rustms/algorithm/peptide.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
use std::collections::HashMap;
use regex::Regex;
use rayon::prelude::*;
use rayon::ThreadPoolBuilder;
use crate::chemistry::constants::{MASS_CO, MASS_NH3, MASS_PROTON, MASS_WATER};
use crate::chemistry::formula::calculate_mz;
use crate::chemistry::unimod::{modification_atomic_composition, unimod_modifications_mass_numerical};
use crate::chemistry::utility::{find_unimod_patterns, unimod_sequence_to_tokens};
use crate::proteomics::amino_acid::{amino_acid_composition, amino_acid_masses};
use crate::proteomics::peptide::{FragmentType, PeptideProductIon, PeptideSequence};
/// calculate the monoisotopic mass of a peptide sequence
///
/// Arguments:
///
/// * `sequence` - peptide sequence
///
/// Returns:
///
/// * `mass` - monoisotopic mass of the peptide
///
/// # Examples
///
/// ```
/// use rustms::algorithm::peptide::calculate_peptide_mono_isotopic_mass;
/// use rustms::proteomics::peptide::PeptideSequence;
///
/// let peptide_sequence = PeptideSequence::new("PEPTIDEH".to_string(), Some(1));
/// let mass = calculate_peptide_mono_isotopic_mass(&peptide_sequence);
/// let mass_quantized = (mass * 1e6).round() as i32;
/// assert_eq!(mass_quantized, 936418877);
/// ```
pub fn calculate_peptide_mono_isotopic_mass(peptide_sequence: &PeptideSequence) -> f64 {
let amino_acid_masses = amino_acid_masses();
let modifications_mz_numerical = unimod_modifications_mass_numerical();
let pattern = Regex::new(r"\[UNIMOD:(\d+)]").unwrap();
let sequence = peptide_sequence.sequence.as_str();
// Find all occurrences of the pattern
let modifications: Vec<u32> = pattern
.find_iter(sequence)
.filter_map(|mat| mat.as_str()[8..mat.as_str().len() - 1].parse().ok())
.collect();
// Remove the modifications from the sequence
let sequence = pattern.replace_all(sequence, "");
// Count occurrences of each amino acid
let mut aa_counts = HashMap::new();
for char in sequence.chars() {
*aa_counts.entry(char).or_insert(0) += 1;
}
// Mass of amino acids and modifications
let mass_sequence: f64 = aa_counts.iter().map(|(aa, &count)| amino_acid_masses.get(&aa.to_string()[..]).unwrap_or(&0.0) * count as f64).sum();
let mass_modifications: f64 = modifications.iter().map(|&mod_id| modifications_mz_numerical.get(&mod_id).unwrap_or(&0.0)).sum();
mass_sequence + mass_modifications + MASS_WATER
}
/// calculate the monoisotopic mass of a peptide product ion for a given fragment type
///
/// Arguments:
///
/// * `sequence` - peptide sequence
/// * `kind` - fragment type
///
/// Returns:
///
/// * `mass` - monoisotopic mass of the peptide
///
/// # Examples
/// ```
/// use rustms::algorithm::peptide::calculate_peptide_product_ion_mono_isotopic_mass;
/// use rustms::proteomics::peptide::FragmentType;
/// let sequence = "PEPTIDEH";
/// let mass = calculate_peptide_product_ion_mono_isotopic_mass(sequence, FragmentType::Y);
/// assert_eq!(mass, 936.4188766862999);
/// ```
pub fn calculate_peptide_product_ion_mono_isotopic_mass(sequence: &str, kind: FragmentType) -> f64 {
let (sequence, modifications) = find_unimod_patterns(sequence);
// Return mz of empty sequence
if sequence.is_empty() {
return 0.0;
}
let amino_acid_masses = amino_acid_masses();
// Add up raw amino acid masses and potential modifications
let mass_sequence: f64 = sequence.chars()
.map(|aa| amino_acid_masses.get(&aa.to_string()[..]).unwrap_or(&0.0))
.sum();
let mass_modifications: f64 = modifications.iter().sum();
// Calculate total mass
let mass = mass_sequence + mass_modifications + MASS_WATER;
let mass = match kind {
FragmentType::A => mass - MASS_CO - MASS_WATER,
FragmentType::B => mass - MASS_WATER,
FragmentType::C => mass + MASS_NH3 - MASS_WATER,
FragmentType::X => mass + MASS_CO - 2.0 * MASS_PROTON,
FragmentType::Y => mass,
FragmentType::Z => mass - MASS_NH3,
};
mass
}
/// calculate the monoisotopic m/z of a peptide product ion for a given fragment type and charge
///
/// Arguments:
///
/// * `sequence` - peptide sequence
/// * `kind` - fragment type
/// * `charge` - charge
///
/// Returns:
///
/// * `mz` - monoisotopic mass of the peptide
///
/// # Examples
/// ```
/// use rustms::algorithm::peptide::calculate_product_ion_mz;
/// use rustms::chemistry::constants::MASS_PROTON;
/// use rustms::proteomics::peptide::FragmentType;
/// let sequence = "PEPTIDEH";
/// let mz = calculate_product_ion_mz(sequence, FragmentType::Y, Some(1));
/// assert_eq!(mz, 936.4188766862999 + MASS_PROTON);
/// ```
pub fn calculate_product_ion_mz(sequence: &str, kind: FragmentType, charge: Option<i32>) -> f64 {
let mass = calculate_peptide_product_ion_mono_isotopic_mass(sequence, kind);
calculate_mz(mass, charge.unwrap_or(1))
}
/// get a count dictionary of the amino acid composition of a peptide sequence
///
/// Arguments:
///
/// * `sequence` - peptide sequence
///
/// Returns:
///
/// * `composition` - a dictionary of amino acid composition
///
/// # Examples
///
/// ```
/// use rustms::algorithm::peptide::calculate_amino_acid_composition;
///
/// let sequence = "PEPTIDEH";
/// let composition = calculate_amino_acid_composition(sequence);
/// assert_eq!(composition.get("P"), Some(&2));
/// assert_eq!(composition.get("E"), Some(&2));
/// assert_eq!(composition.get("T"), Some(&1));
/// assert_eq!(composition.get("I"), Some(&1));
/// assert_eq!(composition.get("D"), Some(&1));
/// assert_eq!(composition.get("H"), Some(&1));
/// ```
pub fn calculate_amino_acid_composition(sequence: &str) -> HashMap<String, i32> {
let mut composition = HashMap::new();
for char in sequence.chars() {
*composition.entry(char.to_string()).or_insert(0) += 1;
}
composition
}
/// calculate the atomic composition of a peptide sequence
pub fn peptide_sequence_to_atomic_composition(peptide_sequence: &PeptideSequence) -> HashMap<&'static str, i32> {
let token_sequence = unimod_sequence_to_tokens(peptide_sequence.sequence.as_str(), false);
let mut collection: HashMap<&'static str, i32> = HashMap::new();
// Assuming amino_acid_composition and modification_composition return appropriate mappings...
let aa_compositions = amino_acid_composition();
let mod_compositions = modification_atomic_composition();
// No need for conversion to HashMap<String, ...> as long as you're directly accessing
// the HashMap provided by modification_composition() if it uses String keys.
for token in token_sequence {
if token.len() == 1 {
let char = token.chars().next().unwrap();
if let Some(composition) = aa_compositions.get(&char) {
for (key, value) in composition.iter() {
*collection.entry(key).or_insert(0) += *value;
}
}
} else {
// Directly use &token without .as_str() conversion
if let Some(composition) = mod_compositions.get(&token) {
for (key, value) in composition.iter() {
*collection.entry(key).or_insert(0) += *value;
}
}
}
}
// Add water
*collection.entry("H").or_insert(0) += 2; //
*collection.entry("O").or_insert(0) += 1; //
collection
}
/// calculate the atomic composition of a product ion
///
/// Arguments:
///
/// * `product_ion` - a PeptideProductIon instance
///
/// Returns:
///
/// * `Vec<(&str, i32)>` - a vector of tuples representing the atomic composition of the product ion
pub fn atomic_product_ion_composition(product_ion: &PeptideProductIon) -> Vec<(&str, i32)> {
let mut composition = peptide_sequence_to_atomic_composition(&product_ion.ion.sequence);
match product_ion.kind {
FragmentType::A => {
// A: peptide_mass - CO - Water
*composition.entry("H").or_insert(0) -= 2;
*composition.entry("O").or_insert(0) -= 2;
*composition.entry("C").or_insert(0) -= 1;
},
FragmentType::B => {
// B: peptide_mass - Water
*composition.entry("H").or_insert(0) -= 2;
*composition.entry("O").or_insert(0) -= 1;
},
FragmentType::C => {
// C: peptide_mass + NH3 - Water
*composition.entry("H").or_insert(0) += 1;
*composition.entry("N").or_insert(0) += 1;
*composition.entry("O").or_insert(0) -= 1;
},
FragmentType::X => {
// X: peptide_mass + CO
*composition.entry("C").or_insert(0) += 1; // Add 1 for CO
*composition.entry("O").or_insert(0) += 1; // Add 1 for CO
*composition.entry("H").or_insert(0) -= 2; // Subtract 2 for 2 protons
},
FragmentType::Y => {
()
},
FragmentType::Z => {
*composition.entry("H").or_insert(0) -= 3;
*composition.entry("N").or_insert(0) -= 1;
},
}
composition.iter().map(|(k, v)| (*k, *v)).collect()
}
/// calculate the atomic composition of a peptide product ion series
/// Arguments:
///
/// * `product_ions` - a vector of PeptideProductIon instances
/// * `num_threads` - an usize representing the number of threads to use
/// Returns:
///
/// * `Vec<Vec<(String, i32)>>` - a vector of vectors of tuples representing the atomic composition of each product ion
///
pub fn fragments_to_composition(product_ions: Vec<PeptideProductIon>, num_threads: usize) -> Vec<Vec<(String, i32)>> {
let thread_pool = ThreadPoolBuilder::new().num_threads(num_threads).build().unwrap();
let result = thread_pool.install(|| {
product_ions.par_iter().map(|ion| atomic_product_ion_composition(ion)).map(|composition| {
composition.iter().map(|(k, v)| (k.to_string(), *v)).collect()
}).collect()
});
result
}
/// count the number of protonizable sites in a peptide sequence
///
/// # Arguments
///
/// * `sequence` - a string representing the peptide sequence
///
/// # Returns
///
/// * `usize` - the number of protonizable sites in the peptide sequence
///
/// # Example
///
/// ```
/// use rustms::algorithm::peptide::get_num_protonizable_sites;
///
/// let sequence = "PEPTIDEH";
/// let num_protonizable_sites = get_num_protonizable_sites(sequence);
/// assert_eq!(num_protonizable_sites, 2);
/// ```
pub fn get_num_protonizable_sites(sequence: &str) -> usize {
let mut sites = 1; // n-terminus
for s in sequence.chars() {
match s {
'H' | 'R' | 'K' => sites += 1,
_ => {}
}
}
sites
}