: read, type: "reads" }, { name: read2, type: "reads" }, { name: index, type: "snap_index", file: index, description: "Index files for snap alignment" }],
+ outputs: [{ name: bam, type: "bams", file: "{sample}.bam", description: "Alignment file" }],
+ options:
+ [
+ {
+ name: snap_threads,
+ prefix: -t,
+ type: numeric,
+ value: 4,
+ min: 1,
+ max: NA,
+ step: 1,
+ label: "Number of threads to use",
+ },
+ {
+ name: snap_seed_number,
+ prefix: -n,
+ type: numeric,
+ value: 4,
+ min: 1,
+ max: 10,
+ step: 1,
+ label: "number of seeds to use per read",
+ },
+ {
+ name: snap_min_insert_size,
+ prefix: -s,
+ type: numeric,
+ value: 0,
+ min: 10,
+ max: 400,
+ step: 10,
+ label: "minimum spacing to allow between paired ends",
+ },
+ {
+ name: snap_max_insert_size,
+ prefix: -s,
+ type: numeric,
+ value: 1000,
+ min: 10,
+ max: 3000,
+ step: 10,
+ label: "maximum spacing to allow between paired ends",
+ },
+ {
+ name: snap_force_spacing,
+ prefix: -sf,
+ type: checkbox,
+ value: FALSE,
+ label: "force spacing to lie between min and max.",
+ },
+ {
+ name: snap_disable_alt_awareness,
+ prefix: -A-,
+ type: checkbox,
+ value: FALSE,
+ label: "Disable ALT awareness. By default snap try to map reads to the primary assembly and only to choose ALT alignments when they're much better, and to compute MAPQ for non-ALT alignments using only non-ALT hits. This flag disables that behavior",
+ },
+ {
+ name: snap_max_score_gap,
+ prefix: -asg,
+ type: numeric,
+ value: 2,
+ min: 1,
+ max: 10,
+ step: 1,
+ label: "Maximum score gap to prefer a non-ALT alignment. If the best non-ALT alignment is more than this much worse than the best ALT alignment emit the ALT alignment as the primary result rather than as",
+ },
+ ]
+ },
+ {
+ name: snap_SE,
+ cname: "snap SE",
+ command: snap-aligner single,
+ category: "mapping",
+ output_dir: snap/SE,
+ inputs: [{ name: read, type: "reads" }, { name: index, type: "snap_index", file: index, description: "Index files for snap alignment" }],
+ outputs: [{ name: bam, type: "bams", file: "{sample}.bam", description: "Alignment file" }],
+ options:
+ [
+ {
+ name: snap_threads,
+ prefix: -t,
+ type: numeric,
+ value: 4,
+ min: 1,
+ max: NA,
+ step: 1,
+ label: "Number of threads to use",
+ },
+ {
+ name: snap_seed_number,
+ prefix: -n,
+ type: numeric,
+ value: 4,
+ min: 1,
+ max: 10,
+ step: 1,
+ label: "number of seeds to use per read",
+ },
+ {
+ name: snap_disable_alt_awareness,
+ prefix: -A-,
+ type: checkbox,
+ value: FALSE,
+ label: "Disable ALT awareness. By default snap try to map reads to the primary assembly and only to choose ALT alignments when they're much better, and to compute MAPQ for non-ALT alignments using only non-ALT hits. This flag disables that behavior",
+ },
+ {
+ name: snap_max_score_gap,
+ prefix: -asg,
+ type: numeric,
+ value: 2,
+ min: 1,
+ max: 10,
+ step: 1,
+ label: "Maximum score gap to prefer a non-ALT alignment. If the best non-ALT alignment is more than this much worse than the best ALT alignment emit the ALT alignment as the primary result rather than as",
+ },
+ ]
+ }
+ ],
+ install: {
+ snap: [
+ "cd /opt/biotools",
+ "git clone https://github.com/amplab/snap.git",
+ "cd snap",
+ "make -j 8",
+ "ENV PATH /opt/biotools/snap:$PATH",
+ ]
+ },
+ citations: {
+ snap: [
+ "Faster and More Accurate Sequence Alignment with SNAP. Matei Zaharia, William J. Bolosky, Kristal Curtis, Armando Fox, David Patterson, Scott Shenker, Ion Stoica, Richard M. Karp, and Taylor Sittler. arXiv:1111.5572v1, November 2011."
+ ]
+ }
+}
\ No newline at end of file