Merge branch 'master' into 1392_notes

Author: david4096

docs/installation.rst

@@ -62,8 +62,8 @@ Download and unpack the example data:
 
 .. code-block:: bash
 
-  $ wget https://github.com/ga4gh/server/releases/download/data/ga4gh-example-data-v4.3.tar
-  $ tar -xf ga4gh-example-data-v4.3.tar
+  $ wget https://github.com/ga4gh/server/releases/download/data/ga4gh-example-data-v4.5.tar
+  $ tar -xf ga4gh-example-data-v4.5.tar
 
 Create the WSGI file at ``/srv/ga4gh/application.wsgi`` and write the following
 contents:
@@ -190,13 +190,13 @@ If you already have a dataset on your machine, you can download and deploy the a
 
 .. code-block:: bash
 
-  $ docker run -e GA4GH_DATA_SOURCE=/data -v /my/ga4gh_data/:/data:ro -d -p 8000:80 --name ga4gh_server afirth/ga4gh-server:latest
+  $ docker run -e GA4GH_DATA_SOURCE=/data -v /my/ga4gh_data/:/data:ro -d -p 8000:80 --name ga4gh_server ga4gh/ga4gh-server:latest
 
 Replace ``/my/ga4gh_data/`` with the path to your data.
 
 This will:
 
-* pull the automatically built image from `Dockerhub <https://registry.hub.docker.com/u/afirth/ga4gh-server/>`_
+* pull the automatically built image from `Dockerhub <https://registry.hub.docker.com/u/ga4gh/ga4gh-server/>`_
 * start an apache server running mod_wsgi on container port 80
 * mount your data read-only to the docker container
 * assign a name to the container
@@ -210,7 +210,7 @@ If you do not have a dataset yet, you can deploy a container which includes the
 
 .. code-block:: bash
 
-  $ docker run -d -p 8000:80 --name ga4gh_demo afirth/ga4gh-server:develop-demo
+  $ docker run -d -p 8000:80 --name ga4gh_demo ga4gh/ga4gh-server:develop-demo
 
 This is identical to the production container, except that a copy of the demo data is included and appropriate defaults are set.
 
@@ -228,11 +228,11 @@ From the client, the server is accessible at ``http://server/``, and the ``/tmp/
 
   # start the server daemon
   # assumes the demo data on host at /my/ga4gh_data
-  $ docker run -e GA4GH_DEBUG=True -e GA4GH_DATA_SOURCE=/data -v /my/ga4gh_data/:/data:ro -d --name ga4gh_server afirth/ga4gh-server:latest
+  $ docker run -e GA4GH_DEBUG=True -e GA4GH_DATA_SOURCE=/data -v /my/ga4gh_data/:/data:ro -d --name ga4gh_server ga4gh/ga4gh-server:latest
 
   # start the client and drop into a bash shell, with mydev/ mounted read/write
   # --link adds a host entry for server, and --rm destroys the container when you exit
-  $ docker run -e GA4GH_DEBUG=True -v /tmp/mydev/:/app/mydev:rw -it --name ga4gh_client --link ga4gh_server:server --entrypoint=/bin/bash --rm afirth/ga4gh-server:latest
+  $ docker run -e GA4GH_DEBUG=True -v /tmp/mydev/:/app/mydev:rw -it --name ga4gh_client --link ga4gh_server:server --entrypoint=/bin/bash --rm ga4gh/ga4gh-server:latest
 
   # call the client code script
   root@md5:/app# ./mydev/demo_example.py
@@ -260,7 +260,7 @@ For more info on port forwarding see `the VirtualBox manual <https://www.virtual
 Advanced
 ++++++++
 
-If you want to build the images yourself, that is possible. The `afirth/ga4gh-server repo <https://registry.hub.docker.com/u/afirth/ga4gh-server/>`_
+If you want to build the images yourself, that is possible. The `ga4gh/ga4gh-server repo <https://registry.hub.docker.com/u/ga4gh/ga4gh-server/>`_
 builds automatically on new commits, so this is only needed if you want to modify the Dockerfiles, or build from a different source.
 
 The prod and demo builds are based off of `mod_wsgi-docker <https://github.com/GrahamDumpleton/mod_wsgi-docker>`_, a project from the author of mod_wsgi.
@@ -319,7 +319,7 @@ To enable DEBUG on your docker server, call docker run with ``-e GA4GH_DEBUG=Tru
 
 .. code-block:: bash
 
-  $ docker run -itd -p 8000:80 --name ga4gh_demo -e GA4GH_DEBUG=True afirth/ga4gh-server:develop-demo
+  $ docker run -itd -p 8000:80 --name ga4gh_demo -e GA4GH_DEBUG=True ga4gh/ga4gh-server:latest
 
 This will set the environment variable which is read by config.py
 

ga4gh/repo/rnaseq2ga.py

@@ -20,7 +20,7 @@ class RnaSqliteStore(object):
     def __init__(self, sqliteFileName):
         self._dbConn = sqlite3.connect(sqliteFileName)
         self._cursor = self._dbConn.cursor()
-        self._batchSize = 100
+        self._batchSize = 2000
         self._rnaValueList = []
         self._expressionValueList = []
 
@@ -109,16 +109,20 @@ def setUnits(self, units):
         elif units == "tpm":
             self._units = 2
 
-    def writeExpression(self, rnaQuantificationId, quantfilename):
+    def writeExpression(self, rnaQuantificationId, quantfilename,
+                        featureSetNames=None):
         """
         Reads the quantification results file and adds entries to the
         specified database.
         """
         isNormalized = self._isNormalized
         units = self._units
         featureSets = None
-        if self._dataset:
-            featureSets = self._dataset.getFeatureSets()
+        if self._dataset and featureSetNames:
+            featureSets = []
+            for annotationName in featureSetNames.split(","):
+                featureSets.append(
+                    self._dataset.getFeatureSetByName(annotationName))
         with open(quantfilename, "r") as quantFile:
             quantificationReader = csv.DictReader(quantFile, delimiter=b"\t")
             for expression in quantificationReader:
@@ -246,9 +250,10 @@ def writeRnaseqTable(rnaDB, analysisIds, description, annotationId,
     rnaDB.batchaddRNAQuantification()
 
 
-def writeExpressionTable(writer, data):
+def writeExpressionTable(writer, data, featureSetNames=None):
     for rnaQuantId, quantfilename in data:
-        writer.writeExpression(rnaQuantId, quantfilename)
+        writer.writeExpression(
+            rnaQuantId, quantfilename, featureSetNames=featureSetNames)
 
 
 def rnaseq2ga(quantificationFilename, sqlFilename, localName, rnaType,
@@ -291,4 +296,6 @@ def rnaseq2ga(quantificationFilename, sqlFilename, localName, rnaType,
                      featureSetIds,
                      readGroupId=readGroupIds, programs=programs,
                      bioSampleId=bioSampleId)
-    writeExpressionTable(writer, [(localName, quantificationFilename)])
+    writeExpressionTable(
+        writer, [(localName, quantificationFilename)],
+        featureSetNames=featureSetNames)