Added general open identified peptides file function

.vscode/settings.json

@@ -116,6 +116,7 @@
                 "Psicose",
                 "Psimod",
                 "psms",
+                "psmtsv",
                 "pyclass",
                 "pymethods",
                 "pymodule",

Cargo.toml

@@ -7,6 +7,8 @@ members = [
     "examples/*",
 ]
 resolver = "2"
+package.edition = "2021"
+package.version = "0.9.0-alpha.1"
 
 [profile.release]
 debug = true

examples/de-novo-align/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "de-novo-align"
+version = "0.1.0"
+publish = false
+edition.workspace = true
+
+[dependencies]
+rustyms = { path = "../../rustyms" }
+clap = { workspace = true, features = ["derive", "cargo"] }
+itertools = { workspace = true }
+rayon = { workspace = true }
+serde_json = { workspace = true }

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

@@ -0,0 +1,36 @@
+use std::{
+    fs::File,
+    io::{BufReader, BufWriter},
+};
+
+use clap::Parser;
+use fragment::FragmentType;
+use identification::{open_identified_peptides_file, FastaData};
+use itertools::Itertools;
+use rayon::prelude::*;
+use rustyms::{
+    spectrum::{Score, Scores},
+    system::{e, usize::Charge},
+    *,
+};
+use spectrum::PeakSpectrum;
+use std::collections::HashMap;
+
+#[derive(Parser)]
+struct Cli {
+    /// The input identified peptides file
+    #[arg(short, long)]
+    peptides: String,
+    /// The fasta database of known proteins
+    #[arg(short, long)]
+    database: String,
+    /// Where to store the results
+    #[arg(long)]
+    out_path: String,
+}
+
+fn main() {
+    let args = Cli::parse();
+    let peptides = open_identified_peptides_file(args.peptides, None).unwrap();
+    let database = FastaData::parse_file(args.database).unwrap();
+}

examples/multi-annotator/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "multi-annotator"
 version = "0.1.0"
-edition = "2021"
+edition.workspace = true
 publish = false
 
 [dependencies]

fuzz/Cargo.toml

@@ -2,7 +2,7 @@
 name = "rustyms-fuzz"
 version = "0.0.0"
 publish = false
-edition = "2021"
+edition.workspace = true
 
 [package.metadata]
 cargo-fuzz = true

rustyms-imgt-generate/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "rustyms-imgt-generate"
 version = "0.1.0"
-edition = "2021"
+edition.workspace = true
 license = "MIT OR Apache-2.0"
 authors = ["Douwe Schulte <[email protected]>"]
 rust-version = "1.70.0"

rustyms-py/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "rustyms-py"
-version = "0.9.0-alpha.1"
-edition = "2021"
+version.workspace = true
+edition.workspace = true
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 [lib]

rustyms/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "rustyms"
-version = "0.9.0-alpha.1"
-edition = "2021"
+version.workspace = true
+edition.workspace = true
 license = "MIT OR Apache-2.0"
 authors = ["Douwe Schulte <[email protected]>"]
 description = "A library to handle proteomic mass spectrometry data and match peptides to spectra."

rustyms/src/identification/fasta.rs

@@ -4,7 +4,10 @@ use crate::{
     CompoundPeptidoform, LinearPeptide, SequenceElement,
 };
 use serde::{Deserialize, Serialize};
-use std::io::{BufRead, BufReader};
+use std::{
+    io::{BufRead, BufReader},
+    path::Path,
+};
 
 use super::{IdentifiedPeptide, MetaData};
 
@@ -21,12 +24,13 @@ impl FastaData {
     /// Parse a single fasta file
     /// # Errors
     /// A custom error when it is not a valid fasta file
-    pub fn parse_file(path: &str) -> Result<Vec<Self>, CustomError> {
+    pub fn parse_file(path: impl AsRef<Path>) -> Result<Vec<Self>, CustomError> {
+        let path = path.as_ref();
         let file = std::fs::File::open(path).map_err(|_| {
             CustomError::error(
                 "Failed reading fasta file",
                 "Error occurred while opening the file",
-                Context::show(path),
+                Context::show(path.to_string_lossy()),
             )
         })?;
         let reader = BufReader::new(file);
@@ -39,7 +43,7 @@ impl FastaData {
                 CustomError::error(
                     "Failed reading fasta file",
                     format!("Error occurred while reading line {}", line_index + 1),
-                    Context::show(path),
+                    Context::show(path.to_string_lossy()),
                 )
             })?;
             #[allow(clippy::manual_strip)]

rustyms/src/identification/general.rs

@@ -0,0 +1,69 @@
+use std::path::Path;
+
+use super::{
+    error::{Context, CustomError},
+    ontologies::CustomDatabase,
+    FastaData, IdentifiedPeptide, IdentifiedPeptideIter, IdentifiedPeptideSource, MSFraggerData,
+    MaxQuantData, NovorData, OpairData, PeaksData, SageData,
+};
+
+/// Open the selected path and automatically determine the file type.
+/// # Errors
+/// It errors if the file type could not be determined or if opening the file errors.
+pub fn open_identified_peptides_file<'a>(
+    path: impl AsRef<Path>,
+    custom_database: Option<&'a CustomDatabase>,
+) -> Result<Box<dyn Iterator<Item = Result<IdentifiedPeptide, CustomError>> + 'a>, CustomError> {
+    let path = path.as_ref();
+    let actual_extension = path
+        .extension()
+        .map(|ex| {
+            (ex == "gz")
+                .then_some(path)
+                .and_then(|p| p.file_stem())
+                .and_then(|p| Path::new(p).extension())
+                .unwrap_or(ex)
+        })
+        .map(|ex| ex.to_string_lossy().to_lowercase());
+    match actual_extension.as_deref() {
+        Some("csv") => PeaksData::parse_file(path, custom_database)
+            .map(IdentifiedPeptideIter::into_box)
+            .or_else(|_| {
+                NovorData::parse_file(path, custom_database).map(IdentifiedPeptideIter::into_box)
+            })
+            .map_err(|_| {
+                CustomError::error(
+                    "Unknown file",
+                    "Could not be recognised as either a Peaks or Novor file",
+                    Context::show(path.to_string_lossy()),
+                )
+            }),
+        Some("tsv") => MSFraggerData::parse_file(path, custom_database)
+            .map(IdentifiedPeptideIter::into_box)
+            .or_else(|_| {
+                SageData::parse_file(path, custom_database).map(IdentifiedPeptideIter::into_box)
+            })
+            .map_err(|_| {
+                CustomError::error(
+                    "Unknown file",
+                    "Could not be recognised as either a MSFragger or Sage file",
+                    Context::show(path.to_string_lossy()),
+                )
+            }),
+        Some("psmtsv") => {
+            OpairData::parse_file(path, custom_database).map(IdentifiedPeptideIter::into_box)
+        }
+        Some("fasta") => FastaData::parse_file(path).map(|peptides| {
+            Box::new(peptides.into_iter().map(|p| Ok(p.into())))
+                as Box<dyn Iterator<Item = Result<IdentifiedPeptide, CustomError>> + 'a>
+        }),
+        Some("txt") => {
+            MaxQuantData::parse_file(path, custom_database).map(IdentifiedPeptideIter::into_box)
+        }
+        _ => Err(CustomError::error(
+            "Unknown extension",
+            "Use CSV, TSV, TXT, PSMTSV, or Fasta, or any of these as a gzipped file (eg csv.gz).",
+            Context::show(path.to_string_lossy()),
+        )),
+    }
+}

rustyms/src/identification/identified_peptide.rs

@@ -237,3 +237,19 @@ where
         }
     }
 }
+
+impl<'lifetime, R, I> IdentifiedPeptideIter<'lifetime, R, I>
+where
+    R: IdentifiedPeptideSource + Into<IdentifiedPeptide> + 'lifetime,
+    I: Iterator<Item = Result<R::Source, CustomError>> + 'lifetime,
+    R::Format: 'static,
+{
+    pub(super) fn into_box(
+        self,
+    ) -> Box<dyn Iterator<Item = Result<IdentifiedPeptide, CustomError>> + 'lifetime> {
+        Box::new(self.map(|p: Result<R, CustomError>| match p {
+            Ok(p) => Ok(p.into()),
+            Err(e) => Err(e),
+        }))
+    }
+}

rustyms/src/identification/mod.rs

@@ -4,6 +4,7 @@
 mod common_parser;
 
 mod fasta;
+mod general;
 mod helper_functions;
 mod identified_peptide;
 mod maxquant;
@@ -15,6 +16,7 @@ mod sage;
 
 use crate::*;
 pub use fasta::*;
+pub use general::*;
 pub use identified_peptide::*;
 pub use maxquant::*;
 pub use msfragger::*;