fix!: adjusting enum values (#279)

This adds a dummy "_UNKNOWN = 0;" value to all enums for compatility
with pb-json package.

Release-As: 0.21.0

Cargo.toml

@@ -27,7 +27,7 @@ path = "src/main.rs"
 
 [dependencies]
 actix-web = "4.4"
-annonars = "0.24"
+annonars = "0.29"
 anyhow = "1.0"
 async-compression = { version = "0.4", features = ["tokio", "gzip"] }
 bgzip = "0.3"
@@ -53,10 +53,10 @@ log = "0.4"
 nom = "7.1"
 noodles-bgzf = { version = "0.25", features = ["async"] }
 noodles-core = "0.12"
-noodles-csi = "0.26"
+noodles-csi = "0.28"
 noodles-fasta = "0.30"
-noodles-tabix = "0.32"
-noodles-vcf = { version = "0.45", features = ["async"] }
+noodles-tabix = "0.34"
+noodles-vcf = { version = "0.47", features = ["async"] }
 parse-display = "0.8"
 procfs = "0.16"
 prost = "0.12"
@@ -95,3 +95,9 @@ pretty_assertions = "1.4"
 rstest = "0.18"
 temp_testdir = "0.2"
 tracing-test = "0.2"
+
+# Compile insta with full optimization.
+[profile.dev.package.insta]
+opt-level = 3
+[profile.dev.package.similar]
+opt-level = 3

build.rs

@@ -1,7 +1,6 @@
 // The custo build script, used to (1) generate the Rust classes for the
 // protobuf implementation and (2) use pbjson for proto3 JSON serialization.
 
-use pbjson_build;
 use std::{env, path::PathBuf};
 
 fn main() -> Result<(), anyhow::Error> {

protos/mehari/txs.proto

@@ -35,26 +35,30 @@ message TranscriptDb {
 
 // Enumeration for `Transcript::biotype`.
 enum TranscriptBiotype {
+    // unknown
+    TRANSCRIPT_BIOTYPE_UNKNOWN = 0;
     // Coding transcript.
-    CODING = 0;
+    TRANSCRIPT_BIOTYPE_CODING = 1;
     // Non-coding transcript.
-    NON_CODING = 1;
+    TRANSCRIPT_BIOTYPE_NON_CODING = 2;
 }
 
 // Bit values for the transcript tags.
-enum TranscriptTag{
+enum TranscriptTag {
+    // unknown
+    TRANSCRIPT_TAG_UNKNOWN = 0;
     // Member of Ensembl basic.
-    BASIC = 0;
+    TRANSCRIPT_TAG_BASIC = 1;
     // Member of Ensembl canonical.
-    ENSEMBL_CANONICAL = 1;
+    TRANSCRIPT_TAG_ENSEMBL_CANONICAL = 2;
     // Member of MANE Select.
-    MANE_SELECT = 2;
+    TRANSCRIPT_TAG_MANE_SELECT = 3;
     // Member of MANE Plus Clinical.
-    MANE_PLUS_CLINICAL = 3;
+    TRANSCRIPT_TAG_MANE_PLUS_CLINICAL = 4;
     // Member of RefSeq Select.
-    REF_SEQ_SELECT = 4;
+    TRANSCRIPT_TAG_REF_SEQ_SELECT = 5;
     // Flagged as being a selenoprotein (UGA => selenon).
-    SELENOPROTEIN = 5;
+    TRANSCRIPT_TAG_SELENOPROTEIN = 6;
 }
 
 // Store information about a transcript.
@@ -80,19 +84,23 @@ message Transcript {
 }
 
 // Enumeration for the known genome builds.
-enum GenomeBuild{
+enum GenomeBuild {
+    // unknown
+    GENOME_BUILD_UNKNOWN = 0;
     // GRCH37.
-    GRCH37 = 0;
+    GENOME_BUILD_GRCH37 = 1;
     // GRCh38.
-    GRCH38 = 1;
+    GENOME_BUILD_GRCH38 = 2;
 }
 
 // Enumeration for the two strands of the genome.
-enum Strand{
+enum Strand {
+    // unknown
+    STRAND_UNKNOWN = 0;
     // Forward / plus
-    PLUS = 0;
+    STRAND_PLUS = 1;
     // Reverse / minus
-    MINUS = 1;
+    STRAND_MINUS = 2;
 }
 
 // Store information about a transcript aligning to a genome.

src/annotate/seqvars/csq.rs

@@ -398,6 +398,7 @@ impl ConsequencePredictor {
                     match Strand::try_from(alignment.strand).expect("invalid strand") {
                         Strand::Plus => consequences.push(Consequence::SpliceDonorVariant),
                         Strand::Minus => consequences.push(Consequence::SpliceAcceptorVariant),
+                        _ => unreachable!("invalid strand: {}", alignment.strand),
                     }
                 }
                 // Check the case where the variant overlaps with the splice donor site.
@@ -406,6 +407,7 @@ impl ConsequencePredictor {
                     match Strand::try_from(alignment.strand).expect("invalid strand") {
                         Strand::Plus => consequences.push(Consequence::SpliceAcceptorVariant),
                         Strand::Minus => consequences.push(Consequence::SpliceDonorVariant),
+                        _ => unreachable!("invalid strand: {}", alignment.strand),
                     }
                 }
             }
@@ -459,6 +461,7 @@ impl ConsequencePredictor {
             let mut feature_biotypes = vec![match transcript_biotype {
                 TranscriptBiotype::Coding => FeatureBiotype::Coding,
                 TranscriptBiotype::NonCoding => FeatureBiotype::Noncoding,
+                _ => unreachable!("invalid biotype: {:?}", transcript_biotype),
             }];
 
             if tx.tags.contains(&(TranscriptTag::ManeSelect as i32)) {
@@ -488,6 +491,7 @@ impl ConsequencePredictor {
                 match Strand::try_from(alignment.strand).expect("invalid strand") {
                     Strand::Plus => consequences.push(Consequence::UpstreamGeneVariant),
                     Strand::Minus => consequences.push(Consequence::DownstreamGeneVariant),
+                    _ => unreachable!("invalid strand: {}", alignment.strand),
                 }
             }
             if distance.is_none() {
@@ -499,6 +503,7 @@ impl ConsequencePredictor {
                 match Strand::try_from(alignment.strand).expect("invalid strand") {
                     Strand::Plus => consequences.push(Consequence::DownstreamGeneVariant),
                     Strand::Minus => consequences.push(Consequence::UpstreamGeneVariant),
+                    _ => unreachable!("invalid strand: {}", alignment.strand),
                 }
             }
             if distance.is_none() {
@@ -752,6 +757,7 @@ impl ConsequencePredictor {
                     (var_c, Some(var_p), hgvs_p, cds_pos, protein_pos)
                 }
                 TranscriptBiotype::NonCoding => (var_n, None, None, None, None),
+                _ => unreachable!("invalid transcript biotype: {:?}", transcript_biotype),
             };
             let hgvs_t = format!("{}", &var_t);
             let hgvs_t = hgvs_t.split(':').nth(1).unwrap().to_owned();

src/annotate/seqvars/mod.rs

@@ -417,15 +417,15 @@ where
 {
     if let Some(raw_value) = db.get_cf(cf, key)? {
         let clinvar_record =
-            clinvar_minimal::pbs::Record::decode(&mut std::io::Cursor::new(&raw_value))?;
+            annonars::pbs::clinvar::minimal::Record::decode(&mut std::io::Cursor::new(&raw_value))?;
 
-        let clinvar_minimal::pbs::Record {
+        let annonars::pbs::clinvar::minimal::Record {
             vcv,
             reference_assertions,
             ..
         } = clinvar_record;
         if let Some(reference_assertion) = reference_assertions.first() {
-            let clinvar_minimal::pbs::ReferenceAssertion {
+            let annonars::pbs::clinvar::minimal::ReferenceAssertion {
                 rcv,
                 clinical_significance,
                 ..

src/annotate/seqvars/provider.rs

@@ -432,6 +432,7 @@ impl ProviderInterface for Provider {
                         {
                             Strand::Plus => 1,
                             Strand::Minus => -1,
+                            _ => unreachable!("invalid strand {}", &genome_alignment.strand),
                         },
                         ord: exon.ord,
                         tx_start_i: exon.alt_cds_start_i.map(|val| val - 1).unwrap_or(-1),
@@ -530,6 +531,7 @@ impl ProviderInterface for Provider {
                     alt_strand: match Strand::try_from(alt_strand).expect("invalid strand") {
                         Strand::Plus => 1,
                         Strand::Minus => -1,
+                        _ => unreachable!("invalid strand {}", alt_strand),
                     },
                     alt_aln_method: ALT_ALN_METHOD.to_string(),
                     start_i,

src/annotate/seqvars/snapshots/mehari__annotate__seqvars__csq__test__annotate_snv_ttn_transcript_picking_reporting@2-179631246-G-A-false-true.snap

@@ -137,7 +137,6 @@ expression: res
   feature_id: NM_133379.5
   feature_biotype:
     - Coding
-    - ManePlusClinical
   rank:
     ord: 41
     total: 46

src/annotate/seqvars/snapshots/mehari__annotate__seqvars__csq__test__annotate_snv_ttn_transcript_picking_reporting@2-179631246-G-A-true-true.snap

@@ -33,35 +33,4 @@ expression: res
     total: 35992
   distance: 0
   messages: ~
-- allele:
-    Alt:
-      alternative: A
-  consequences:
-    - stop_gained
-  putative_impact: HIGH
-  gene_symbol: TTN
-  gene_id: "HGNC:12403"
-  feature_type:
-    SoTerm:
-      term: Transcript
-  feature_id: NM_133379.5
-  feature_biotype:
-    - Coding
-    - ManePlusClinical
-  rank:
-    ord: 41
-    total: 46
-  hgvs_t: c.9565C>T
-  hgvs_p: p.Q3189*
-  tx_pos:
-    ord: 9790
-    total: 18220
-  cds_pos:
-    ord: 9565
-    total: 16815
-  protein_pos:
-    ord: 3189
-    total: 5605
-  distance: 0
-  messages: ~
 

src/db/create/mod.rs

@@ -98,6 +98,7 @@ fn load_and_extract(
                     .collect::<Vec<_>>(),
             );
         }
+        tracing::info!("{:?}", txid_to_label);
 
         tracing::info!(
             "...done loading label TSV file ({} entries)",

src/db/create/snapshots/mehari__db__create__test__run_smoke_selenoproteins.snap

@@ -7,18 +7,19 @@ txDb:
   - id: NM_004261.5
     geneSymbol: SELENOF
     geneId: HGNC:17705
+    biotype: TRANSCRIPT_BIOTYPE_CODING
     tags:
-    - MANE_SELECT
-    - SELENOPROTEIN
+    - TRANSCRIPT_TAG_MANE_SELECT
+    - TRANSCRIPT_TAG_SELENOPROTEIN
     protein: NP_004252.2
     startCodon: 15
     stopCodon: 513
     genomeAlignments:
-    - genomeBuild: GRCH38
+    - genomeBuild: GENOME_BUILD_GRCH38
       contig: NC_000001.11
       cdsStart: 86863473
       cdsEnd: 86914111
-      strand: MINUS
+      strand: STRAND_MINUS
       exons:
       - altStartI: 86862444
         altEndI: 86863605
@@ -52,17 +53,18 @@ txDb:
   - id: NM_203341.3
     geneSymbol: SELENOF
     geneId: HGNC:17705
+    biotype: TRANSCRIPT_BIOTYPE_CODING
     tags:
-    - SELENOPROTEIN
+    - TRANSCRIPT_TAG_SELENOPROTEIN
     protein: NP_976086.1
     startCodon: 15
     stopCodon: 390
     genomeAlignments:
-    - genomeBuild: GRCH38
+    - genomeBuild: GENOME_BUILD_GRCH38
       contig: NC_000001.11
       cdsStart: 86863546
       cdsEnd: 86914111
-      strand: MINUS
+      strand: STRAND_MINUS
       exons:
       - altStartI: 86862444
         altEndI: 86863605