Merge pull request #24 from PacificBiosciences/sv_variant_relax

syncing changes for 1.3.0

CHANGELOG.md

@@ -1,3 +1,13 @@
+# v1.3.0
+## Changes
+- Relaxes the requirements for SV deletion and insertion events such that they no longer require an alternate or reference allele, respectively, to have length 1
+
+## Internal changes
+- The interface for variant creation was modified to reduce panics from invalid variant construction. This modification changes all the return types for the various `Variant::new*(...)` functions from `Variant` to `Result<Variant, VariantError>`.
+
+## Fixed
+- SV events with a placeholder ALT sequence (e.g., \<DEL\>, \<INS\>) are now properly ignored by HiPhase instead of creating an error.
+
 # v1.2.1
 ## Fixed
 - Fixed [a rare issue](https://github.com/PacificBiosciences/pbbioconda/issues/640) where reference alleles with stripped IUPAC codes were throwing errors due to reference mismatch

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "hiphase"
-version = "1.2.1"
+version = "1.3.0"
 authors = ["J. Matthew Holt <mholt@pacificbiosciences.com>"]
 description = "A tool for jointly phasing small, structural, and tandem repeat variants for PacBio sequencing data"
 edition = "2021"
@@ -31,6 +31,7 @@ rust-htslib = { version = "0.39.5", default-features = false, features = ["stati
 rustc-hash = "1.1.0"
 serde = "1.0.147"
 simple-error = "0.2.3"
+thiserror = "1.0.56"
 threadpool = "1.8.1"
 
 [profile.release]

LICENSE-THIRDPARTY.json

@@ -496,7 +496,7 @@
   },
   {
     "name": "hiphase",
-    "version": "1.2.1",
+    "version": "1.3.0",
     "authors": "J. Matthew Holt <mholt@pacificbiosciences.com>",
     "repository": null,
     "license": null,
@@ -910,7 +910,7 @@
   },
   {
     "name": "proc-macro2",
-    "version": "1.0.58",
+    "version": "1.0.78",
     "authors": "David Tolnay <dtolnay@gmail.com>|Alex Crichton <alex@alexcrichton.com>",
     "repository": "https://github.com/dtolnay/proc-macro2",
     "license": "Apache-2.0 OR MIT",
@@ -928,7 +928,7 @@
   },
   {
     "name": "quote",
-    "version": "1.0.27",
+    "version": "1.0.35",
     "authors": "David Tolnay <dtolnay@gmail.com>",
     "repository": "https://github.com/dtolnay/quote",
     "license": "Apache-2.0 OR MIT",
@@ -1160,6 +1160,15 @@
     "license_file": null,
     "description": "Parser for Rust source code"
   },
+  {
+    "name": "syn",
+    "version": "2.0.48",
+    "authors": "David Tolnay <dtolnay@gmail.com>",
+    "repository": "https://github.com/dtolnay/syn",
+    "license": "Apache-2.0 OR MIT",
+    "license_file": null,
+    "description": "Parser for Rust source code"
+  },
   {
     "name": "termcolor",
     "version": "1.1.3",
@@ -1171,7 +1180,7 @@
   },
   {
     "name": "thiserror",
-    "version": "1.0.37",
+    "version": "1.0.56",
     "authors": "David Tolnay <dtolnay@gmail.com>",
     "repository": "https://github.com/dtolnay/thiserror",
     "license": "Apache-2.0 OR MIT",
@@ -1180,7 +1189,7 @@
   },
   {
     "name": "thiserror-impl",
-    "version": "1.0.37",
+    "version": "1.0.56",
     "authors": "David Tolnay <dtolnay@gmail.com>",
     "repository": "https://github.com/dtolnay/thiserror",
     "license": "Apache-2.0 OR MIT",

src/block_gen.rs

@@ -152,7 +152,7 @@ pub fn is_phasable_variant(record: &bcf::Record, sample_index: usize, min_qualit
             VariantType::SvDuplication |
             VariantType::SvInversion |
             VariantType::SvBreakend |
-            VariantType::Unknown=> { Ok(false) }
+            VariantType::Unknown => { Ok(false) }
         }
     }
 }
@@ -231,6 +231,12 @@ pub fn get_variant_type(record: &bcf::Record) -> Result<VariantType, Box<dyn std
                 // make sure these only have one ALT allele
                 let num_alleles = record.alleles().len();
                 assert_eq!(num_alleles, 2);
+
+                // make sure the alternate allele is not a placeholder like <DEL>; if so, return Unknown because we do not want to phase it
+                let alt_allele = std::str::from_utf8(record.alleles()[1]).unwrap_or("<unknown>");
+                if alt_allele.starts_with('<') && alt_allele.ends_with('>') {
+                    return Ok(VariantType::Unknown);
+                }
 
                 let svtype_str = std::str::from_utf8(svtype[0]).unwrap();
                 let sv_tag = match svtype_str {