Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: ims model #98

Merged
merged 1 commit into from
Feb 3, 2024
Merged

Feature: ims model #98

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions crates/sage-cli/src/main.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,6 +275,8 @@ impl Runner {
self.parameters.mzml_paths.len(),
);
let _ = sage_core::ml::retention_model::predict(&self.database, &mut outputs.features);
let _ =
sage_core::ml::mobility_model::predict(&self.database, &mut outputs.features);
Some(alignments)
} else {
None
Expand Down
20 changes: 20 additions & 0 deletions crates/sage-cli/src/output.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,13 @@ impl Runner {
record.push_field(ryu::Buffer::new().format(feature.aligned_rt).as_bytes());
record.push_field(ryu::Buffer::new().format(feature.predicted_rt).as_bytes());
record.push_field(ryu::Buffer::new().format(feature.delta_rt_model).as_bytes());
record.push_field(ryu::Buffer::new().format(feature.ims).as_bytes());
record.push_field(ryu::Buffer::new().format(feature.predicted_ims).as_bytes());
record.push_field(
ryu::Buffer::new()
.format(feature.delta_ims_model)
.as_bytes(),
);
record.push_field(itoa::Buffer::new().format(feature.matched_peaks).as_bytes());
record.push_field(itoa::Buffer::new().format(feature.longest_b).as_bytes());
record.push_field(itoa::Buffer::new().format(feature.longest_y).as_bytes());
Expand Down Expand Up @@ -174,6 +181,9 @@ impl Runner {
"aligned_rt",
"predicted_rt",
"delta_rt_model",
"ion_mobility",
"predicted_mobility",
"delta_mobility",
"matched_peaks",
"longest_b",
"longest_y",
Expand Down Expand Up @@ -261,6 +271,7 @@ impl Runner {
record.push_field(ryu::Buffer::new().format(feature.calcmass).as_bytes());
record.push_field(filenames[feature.file_id].as_bytes());
record.push_field(ryu::Buffer::new().format(feature.rt).as_bytes());
record.push_field(ryu::Buffer::new().format(feature.ims).as_bytes());
record.push_field(itoa::Buffer::new().format(feature.rank).as_bytes());
record.push_field(
itoa::Buffer::new()
Expand Down Expand Up @@ -336,6 +347,12 @@ impl Runner {
.format(feature.delta_rt_model.clamp(0.001, 1.0).sqrt())
.as_bytes(),
);
record.push_field(ryu::Buffer::new().format(feature.predicted_ims).as_bytes());
record.push_field(
ryu::Buffer::new()
.format(feature.delta_ims_model)
.as_bytes(),
);
record.push_field(itoa::Buffer::new().format(feature.matched_peaks).as_bytes());
record.push_field(itoa::Buffer::new().format(feature.longest_b).as_bytes());
record.push_field(itoa::Buffer::new().format(feature.longest_y).as_bytes());
Expand Down Expand Up @@ -384,6 +401,7 @@ impl Runner {
"CalcMass",
"FileName",
"retentiontime",
"ion_mobility",
"rank",
"z=2",
"z=3",
Expand All @@ -403,6 +421,8 @@ impl Runner {
"aligned_rt",
"predicted_rt",
"sqrt(delta_rt_model)",
"predicted_mobility",
"sqrt(delta_mobility)",
"matched_peaks",
"longest_b",
"longest_y",
Expand Down
10 changes: 10 additions & 0 deletions crates/sage-cloudpath/src/mzml.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,8 @@ const SELECTED_ION_CHARGE: &[u8] = b"MS:1000041";
const ISO_WINDOW_LOWER: &[u8] = b"MS:1000828";
const ISO_WINDOW_UPPER: &[u8] = b"MS:1000829";

const INVERSE_ION_MOBILITY: &[u8] = b"MS:1002815";

pub struct MzMLReader {
ms_level: Option<u8>,
// If set to Some(level) and noise intensities are present in the MzML file,
Expand Down Expand Up @@ -236,6 +238,9 @@ impl MzMLReader {
SELECTED_ION_INT => {
precursor.intensity = Some(extract_value!(ev));
}
INVERSE_ION_MOBILITY => {
precursor.inverse_ion_mobility = Some(extract_value!(ev));
}
_ => {}
}
}
Expand Down Expand Up @@ -448,6 +453,7 @@ mod test {
<selectedIon>
<cvParam cvRef="MS" accession="MS:1000744" name="selected ion m/z" value="457.723968505859" unitAccession="MS:1000040" unitName="m/z" unitCvRef="MS" />
<cvParam cvRef="MS" accession="MS:1000041" name="charge state" value="2" />
<cvParam cvRef="MS" accession="MS:1002815" name="inverse reduced ion mobility" value="1.078628" unitAccession="MS:1002814" unitName="volt-second per square centimeter"/>
</selectedIon>
</selectedIonList>
<activation>
Expand Down Expand Up @@ -483,6 +489,10 @@ mod test {
assert_eq!(s.precursors.len(), 1);
assert_eq!(s.precursors[0].charge, Some(2));
assert!((s.precursors[0].mz - 457.723968) < 0.0001);
assert!(match s.precursors[0].inverse_ion_mobility {
Some(x) => (x - 1.0786) < 0.0001,
None => false,
});
assert_eq!(
s.precursors[0].isolation_window,
Some(Tolerance::Da(-1.5, 0.75))
Expand Down
1 change: 1 addition & 0 deletions crates/sage-cloudpath/src/tdf.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ impl TdfReader {
// precursor.ion_mobility = Option::from(dda_precursor.im as f32);
precursor.intensity = Option::from(dda_precursor.intensity as f32);
precursor.spectrum_ref = Option::from(dda_precursor.frame_index.to_string());
precursor.inverse_ion_mobility = Option::from(dda_precursor.im as f32);
let spectrum: RawSpectrum = RawSpectrum {
file_id,
precursors: vec![precursor],
Expand Down
6 changes: 5 additions & 1 deletion crates/sage/src/ml/linear_discriminant.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ use crate::mass::Tolerance;
use crate::scoring::Feature;

// Declare, so that we have compile time checking of matrix dimensions
const FEATURES: usize = 18;
const FEATURES: usize = 20;
const FEATURE_NAMES: [&str; FEATURES] = [
"rank",
"charge",
Expand All @@ -35,7 +35,9 @@ const FEATURE_NAMES: [&str; FEATURES] = [
"ln1p(peptide_len)",
"missed_cleavages",
"rt",
"ims",
"sqrt(delta_rt_model)",
"sqrt(delta_ims_model)",
];

struct Features<'a>(&'a [f64]);
Expand Down Expand Up @@ -174,7 +176,9 @@ pub fn score_psms(scores: &mut [Feature], precursor_tol: Tolerance) -> Option<()
(perc.peptide_len as f64).ln_1p(),
(perc.missed_cleavages as f64),
(perc.aligned_rt as f64),
(perc.ims as f64),
(perc.delta_rt_model as f64).clamp(0.001, 0.999).sqrt(),
(perc.delta_ims_model as f64).clamp(0.001, 0.999).sqrt(),
];
x
})
Expand Down
Loading
Loading