pre release changes (#127)

* pre release changes

* building docker images

* changing version in dockerfile

* automatic version_number population to Dockerfile

Docker/bdg-sequila/Dockerfile

@@ -8,10 +8,10 @@ RUN useradd -m tempuser
 # Spark related variables.
 ##COMPONENT_VERSION variable will be replaced during the build process
 
-ARG BDG_VERSION=0.4.1-SNAPSHOT
+ARG BDG_VERSION
 
 ####set variable used in all shell scritps for downloading jars
-ENV BDG_VERSION=0.4.1-SNAPSHOT
+ENV BDG_VERSION=$BDG_VERSION
 
 
 

Docker/bdg-sequila/version

@@ -1 +1 @@
-0.3-SNAPSHOT
+0.5

Jenkinsfile

@@ -138,7 +138,7 @@ node {
            stage('Building Docker images') {
 
                      echo 'Building Docker images....'
-                     //sh './build.sh'
+                     sh './build.sh'
 
                      }
 

build.sbt

@@ -2,7 +2,7 @@ import scala.util.Properties
 
 name := """bdg-sequila"""
 
-version := "0.4.1-SNAPSHOT"
+version := "0.5"
 
 organization := "org.biodatageeks"
 

build.sh

@@ -37,9 +37,9 @@ do
   #if [ $diffTs -lt $MAX_COMMIT_TS_DIFF ]; then
     cd $dir
      if [[ ${BUILD_MODE} != "local" ]]; then
-         docker build --no-cache -t $image:$version .
+         docker build --no-cache --build-arg BDG_VERSION=${version} -t $image:$version .
      else
-         docker build --no-cache  -t $image:$version .
+         docker build --no-cache --build-arg BDG_VERSION=${version} -t $image:$version .
      fi
     docker build  -t $image:latest .
     if [[ ${BUILD_MODE} != "local" ]]; then

docs/source/function/function.rst

@@ -254,7 +254,7 @@ bdg_coverage is a function that calculates depth of coverage for specified sampl
   
   //CALCULATE COVERAGE - FIXED LENGTH WINDOWS 
   
-  ss.sql(s"SELECT * FROM bdg_coverage('${tableNameBAM}','NA12878.chr21', '', 100)").show(5)
+  ss.sql(s"SELECT * FROM bdg_coverage('${tableNameBAM}','NA12878.chr21', 'blocks', 100)").show(5)
           +----------+-----+---+--------+
           |contigName|start|end|coverage|
           +----------+-----+---+--------+
@@ -267,8 +267,8 @@ bdg_coverage is a function that calculates depth of coverage for specified sampl
           +----------+-----+---+--------+
 
 Parameters for bdg_coverage functions:
-resultType - blocks/bases
-target - fixed-length windows/regions from bed file
+resultType - blocks or bases (blocks by default)
+target - size of fixed-length windows
 ShowAllPositions - true/false. When set to true returns all positions in contig.
 
 

docs/source/index.rst

@@ -6,16 +6,16 @@
 SeQuiLa User Guide 
 ====================
 
-SeQuiLa is an ANSI-SQL compliant solution for efficient genomic intervals querying and processing built on top of `Apache Spark`_. Range joins are bread and butter for NGS analysis but the high volume of data make them execute very slowly or even failing to compute.
+SeQuiLa is an ANSI-SQL compliant solution for efficient genomic intervals querying and processing built on top of `Apache Spark`_. Range joins and depth of coverage computations are bread and butter for NGS analysis but the high volume of data make them execute very slowly or even failing to compute.
 
 .. _Apache Spark: https://spark.apache.org/ 
 
 * SeQuiLa is fast:
 
-   - genome-wide analyses in several minutes
+   - genome-wide analyses in less than a minute (for depth of coverage calculations) and several minutes (for range joins)
    - 22x+ speedup over Spark default join operation
    - up to 100x+ speedup for interval queries for BAM datasource using indexes (>= 0.4.1)
-   - 100% accuracy in functional tests against GRanges
+   - 100% accuracy in functional tests against GRanges and samtools
 
 * SeQuiLa is elastic:
 
@@ -85,6 +85,11 @@ Example.scala
 
 .. rubric:: Release notes:
 
+0.5
+
+ - new result type (fixed lenght windows) for depth of coverage calculations
+
+
 0.4.1
 
  - a new highly-optimized  `mosdepth <https://github.com/brentp/mosdepth>`_ distributed implementation for depth of coverage calculations

src/test/scala/pl/edu/pw/ii/biodatageeks/tests/CoverageTestSuite.scala

@@ -86,7 +86,7 @@ class CoverageTestSuite extends FunSuite with DataFrameSuiteBase with BeforeAndA
     SequilaRegister.register(session)
 
     val windowLength = 100
-    val bdg = session.sql(s"SELECT * FROM bdg_coverage('${tableNameMultiBAM}','NA12878', '', '${windowLength}')")
+    val bdg = session.sql(s"SELECT * FROM bdg_coverage('${tableNameMultiBAM}','NA12878', 'blocks', '${windowLength}')")
 
     assert (bdg.count == 267)
     assert (bdg.first().getInt(1) % windowLength == 0) // check for fixed window start position