From 720fac7d8766e2aecd1920321d37daedc8e5e155 Mon Sep 17 00:00:00 2001
From: Manuel Holtgrewe <manuel.holtgrewe@bih-charite.de>
Date: Thu, 5 Oct 2023 10:13:57 +0200
Subject: [PATCH] feat: implement "seqvars ingest" command (#199)

---
 Cargo.lock                                    |   1 +
 Cargo.toml                                    |   1 +
 README.md                                     |  58 +++++++
 src/common.rs                                 |   8 +
 src/main.rs                                   |  23 +++
 src/seqvars/ingest/header.rs                  | 113 ++++++++++++++
 src/seqvars/ingest/mod.rs                     | 103 ++++++++++++
 ...e_dragen.07.021.624.3.10.4.vcf\".snap.new" | 124 +++++++++++++++
 ...e_dragen.07.021.624.3.10.9.vcf\".snap.new" | 146 ++++++++++++++++++
 ...er@\"example_gatk_hc.3.7-0.vcf\".snap.new" | 126 +++++++++++++++
 ...@\"example_gatk_hc.4.4.0.0.vcf\".snap.new" | 146 ++++++++++++++++++
 ...ample_dragen.07.021.624.3.10.4.vcf\".snap" |   7 +
 ...ample_dragen.07.021.624.3.10.9.vcf\".snap" |   7 +
 ...ample_dragen_07_021_624_3_10_9_vcf\".snap" |   7 +
 ..._guess@\"example_gatk_hc.3.7-0.vcf\".snap" |   7 +
 ...uess@\"example_gatk_hc.4.4.0.0.vcf\".snap" |   7 +
 src/seqvars/mod.rs                            |   1 +
 .../example_dragen.07.021.624.3.10.4.vcf      | 120 ++++++++++++++
 .../example_dragen.07.021.624.3.10.9.vcf      | 142 +++++++++++++++++
 .../seqvars/ingest/example_gatk_hc.3.7-0.vcf  | 122 +++++++++++++++
 .../ingest/example_gatk_hc.4.4.0.0.vcf        | 142 +++++++++++++++++
 21 files changed, 1411 insertions(+)
 create mode 100644 src/seqvars/ingest/header.rs
 create mode 100644 src/seqvars/ingest/mod.rs
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.4.vcf\".snap.new"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.9.vcf\".snap.new"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.3.7-0.vcf\".snap.new"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.4.4.0.0.vcf\".snap.new"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.4.vcf\".snap"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.9.vcf\".snap"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen_07_021_624_3_10_9_vcf\".snap"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.3.7-0.vcf\".snap"
 create mode 100644 "src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.4.4.0.0.vcf\".snap"
 create mode 100644 src/seqvars/mod.rs
 create mode 100644 tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf
 create mode 100644 tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf
 create mode 100644 tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf
 create mode 100644 tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf

diff --git a/Cargo.lock b/Cargo.lock
index ce5a457f..af28aa07 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -3442,6 +3442,7 @@ dependencies = [
  "log",
  "mehari",
  "multimap 0.9.0",
+ "noodles-vcf",
  "pretty_assertions",
  "procfs",
  "prost",
diff --git a/Cargo.toml b/Cargo.toml
index 376aaddc..bb31bb89 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -47,6 +47,7 @@ thousands = "0.2"
 tracing = "0.1"
 tracing-subscriber = "0.3"
 uuid = { version = "1.4", features = ["v4", "fast-rng", "serde"] }
+noodles-vcf = "0.40.0"
 
 
 [build-dependencies]
diff --git a/README.md b/README.md
index b0827246..f80d0da4 100644
--- a/README.md
+++ b/README.md
@@ -71,6 +71,64 @@ $ varfish-server-worker db mk-inhouse \
     [--path-input-tsvs @IN/path-list2.txt]
 ```
 
+## The `seqvars ingest` Command
+
+This command takes as the input a single VCF file from a (supported) variant caller and converts it into a file for further querying.
+The command interprets the following fields which are written out by the commonly used variant callers such as GATK UnifiedGenotyper, GATK HaplotypeCaller, and Illumina Dragen.
+
+- `FORMAT/AD` -- allelic depth, one value per allele (including reference0)
+- `FORMAT/DP` -- total read coverage
+- `FORMAT/GQ` -- genotype quality
+- `FORMAT/GT` -- genotype
+- `FORMAT/PID` -- physical phasing information as written out by GATK HaplotypeCaller in GVCF workflow
+- `FORMAT/PIS` -- physical phasing information as written out by Dragen variant caller
+    - this field fill be written as `FORMAT/PID`
+- `FORMAT/SQ` -- "somatic quality" for each alternate allele, as written out by Illumina Dragen variant caller
+    - this field will be written as `FORMAT/GQ`
+
+The `seqvars ingest` command will annotate the variants with the following information:
+
+- gnomAD genomes and exomes allele frequencies
+- gnomAD-mtDNA and HelixMtDb allele frequencies
+- functional annotation following the [VCF ANN field standard](https://pcingola.github.io/SnpEff/adds/VCFannotationformat_v1.0.pdf)
+
+The command will emit one output line for each variant allele from the input and each affected gene.
+That is, if two variant alleles affect two genes, four records will be written to the output file.
+The annotation will be written out for one highest impact.
+
+Overall, the command will emit the following header rows in addition to the `##contig=<ID=.,length=.>` lines.
+
+```
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##INFO=<ID=gnomad_exomes_an,Number=1,Type=Integer,Description="Number of samples in gnomAD exomes">
+##INFO=<ID=gnomad_exomes_hom,Number=1,Type=Integer,Description="Number of hom. alt. carriers in gnomAD exomes">
+##INFO=<ID=gnomad_exomes_het,Number=1,Type=Integer,Description="Number of het. alt. carriers in gnomAD exomes">
+##INFO=<ID=gnomad_exomes_hemi,Number=1,Type=Integer,Description="Number of hemi. alt. carriers in gnomAD exomes">
+##INFO=<ID=gnomad_genomes_an,Number=1,Type=Integer,Description="Number of samples in gnomAD genomes">
+##INFO=<ID=gnomad_genomes_hom,Number=1,Type=Integer,Description="Number of hom. alt. carriers in gnomAD genomes">
+##INFO=<ID=gnomad_genomes_het,Number=1,Type=Integer,Description="Number of het. alt. carriers in gnomAD genomes">
+##INFO=<ID=gnomad_genomes_hemi,Number=1,Type=Integer,Description="Number of hemi. alt. carriers in gnomAD genomes">
+##INFO=<ID=helix_an,Number=1,Type=Integer,Description="Number of samples in HelixMtDb">
+##INFO=<ID=helix_hom,Number=1,Type=Integer,Description="Number of hom. alt. carriers in HelixMtDb">
+##INFO=<ID=helix_het,Number=1,Type=Integer,Description="Number of het. alt. carriers in HelixMtDb">
+##INFO=<ID=ANN,Number=.,Type=String,Description="Functional annotations: 'Allele | Annotation | Annotation_Impact | Gene_Name | Gene_ID | Feature_Type | Feature_ID | Transcript_BioType | Rank | HGVS.c | HGVS.p | cDNA.pos / cDNA.length | CDS.pos / CDS.length | AA.pos / AA.length | Distance | ERRORS / WARNINGS / INFO'">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##x-varfish-version=<ID=varfish-server-worker,Version=x.y.z>
+##x-varfish-version=<ID=orig-caller,Name=Dragen,Version=SW: 07.021.624.3.10.9, HW: 07.021.624>
+##x-varfish-version=<ID=orig-caller,Name=GatkHaplotypeCaller,Version=4.4.0.0>
+```
+
+> [!NOTE]
+> The gnomad-mtDNA information is written to the `INFO/gnomdad_genome_*` fields.
+
+> [!NOTE]
+> Future versions of the worker will annotate the worst effect on a MANE select or MANE Clinical transcript.
+
 # Developer Information
 
 This section is only relevant for developers of `varfish-server-worker`.
diff --git a/src/common.rs b/src/common.rs
index 33dea389..fee69574 100644
--- a/src/common.rs
+++ b/src/common.rs
@@ -23,6 +23,14 @@ pub struct Args {
     pub verbose: Verbosity<InfoLevel>,
 }
 
+impl Default for Args {
+    fn default() -> Self {
+        Self {
+            verbose: Verbosity::new(0, 0),
+        }
+    }
+}
+
 /// Helper to print the current memory resident set size via `tracing`.
 pub fn trace_rss_now() {
     let me = procfs::process::Process::myself().unwrap();
diff --git a/src/main.rs b/src/main.rs
index fc2103c6..6ea9bca6 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -2,6 +2,7 @@
 
 pub mod common;
 pub mod db;
+pub mod seqvars;
 pub mod sv;
 
 use clap::{Args, Parser, Subcommand};
@@ -33,6 +34,8 @@ enum Commands {
     Db(Db),
     /// SV filtration related commands.
     Sv(Sv),
+    /// Sequence variant related commands.
+    Seqvars(Seqvars),
 }
 
 /// Parsing of "db *" sub commands.
@@ -67,6 +70,21 @@ enum SvCommands {
     Query(sv::query::Args),
 }
 
+/// Parsing of "seqvars *" sub commands.
+#[derive(Debug, Args)]
+#[command(args_conflicts_with_subcommands = true)]
+struct Seqvars {
+    /// The sub command to run
+    #[command(subcommand)]
+    command: SeqvarsCommands,
+}
+
+/// Enum supporting the parsing of "sv *" sub commands.
+#[derive(Debug, Subcommand)]
+enum SeqvarsCommands {
+    Ingest(seqvars::ingest::Args),
+}
+
 fn main() -> Result<(), anyhow::Error> {
     let cli = Cli::parse();
 
@@ -98,6 +116,11 @@ fn main() -> Result<(), anyhow::Error> {
                     db::to_bin::cli::run(&cli.common, args)?;
                 }
             },
+            Commands::Seqvars(seqvars) => match &seqvars.command {
+                SeqvarsCommands::Ingest(args) => {
+                    seqvars::ingest::run(&cli.common, args)?;
+                }
+            },
             Commands::Sv(sv) => match &sv.command {
                 SvCommands::Query(args) => {
                     sv::query::run(&cli.common, args)?;
diff --git a/src/seqvars/ingest/header.rs b/src/seqvars/ingest/header.rs
new file mode 100644
index 00000000..6f2c51e3
--- /dev/null
+++ b/src/seqvars/ingest/header.rs
@@ -0,0 +1,113 @@
+use noodles_vcf as vcf;
+
+use crate::common::GenomeRelease;
+
+/// Enumeration for the known variant callers.
+#[derive(Debug, Clone, PartialEq, Eq, serde::Deserialize, serde::Serialize)]
+pub enum VariantCaller {
+    GatkHaplotypeCaller { version: String },
+    GatkUnifiedGenotyper { version: String },
+    Dragen { version: String },
+    Other,
+}
+
+impl VariantCaller {
+    pub fn guess(header: &vcf::Header) -> Option<Self> {
+        for (other, collection) in header.other_records() {
+            if other.as_ref().starts_with("GATKCommandLine")
+                || other.as_ref().starts_with("DRAGENCommandLine")
+            {
+                use vcf::header::record::value::collection::Collection;
+                if let Collection::Structured(map) = collection {
+                    for (key, values) in map.iter() {
+                        if let ("HaplotypeCaller", Some(version)) =
+                            (key.as_str(), values.other_fields().get("Version").cloned())
+                        {
+                            return Some(VariantCaller::GatkHaplotypeCaller { version });
+                        }
+                        if let ("UnifiedGenotyper", Some(version)) =
+                            (key.as_str(), values.other_fields().get("Version").cloned())
+                        {
+                            return Some(VariantCaller::GatkUnifiedGenotyper { version });
+                        }
+                        if let ("dragen", Some(version)) =
+                            (key.as_str(), values.other_fields().get("Version").cloned())
+                        {
+                            return Some(VariantCaller::Dragen { version });
+                        }
+                    }
+                }
+            }
+        }
+        None
+    }
+}
+
+/// Generate the output header from the input header.
+pub fn build_output_header(
+    input_header: &vcf::Header,
+    genomebuild: GenomeRelease,
+) -> Result<vcf::Header, anyhow::Error> {
+    let variant_caller = VariantCaller::guess(input_header)
+        .ok_or_else(|| anyhow::anyhow!("Unable to guess variant caller"))?;
+    todo!()
+}
+
+#[cfg(test)]
+mod test {
+    use rstest::rstest;
+
+    use super::VariantCaller;
+
+    macro_rules! set_snapshot_suffix {
+        ($($expr:expr),*) => {
+            let mut settings = insta::Settings::clone_current();
+            settings.set_snapshot_suffix(format!($($expr,)*));
+            let _guard = settings.bind_to_scope();
+        }
+    }
+
+    #[rstest]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf")]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf")]
+    fn variant_caller_guess(#[case] path: &str) -> Result<(), anyhow::Error> {
+        set_snapshot_suffix!("{:?}", path.split('/').last().unwrap());
+
+        let vcf_header = noodles_vcf::reader::Builder::default()
+            .build_from_path(path)?
+            .read_header()?;
+
+        insta::assert_yaml_snapshot!(VariantCaller::guess(&vcf_header));
+
+        Ok(())
+    }
+
+    #[rstest]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf")]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf")]
+    fn build_output_header(#[case] path: &str) -> Result<(), anyhow::Error> {
+        set_snapshot_suffix!("{:?}", path.split('/').last().unwrap());
+        let tmpdir = temp_testdir::TempDir::default();
+
+        let input_vcf_header = noodles_vcf::reader::Builder::default()
+            .build_from_path(path)?
+            .read_header()?;
+        let output_vcf_header =
+            super::build_output_header(&input_vcf_header, crate::common::GenomeRelease::Grch37)?;
+
+        let out_path = tmpdir.join("out.vcf");
+        let out_path_str = out_path.to_str().expect("invalid path");
+        {
+            noodles_vcf::writer::Writer::new(std::fs::File::create(out_path_str)?)
+                .write_header(&input_vcf_header)?;
+        }
+
+        insta::assert_snapshot!(std::fs::read_to_string(out_path_str)?);
+
+        Ok(())
+    }
+}
diff --git a/src/seqvars/ingest/mod.rs b/src/seqvars/ingest/mod.rs
new file mode 100644
index 00000000..bd487577
--- /dev/null
+++ b/src/seqvars/ingest/mod.rs
@@ -0,0 +1,103 @@
+//! Implementation of `seqvars ingest` subcommand.
+
+use crate::common::{self, GenomeRelease};
+use noodles_vcf as vcf;
+
+pub mod header;
+
+/// Command line arguments for `seqvars ingest` subcommand.
+#[derive(Debug, clap::Parser)]
+#[command(author, version, about = "ingest sequence variant VCF", long_about = None)]
+pub struct Args {
+    /// The assumed genome build.
+    #[clap(long)]
+    pub genomebuild: GenomeRelease,
+    /// Path to input file.
+    #[clap(long)]
+    pub path_in: String,
+    /// Path to output file.
+    #[clap(long)]
+    pub path_out: String,
+}
+
+/// Main entry point for `seqvars ingest` sub command.
+pub fn run(args_common: &crate::common::Args, args: &Args) -> Result<(), anyhow::Error> {
+    let before_anything = std::time::Instant::now();
+    tracing::info!("args_common = {:#?}", &args_common);
+    tracing::info!("args = {:#?}", &args);
+
+    common::trace_rss_now();
+
+    tracing::info!("opening input file...");
+    let mut input_reader = {
+        let file = std::fs::File::open(&args.path_in)
+            .map_err(|e| anyhow::anyhow!("could not open input file {}: {}", &args.path_in, e))
+            .map(std::io::BufReader::new)?;
+        vcf::reader::Builder::default()
+            .build_from_reader(file)
+            .map_err(|e| anyhow::anyhow!("could not build VCF reader: {}", e))?
+    };
+
+    tracing::info!("analyzing header...");
+    let input_header = input_reader
+        .read_header()
+        .map_err(|e| anyhow::anyhow!("problem reading VCF header: {}", e))?;
+    let output_header = header::build_output_header(&input_header, args.genomebuild)?;
+
+    let mut output_writer = {
+        let writer = std::fs::File::create(&args.path_out).map_err(|e| {
+            anyhow::anyhow!(
+                "could not output file for writing {}: {}",
+                &args.path_out,
+                e
+            )
+        })?;
+        let writer = std::io::BufWriter::new(writer);
+        vcf::writer::Writer::new(writer)
+    };
+    output_writer.write_header(&output_header)?;
+
+    tracing::info!(
+        "All of `seqvars ingest` completed in {:?}",
+        before_anything.elapsed()
+    );
+    Ok(())
+}
+
+#[cfg(test)]
+mod test {
+    use rstest::rstest;
+
+    use crate::common::GenomeRelease;
+
+    macro_rules! set_snapshot_suffix {
+        ($($expr:expr),*) => {
+            let mut settings = insta::Settings::clone_current();
+            settings.set_snapshot_suffix(format!($($expr,)*));
+            let _guard = settings.bind_to_scope();
+        }
+    }
+
+    #[rstest]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf")]
+    #[case("tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf")]
+    #[case("tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf")]
+    fn smoke_test_run(#[case] path: &str) {
+        set_snapshot_suffix!("{:?}", path.split('/').last().unwrap().replace(".", "_"));
+
+        let tmpdir = temp_testdir::TempDir::default();
+
+        let args_common = Default::default();
+        let args = super::Args {
+            genomebuild: GenomeRelease::Grch37,
+            path_in: path.into(),
+            path_out: tmpdir
+                .join("out.vcf")
+                .to_str()
+                .expect("invalid path")
+                .into(),
+        };
+        super::run(&args_common, &args).unwrap();
+    }
+}
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.4.vcf\".snap.new" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.4.vcf\".snap.new"
new file mode 100644
index 00000000..84098cd4
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.4.vcf\".snap.new"
@@ -0,0 +1,124 @@
+---
+source: src/seqvars/ingest/header.rs
+assertion_line: 107
+expression: "std::fs::read_to_string(out_path_str)?"
+---
+##fileformat=VCFv4.2
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (informative and non-informative); some reads may have been filtered based on mapq etc.">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FractionInformativeReads,Number=1,Type=Float,Description="The fraction of informative reads out of the total reads">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths (counting only informative reads out of the total reads) for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions for alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GP,Number=G,Type=Float,Description="Phred-scaled posterior probabilities for genotypes as defined in the VCF specification">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MB,Number=4,Type=Integer,Description="Per-sample component statistics to detect mate bias">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PRI,Number=G,Type=Float,Description="Phred-scaled prior probabilities for genotypes">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias">
+##FORMAT=<ID=SQ,Number=A,Type=Float,Description="Somatic quality">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##DRAGENCommandLine=<ID=HashTableBuild,Version="SW: 01.003.044.3.10.4, HashTableVersion: 8",CommandLineOptions="dragen --build-hash-table true --ht-reference /staging/human/reference/hs37d5/hs37d5.fa --output-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --ht-num-threads 32 --ht-seed-len 21 --enable-cnv true">
+##DRAGENCommandLine=<ID=dragen,Version="SW: 07.021.624.3.10.4, HW: 07.021.624",Date="Mon Mar 21 19:12:18 CET 2022",CommandLineOptions="--ref-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --fastq-file1 /mnt/smb01-hum/NGSRawData/220318_A01077_0174_AH7JGVDMXY/Data/Intensities/BaseCalls/NA-12878WGS-Genom-size_S1_R1_001.fastq.gz --fastq-file2 /mnt/smb01-hum/NGSRawData/220318_A01077_0174_AH7JGVDMXY/Data/Intensities/BaseCalls/NA-12878WGS-Genom-size_S1_R2_001.fastq.gz --output-directory /staging/output/220318_A01077_0174_AH7JGVDMXY/NA-12878WGSWGS/ --output-file-prefix NA-12878WGSWGS_dragen --RGID WGS --RGSM NA-12878WGSWGS --num-threads 46 --enable-map-align true --enable-map-align-output true --enable-duplicate-marking true --enable-variant-caller true --qc-cross-cont-vcf /opt/edico/config/sample_cross_contamination_resource_GRCh37.vcf.gz --enable-cnv true --cnv-enable-self-normalization true --enable-sv true --qc-coverage-region-1 /staging/human/bed/CDS-v19-ROIs_v2.bed --qc-coverage-reports-1 cov_report full_res --qc-coverage-region-2 /staging/human/bed/Regions_Exomev8.bed --qc-coverage-reports-2 cov_report full_res --qc-coverage-region-3 /staging/human/bed/Padded_Exomev8.bed --qc-coverage-reports-3 cov_report full_res">
+##reference=file:///staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149/reference.bin
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA12878
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.9.vcf\".snap.new" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.9.vcf\".snap.new"
new file mode 100644
index 00000000..bd9f112c
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_dragen.07.021.624.3.10.9.vcf\".snap.new"
@@ -0,0 +1,146 @@
+---
+source: src/seqvars/ingest/header.rs
+assertion_line: 107
+expression: "std::fs::read_to_string(out_path_str)?"
+---
+##fileformat=VCFv4.2
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (informative and non-informative); some reads may have been filtered based on mapq etc.">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FractionInformativeReads,Number=1,Type=Float,Description="The fraction of informative reads out of the total reads">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##FILTER=<ID=DRAGENSnpHardQUAL,Description="Set if true:QUAL < 10.41">
+##FILTER=<ID=DRAGENIndelHardQUAL,Description="Set if true:QUAL < 7.83">
+##FILTER=<ID=LowDepth,Description="Set if true:DP <= 1">
+##FILTER=<ID=LowGQ,Description="Set if true:GQ = 0">
+##FILTER=<ID=PloidyConflict,Description="Genotype call from variant caller not consistent with chromosome ploidy">
+##FILTER=<ID=base_quality,Description="Site filtered because median base quality of alt reads at this locus does not meet threshold">
+##FILTER=<ID=filtered_reads,Description="Site filtered because too large a fraction of reads have been filtered out">
+##FILTER=<ID=fragment_length,Description="Site filtered because absolute difference between the median fragment length of alt reads and median fragment length of ref reads at this locus exceeds threshold">
+##FILTER=<ID=low_depth,Description="Site filtered because the read depth is too low">
+##FILTER=<ID=low_frac_info_reads,Description="Site filtered because the fraction of informative reads is below threshold">
+##FILTER=<ID=low_normal_depth,Description="Site filtered because the normal sample read depth is too low">
+##FILTER=<ID=long_indel,Description="Site filtered because the indel length is too long">
+##FILTER=<ID=mapping_quality,Description="Site filtered because median mapping quality of alt reads at this locus does not meet threshold">
+##FILTER=<ID=multiallelic,Description="Site filtered because more than two alt alleles pass tumor LOD">
+##FILTER=<ID=non_homref_normal,Description="Site filtered because the normal sample genotype is not homozygous reference">
+##FILTER=<ID=no_reliable_supporting_read,Description="Site filtered because no reliable supporting somatic read exists">
+##FILTER=<ID=panel_of_normals,Description="Seen in at least one sample in the panel of normals vcf">
+##FILTER=<ID=read_position,Description="Site filtered because median of distances between start/end of read and this locus is below threshold">
+##FILTER=<ID=RMxNRepeatRegion,Description="Site filtered because all or part of the variant allele is a repeat of the reference">
+##FILTER=<ID=str_contraction,Description="Site filtered due to suspected PCR error where the alt allele is one repeat unit less than the reference">
+##FILTER=<ID=too_few_supporting_reads,Description="Site filtered because there are too few supporting reads in the tumor sample">
+##FILTER=<ID=weak_evidence,Description="Somatic variant score does not meet threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths (counting only informative reads out of the total reads) for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions for alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GP,Number=G,Type=Float,Description="Phred-scaled posterior probabilities for genotypes as defined in the VCF specification">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MB,Number=4,Type=Integer,Description="Per-sample component statistics to detect mate bias">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PRI,Number=G,Type=Float,Description="Phred-scaled prior probabilities for genotypes">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias">
+##FORMAT=<ID=SQ,Number=A,Type=Float,Description="Somatic quality">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##DRAGENCommandLine=<ID=HashTableBuild,Version="SW: 01.003.044.3.10.4, HashTableVersion: 8",CommandLineOptions="dragen --build-hash-table true --ht-reference /staging/human/reference/hs37d5/hs37d5.fa --output-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --ht-num-threads 32 --ht-seed-len 21 --enable-cnv true">
+##DRAGENCommandLine=<ID=dragen,Version="SW: 07.021.624.3.10.9, HW: 07.021.624",Date="Fri Sep 15 14:27:23 CEST 2023",CommandLineOptions="--ref-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --fastq-file1 /data/CASE_R1_001.fastq.gz --fastq-file2 /data/CASE_R2_001.fastq.gz --output-directory /data/CASE/ --output-file-prefix CASE_dragen --RGID WGS --RGSM CASE --RGLB CASE --num-threads 46 --enable-map-align true --enable-map-align-output true --enable-duplicate-marking true --generate-sa-tags true --generate-zs-tags true --vc-output-evidence-bam true --vc-evidence-bam-output-haplotypes true --vc-evidence-bam-force-output true --enable-variant-caller true --vc-emit-ref-confidence gvcf --vc-enable-vcf-output true --qc-cross-cont-vcf /opt/edico/config/sample_cross_contamination_resource_GRCh37.vcf.gz --enable-cnv true --cnv-enable-self-normalization true --enable-sv true --enable-cyp2d6 false --repeat-genotype-enable true --repeat-genotype-specs /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/expansionhunter/GRCh37_edico+stripy+smn.json --enable-hla false --enable-smn false --qc-coverage-ignore-overlaps true --qc-coverage-region-1 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/padded_agilentv8_MT.bed --qc-coverage-reports-1 cov_report full_res --qc-coverage-filters-1 mapq<1,bq<0 --qc-coverage-region-2 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/difficult_regions.bed --qc-coverage-reports-2 cov_report full_res --qc-coverage-filters-2 mapq<1,bq<0 --qc-coverage-region-3 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/padded_agilentv8_MT.bed --qc-coverage-reports-3 cov_report full_res --qc-coverage-filters-3 mapq<0,bq<0">
+##reference=file:///staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149/reference.bin
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CASE
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.3.7-0.vcf\".snap.new" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.3.7-0.vcf\".snap.new"
new file mode 100644
index 00000000..371c8640
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.3.7-0.vcf\".snap.new"
@@ -0,0 +1,126 @@
+---
+source: src/seqvars/ingest/header.rs
+assertion_line: 107
+expression: "std::fs::read_to_string(out_path_str)?"
+---
+##fileformat=VCFv4.2
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##GATKCommandLine.HaplotypeCaller=<ID=HaplotypeCaller,Version="3.7-0-gcfedb67",Date="Fri Aug 26 20:52:06 CEST 2022",Epoch="1661539926702",CommandLineOptions="analysis_type=HaplotypeCaller input_file=[/fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_index-N1-DNA1-WGS1/out/bwa.Case_1_index-N1-DNA1-WGS1.bam, /fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_father-N1-DNA1-WGS1/out/bwa.Case_1_father-N1-DNA1-WGS1.bam, /fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_mother-N1-DNA1-WGS1/out/bwa.Case_1_mother-N1-DNA1-WGS1.bam] showFullBamList=false read_buffer_size=null read_filter=[] disable_read_filter=[] intervals=[1:1-5,010,000] excludeIntervals=null interval_set_rule=UNION interval_merging=ALL interval_padding=0 reference_sequence=/fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa nonDeterministicRandomSeed=false disableDithering=false maxRuntime=-1 maxRuntimeUnits=MINUTES downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=500 baq=OFF baqGapOpenPenalty=40.0 refactor_NDN_cigar_string=false fix_misencoded_quality_scores=false allow_potentially_misencoded_quality_scores=false useOriginalQualities=false defaultBaseQualities=-1 performanceLog=null BQSR=null quantize_quals=0 static_quantized_quals=null round_down_quantized=false disable_indel_quals=false emit_original_quals=false preserve_qscores_less_than=6 globalQScorePrior=-1.0 secondsBetweenProgressUpdates=10 validation_strictness=SILENT remove_program_records=false keep_program_records=false sample_rename_mapping_file=null unsafe=null disable_auto_index_creation_and_locking_when_reading_rods=false no_cmdline_in_header=false sites_only=false never_trim_vcf_format_field=false bcf=false bam_compression=null simplifyBAM=false disable_bam_indexing=false generate_md5=false num_threads=1 num_cpu_threads_per_data_thread=1 num_io_threads=0 monitorThreadEfficiency=false num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false generateShadowBCF=false variant_index_type=DYNAMIC_SEEK variant_index_parameter=-1 reference_window_stop=0 phone_home= gatk_key=null tag=NA logging_level=INFO log_to_file=null help=false version=false out=/data/gpfs-1/users/holtgrem_c/scratch/tmp/tmp.uG5Q6d0QYe/tmp.vcf.gz likelihoodCalculationEngine=PairHMM heterogeneousKmerSizeResolution=COMBO_MIN dbsnp=(RodBinding name=dbsnp source=/fast/projects/cubit/current/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz) dontTrimActiveRegions=false maxDiscARExtension=25 maxGGAARExtension=300 paddingAroundIndels=150 paddingAroundSNPs=20 comp=[] annotation=[] excludeAnnotation=[] group=[StandardAnnotation, StandardHCAnnotation] debug=false useFilteredReadsForAnnotations=false emitRefConfidence=NONE bamOutput=null bamWriterType=CALLED_HAPLOTYPES emitDroppedReads=false disableOptimizations=false annotateNDA=false useNewAFCalculator=false heterozygosity=0.001 indel_heterozygosity=1.25E-4 heterozygosity_stdev=0.01 standard_min_confidence_threshold_for_calling=10.0 standard_min_confidence_threshold_for_emitting=30.0 max_alternate_alleles=6 max_genotype_count=1024 max_num_PL_values=100 input_prior=[] sample_ploidy=2 genotyping_mode=DISCOVERY alleles=(RodBinding name= source=UNBOUND) contamination_fraction_to_filter=0.0 contamination_fraction_per_sample_file=null p_nonref_model=null exactcallslog=null output_mode=EMIT_VARIANTS_ONLY allSitePLs=false gcpHMM=10 pair_hmm_implementation=VECTOR_LOGLESS_CACHING pair_hmm_sub_implementation=ENABLE_ALL always_load_vector_logless_PairHMM_lib=false phredScaledGlobalReadMismappingRate=45 noFpga=false sample_name=null kmerSize=[10, 25] dontIncreaseKmerSizesForCycles=false allowNonUniqueKmersInRef=false numPruningSamples=1 recoverDanglingHeads=false doNotRecoverDanglingBranches=false minDanglingBranchLength=4 consensus=false maxNumHaplotypesInPopulation=128 errorCorrectKmers=false minPruning=3 debugGraphTransformations=false allowCyclesInKmerGraphToGeneratePaths=false graphOutput=null kmerLengthForReadErrorCorrection=25 minObservationsForKmerToBeSolid=20 GVCFGQBands=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 70, 80, 90, 99] indelSizeToEliminateInRefModel=10 min_base_quality_score=10 includeUmappedReads=false useAllelesTrigger=false doNotRunPhysicalPhasing=true keepRG=null justDetermineActiveRegions=false dontGenotype=false dontUseSoftClippedBases=false captureAssemblyFailureBAM=false errorCorrectReads=false pcr_indel_model=CONSERVATIVE maxReadsInRegionPerSample=10000 minReadsPerAlignmentStart=10 mergeVariantsViaLD=false activityProfileOut=null activeRegionOut=null activeRegionIn=null activeRegionExtension=null forceActive=false activeRegionMaxSize=null bandPassSigma=null maxReadsInMemoryPerSample=30000 maxTotalReadsInMemory=10000000 maxProbPropagationDistance=50 activeProbabilityThreshold=0.002 min_mapping_quality_score=20 filter_reads_with_N_cigar=false filter_mismatching_base_and_quals=false filter_bases_not_stored=false">
+##reference=file:///fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa
+##SAMPLE=<ID=Case_1_index-N1-DNA1-WGS1,Sex="Male",Disease="Affected">
+##SAMPLE=<ID=Case_1_father-N1-DNA1-WGS1,Sex="Male",Disease="Unaffected">
+##SAMPLE=<ID=Case_1_mother-N1-DNA1-WGS1,Sex="Female",Disease="Unaffected">
+##PEDIGREE=<ID=Case_1_index-N1-DNA1-WGS1,Family="FAM_Case_1_index",Father="Case_1_father-N1-DNA1-WGS1",Mother="Case_1_mother-N1-DNA1-WGS1">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Case_1_father-N1-DNA1-WGS1	Case_1_index-N1-DNA1-WGS1	Case_1_mother-N1-DNA1-WGS1
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.4.4.0.0.vcf\".snap.new" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.4.4.0.0.vcf\".snap.new"
new file mode 100644
index 00000000..40ff83e8
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__build_output_header@\"example_gatk_hc.4.4.0.0.vcf\".snap.new"
@@ -0,0 +1,146 @@
+---
+source: src/seqvars/ingest/header.rs
+assertion_line: 107
+expression: "std::fs::read_to_string(out_path_str)?"
+---
+##fileformat=VCFv4.2
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AS_BaseQRankSum,Number=A,Type=Float,Description="allele specific Z-score from Wilcoxon rank sum test of each Alt Vs. Ref base qualities">
+##INFO=<ID=AS_FS,Number=A,Type=Float,Description="allele specific phred-scaled p-value using Fisher's exact test to detect strand bias of each alt allele">
+##INFO=<ID=AS_InbreedingCoeff,Number=A,Type=Float,Description="Allele-specific inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=AS_MQ,Number=A,Type=Float,Description="Allele-specific RMS Mapping Quality">
+##INFO=<ID=AS_MQRankSum,Number=A,Type=Float,Description="Allele-specific Mapping Quality Rank Sum">
+##INFO=<ID=AS_QD,Number=A,Type=Float,Description="Allele-specific Variant Confidence/Quality by Depth">
+##INFO=<ID=AS_RAW_BaseQRankSum,Number=1,Type=String,Description="raw data for allele specific rank sum test of base qualities">
+##INFO=<ID=AS_RAW_MQ,Number=1,Type=String,Description="Allele-specfic raw data for RMS Mapping Quality">
+##INFO=<ID=AS_RAW_MQRankSum,Number=1,Type=String,Description="Allele-specfic raw data for Mapping Quality Rank Sum">
+##INFO=<ID=AS_RAW_ReadPosRankSum,Number=1,Type=String,Description="allele specific raw data for rank sum test of read position bias">
+##INFO=<ID=AS_ReadPosRankSum,Number=A,Type=Float,Description="allele specific Z-score from Wilcoxon rank sum test of each Alt vs. Ref read position bias">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_SOR,Number=A,Type=Float,Description="Allele specific strand Odds Ratio of 2x|Alts| contingency table to detect allele specific strand bias">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=RAW_MQandDP,Number=2,Type=Integer,Description="Raw data (sum of squared MQ and total depth) for improved RMS Mapping Quality calculation. Incompatible with deprecated RAW_MQ formulation.">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum DP observed within the GVCF block">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=RGQ,Number=1,Type=Integer,Description="Unconditional reference genotype confidence, encoded as a phred quality -10*log10 p(genotype call is wrong)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##ALT=<ID=*,Description="Represents any possible alternative allele not already represented at this location by REF and ALT">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##GATKCommandLine=<ID=CombineGVCFs,CommandLine="CombineGVCFs --output /data/CASE.g.vcf.gz --break-bands-at-multiples-of 10000000 --variant /data/CASE.g.vcf.gz --intervals 1:1-10000000 --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --annotation-group AlleleSpecificAnnotation --convert-to-base-pair-resolution false --input-is-somatic false --drop-somatic-filtering-annotations false --call-genotypes false --ignore-variants-starting-outside-interval false --combine-variants-distance 0 --max-distance 2147483647 --ref-padding 1 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 2:23:49 AM CEST">
+##GATKCommandLine=<ID=GenotypeGVCFs,CommandLine="GenotypeGVCFs --output /data/CASE.g.vcf.gz --variant /data/CASE.g.vcf.gz --intervals 1:1-10000000 --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --include-non-variant-sites false --merge-input-intervals false --input-is-somatic false --tumor-lod-to-emit 3.5 --allele-fraction-error 0.001 --keep-combined-raw-annotations false --use-posteriors-to-calculate-qual false --dont-use-dragstr-priors false --use-new-qual-calculator true --annotate-with-num-discovered-alleles false --heterozygosity 0.001 --indel-heterozygosity 1.25E-4 --heterozygosity-stdev 0.01 --standard-min-confidence-threshold-for-calling 30.0 --max-alternate-alleles 6 --max-genotype-count 1024 --sample-ploidy 2 --num-reference-samples-if-no-call 0 --genotype-assignment-method USE_PLS_TO_ASSIGN --genomicsdb-max-alternate-alleles 50 --call-genotypes false --genomicsdb-use-bcf-codec false --genomicsdb-shared-posixfs-optimizations false --genomicsdb-use-gcs-hdfs-connector false --only-output-calls-starting-in-intervals false --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 2:40:40 AM CEST">
+##GATKCommandLine=<ID=HaplotypeCaller,CommandLine="HaplotypeCaller --dbsnp /fast/projects/cubit/20.05/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz --emit-ref-confidence GVCF --output /data/CASE.g.vcf.gz --intervals 1:1-10000000 --input /data/CASE.bam --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --annotation-group AlleleSpecificAnnotation --use-posteriors-to-calculate-qual false --dont-use-dragstr-priors false --use-new-qual-calculator true --annotate-with-num-discovered-alleles false --heterozygosity 0.001 --indel-heterozygosity 1.25E-4 --heterozygosity-stdev 0.01 --standard-min-confidence-threshold-for-calling 30.0 --max-alternate-alleles 6 --max-genotype-count 1024 --sample-ploidy 2 --num-reference-samples-if-no-call 0 --genotype-assignment-method USE_PLS_TO_ASSIGN --contamination-fraction-to-filter 0.0 --output-mode EMIT_VARIANTS_ONLY --all-site-pls false --flow-likelihood-parallel-threads 0 --flow-likelihood-optimized-comp false --flow-use-t0-tag false --flow-probability-threshold 0.003 --flow-remove-non-single-base-pair-indels false --flow-remove-one-zero-probs false --flow-quantization-bins 121 --flow-fill-empty-bins-value 0.001 --flow-symmetric-indel-probs false --flow-report-insertion-or-deletion false --flow-disallow-probs-larger-than-call false --flow-lump-probs false --flow-retain-max-n-probs-base-format false --flow-probability-scaling-factor 10 --flow-order-cycle-length 4 --flow-number-of-uncertain-flows-to-clip 0 --flow-nucleotide-of-first-uncertain-flow T --keep-boundary-flows false --gvcf-gq-bands 1 --gvcf-gq-bands 2 --gvcf-gq-bands 3 --gvcf-gq-bands 4 --gvcf-gq-bands 5 --gvcf-gq-bands 6 --gvcf-gq-bands 7 --gvcf-gq-bands 8 --gvcf-gq-bands 9 --gvcf-gq-bands 10 --gvcf-gq-bands 11 --gvcf-gq-bands 12 --gvcf-gq-bands 13 --gvcf-gq-bands 14 --gvcf-gq-bands 15 --gvcf-gq-bands 16 --gvcf-gq-bands 17 --gvcf-gq-bands 18 --gvcf-gq-bands 19 --gvcf-gq-bands 20 --gvcf-gq-bands 21 --gvcf-gq-bands 22 --gvcf-gq-bands 23 --gvcf-gq-bands 24 --gvcf-gq-bands 25 --gvcf-gq-bands 26 --gvcf-gq-bands 27 --gvcf-gq-bands 28 --gvcf-gq-bands 29 --gvcf-gq-bands 30 --gvcf-gq-bands 31 --gvcf-gq-bands 32 --gvcf-gq-bands 33 --gvcf-gq-bands 34 --gvcf-gq-bands 35 --gvcf-gq-bands 36 --gvcf-gq-bands 37 --gvcf-gq-bands 38 --gvcf-gq-bands 39 --gvcf-gq-bands 40 --gvcf-gq-bands 41 --gvcf-gq-bands 42 --gvcf-gq-bands 43 --gvcf-gq-bands 44 --gvcf-gq-bands 45 --gvcf-gq-bands 46 --gvcf-gq-bands 47 --gvcf-gq-bands 48 --gvcf-gq-bands 49 --gvcf-gq-bands 50 --gvcf-gq-bands 51 --gvcf-gq-bands 52 --gvcf-gq-bands 53 --gvcf-gq-bands 54 --gvcf-gq-bands 55 --gvcf-gq-bands 56 --gvcf-gq-bands 57 --gvcf-gq-bands 58 --gvcf-gq-bands 59 --gvcf-gq-bands 60 --gvcf-gq-bands 70 --gvcf-gq-bands 80 --gvcf-gq-bands 90 --gvcf-gq-bands 99 --floor-blocks false --indel-size-to-eliminate-in-ref-model 10 --disable-optimizations false --dragen-mode false --flow-mode NONE --apply-bqd false --apply-frd false --disable-spanning-event-genotyping false --transform-dragen-mapping-quality false --mapping-quality-threshold-for-genotyping 20 --max-effective-depth-adjustment-for-frd 0 --just-determine-active-regions false --dont-genotype false --do-not-run-physical-phasing false --do-not-correct-overlapping-quality false --use-filtered-reads-for-annotations false --use-flow-aligner-for-stepwise-hc-filtering false --adaptive-pruning false --do-not-recover-dangling-branches false --recover-dangling-heads false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --enable-legacy-graph-cycle-detection false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --num-matching-bases-in-dangling-end-to-recover -1 --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --likelihood-calculation-engine PairHMM --base-quality-score-threshold 18 --dragstr-het-hom-ratio 2 --dont-use-dragstr-pair-hmm-scores false --pair-hmm-gap-continuation-penalty 10 --expected-mismatch-rate-for-read-disqualification 0.02 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --disable-symmetric-hmm-normalizing false --disable-cap-base-qualities-to-map-quality false --enable-dynamic-read-disqualification-for-genotyping false --dynamic-read-disqualification-threshold 1.0 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --flow-hmm-engine-min-indel-adjust 6 --flow-hmm-engine-flat-insertion-penatly 45 --flow-hmm-engine-flat-deletion-penatly 45 --pileup-detection false --pileup-detection-enable-indel-pileup-calling false --num-artificial-haplotypes-to-add-per-allele 5 --artifical-haplotype-filtering-kmer-size 10 --pileup-detection-snp-alt-threshold 0.1 --pileup-detection-indel-alt-threshold 0.5 --pileup-detection-absolute-alt-depth 0.0 --pileup-detection-snp-adjacent-to-assembled-indel-range 5 --pileup-detection-bad-read-tolerance 0.0 --pileup-detection-proper-pair-read-badness true --pileup-detection-edit-distance-read-badness-threshold 0.08 --pileup-detection-chimeric-read-badness true --pileup-detection-template-mean-badness-threshold 0.0 --pileup-detection-template-std-badness-threshold 0.0 --bam-writer-type CALLED_HAPLOTYPES --dont-use-soft-clipped-bases false --override-fragment-softclip-check false --min-base-quality-score 10 --smith-waterman JAVA --max-mnp-distance 0 --force-call-filtered-alleles false --reference-model-deletion-quality 30 --soft-clip-low-quality-ends false --allele-informative-reads-overlap-margin 2 --smith-waterman-dangling-end-match-value 25 --smith-waterman-dangling-end-mismatch-penalty -50 --smith-waterman-dangling-end-gap-open-penalty -110 --smith-waterman-dangling-end-gap-extend-penalty -6 --smith-waterman-haplotype-to-reference-match-value 200 --smith-waterman-haplotype-to-reference-mismatch-penalty -150 --smith-waterman-haplotype-to-reference-gap-open-penalty -260 --smith-waterman-haplotype-to-reference-gap-extend-penalty -11 --smith-waterman-read-to-haplotype-match-value 10 --smith-waterman-read-to-haplotype-mismatch-penalty -15 --smith-waterman-read-to-haplotype-gap-open-penalty -30 --smith-waterman-read-to-haplotype-gap-extend-penalty -5 --flow-assembly-collapse-hmer-size 0 --flow-assembly-collapse-partial-mode false --flow-filter-alleles false --flow-filter-alleles-qual-threshold 30.0 --flow-filter-alleles-sor-threshold 3.0 --flow-filter-lone-alleles false --flow-filter-alleles-debug-graphs false --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-extension-into-assembly-region-padding-legacy 25 --max-reads-per-alignment-start 50 --enable-legacy-assembly-region-trimming false --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --minimum-mapping-quality 20 --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 1:10:35 AM CEST">
+##source=CombineGVCFs
+##source=GenotypeGVCFs
+##source=HaplotypeCaller
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CASE
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.4.vcf\".snap" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.4.vcf\".snap"
new file mode 100644
index 00000000..0df41bd3
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.4.vcf\".snap"
@@ -0,0 +1,7 @@
+---
+source: src/seqvars/ingest/header.rs
+expression: "VariantCaller::guess(&vcf_header)"
+---
+Dragen:
+  version: "SW: 07.021.624.3.10.4, HW: 07.021.624"
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.9.vcf\".snap" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.9.vcf\".snap"
new file mode 100644
index 00000000..5089a957
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen.07.021.624.3.10.9.vcf\".snap"
@@ -0,0 +1,7 @@
+---
+source: src/seqvars/ingest/header.rs
+expression: "VariantCaller::guess(&vcf_header)"
+---
+Dragen:
+  version: "SW: 07.021.624.3.10.9, HW: 07.021.624"
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen_07_021_624_3_10_9_vcf\".snap" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen_07_021_624_3_10_9_vcf\".snap"
new file mode 100644
index 00000000..5089a957
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_dragen_07_021_624_3_10_9_vcf\".snap"
@@ -0,0 +1,7 @@
+---
+source: src/seqvars/ingest/header.rs
+expression: "VariantCaller::guess(&vcf_header)"
+---
+Dragen:
+  version: "SW: 07.021.624.3.10.9, HW: 07.021.624"
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.3.7-0.vcf\".snap" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.3.7-0.vcf\".snap"
new file mode 100644
index 00000000..d6f9fb36
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.3.7-0.vcf\".snap"
@@ -0,0 +1,7 @@
+---
+source: src/seqvars/ingest/header.rs
+expression: "VariantCaller::guess(&vcf_header)"
+---
+GatkHaplotypeCaller:
+  version: 3.7-0-gcfedb67
+
diff --git "a/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.4.4.0.0.vcf\".snap" "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.4.4.0.0.vcf\".snap"
new file mode 100644
index 00000000..aeddbb48
--- /dev/null
+++ "b/src/seqvars/ingest/snapshots/varfish_server_worker__seqvars__ingest__header__test__variant_caller_guess@\"example_gatk_hc.4.4.0.0.vcf\".snap"
@@ -0,0 +1,7 @@
+---
+source: src/seqvars/ingest/header.rs
+expression: "VariantCaller::guess(&vcf_header)"
+---
+GatkHaplotypeCaller:
+  version: 4.4.0.0
+
diff --git a/src/seqvars/mod.rs b/src/seqvars/mod.rs
new file mode 100644
index 00000000..b3ac910a
--- /dev/null
+++ b/src/seqvars/mod.rs
@@ -0,0 +1 @@
+pub mod ingest;
diff --git a/tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf b/tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf
new file mode 100644
index 00000000..91cd29a7
--- /dev/null
+++ b/tests/seqvars/ingest/example_dragen.07.021.624.3.10.4.vcf
@@ -0,0 +1,120 @@
+##fileformat=VCFv4.2
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths (counting only informative reads out of the total reads) for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions for alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GP,Number=G,Type=Float,Description="Phred-scaled posterior probabilities for genotypes as defined in the VCF specification">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MB,Number=4,Type=Integer,Description="Per-sample component statistics to detect mate bias">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PRI,Number=G,Type=Float,Description="Phred-scaled prior probabilities for genotypes">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias">
+##FORMAT=<ID=SQ,Number=A,Type=Float,Description="Somatic quality">
+##DRAGENCommandLine=<ID=HashTableBuild,Version="SW: 01.003.044.3.10.4, HashTableVersion: 8",CommandLineOptions="dragen --build-hash-table true --ht-reference /staging/human/reference/hs37d5/hs37d5.fa --output-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --ht-num-threads 32 --ht-seed-len 21 --enable-cnv true">
+##DRAGENCommandLine=<ID=dragen,Version="SW: 07.021.624.3.10.4, HW: 07.021.624",Date="Mon Mar 21 19:12:18 CET 2022",CommandLineOptions="--ref-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --fastq-file1 /mnt/smb01-hum/NGSRawData/220318_A01077_0174_AH7JGVDMXY/Data/Intensities/BaseCalls/NA-12878WGS-Genom-size_S1_R1_001.fastq.gz --fastq-file2 /mnt/smb01-hum/NGSRawData/220318_A01077_0174_AH7JGVDMXY/Data/Intensities/BaseCalls/NA-12878WGS-Genom-size_S1_R2_001.fastq.gz --output-directory /staging/output/220318_A01077_0174_AH7JGVDMXY/NA-12878WGSWGS/ --output-file-prefix NA-12878WGSWGS_dragen --RGID WGS --RGSM NA-12878WGSWGS --num-threads 46 --enable-map-align true --enable-map-align-output true --enable-duplicate-marking true --enable-variant-caller true --qc-cross-cont-vcf /opt/edico/config/sample_cross_contamination_resource_GRCh37.vcf.gz --enable-cnv true --cnv-enable-self-normalization true --enable-sv true --qc-coverage-region-1 /staging/human/bed/CDS-v19-ROIs_v2.bed --qc-coverage-reports-1 cov_report full_res --qc-coverage-region-2 /staging/human/bed/Regions_Exomev8.bed --qc-coverage-reports-2 cov_report full_res --qc-coverage-region-3 /staging/human/bed/Padded_Exomev8.bed --qc-coverage-reports-3 cov_report full_res">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (informative and non-informative); some reads may have been filtered based on mapq etc.">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FractionInformativeReads,Number=1,Type=Float,Description="The fraction of informative reads out of the total reads">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##reference=file:///staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149/reference.bin
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA12878
+17	41256074	.	CA	C	44.34	.	AC=1;AF=0.500;AN=2;DP=18;FS=0.000;MQ=243.16;MQRankSum=3.266;QD=2.46;ReadPosRankSum=2.663;SOR=1.112;FractionInformativeReads=0.944	GT:AD:AF:DP:F1R2:F2R1:GQ:PL:GP:PRI:SB:MB:PS	0|1:11,6:0.353:17:8,3:3,3:43:55,0,47:4.4342e+01,2.0325e-04,5.0000e+01:0.00,11.00,14.01:5,6,2,4:4,7,5,1:41256074
+MT	750	.	A	G	.	.	DP=7835;MQ=167.68;FractionInformativeReads=0.998	GT:SQ:AD:AF:F1R2:F2R1:DP:SB:MB	1/1:98.13:1,7818:1.000:1,3815:0,4003:7819:1,0,4126,3692:1,0,3979,3839
diff --git a/tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf b/tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf
new file mode 100644
index 00000000..329baacb
--- /dev/null
+++ b/tests/seqvars/ingest/example_dragen.07.021.624.3.10.9.vcf
@@ -0,0 +1,142 @@
+##fileformat=VCFv4.2
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths (counting only informative reads out of the total reads) for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions for alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GP,Number=G,Type=Float,Description="Phred-scaled posterior probabilities for genotypes as defined in the VCF specification">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MB,Number=4,Type=Integer,Description="Per-sample component statistics to detect mate bias">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PRI,Number=G,Type=Float,Description="Phred-scaled prior probabilities for genotypes">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias">
+##FORMAT=<ID=SQ,Number=A,Type=Float,Description="Somatic quality">
+##DRAGENCommandLine=<ID=HashTableBuild,Version="SW: 01.003.044.3.10.4, HashTableVersion: 8",CommandLineOptions="dragen --build-hash-table true --ht-reference /staging/human/reference/hs37d5/hs37d5.fa --output-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --ht-num-threads 32 --ht-seed-len 21 --enable-cnv true">
+##DRAGENCommandLine=<ID=dragen,Version="SW: 07.021.624.3.10.9, HW: 07.021.624",Date="Fri Sep 15 14:27:23 CEST 2023",CommandLineOptions="--ref-dir /staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149 --fastq-file1 /data/CASE_R1_001.fastq.gz --fastq-file2 /data/CASE_R2_001.fastq.gz --output-directory /data/CASE/ --output-file-prefix CASE_dragen --RGID WGS --RGSM CASE --RGLB CASE --num-threads 46 --enable-map-align true --enable-map-align-output true --enable-duplicate-marking true --generate-sa-tags true --generate-zs-tags true --vc-output-evidence-bam true --vc-evidence-bam-output-haplotypes true --vc-evidence-bam-force-output true --enable-variant-caller true --vc-emit-ref-confidence gvcf --vc-enable-vcf-output true --qc-cross-cont-vcf /opt/edico/config/sample_cross_contamination_resource_GRCh37.vcf.gz --enable-cnv true --cnv-enable-self-normalization true --enable-sv true --enable-cyp2d6 false --repeat-genotype-enable true --repeat-genotype-specs /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/expansionhunter/GRCh37_edico+stripy+smn.json --enable-hla false --enable-smn false --qc-coverage-ignore-overlaps true --qc-coverage-region-1 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/padded_agilentv8_MT.bed --qc-coverage-reports-1 cov_report full_res --qc-coverage-filters-1 mapq<1,bq<0 --qc-coverage-region-2 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/difficult_regions.bed --qc-coverage-reports-2 cov_report full_res --qc-coverage-filters-2 mapq<1,bq<0 --qc-coverage-region-3 /home/helmuth/workspace/hum-dragen-routine.git/scripts/../resources/padded_agilentv8_MT.bed --qc-coverage-reports-3 cov_report full_res --qc-coverage-filters-3 mapq<0,bq<0">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (informative and non-informative); some reads may have been filtered based on mapq etc.">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FractionInformativeReads,Number=1,Type=Float,Description="The fraction of informative reads out of the total reads">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##FILTER=<ID=DRAGENSnpHardQUAL,Description="Set if true:QUAL < 10.41">
+##FILTER=<ID=DRAGENIndelHardQUAL,Description="Set if true:QUAL < 7.83">
+##FILTER=<ID=LowDepth,Description="Set if true:DP <= 1">
+##FILTER=<ID=LowGQ,Description="Set if true:GQ = 0">
+##FILTER=<ID=PloidyConflict,Description="Genotype call from variant caller not consistent with chromosome ploidy">
+##FILTER=<ID=base_quality,Description="Site filtered because median base quality of alt reads at this locus does not meet threshold">
+##FILTER=<ID=filtered_reads,Description="Site filtered because too large a fraction of reads have been filtered out">
+##FILTER=<ID=fragment_length,Description="Site filtered because absolute difference between the median fragment length of alt reads and median fragment length of ref reads at this locus exceeds threshold">
+##FILTER=<ID=low_depth,Description="Site filtered because the read depth is too low">
+##FILTER=<ID=low_frac_info_reads,Description="Site filtered because the fraction of informative reads is below threshold">
+##FILTER=<ID=low_normal_depth,Description="Site filtered because the normal sample read depth is too low">
+##FILTER=<ID=long_indel,Description="Site filtered because the indel length is too long">
+##FILTER=<ID=mapping_quality,Description="Site filtered because median mapping quality of alt reads at this locus does not meet threshold">
+##FILTER=<ID=multiallelic,Description="Site filtered because more than two alt alleles pass tumor LOD">
+##FILTER=<ID=non_homref_normal,Description="Site filtered because the normal sample genotype is not homozygous reference">
+##FILTER=<ID=no_reliable_supporting_read,Description="Site filtered because no reliable supporting somatic read exists">
+##FILTER=<ID=panel_of_normals,Description="Seen in at least one sample in the panel of normals vcf">
+##FILTER=<ID=read_position,Description="Site filtered because median of distances between start/end of read and this locus is below threshold">
+##FILTER=<ID=RMxNRepeatRegion,Description="Site filtered because all or part of the variant allele is a repeat of the reference">
+##FILTER=<ID=str_contraction,Description="Site filtered due to suspected PCR error where the alt allele is one repeat unit less than the reference">
+##FILTER=<ID=too_few_supporting_reads,Description="Site filtered because there are too few supporting reads in the tumor sample">
+##FILTER=<ID=weak_evidence,Description="Somatic variant score does not meet threshold">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##reference=file:///staging/human/reference/hs37d5/hs37d5.fa.k_21.f_16.m_149/reference.bin
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CASE
+17	41256074	.	CA	C	49.57	PASS	AC=1;AF=0.500;AN=2;DP=40;FS=1.397;MQ=249.24;MQRankSum=4.084;QD=1.24;ReadPosRankSum=1.804;SOR=1.051;FractionInformativeReads=0.800	GT:AD:AF:DP:F1R2:F2R1:GQ:PL:GP:PRI:SB:MB:PS	0|1:18,14:0.438:32:9,10:9,4:47:60,0,47:4.9567e+01,9.1418e-05,5.0000e+01:0.00,10.00,13.01:10,8,9,5:9,9,9,5:41256074
+MT	750	.	A	G	.	PASS	DP=5639;MQ=150.72;FractionInformativeReads=0.995	GT:SQ:AD:AF:F1R2:F2R1:DP:SB:MB	1/1:98.13:1,5607:1.000:0,2721:1,2886:5608:0,1,3291,2316:1,0,2879,2728
diff --git a/tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf b/tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf
new file mode 100644
index 00000000..430e8919
--- /dev/null
+++ b/tests/seqvars/ingest/example_gatk_hc.3.7-0.vcf
@@ -0,0 +1,122 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##GATKCommandLine.HaplotypeCaller=<ID=HaplotypeCaller,Version=3.7-0-gcfedb67,Date="Fri Aug 26 20:52:06 CEST 2022",Epoch=1661539926702,CommandLineOptions="analysis_type=HaplotypeCaller input_file=[/fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_index-N1-DNA1-WGS1/out/bwa.Case_1_index-N1-DNA1-WGS1.bam, /fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_father-N1-DNA1-WGS1/out/bwa.Case_1_father-N1-DNA1-WGS1.bam, /fast/work/groups/cubi/projects/2022-07-06_VarFish_Course_Data/snappy-processing/ngs_mapping/work/bwa.Case_1_mother-N1-DNA1-WGS1/out/bwa.Case_1_mother-N1-DNA1-WGS1.bam] showFullBamList=false read_buffer_size=null read_filter=[] disable_read_filter=[] intervals=[1:1-5,010,000] excludeIntervals=null interval_set_rule=UNION interval_merging=ALL interval_padding=0 reference_sequence=/fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa nonDeterministicRandomSeed=false disableDithering=false maxRuntime=-1 maxRuntimeUnits=MINUTES downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=500 baq=OFF baqGapOpenPenalty=40.0 refactor_NDN_cigar_string=false fix_misencoded_quality_scores=false allow_potentially_misencoded_quality_scores=false useOriginalQualities=false defaultBaseQualities=-1 performanceLog=null BQSR=null quantize_quals=0 static_quantized_quals=null round_down_quantized=false disable_indel_quals=false emit_original_quals=false preserve_qscores_less_than=6 globalQScorePrior=-1.0 secondsBetweenProgressUpdates=10 validation_strictness=SILENT remove_program_records=false keep_program_records=false sample_rename_mapping_file=null unsafe=null disable_auto_index_creation_and_locking_when_reading_rods=false no_cmdline_in_header=false sites_only=false never_trim_vcf_format_field=false bcf=false bam_compression=null simplifyBAM=false disable_bam_indexing=false generate_md5=false num_threads=1 num_cpu_threads_per_data_thread=1 num_io_threads=0 monitorThreadEfficiency=false num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false generateShadowBCF=false variant_index_type=DYNAMIC_SEEK variant_index_parameter=-1 reference_window_stop=0 phone_home= gatk_key=null tag=NA logging_level=INFO log_to_file=null help=false version=false out=/data/gpfs-1/users/holtgrem_c/scratch/tmp/tmp.uG5Q6d0QYe/tmp.vcf.gz likelihoodCalculationEngine=PairHMM heterogeneousKmerSizeResolution=COMBO_MIN dbsnp=(RodBinding name=dbsnp source=/fast/projects/cubit/current/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz) dontTrimActiveRegions=false maxDiscARExtension=25 maxGGAARExtension=300 paddingAroundIndels=150 paddingAroundSNPs=20 comp=[] annotation=[] excludeAnnotation=[] group=[StandardAnnotation, StandardHCAnnotation] debug=false useFilteredReadsForAnnotations=false emitRefConfidence=NONE bamOutput=null bamWriterType=CALLED_HAPLOTYPES emitDroppedReads=false disableOptimizations=false annotateNDA=false useNewAFCalculator=false heterozygosity=0.001 indel_heterozygosity=1.25E-4 heterozygosity_stdev=0.01 standard_min_confidence_threshold_for_calling=10.0 standard_min_confidence_threshold_for_emitting=30.0 max_alternate_alleles=6 max_genotype_count=1024 max_num_PL_values=100 input_prior=[] sample_ploidy=2 genotyping_mode=DISCOVERY alleles=(RodBinding name= source=UNBOUND) contamination_fraction_to_filter=0.0 contamination_fraction_per_sample_file=null p_nonref_model=null exactcallslog=null output_mode=EMIT_VARIANTS_ONLY allSitePLs=false gcpHMM=10 pair_hmm_implementation=VECTOR_LOGLESS_CACHING pair_hmm_sub_implementation=ENABLE_ALL always_load_vector_logless_PairHMM_lib=false phredScaledGlobalReadMismappingRate=45 noFpga=false sample_name=null kmerSize=[10, 25] dontIncreaseKmerSizesForCycles=false allowNonUniqueKmersInRef=false numPruningSamples=1 recoverDanglingHeads=false doNotRecoverDanglingBranches=false minDanglingBranchLength=4 consensus=false maxNumHaplotypesInPopulation=128 errorCorrectKmers=false minPruning=3 debugGraphTransformations=false allowCyclesInKmerGraphToGeneratePaths=false graphOutput=null kmerLengthForReadErrorCorrection=25 minObservationsForKmerToBeSolid=20 GVCFGQBands=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 70, 80, 90, 99] indelSizeToEliminateInRefModel=10 min_base_quality_score=10 includeUmappedReads=false useAllelesTrigger=false doNotRunPhysicalPhasing=true keepRG=null justDetermineActiveRegions=false dontGenotype=false dontUseSoftClippedBases=false captureAssemblyFailureBAM=false errorCorrectReads=false pcr_indel_model=CONSERVATIVE maxReadsInRegionPerSample=10000 minReadsPerAlignmentStart=10 mergeVariantsViaLD=false activityProfileOut=null activeRegionOut=null activeRegionIn=null activeRegionExtension=null forceActive=false activeRegionMaxSize=null bandPassSigma=null maxReadsInMemoryPerSample=30000 maxTotalReadsInMemory=10000000 maxProbPropagationDistance=50 activeProbabilityThreshold=0.002 min_mapping_quality_score=20 filter_reads_with_N_cigar=false filter_mismatching_base_and_quals=false filter_bases_not_stored=false">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##reference=file:///fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa
+##SAMPLE=<ID=Case_1_index-N1-DNA1-WGS1,Sex=Male,Disease=Affected>
+##SAMPLE=<ID=Case_1_father-N1-DNA1-WGS1,Sex=Male,Disease=Unaffected>
+##SAMPLE=<ID=Case_1_mother-N1-DNA1-WGS1,Sex=Female,Disease=Unaffected>
+##PEDIGREE=<ID=Case_1_index-N1-DNA1-WGS1,Family=FAM_Case_1_index,Father=Case_1_father-N1-DNA1-WGS1,Mother=Case_1_mother-N1-DNA1-WGS1>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Case_1_father-N1-DNA1-WGS1	Case_1_index-N1-DNA1-WGS1	Case_1_mother-N1-DNA1-WGS1
+17	41210126	rs542522579	C	CTAGCACTT	1136.12	.	AC=2;AF=0.333;AN=6;BaseQRankSum=-1.948;ClippingRankSum=0;DB;DP=98;ExcessHet=3.9794;FS=0.876;MLEAC=2;MLEAF=0.333;MQ=60;MQRankSum=0;QD=16.71;ReadPosRankSum=-1.999;SOR=0.527	GT:AD:DP:GQ:PL	0/0:29,0:29:87:0,87,2916	0/1:23,13:36:99:466,0,2205	0/1:15,17:32:99:711,0,1410
+MT	750	rs2853518	A	G	263720	.	AC=6;AF=1;AN=6;DB;DP=6791;ExcessHet=3.0103;FS=0;MLEAC=6;MLEAF=1;MQ=59.96;QD=28.69;SOR=0.952	GT:AD:DP:GQ:PL	1/1:0,2757:2757:99:95517,8285,0	1/1:0,2392:2392:99:99668,7257,0	1/1:0,1621:1621:99:68561,4944,0
diff --git a/tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf b/tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf
new file mode 100644
index 00000000..f53cd4d2
--- /dev/null
+++ b/tests/seqvars/ingest/example_gatk_hc.4.4.0.0.vcf
@@ -0,0 +1,142 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##ALT=<ID=NON_REF,Description="Represents any possible alternative allele not already represented at this location by REF and ALT">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum DP observed within the GVCF block">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=RGQ,Number=1,Type=Integer,Description="Unconditional reference genotype confidence, encoded as a phred quality -10*log10 p(genotype call is wrong)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=CombineGVCFs,CommandLine="CombineGVCFs --output /data/CASE.g.vcf.gz --break-bands-at-multiples-of 10000000 --variant /data/CASE.g.vcf.gz --intervals 1:1-10000000 --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --annotation-group AlleleSpecificAnnotation --convert-to-base-pair-resolution false --input-is-somatic false --drop-somatic-filtering-annotations false --call-genotypes false --ignore-variants-starting-outside-interval false --combine-variants-distance 0 --max-distance 2147483647 --ref-padding 1 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 2:23:49 AM CEST">
+##GATKCommandLine=<ID=GenotypeGVCFs,CommandLine="GenotypeGVCFs --output /data/CASE.g.vcf.gz --variant /data/CASE.g.vcf.gz --intervals 1:1-10000000 --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --include-non-variant-sites false --merge-input-intervals false --input-is-somatic false --tumor-lod-to-emit 3.5 --allele-fraction-error 0.001 --keep-combined-raw-annotations false --use-posteriors-to-calculate-qual false --dont-use-dragstr-priors false --use-new-qual-calculator true --annotate-with-num-discovered-alleles false --heterozygosity 0.001 --indel-heterozygosity 1.25E-4 --heterozygosity-stdev 0.01 --standard-min-confidence-threshold-for-calling 30.0 --max-alternate-alleles 6 --max-genotype-count 1024 --sample-ploidy 2 --num-reference-samples-if-no-call 0 --genotype-assignment-method USE_PLS_TO_ASSIGN --genomicsdb-max-alternate-alleles 50 --call-genotypes false --genomicsdb-use-bcf-codec false --genomicsdb-shared-posixfs-optimizations false --genomicsdb-use-gcs-hdfs-connector false --only-output-calls-starting-in-intervals false --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 2:40:40 AM CEST">
+##GATKCommandLine=<ID=HaplotypeCaller,CommandLine="HaplotypeCaller --dbsnp /fast/projects/cubit/20.05/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz --emit-ref-confidence GVCF --output /data/CASE.g.vcf.gz --intervals 1:1-10000000 --input /data/CASE.bam --reference /fast/projects/cubit/20.05/static_data/reference/GRCh37/hs37d5/hs37d5.fa --tmp-dir /tmp --annotation-group StandardAnnotation --annotation-group AS_StandardAnnotation --annotation-group StandardHCAnnotation --annotation-group AlleleSpecificAnnotation --use-posteriors-to-calculate-qual false --dont-use-dragstr-priors false --use-new-qual-calculator true --annotate-with-num-discovered-alleles false --heterozygosity 0.001 --indel-heterozygosity 1.25E-4 --heterozygosity-stdev 0.01 --standard-min-confidence-threshold-for-calling 30.0 --max-alternate-alleles 6 --max-genotype-count 1024 --sample-ploidy 2 --num-reference-samples-if-no-call 0 --genotype-assignment-method USE_PLS_TO_ASSIGN --contamination-fraction-to-filter 0.0 --output-mode EMIT_VARIANTS_ONLY --all-site-pls false --flow-likelihood-parallel-threads 0 --flow-likelihood-optimized-comp false --flow-use-t0-tag false --flow-probability-threshold 0.003 --flow-remove-non-single-base-pair-indels false --flow-remove-one-zero-probs false --flow-quantization-bins 121 --flow-fill-empty-bins-value 0.001 --flow-symmetric-indel-probs false --flow-report-insertion-or-deletion false --flow-disallow-probs-larger-than-call false --flow-lump-probs false --flow-retain-max-n-probs-base-format false --flow-probability-scaling-factor 10 --flow-order-cycle-length 4 --flow-number-of-uncertain-flows-to-clip 0 --flow-nucleotide-of-first-uncertain-flow T --keep-boundary-flows false --gvcf-gq-bands 1 --gvcf-gq-bands 2 --gvcf-gq-bands 3 --gvcf-gq-bands 4 --gvcf-gq-bands 5 --gvcf-gq-bands 6 --gvcf-gq-bands 7 --gvcf-gq-bands 8 --gvcf-gq-bands 9 --gvcf-gq-bands 10 --gvcf-gq-bands 11 --gvcf-gq-bands 12 --gvcf-gq-bands 13 --gvcf-gq-bands 14 --gvcf-gq-bands 15 --gvcf-gq-bands 16 --gvcf-gq-bands 17 --gvcf-gq-bands 18 --gvcf-gq-bands 19 --gvcf-gq-bands 20 --gvcf-gq-bands 21 --gvcf-gq-bands 22 --gvcf-gq-bands 23 --gvcf-gq-bands 24 --gvcf-gq-bands 25 --gvcf-gq-bands 26 --gvcf-gq-bands 27 --gvcf-gq-bands 28 --gvcf-gq-bands 29 --gvcf-gq-bands 30 --gvcf-gq-bands 31 --gvcf-gq-bands 32 --gvcf-gq-bands 33 --gvcf-gq-bands 34 --gvcf-gq-bands 35 --gvcf-gq-bands 36 --gvcf-gq-bands 37 --gvcf-gq-bands 38 --gvcf-gq-bands 39 --gvcf-gq-bands 40 --gvcf-gq-bands 41 --gvcf-gq-bands 42 --gvcf-gq-bands 43 --gvcf-gq-bands 44 --gvcf-gq-bands 45 --gvcf-gq-bands 46 --gvcf-gq-bands 47 --gvcf-gq-bands 48 --gvcf-gq-bands 49 --gvcf-gq-bands 50 --gvcf-gq-bands 51 --gvcf-gq-bands 52 --gvcf-gq-bands 53 --gvcf-gq-bands 54 --gvcf-gq-bands 55 --gvcf-gq-bands 56 --gvcf-gq-bands 57 --gvcf-gq-bands 58 --gvcf-gq-bands 59 --gvcf-gq-bands 60 --gvcf-gq-bands 70 --gvcf-gq-bands 80 --gvcf-gq-bands 90 --gvcf-gq-bands 99 --floor-blocks false --indel-size-to-eliminate-in-ref-model 10 --disable-optimizations false --dragen-mode false --flow-mode NONE --apply-bqd false --apply-frd false --disable-spanning-event-genotyping false --transform-dragen-mapping-quality false --mapping-quality-threshold-for-genotyping 20 --max-effective-depth-adjustment-for-frd 0 --just-determine-active-regions false --dont-genotype false --do-not-run-physical-phasing false --do-not-correct-overlapping-quality false --use-filtered-reads-for-annotations false --use-flow-aligner-for-stepwise-hc-filtering false --adaptive-pruning false --do-not-recover-dangling-branches false --recover-dangling-heads false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --enable-legacy-graph-cycle-detection false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --num-matching-bases-in-dangling-end-to-recover -1 --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --likelihood-calculation-engine PairHMM --base-quality-score-threshold 18 --dragstr-het-hom-ratio 2 --dont-use-dragstr-pair-hmm-scores false --pair-hmm-gap-continuation-penalty 10 --expected-mismatch-rate-for-read-disqualification 0.02 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --disable-symmetric-hmm-normalizing false --disable-cap-base-qualities-to-map-quality false --enable-dynamic-read-disqualification-for-genotyping false --dynamic-read-disqualification-threshold 1.0 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --flow-hmm-engine-min-indel-adjust 6 --flow-hmm-engine-flat-insertion-penatly 45 --flow-hmm-engine-flat-deletion-penatly 45 --pileup-detection false --pileup-detection-enable-indel-pileup-calling false --num-artificial-haplotypes-to-add-per-allele 5 --artifical-haplotype-filtering-kmer-size 10 --pileup-detection-snp-alt-threshold 0.1 --pileup-detection-indel-alt-threshold 0.5 --pileup-detection-absolute-alt-depth 0.0 --pileup-detection-snp-adjacent-to-assembled-indel-range 5 --pileup-detection-bad-read-tolerance 0.0 --pileup-detection-proper-pair-read-badness true --pileup-detection-edit-distance-read-badness-threshold 0.08 --pileup-detection-chimeric-read-badness true --pileup-detection-template-mean-badness-threshold 0.0 --pileup-detection-template-std-badness-threshold 0.0 --bam-writer-type CALLED_HAPLOTYPES --dont-use-soft-clipped-bases false --override-fragment-softclip-check false --min-base-quality-score 10 --smith-waterman JAVA --max-mnp-distance 0 --force-call-filtered-alleles false --reference-model-deletion-quality 30 --soft-clip-low-quality-ends false --allele-informative-reads-overlap-margin 2 --smith-waterman-dangling-end-match-value 25 --smith-waterman-dangling-end-mismatch-penalty -50 --smith-waterman-dangling-end-gap-open-penalty -110 --smith-waterman-dangling-end-gap-extend-penalty -6 --smith-waterman-haplotype-to-reference-match-value 200 --smith-waterman-haplotype-to-reference-mismatch-penalty -150 --smith-waterman-haplotype-to-reference-gap-open-penalty -260 --smith-waterman-haplotype-to-reference-gap-extend-penalty -11 --smith-waterman-read-to-haplotype-match-value 10 --smith-waterman-read-to-haplotype-mismatch-penalty -15 --smith-waterman-read-to-haplotype-gap-open-penalty -30 --smith-waterman-read-to-haplotype-gap-extend-penalty -5 --flow-assembly-collapse-hmer-size 0 --flow-assembly-collapse-partial-mode false --flow-filter-alleles false --flow-filter-alleles-qual-threshold 30.0 --flow-filter-alleles-sor-threshold 3.0 --flow-filter-lone-alleles false --flow-filter-alleles-debug-graphs false --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-extension-into-assembly-region-padding-legacy 25 --max-reads-per-alignment-start 50 --enable-legacy-assembly-region-trimming false --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --max-variants-per-shard 0 --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --minimum-mapping-quality 20 --disable-tool-default-annotations false --enable-all-annotations false --allow-old-rms-mapping-quality-annotation-data false",Version="4.4.0.0",Date="June 6, 2023 at 1:10:35 AM CEST">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AS_BaseQRankSum,Number=A,Type=Float,Description="allele specific Z-score from Wilcoxon rank sum test of each Alt Vs. Ref base qualities">
+##INFO=<ID=AS_FS,Number=A,Type=Float,Description="allele specific phred-scaled p-value using Fisher's exact test to detect strand bias of each alt allele">
+##INFO=<ID=AS_InbreedingCoeff,Number=A,Type=Float,Description="Allele-specific inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=AS_MQ,Number=A,Type=Float,Description="Allele-specific RMS Mapping Quality">
+##INFO=<ID=AS_MQRankSum,Number=A,Type=Float,Description="Allele-specific Mapping Quality Rank Sum">
+##INFO=<ID=AS_QD,Number=A,Type=Float,Description="Allele-specific Variant Confidence/Quality by Depth">
+##INFO=<ID=AS_RAW_BaseQRankSum,Number=1,Type=String,Description="raw data for allele specific rank sum test of base qualities">
+##INFO=<ID=AS_RAW_MQ,Number=1,Type=String,Description="Allele-specfic raw data for RMS Mapping Quality">
+##INFO=<ID=AS_RAW_MQRankSum,Number=1,Type=String,Description="Allele-specfic raw data for Mapping Quality Rank Sum">
+##INFO=<ID=AS_RAW_ReadPosRankSum,Number=1,Type=String,Description="allele specific raw data for rank sum test of read position bias">
+##INFO=<ID=AS_ReadPosRankSum,Number=A,Type=Float,Description="allele specific Z-score from Wilcoxon rank sum test of each Alt vs. Ref read position bias">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_SOR,Number=A,Type=Float,Description="Allele specific strand Odds Ratio of 2x|Alts| contingency table to detect allele specific strand bias">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=RAW_MQandDP,Number=2,Type=Integer,Description="Raw data (sum of squared MQ and total depth) for improved RMS Mapping Quality calculation. Incompatible with deprecated RAW_MQ formulation.">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##contig=<ID=NC_007605,length=171823>
+##contig=<ID=hs37d5,length=35477943>
+##source=CombineGVCFs
+##source=GenotypeGVCFs
+##source=HaplotypeCaller
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CASE
+17	41256074	.	CA	C	3524.03	.	AC=2;AF=1;AN=2;AS_BaseQRankSum=.;AS_FS=0;AS_MQ=60;AS_MQRankSum=.;AS_QD=27.59;AS_ReadPosRankSum=.;AS_SOR=2.245;AS_UNIQ_ALT_READ_COUNT=80;DP=88;ExcessHet=0;FS=0;MLEAC=2;MLEAF=1;MQ=60;QD=30.55;SOR=2.245	GT:AD:DP:GQ:PGT:PID:PL:PS	1|1:0,80:80:99:1|1:41256074_CA_C:3538,241,0:41256074
+MT	750	.	A	G	1143.06	.	AC=2;AF=1;AN=2;AS_BaseQRankSum=.;AS_FS=0;AS_MQ=60;AS_MQRankSum=.;AS_QD=32.66;AS_ReadPosRankSum=.;AS_SOR=1.148;AS_UNIQ_ALT_READ_COUNT=35;DP=35;ExcessHet=0;FS=0;MLEAC=2;MLEAF=1;MQ=60;QD=32.66;SOR=1.148	GT:AD:DP:GQ:PL	1/1:0,35:35:99:1157,105,0