test data

varfish-org · Oct 5, 2023 · dc84e73 · dc84e73
1 parent 0ea5bf9
commit dc84e73
Show file tree

Hide file tree

Showing 10 changed files with 379 additions and 124 deletions.
diff --git 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
@@ -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/mod.rs b/src/seqvars/ingest/mod.rs
@@ -0,0 +1,71 @@
+//! Implementation of `seqvars ingest` subcommand.
+
+use crate::common::{self, GenomeRelease};
+
+/// 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!(
+        "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/mod.rs 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
@@ -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