Merge branch 'main' of https://github.com/snijderlab/rustyms

.github/workflows/generate-databases.yml

@@ -0,0 +1,49 @@
+name: Generate databases
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "7 4 1 * *"
+  push:
+    branches: ["release", "main"]
+
+permissions:
+  contents: write
+  pull-requests: write
+
+env:
+  CARGO_TERM_COLOR: always
+  CARGO_ENCODED_RUSTFLAGS: --cfg=github_action
+
+jobs:
+  generate-databases:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Check
+        run: cargo check
+      - name: Download and build external databases
+        run: |
+          bash ./.github/workflows/scripts/update-all-databases.sh
+          MESSAGE="$(cat /tmp/MESSAGES)"
+          echo "MESSAGE=${MESSAGE}" >> "${GITHUB_ENV}"
+      - name: Create pull request
+        id: cpr
+        uses: peter-evans/create-pull-request@v7
+        with:
+          token: ${{ secrets.RUSTEOMICS_MZCORE_PR_TOKEN }}
+          commit-message: Update external databases and ontologies
+          committer: GitHub <[email protected]>
+          author: GitHub <[email protected]>
+          branch: update-databases
+          delete-branch: true
+          title: "Update external databases and ontologies"
+          body: |
+            This automated PR updates the binary blobs for external databases
+            and ontologies.
+
+            Below are messages from script execution:
+              > ${{ env.MESSAGE }}
+          labels: |
+            A-rustyms-generate-databases
+            C-maintenance

.github/workflows/scripts/update-all-databases.sh

@@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+
+
+function help {
+    echo "Usage: generate-all-databases.sh"
+    echo ""
+    echo "Download the required databases and build the "
+    echo "required binary representations of the ontologies."
+    echo ""
+    echo "Options:"
+    echo "  -h, --help     Display this help and exit"
+    exit 1
+}
+
+
+# Download IMGT and process and serialize it to a binary blob.
+function make-imgt {
+    echo "Downloading IMGT..."
+    mkdir -p rustyms-generate-imgt/data
+    # IMGT is not very reliable, so sometimes the server is down.
+    # The || clause here allows the rest of the script to continue
+    # even if this fails.
+    curl https://www.imgt.org/download/LIGM-DB/imgt.dat.Z \
+        | gunzip -c > rustyms-generate-imgt/data/imgt.dat \
+        && echo "Serializing IMGT ..." \
+        && cargo run --bin rustyms-generate-imgt \
+        || echo "Failed to download IMGT. I did not update it." >> /tmp/MESSAGES
+}
+
+
+# Download the relevant ontologies and serialize them to binary blobs.
+function make-ontologies {
+    echo "Downloading databases..."
+    db_data="rustyms-generate-databases/data"
+    mkdir -p ${db_data}
+    curl https://raw.githubusercontent.com/HUPO-PSI/psi-mod-CV/refs/heads/master/PSI-MOD-newstyle.obo \
+        > ${db_data}/PSI-MOD-newstyle.obo
+    curl http://www.unimod.org/obo/unimod.obo > ${db_data}/unimod.obo
+    curl ftp://ftp.proteininformationresource.org/pir_databases/other_databases/resid/RESIDUES.XML \
+        > ${db_data}/RESID-RESIDUES.XML
+    curl https://raw.githubusercontent.com/HUPO-PSI/mzIdentML/master/cv/XLMOD.obo \
+        > ${db_data}/XLMOD.obo
+    curl -L http://purl.obolibrary.org/obo/gno.obo \
+        | sed '/(property_value: GNO:00000(022|023|041|042|101|102) .*$\n)|(def: .*$\n)/d' \
+        | gzip -c \
+        > ${db_data}/GNOme.obo.gz
+    curl -L https://glycosmos.org/download/glycosmos_glycans_list.csv \
+        | gzip -c > ${db_data}/glycosmos_glycans_list.csv.gz
+
+
+    echo "Serializing the other databases..."
+    cargo run --bin rustyms-generate-databases
+}
+
+
+function main {
+    while [[ $# -gt 0 ]]; do
+        case "$1" in
+            -h|--help)
+                help
+                ;;
+            *)
+                echo "Unknown argument: $1"
+                help
+                ;;
+        esac
+    done
+
+    touch /tmp/MESSAGES
+
+    make-imgt
+    make-ontologies
+}
+
+
+main "$@"

.gitignore

@@ -1,3 +1,6 @@
+rustyms-generate-databases/data/*
+!rustyms-generate-databases/data/CIAAW*
+!rustyms-generate-databases/data/IUPAC*
 /target
 Cargo.lock
 */target/
@@ -11,4 +14,4 @@ docs/**/_build/
 out
 out_peaks
 out_pro_forma
-out_sloppy_pro_forma
+out_sloppy_pro_forma

CITATION.cff

@@ -0,0 +1,37 @@
+title: rustyms
+version: 0.9.0
+abstract:  A rust library for parsing Pro Forma peptides and matching them against MS spectra .
+authors:
+  - affiliation: Utrecht University
+    family-names: Schulte
+    given-names: Douwe
+    orcid: https://orcid.org/0000-0003-0594-0993
+  - affiliation: VIB-UGent Center for Medical Biotechnology
+    family-names: Gabriels
+    given-names: Ralf
+    orcid: https://orcid.org/0000-0002-1679-1711
+  - affiliation: Utrecht University
+    family-names: Heerdink
+    given-names: Auke
+cff-version: 1.2.0
+identifiers:
+  - description: Main paper (preprint)
+    type: doi
+    value: 10.1101/2025.01.18.633732 
+  - description: Mass alignment algorithm paper
+    type: doi
+    value: 10.1021/acs.jproteome.4c00188
+  - description: Mass alignment algorithm paper (preprint)
+    type: url
+    value: https://www.biorxiv.org/content/10.1101/2024.02.20.581155v1
+  - description: Repository
+    type: url
+    value: https://github.com/snijderlab/rustyms
+keywords:
+  - sequencing
+  - antibody
+  - mass-spectrometry
+  - de novo
+license: MIT OR Apache-2.0
+message: If you use this software, please cite it using these metadata.
+repository-code: https://github.com/snijderlab/rustyms

Cargo.toml

@@ -15,8 +15,8 @@ package.authors = [
 ]
 package.edition = "2021"
 package.license = "MIT OR Apache-2.0"
-package.rust-version = "1.75.0"
-package.version = "0.9.0-alpha.3"
+package.rust-version = "1.84.0"
+package.version = "0.9.0"
 
 [profile.release]
 debug = true
@@ -29,21 +29,28 @@ codegen-units = 1
 afl = "0.15"
 bincode = "1.3"
 clap = { version = "4.5", features = ["derive", "cargo"] }
-directories = "5.0"
+directories = "6.0"
 flate2 = "1.0"
 iai-callgrind = "0.14"
-itertools = "0.13"
-mzdata = "0.40"
+itertools = "0.14"
+mzdata = "0.44"
 ndarray = "0.16"
-ordered-float = { version = "4.5", features = ["serde"] }
+ordered-float = { version = "4.6", features = ["serde"] }
 probability = "0.20"
 pyo3 = "0.23"
-rand = "0.8"
-rayon = "1.9"
+rand = "0.9"
+rayon = "1.10"
 regex = "1.11"
 roxmltree = "0.20"
 serde = { version = "1.0", features = ["derive", "rc"] }
 serde_json = "1.0"
-similar = "2.6"
+similar = "2.7"
 thin-vec = { version = "0.2", features = ["serde"] }
 uom = { version = "0.36", features = ["use_serde", "usize", "isize"] }
+
+[workspace.lints.rust]
+unexpected_cfgs = { level = "allow", check-cfg = [
+    "cfg(github_action)",
+    "cfg(si)",
+    "cfg(f32)",
+] }

README.md

@@ -3,22 +3,22 @@
 
 # Match those fragments!
 
-A peptide fragmentation matching library for Rust. Built to handle very complex peptides in a sensible way.
+A peptide fragmentation matching library for Rust. Built to handle very complex peptidoforms in a sensible way.
 
 ## Features
 
- - Read [ProForma](https://github.com/HUPO-PSI/ProForma) sequences (complete specification supported: 'level 2-ProForma + top-down compliant + cross-linking compliant + glycans compliant + mass spectrum compliant')
- - Generate theoretical fragments with control over the fragmentation model from any ProForma peptidoform/proteoform
+ - Read [ProForma](https://github.com/HUPO-PSI/ProForma) sequences (complete 2.0 specification supported: 'level 2-ProForma + top-down compliant + cross-linking compliant + glycans compliant + mass spectrum compliant')
+ - Generate theoretical fragments with control over the fragmentation model from any ProForma peptidoform
    - Generate theoretical fragments for chimeric spectra
    - Generate theoretical fragments for cross-links (also disulfides)
    - Generate theoretical fragments for modifications of unknown position
-   - Generate peptide backbone (a, b, c, x, y, and z) and satellite ion fragments (w, d, and v)
+   - Generate peptide backbone (a, b, c, x, y, and z) and satellite ion fragments (d, v, and w)
    - Generate glycan fragments (B, Y, and internal fragments)
  - Integrated with [mzdata](https://crates.io/crates/mzdata) for reading raw data files
  - Match spectra to the generated fragments
  - [Align peptides based on mass](https://pubs.acs.org/doi/10.1021/acs.jproteome.4c00188)
  - Fast access to the IMGT database of antibody germlines
- - Reading of multiple identified peptide file formats (Fasta, MaxQuant, MSFragger, Novor, OPair, Peaks, and Sage)
+ - Reading of multiple identified peptide file formats (among others: Fasta, MaxQuant, MSFragger, Novor, OPair, Peaks, and Sage)
  - Exhaustively fuzz tested for reliability (using [cargo-afl](https://crates.io/crates/cargo-afl))
  - Extensive use of [uom](https://docs.rs/uom/latest/uom/) for compile time unit checking
  - Python bindings are provided to several core components of the rustyms library. Go to the [Python documentation](https://rustyms.readthedocs.io/) for more information.

docs/python/source/index.md

@@ -17,7 +17,7 @@ Python bindings are provided to several core components of the rustyms library,
 - {py:class}`~rustyms.Fragment` Theoretical fragment ion
 - {py:class}`~rustyms.SequenceElement` One position in a peptide sequence with amino acid and
   modifications
-- {py:class}`~rustyms.LinearPeptide` Peptide sequence, modifications, and charge, using
+- {py:class}`~rustyms.CompoundPeptidoformIon` Peptide sequence, modifications, and charge, using
   [ProForma 2.0](https://proforma.readthedocs.io) (see {ref}`ProForma support` for more
   information)
 - {py:class}`~rustyms.RawPeak` A single peak in a mass spectrum
@@ -43,7 +43,7 @@ raw_spectrum = rustyms.RawSpectrum(
 )
 
 # Create a new peptide from a ProForma 2.0 string
-peptide = rustyms.LinearPeptide("ACDE/2")
+peptide = rustyms.CompoundPeptidoformIon("ACDE/2")
 
 # Annotate the spectrum with the peptide
 annotated_spectrum = raw_spectrum.annotate(peptide, "cid_hcd")
@@ -68,7 +68,6 @@ rustyms Python bindings.
 :maxdepth: 2
 
 About <self>
-proforma-support
 api
 contributing
 ```

examples/de-novo-align/Cargo.toml

@@ -12,3 +12,6 @@ clap = { workspace = true }
 itertools = { workspace = true }
 rayon = { workspace = true }
 serde_json = { workspace = true }
+
+[lints]
+workspace = true

examples/de-novo-align/src/main.rs

@@ -51,7 +51,7 @@ fn main() {
                         peptide,
                         align::<4, SemiAmbiguous, SemiAmbiguous>(
                             db.peptide(),
-                            &linear_peptide,
+                            linear_peptide,
                             AlignScoring::default(),
                             AlignType::EITHER_GLOBAL,
                         ),

examples/multi-annotator/Cargo.toml

@@ -13,3 +13,6 @@ directories = { workspace = true }
 itertools = { workspace = true }
 rayon = { workspace = true }
 serde_json = { workspace = true }
+
+[lints]
+workspace = true

examples/multi-annotator/src/main.rs

@@ -98,7 +98,7 @@ fn main() {
                     .parse::<usize>()
                     .unwrap();
                 let z = line.index_column("z").unwrap().0.parse::<usize>().unwrap();
-                let peptide = CompoundPeptidoform::pro_forma(
+                let peptide = CompoundPeptidoformIon::pro_forma(
                     line.index_column("sequence").unwrap().0,
                     custom_database.as_ref(),
                 )

fuzz/Cargo.toml

@@ -33,3 +33,6 @@ path = "fuzz_targets/peaks.rs"
 test = false
 doc = false
 bench = false
+
+[lints]
+workspace = true

fuzz/fuzz_targets/peaks.rs

@@ -21,7 +21,7 @@ impl<'a> StringReader<'a> {
     }
 }
 
-impl<'a> Read for StringReader<'a> {
+impl Read for StringReader<'_> {
     fn read(&mut self, buf: &mut [u8]) -> Result<usize> {
         for (i, item) in buf.iter_mut().enumerate() {
             if let Some(x) = self.iter.next() {

fuzz/fuzz_targets/pro_forma.rs

@@ -3,7 +3,7 @@ use afl::*;
 fn main() {
     fuzz!(|data: &[u8]| {
         if let Ok(s) = std::str::from_utf8(data) {
-            let _ = rustyms::CompoundPeptidoform::pro_forma(s, None);
+            let _ = rustyms::CompoundPeptidoformIon::pro_forma(s, None);
         }
     });
 }

fuzz/fuzz_targets/sloppy_pro_forma.rs

@@ -3,7 +3,7 @@ use afl::*;
 fn main() {
     fuzz!(|data: &[u8]| {
         if let Ok(s) = std::str::from_utf8(data) {
-            let _ = rustyms::LinearPeptide::sloppy_pro_forma(
+            let _ = rustyms::Peptidoform::sloppy_pro_forma(
                 s,
                 0..s.len(),
                 None,

rustyms-generate-databases/Cargo.toml

@@ -20,3 +20,6 @@ uom = { workspace = true }
 
 [features]
 rayon = []
+
+[lints]
+workspace = true