DNAnexus/Makefile

@@ -0,0 +1,15 @@
+all: default
+
+default:
+	rm -rf resources/PhyloCSF*
+	mkdir -p resources
+	cp -r ../PhyloCSF ../PhyloCSF.Linux.x86_64 ../PhyloCSF_Parameters resources
+	$(MAKE) -C src all
+
+clean:
+	$(MAKE) -C src clean
+
+test: all
+	test/test.sh
+
+.PHONY: all default clean test

DNAnexus/Readme.developer.md

@@ -0,0 +1,35 @@
+# PhyloCSF Developer Readme
+
+<!--
+TODO: Please edit this Readme.developer.md file to include information
+for developers or advanced users, for example:
+
+* Information about app internals and implementation details
+* How to report bugs or contribute to development
+-->
+
+## Running this app with additional computational resources
+
+This app has the following entry points:
+
+* main
+* process
+* postprocess
+
+When running this app, you can override the instance type to be used for each
+entry point by providing the ``systemRequirements`` field to
+```/applet-XXXX/run``` or ```/app-XXXX/run```, as follows:
+
+    {
+      systemRequirements: {
+        "main": {"instanceType": "dx_m1.large"},
+        "process": {"instanceType": "dx_m1.large"},
+        "postprocess": {"instanceType": "dx_m1.large"}
+      },
+      [...]
+    }
+
+See <a
+href="http://wiki.dnanexus.com/API-Specification-v1.0.0/IO-and-Run-Specifications#Run-Specification">Run
+Specification</a> in the API documentation for more information about the
+available instance types.

DNAnexus/Readme.md

@@ -0,0 +1,51 @@
+<!-- dx-header -->
+# PhyloCSF (DNAnexus Platform App)
+
+Phylogenetic analysis of multi-species genome sequence alignments to identify conserved protein-coding regions
+
+This is the source code for an app that runs on the DNAnexus Platform.
+For more information about how to run or modify it, see
+http://wiki.dnanexus.com/.
+<!-- /dx-header -->
+
+
+
+<!--
+TODO: This app directory was automatically generated by dx-app-wizard;
+please edit this Readme.md file to include essential documentation about
+your app that would be helpful to users. (Also see the
+Readme.developer.md.) Once you're done, you can remove these TODO
+comments.
+
+For more info, see http://wiki.dnanexus.com/Developer-Portal.
+-->
+
+<!--
+TODO: Fill in additional info about how to use each input and output
+below.
+-->
+
+## Inputs
+
+* **alignments** the ``CrossSpeciesAlignments`` to evaluate, usually generated by the MAF Stitcher app
+* **output_name** name of the output table
+* **alignments_per_job** controls the degree of parallelization
+* **species_set** usually auto-detected for alignments produced by the MAF Stitcher app
+* **frames** search over three or six reading frames
+* **orf** search over ORFs within each alignment
+* **min_codons** minimum length considered in ORF search mode (with ``orf != AsIs``)
+
+## Advanced Inputs
+
+* **strategy** model and parameter optimization strategy
+* **all_scores** report all scores computed (with ``frames != 1`` or ``orf != AsIs``)
+* **bls** include a Branch Length Score along with PhyloCSF score in output table
+* **anc_comp** include an ancestral composition score along with PhyloCSF score in output table
+* **dna** include evaluated DNA sequence in output table
+* **aa** include evaluated amino acid sequence in output table
+* **instance_type** instance type for parallel jobs
+
+## Outputs
+
+* **scores**
+* **errors** number of alignments without scores (see job log for details)

DNAnexus/dxapp.json

@@ -0,0 +1,137 @@
+{
+  "name": "PhyloCSF",
+  "title": "PhyloCSF",
+  "summary": "Phylogenetic analysis of multi-species genome sequence alignments to identify conserved protein-coding regions",
+  "dxapi": "1.0.0",
+  "version": "0.1.0",
+  "inputSpec": [
+    {
+      "name": "alignments",
+      "class": "gtable",
+      "type": "CrossSpeciesAlignments",
+      "optional": false,
+      "help": "Alignments to evaluate, usually generated by the MAF Stitcher app"
+    },
+    {
+      "name": "output_name",
+      "class": "string",
+      "optional": true,
+      "help": "Name of output table"
+    },
+    {
+      "name": "alignments_per_job",
+      "class": "int",
+      "optional": true,
+      "default": 500,
+      "help": "Degree of parallelization"
+    },
+    {
+      "name": "species_set",
+      "class": "string",
+      "choices": ["12flies", "29mammals"],
+      "optional": true,
+      "help": "Usually auto-detected for alignments produced by the MAF Stitcher app"
+    },
+    {
+      "name": "frames",
+      "class": "int",
+      "choices": [1,3,6],
+      "optional": true,
+      "default": 1,
+      "help": "Search over three or six reading frames"
+    },
+    {
+      "name": "orf",
+      "class": "string",
+      "choices": ["AsIs", "ATGStop", "StopStop", "StopStop3", "ToFirstStop", "FromLastStop", "ToOrFromStop"],
+      "optional": true,
+      "default": "AsIs",
+      "help": "Search over ORFs within each alignment (usually with frames=3 or frames=6)"
+    },
+    {
+      "name": "min_codons",
+      "class": "int",
+      "optional": true,
+      "default": 25,
+      "help": "Minimum length considered in ORF search mode (with orf != AsIs)"
+    },
+    {
+      "name": "strategy",
+      "class": "string",
+      "choices": ["mle", "fixed", "omega"],
+      "optional": true,
+      "default": "mle",
+      "group": "Advanced",
+      "help": "Model and parameter optimization strategy"
+    },
+    {
+      "name": "all_scores",
+      "class": "boolean",
+      "optional": true,
+      "default": false,
+      "group": "Advanced",
+      "help": "Report all scores computed (with frames != 1 or orf != AsIs)"
+    },
+    {
+      "name": "bls",
+      "class": "boolean",
+      "optional": true,
+      "default": false,
+      "group": "Advanced",
+      "help": "Include a Branch Length Score along with PhyloCSF score in output table"
+    },
+    {
+      "name": "anc_comp",
+      "class": "boolean",
+      "optional": true,
+      "default": false,
+      "group": "Advanced",
+      "help": "Include an ancestral composition score along with PhyloCSF score in output table"
+    },
+    {
+      "name": "dna",
+      "class": "boolean",
+      "optional": true,
+      "default": false,
+      "group": "Advanced",
+      "help": "Include evaluted DNA sequence in output table"
+    },
+    {
+      "name": "aa",
+      "class": "boolean",
+      "optional": true,
+      "default": false,
+      "group": "Advanced",
+      "help": "Include evaluated amino acid sequence in output table"
+    },
+    {
+      "name": "instance_type",
+      "class": "string",
+      "choices": ["dx_m1.large", "dx_c1.xlarge"],
+      "optional": true,
+      "group": "Advanced",
+      "help": "Instance type for parallel jobs"
+    }
+  ],
+  "outputSpec": [
+    {
+      "name": "scores",
+      "class": "gtable"
+    },
+    {
+      "name": "errors",
+      "class": "int"
+    }
+  ],
+  "runSpec": {
+    "interpreter": "bash",
+    "file": "src/run.sh",
+    "execDepends": [ {"name": "gsl-bin"} ]
+  },
+  "details": {
+    "upstreamUrl": "https://github.com/mlin/PhyloCSF",
+    "citations": [
+      "doi:10.1093/bioinformatics/btr209"
+    ]
+  }
+}

DNAnexus/src/Makefile

@@ -0,0 +1,12 @@
+all:
+	mkdir -p ../resources
+	$(MAKE) ../resources/dxPhyloCSF
+
+../resources/dxPhyloCSF: _tags dxPhyloCSF.ml
+	ocamlbuild -use-ocamlfind dxPhyloCSF.native
+	mkdir -p ../resources
+	cp -f dxPhyloCSF.native ../resources/dxPhyloCSF
+
+clean:
+	ocamlbuild -clean
+	rm -f ../resources/dxPhyloCSF

DNAnexus/src/_tags

@@ -0,0 +1,2 @@
+<*.ml{,i}>: pp(ocaml+twt)
+true: package(DNAnexus), package(forkwork), thread, debug