Bachelor:

- remove mappability and hotspot - fail if any input files are missing
hartwigmedical · Sep 24, 2019 · 86d9950 · 86d9950
1 parent a60f92b
commit 86d9950
Show file tree

Hide file tree

Showing 9 changed files with 19 additions and 22 deletions.
diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/BachelorApplication.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/BachelorApplication.java
@@ -53,7 +53,11 @@ private void run()
 
         if(!mConfig.IsBatchMode)
         {
-            mGermlineVcfParser.run(mConfig.GermlineVcf, mConfig.SampleId, mConfig.OutputDir);
+            if(!mGermlineVcfParser.run(mConfig.GermlineVcf, mConfig.SampleId, mConfig.OutputDir))
+            {
+                LOGGER.error("germline VCF parse failed");
+                return;
+            }
 
             final List<BachelorGermlineVariant> bachelorRecords = mGermlineVcfParser.getBachelorRecords();
             mVariantEnricher.run(bachelorRecords);

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/GermlineVariantDAO.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/GermlineVariantDAO.java
@@ -54,8 +54,6 @@ public void write(final String sampleId, final List<GermlineVariant> germlineVar
                 Tables.GERMLINEVARIANT.HGVSPROTEIN,
                 Tables.GERMLINEVARIANT.HGVSCODING,
                 Tables.GERMLINEVARIANT.BIALLELIC,
-                Tables.GERMLINEVARIANT.HOTSPOT,
-                Tables.GERMLINEVARIANT.MAPPABILITY,
                 Tables.GERMLINEVARIANT.MINORALLELEPLOIDY,
                 Tables.GERMLINEVARIANT.REFSTATUS,
                 Tables.GERMLINEVARIANT.MODIFIED);
@@ -86,8 +84,6 @@ public void write(final String sampleId, final List<GermlineVariant> germlineVar
                     variant.hgvsProtein(),
                     variant.hgvsCoding(),
                     variant.biallelic(),
-                    variant.hotspot(),
-                    DatabaseUtil.decimal(variant.mappability()),
                     DatabaseUtil.decimal(variant.minorAllelePloidy()),
                     variant.isHomozygous() ? "HOM" : "HET",
                     timestamp);

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/GermlineVcfParser.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/GermlineVcfParser.java
@@ -59,18 +59,18 @@ public static void addCmdLineOptions(Options options)
 
     public List<BachelorGermlineVariant> getBachelorRecords() { return mProgram.getVariants(); }
 
-    public void run(final String vcfFile, String sampleId, String singleSampleOutputDir)
+    public boolean run(final String vcfFile, String sampleId, String singleSampleOutputDir)
     {
         if (mConfig.ProgramConfigMap.isEmpty())
         {
             LOGGER.error("No programs loaded, exiting");
-            return;
+            return false;
         }
 
         if(!Files.exists(Paths.get(vcfFile)))
         {
             LOGGER.info("sampleId({}) germline VCF({}) not found", sampleId, vcfFile);
-            return;
+            return false;
         }
 
         LOGGER.info("sampleId({}) reading germline VCF({})", sampleId, vcfFile);
@@ -82,8 +82,9 @@ public void run(final String vcfFile, String sampleId, String singleSampleOutput
         if(mProgram.getVariants().isEmpty())
         {
             LOGGER.debug("no valid variants found");
-            return;
         }
+
+        return true;
     }
 
     private void processVCF(final String sampleId, final File vcf)

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/VariantEnricher.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/VariantEnricher.java
@@ -428,8 +428,6 @@ private final List<GermlineVariant> convert(final List<BachelorGermlineVariant>
                     .hgvsProtein(bachRecord.HgvsProtein)
                     .hgvsCoding(bachRecord.HgvsCoding)
                     .biallelic(bachRecord.isBiallelic())
-                    .hotspot(enrichedVariant.isHotspot())
-                    .mappability(enrichedVariant.mappability())
                     .minorAllelePloidy(enrichedVariant.minorAllelePloidy())
                     .program(bachRecord.Program)
                     .variantId(bachRecord.VariantId)

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/BachelorConfig.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/BachelorConfig.java
@@ -105,6 +105,12 @@ public BachelorConfig(final CommandLine cmd)
         OutputDir = sampleOutputDir;
 
         PurpleDataDir = cmd.getOptionValue(PURPLE_DATA_DIRECTORY, "");
+
+        if(GermlineVcf == null || BamFile == null || RefGenomeFile == null)
+        {
+            LOGGER.error("missing input files");
+            mIsValid = false;
+        }
     }
 
     public boolean isValid() { return mIsValid; }

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/GermlineVariant.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/GermlineVariant.java
@@ -31,8 +31,6 @@ public abstract class GermlineVariant
     public abstract String hgvsProtein();
     public abstract String hgvsCoding();
     public abstract boolean biallelic();
-    public abstract boolean hotspot();
-    public abstract double mappability();
     public abstract double minorAllelePloidy();
 
     // other fields

diff --git a/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/GermlineVariantFile.java b/bachelor/src/main/java/com/hartwig/hmftools/bachelor/types/GermlineVariantFile.java
@@ -79,8 +79,6 @@ private static String header() {
                 .add("hgvsProtein")
                 .add("hgvsCoding")
                 .add("biallelic")
-                .add("hotspot")
-                .add("mappability")
                 .add("minorAllelePloidy")
                 .add("program")
                 .add("variantId")
@@ -122,8 +120,6 @@ public static String toString(@NotNull final GermlineVariant data)
                 .add(String.valueOf(data.hgvsProtein()))
                 .add(String.valueOf(data.hgvsCoding()))
                 .add(String.valueOf(data.biallelic()))
-                .add(String.valueOf(data.hotspot()))
-                .add(String.valueOf(data.mappability()))
                 .add(String.valueOf(data.minorAllelePloidy()))
                 .add(String.valueOf(data.program()))
                 .add(String.valueOf(data.variantId()))
@@ -169,8 +165,6 @@ private static GermlineVariant fromString(@NotNull final String data)
                 .hgvsProtein(values[index++])
                 .hgvsCoding(values[index++])
                 .biallelic(Boolean.valueOf(values[index++]))
-                .hotspot(Boolean.valueOf(values[index++]))
-                .mappability(Double.valueOf(values[index++]))
                 .minorAllelePloidy(Double.valueOf(values[index++]))
                 .program(values[index++])
                 .variantId(values[index++])

diff --git a/patient-db/src/main/resources/generate_database.sql b/patient-db/src/main/resources/generate_database.sql
@@ -705,8 +705,6 @@ CREATE TABLE germlineVariant
     hgvsProtein varchar(255) NOT NULL,
     hgvsCoding varchar(255) NOT NULL,
     biallelic BOOLEAN NOT NULL,
-    hotspot BOOLEAN NOT NULL,
-    mappability DOUBLE PRECISION NOT NULL,
     minorAllelePloidy DOUBLE PRECISION NOT NULL,
     refStatus varchar(20) NOT NULL,
     PRIMARY KEY (id),

diff --git a/patient-db/src/main/resources/patches/bachelor_1.9.sql b/patient-db/src/main/resources/patches/bachelor_1.9.sql
@@ -1,3 +1,5 @@
 ALTER TABLE germlineVariant
     DROP COLUMN source,
-    DROP COLUMN program;
+    DROP COLUMN program,
+    DROP COLUMN hotspot,
+    DROP COLUMN mappability;