feat: support for semi-enzymatic digests (#92)

- propagate semi_enzymatic through to output
- add "database.enzyme.semi_enzymatic" parameter, property-based tests for missed cleavages

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+### Added
+- Support for semi-enzymatic digests (`database.enzyme.semi_enzymatic` parameter)
+
 ## [v0.14.4]
 ### Added
 - **Unstable feature**: Preliminary support for reading Bruker .d folders (ddaPASEF; no MS1/LFQ support yet)

DOCS.md

@@ -161,7 +161,8 @@ For additional information about configuration options and output file formats,
       "max_len": 50,          // Optional[int] {default=50}, Maximum AA length of peptides to search
       "cleave_at": "KR",      // Optional[str] {default='KR'}. Amino acids to cleave at
       "restrict": "P",        // Optional[char/single AA] {default='P'}. Do not cleave if this AA follows the cleavage site
-      "c_terminal": true      // Optional[bool] {default=true}. Cleave at c terminus of matching amino acid
+      "c_terminal": false,      // Optional[bool] {default=true}. Cleave at c terminus of matching amino acid
+      "semi_enzymatic": false      // Optional[bool] {default=false}. Generate semi-enzymatic peptides
     },
     "fragment_min_mz": 200.0,       // Optional[float] {default=150.0}, Minimum mass of fragments to search
     "fragment_max_mz": 2000.0,      // Optional[float] {default=2000.0}, Maximum mass of fragments to search 

crates/sage-cli/src/output.rs

@@ -37,6 +37,11 @@ impl Runner {
                 .format(feature.missed_cleavages)
                 .as_bytes(),
         );
+        record.push_field(
+            itoa::Buffer::new()
+                .format(peptide.semi_enzymatic as u8)
+                .as_bytes(),
+        );
         record.push_field(ryu::Buffer::new().format(feature.isotope_error).as_bytes());
         record.push_field(ryu::Buffer::new().format(feature.delta_mass).as_bytes());
         record.push_field(ryu::Buffer::new().format(feature.average_ppm).as_bytes());
@@ -104,6 +109,7 @@ impl Runner {
             "charge",
             "peptide_len",
             "missed_cleavages",
+            "semi_enzymatic",
             "isotope_error",
             "precursor_ppm",
             "fragment_ppm",
@@ -208,6 +214,11 @@ impl Runner {
                 .format(feature.missed_cleavages)
                 .as_bytes(),
         );
+        record.push_field(
+            itoa::Buffer::new()
+                .format(peptide.semi_enzymatic as u8)
+                .as_bytes(),
+        );
         record.push_field(ryu::Buffer::new().format(feature.isotope_error).as_bytes());
         record.push_field(
             ryu::Buffer::new()
@@ -256,6 +267,11 @@ impl Runner {
                 .format((-feature.poisson).ln_1p())
                 .as_bytes(),
         );
+        record.push_field(
+            ryu::Buffer::new()
+                .format(feature.posterior_error)
+                .as_bytes(),
+        );
         record.push_field(peptide.to_string().as_bytes());
         record.push_field(
             peptide
@@ -289,6 +305,7 @@ impl Runner {
             "z=other",
             "peptide_len",
             "missed_cleavages",
+            "semi_enzymatic",
             "isotope_error",
             "ln(precursor_ppm)",
             "fragment_ppm",
@@ -305,6 +322,7 @@ impl Runner {
             "ln(matched_intensity_pct)",
             "scored_candidates",
             "ln(-poisson)",
+            "posterior_error",
             "Peptide",
             "Proteins",
         ]);

crates/sage/src/database.rs

@@ -23,6 +23,7 @@ pub struct EnzymeBuilder {
     pub cleave_at: Option<String>,
     pub restrict: Option<char>,
     pub c_terminal: Option<bool>,
+    pub semi_enzymatic: Option<bool>,
 }
 
 impl Default for EnzymeBuilder {
@@ -34,6 +35,7 @@ impl Default for EnzymeBuilder {
             cleave_at: Some("KR".into()),
             restrict: Some('P'),
             c_terminal: Some(true),
+            semi_enzymatic: Some(false),
         }
     }
 }
@@ -48,6 +50,7 @@ impl From<EnzymeBuilder> for EnzymeParameters {
                 &en.cleave_at.unwrap_or_else(|| "KR".into()),
                 en.restrict,
                 en.c_terminal.unwrap_or(true),
+                en.semi_enzymatic.unwrap_or(false),
             ),
         }
     }