Improve YAML parsing

lirical-cli/src/assemble/distribution.xml

@@ -17,6 +17,13 @@
                 <include>legal/**</include>
             </includes>
         </fileSet>
+        <fileSet>
+            <directory>${project.basedir}/src</directory>
+            <outputDirectory>./</outputDirectory>
+            <includes>
+                <include>examples/</include>
+            </includes>
+        </fileSet>
         <fileSet>
             <directory>${project.build.directory}</directory>
             <outputDirectory>./</outputDirectory>

lirical-cli/src/examples/marfan.vcf

@@ -0,0 +1,78 @@
+##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=1,Type=Float,Description="Somatic quality">
+##DRAGENCommandLine=<ID=HashTableBuild,Version="SW: 01.003.044.3.5.3-38-gefdaeaff, HashTableVersion: 8",CommandLineOptions="/opt/edico/bin/dragen --lic-instance-id-location /root/.edico --build-hash-table true --ht-reference /data/input/appresults/217816899/hg38.fa --ht-alt-liftover /opt/edico/liftover/bwa-kit_hs38DH_liftover.sam --ht-build-rna-hashtable true --enable-cnv true --ht-alt-aware-validate true --output-directory /data/scratch/hg38_altaware">
+##DRAGENCommandLine=<ID=dragen,Version="SW: 05.021.595.3.7.5, HW: 05.021.595",Date="Sun Jan 01 00:00:00 UTC 2022",CommandLineOptions="--lic-server https://XXXXXXXXXXXX:YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY@license.edicogenome.com --lic-instance-id-location /root/.edico --output_status_file /data/scratch/progress.log --enable-duplicate-marking true --enable-map-align true --enable-map-align-output true --output-format BAM --auto-detect-sample-sex true --enable-bam-indexing true --enable-metrics-json true --json-dataset-type /staging/files/dataset-types/dragen_complete_v02.json --enable-variant-caller true --enable-vcf-compression true --vc-emit-ref-confidence GVCF --vc-enable-vcf-output true --vc-enable-bqd true --output-directory /data/output/appresults/292294008/EXAMPLE_SAMPLE --intermediate-results-dir /data/scratch/intermediate --output-file-prefix EXAMPLE_SAMPLE --fastq-list /data/scratch/fastq_sheet.csv --ref-dir /data/scratch/hg38-altaware-cnv-anchor.v8 --qc-cross-cont-vcf /opt/edico/config/sample_cross_contamination_resource_hg38.vcf.gz">
+##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=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=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=FractionInformativeReads,Number=1,Type=Float,Description="The fraction of informative reads out of the total reads">
+##INFO=<ID=LOD,Number=1,Type=Float,Description="Variant LOD score">
+##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=R2_5P_bias,Number=1,Type=Float,Description="Score based on mate bias and distance from 5 prime end">
+##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">
+##INFO=<ID=GENE,Number=1,Type=String,Description="Causal gene symbol. The field is present in true positive variants">
+##INFO=<ID=INHERITANCE,Number=1,Type=String,Description="Mode of inheritance of the disease. The field is present in true positive variants">
+##INFO=<ID=MIM,Number=1,Type=String,Description="OMIM number of the disease associated with the variant presence. The field is present in true positive variants">
+##INFO=<ID=PMID,Number=1,Type=String,Description="Publication describing the variant. The field is present in true positive variants">
+##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=RMxNRepeatRegion,Description="Site filtered because all or part of the variant allele is a repeat of the reference">
+##FILTER=<ID=base_quality,Description="Site filtered because median base quality of alt reads at this locus does not meet threshold">
+##FILTER=<ID=lod_fstar,Description="Variant does not meet likelihood threshold (default threshold is 6.3)">
+##contig=<ID=chr1,length=248956422>
+##contig=<ID=chr2,length=242193529>
+##contig=<ID=chr3,length=198295559>
+##contig=<ID=chr4,length=190214555>
+##contig=<ID=chr5,length=181538259>
+##contig=<ID=chr6,length=170805979>
+##contig=<ID=chr7,length=159345973>
+##contig=<ID=chr8,length=145138636>
+##contig=<ID=chr9,length=138394717>
+##contig=<ID=chr10,length=133797422>
+##contig=<ID=chr11,length=135086622>
+##contig=<ID=chr12,length=133275309>
+##contig=<ID=chr13,length=114364328>
+##contig=<ID=chr14,length=107043718>
+##contig=<ID=chr15,length=101991189>
+##contig=<ID=chr16,length=90338345>
+##contig=<ID=chr17,length=83257441>
+##contig=<ID=chr18,length=80373285>
+##contig=<ID=chr19,length=58617616>
+##contig=<ID=chr20,length=64444167>
+##contig=<ID=chr21,length=46709983>
+##contig=<ID=chr22,length=50818468>
+##contig=<ID=chrX,length=156040895>
+##contig=<ID=chrY,length=57227415>
+##contig=<ID=chrM,length=16569>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	MARFAN_EXAMPLE
+chr1	168044638	rs113151068	G	A	284.62	PASS	AC=1;AF=0.500;AN=2;DP=43	GT:AD:DP:GQ:PL	0/1:23,20:43:41:77,0,45
+chr3	126006425	rs111477552	TAACA	T	258.17	PASS	AC=1;AF=0.500;AN=2;DP=43	GT:AD:DP:GQ:PL	0/1:23,20:43:41:77,0,45
+chr15	48411070	MARFAN_PATHOGENIC	C	A	100	PASS	GENE=FBN1;INHERITANCE=AD;MIM=154700;AC=1;AF=0.500;AN=2;DP=43	GT:AD:DP:GQ:PL	0/1:23,20:43:41:77,0,45
+chrX	101539008	rs6523510	G	C	739.17	PASS	AC=2;AF=1.00;AN=2;DP=31	GT:AD:DP:GQ:PL	1/1:1,30:31:22.40:772,22,0
+chrX	154462369	rs72227759	CTGG	C	196.20	PASS	AC=1;AF=0.500;AN=2;DP=9	GT:AD:DP:GQ:PL	1/1:0,9:9:23:93,26,0
+chr17_KI270907v1_alt	88449	.	C	A	21.05	PASS	AC=1;AF=0.500;AN=2;DP=122	GT:AD:DP:GQ:PL	0/1:5,2:7:21:56,0,44
+chr3_KI270937v1_alt	81596	.	A	G	7.80	DRAGENSnpHardQUAL	AC=2;AF=1.000;AN=2;DP=59	GT:AD:DP:GQ:PL	1/1:0,1:1:2:42,3,0
+HLA-DRB1*09:21	5012	.	T	C	25.79	PASS	AC=2;AF=1.000;AN=2;DP=2	GT:AD:DP:GQ:PL	1/1:0,2:2:5:62,6,0

lirical-cli/src/examples/phenotype-and-genotype.yaml

@@ -0,0 +1,18 @@
+## LIRICAL Analysis Template.
+# Use this as a template for your own set-up.
+---
+# Sample ID
+sampleId: MARFAN_EXAMPLE
+# List of observed HPO terms
+hpoIds: ['HP:0001519', 'HP:0001083', 'HP:0001653']
+# List of excluded HPO terms
+negatedHpoIds: ['HP:0000275']
+
+# Age in ISO8601 notation (e.g. 'P12Y6M5D' to indicate 12 years, 6 months, and 5 days).
+age: P20Y6M
+# Choose from {MALE, FEMALE}
+sex: FEMALE
+# Path to a VCF file. Update to match path to your VCF file,
+#  or to point to an example VCF with deleterious FBN1 variant
+#  stored at `lirical-cli/src/examples/marfan.vcf`.
+#vcf: /path/to/marfan.vcf

lirical-cli/src/examples/phenotype-only.yaml

@@ -0,0 +1,13 @@
+## LIRICAL Analysis Template.
+# Use this as a template for your own set-up.
+---
+sampleId: Sample ID
+hpoIds: ['HP:0002352', 'HP:0002490', 'HP:0001290']
+negatedHpoIds: ['HP:0000486']
+
+# Age in ISO8601 notation (e.g. 'P12Y6M5D' to indicate 12 years, 6 months, and 5 days).
+#age:
+# Choose from {MALE, FEMALE}
+#sex:
+# Path to a VCF file (optional)
+#vcf:

lirical-io/src/main/java/org/monarchinitiative/lirical/io/analysis/YamlAnalysisDataParser.java

@@ -58,6 +58,9 @@ public AnalysisData parse(InputStream is) throws LiricalParseException {
 
 
     private static Sex parseSex(String sex) {
+        if (sex == null)
+            return Sex.UNKNOWN;
+
         return switch (sex.toLowerCase()) {
             case "male" -> Sex.MALE;
             case "female" -> Sex.FEMALE;

lirical-io/src/main/java/org/monarchinitiative/lirical/io/analysis/YamlConfig.java

@@ -10,11 +10,11 @@
  */
 public class YamlConfig {
 
-    private String sampleId;
-    private List<String> hpoIds;
-    private List<String> negatedHpoIds;
+    private String sampleId = "Sample ID";
+    private List<String> hpoIds = List.of();
+    private List<String> negatedHpoIds = List.of();
     private String age;
-    private String sex;
+    private String sex = "UNKNOWN";
     private String vcf;
 
     public void setSampleId(String sampleId) {
@@ -66,7 +66,7 @@ public String vcf() {
     }
 
     public Optional<Path> vcfPath() {
-        return vcf == null ?
+        return vcf == null || vcf.isBlank() ?
                 Optional.empty()
                 : Optional.of(Path.of(vcf));
     }