Merge branch 'development' into feature/add_new_iontypes

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: [email protected]
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.7.2
+version: 0.7.3
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.7.2 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.7.2 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.7.3 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.7.3 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.7.2
+current_version = 0.7.3
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_fundamentals/__init__.py

docs/conf.py

@@ -52,9 +52,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.7.2"
+version = "0.7.3"
 # The full version, including alpha/beta/rc tags.
-release = "0.7.2"
+release = "0.7.3"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "spectrum_fundamentals"
-version = "0.7.2"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.7.3"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "Fundamental functions, annotation pipeline and constants for oktoberfest"
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"

spectrum_fundamentals/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Mario Picciani"
 __email__ = "[email protected]"
-__version__ = "0.7.2"
+__version__ = "0.7.3"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.7.2", message=click.style("spectrum_fundamentals Version: 0.7.2"))
+@click.version_option(version="0.7.3", message=click.style("spectrum_fundamentals Version: 0.7.3"))
 def main() -> None:
     """spectrum_fundamentals."""
 

spectrum_fundamentals/annotation/annotation.py

@@ -322,7 +322,7 @@ def generate_annotation_matrix(
     exp_mass_col = matched_peaks.columns.get_loc("exp_mass")
 
     for peak in matched_peaks.values:
-        ion_type_index = ion_types.index(peak[ion_type][0])
+        ion_type_index = ion_types.index(peak[ion_type].split("-", 1)[0])
         peak_pos = ((peak[no_col] - 1) * charge_const * len(ion_types)) + (peak[charge_col] - 1) + 3 * ion_type_index
 
         if peak_pos >= constants.VEC_LENGTH:

spectrum_fundamentals/constants.py

@@ -17,6 +17,8 @@
 VEC_LENGTH_CMS2 = (SEQ_LEN - 1) * 2 * 3 * 2
 # peptide of length 30 can have 29 b, y, b_short, y_short, b_long and y_long ions, each with charge 1+, 2+ and 3+
 # we do not annotate fragments wth charge 3+. All fragmets with charge 3+ convert to -1
+
+
 #############
 # ALPHABETS #
 #############
@@ -398,7 +400,7 @@
 
 IONS = ["x", "y", "z", "z●" "a", "b", "c"]
 HCD_IONS = ["y", "b"]
-ETD_IONS = ["z●", "c"]
+ETD_IONS = ["z_r", "c"]
 ETCID_IONS = ["y", "z", "b", "c"]
 UVPD_IONS = ["x", "y", "z", "a", "b", "c"]
 
@@ -428,3 +430,48 @@ class RescoreType(Enum):
 
     PROSIT = "prosit"
     ANDROMEDA = "andromeda"
+
+
+#############
+# ION TYPES #
+#############
+FORWARD_IONS = ["a", "b", "c"]
+BACKWARDS_IONS = ["x", "y", "z", "z_r"]  #
+IONS = FORWARD_IONS + BACKWARDS_IONS
+
+FRAGMENTATION_TO_IONS_BY_PAIRS = {
+    "HCD": [BACKWARDS_IONS[1], FORWARD_IONS[1]],  # y,b
+    "CID": [BACKWARDS_IONS[1], FORWARD_IONS[1]],  # y,b
+    "ETD": [BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # z_r,c
+    "ECD": [BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # z_r,c
+    "ETHCD": [BACKWARDS_IONS[1], FORWARD_IONS[1], BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # y,b,z_r,c
+    "ETCID": [BACKWARDS_IONS[1], FORWARD_IONS[1], BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # y,b,z_r,c
+    "UVPD": [
+        BACKWARDS_IONS[0],
+        FORWARD_IONS[0],
+        BACKWARDS_IONS[1],
+        FORWARD_IONS[1],
+        BACKWARDS_IONS[2],
+        FORWARD_IONS[2],
+    ],  # y,b,z,c,x,a
+}
+
+FRAGMENTATION_TO_IONS_BY_DIRECTION = {
+    "HCD": [BACKWARDS_IONS[1], FORWARD_IONS[1]],  # y,b
+    "CID": [BACKWARDS_IONS[1], FORWARD_IONS[1]],  # y,b
+    "ETD": [BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # z_r,c
+    "ECD": [BACKWARDS_IONS[-1], FORWARD_IONS[2]],  # z_r,c
+    "ETHCD": [BACKWARDS_IONS[1], BACKWARDS_IONS[-1]] + FORWARD_IONS[1:],  # y,z_r,b,c
+    "ETCID": [BACKWARDS_IONS[1], BACKWARDS_IONS[-1]] + FORWARD_IONS[1:],  # y,z_r,b,c
+    "UVPD": BACKWARDS_IONS[:-1] + FORWARD_IONS,  # y,z,x,b,c,a
+}
+
+ION_DELTAS = {
+    "a": -ATOM_MASSES["O"] - ATOM_MASSES["C"],
+    "b": 0.0,
+    "c": 3 * ATOM_MASSES["H"] + ATOM_MASSES["N"],
+    "x": 2 * ATOM_MASSES["O"] + ATOM_MASSES["C"],
+    "y": ATOM_MASSES["O"] + 2 * ATOM_MASSES["H"],
+    "z": ATOM_MASSES["O"] - ATOM_MASSES["N"] - ATOM_MASSES["H"],
+    "z_r": ATOM_MASSES["O"] - ATOM_MASSES["N"],
+}

spectrum_fundamentals/fragments.py

@@ -97,16 +97,10 @@ def retrieve_ion_types(fragmentation_method: str) -> List[str]:
     :return: list of possible ion types
     """
     fragmentation_method = fragmentation_method.upper()
-    if fragmentation_method == "HCD" or fragmentation_method == "CID":
-        return ["y", "b"]
-    elif fragmentation_method == "ETD" or fragmentation_method == "ECD":
-        return ["z●", "c"]
-    elif fragmentation_method == "ETCID" or fragmentation_method == "ETHCD":
-        return ["y", "b", "z", "c"]
-    elif fragmentation_method == "UVPD":
-        return ["y", "b", "z", "c", "x", "a"]
-    else:
+    ions = c.FRAGMENTATION_TO_IONS_BY_PAIRS.get(fragmentation_method, [])
+    if not ions:
         raise ValueError(f"Unknown fragmentation method provided: {fragmentation_method}")
+    return ions
 
 
 def retrieve_ion_types_for_peak_initialization(fragmentation_method: str) -> List[str]:
@@ -120,17 +114,10 @@ def retrieve_ion_types_for_peak_initialization(fragmentation_method: str) -> Lis
     :return: list of possible ion types
     """
     fragmentation_method = fragmentation_method.upper()
-    if fragmentation_method == "HCD" or fragmentation_method == "CID":
-        return c.HCD_IONS
-    elif fragmentation_method == "ETD" or fragmentation_method == "ECD":
-        return c.ETD_IONS
-    elif fragmentation_method == "ETCID" or fragmentation_method == "ETHCD":
-        return c.ETCID_IONS
-    elif fragmentation_method == "UVPD":
-        return c.UVPD_IONS
-        return ["x", "y", "z", "a", "b", "c"]
-    else:
+    ions = c.FRAGMENTATION_TO_IONS_BY_DIRECTION.get(fragmentation_method, [])
+    if not ions:
         raise ValueError(f"Unknown fragmentation method provided: {fragmentation_method}")
+    return ions
 
 
 def get_ion_delta(ion_types: List[str]) -> np.ndarray:
@@ -140,19 +127,7 @@ def get_ion_delta(ion_types: List[str]) -> np.ndarray:
     :param ion_types: type of ions for which mass should be calculated
     :return: numpy array with masses of the ions
     """
-    ion_type_offsets = {
-        "a": -c.ATOM_MASSES["O"] - c.ATOM_MASSES["C"],
-        "b": 0.0,
-        "c": 3 * c.ATOM_MASSES["H"] + c.ATOM_MASSES["N"],
-        "x": 2 * c.ATOM_MASSES["O"] + c.ATOM_MASSES["C"],
-        "y": c.ATOM_MASSES["O"] + 2 * c.ATOM_MASSES["H"],
-        "z": c.ATOM_MASSES["O"] - c.ATOM_MASSES["N"] - c.ATOM_MASSES["H"],
-        "z●": c.ATOM_MASSES["O"] - c.ATOM_MASSES["N"],
-    }
-
-    deltas = np.array([ion_type_offsets[ion_type] for ion_type in ion_types]).reshape(len(ion_types), 1)
-
-    return deltas
+    return np.array([c.ION_DELTAS[ion_type] for ion_type in ion_types]).reshape(len(ion_types), 1)
 
 
 def initialize_peaks(

spectrum_fundamentals/mod_string.py

@@ -1,7 +1,7 @@
 import difflib
 import re
 from itertools import combinations, repeat
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, List, Optional, Set, Tuple, Union
 
 import numpy as np
 import pandas as pd
@@ -342,6 +342,15 @@ def split_modstring(sequence: str, r_pattern):
     return map(split_modstring, sequences, repeat(regex_pattern))
 
 
+def get_all_tokens(sequences: List[str]) -> Set[str]:
+    """Parse given sequences in UNIMOD ProForma standard into a set of all tokens."""
+    pattern = r"[ACDEFGHIKLMNPQRSTVWY](\[UNIMOD:\d+\])?"
+    tokens = set()
+    for seq in sequences:
+        tokens |= {match.group() for match in re.finditer(pattern, seq)}
+    return tokens
+
+
 def add_permutations(modified_sequence: str, unimod_id: int, residues: List[str]):
     """
     Generate different peptide sequences with moving the modification to all possible residues.

tests/unit_tests/data/fragments_meta_data_etd_ecd.json

@@ -8,7 +8,7 @@
         "max_mass": 39.034494842950046
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 1,
         "charge": 3,
         "mass": 44.68542100033333,
@@ -24,7 +24,7 @@
         "max_mass": 58.048093958160386
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 1,
         "charge": 2,
         "mass": 66.524493267,
@@ -40,7 +40,7 @@
         "max_mass": 82.04955279357003
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 2,
         "charge": 3,
         "mass": 83.02773533366667,
@@ -64,7 +64,7 @@
         "max_mass": 115.08889130379143
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 3,
         "charge": 3,
         "mass": 120.72242333366667,
@@ -80,15 +80,15 @@
         "max_mass": 122.57068088409038
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 2,
         "charge": 2,
         "mass": 124.037964767,
         "min_mass": 124.03548400770467,
         "max_mass": 124.04044552629534
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 1,
         "charge": 1,
         "mass": 132.041710067,
@@ -104,7 +104,7 @@
         "max_mass": 148.08435446319004
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 4,
         "charge": 3,
         "mass": 154.40498300033335,
@@ -120,7 +120,7 @@
         "max_mass": 171.0980334117304
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 3,
         "charge": 2,
         "mass": 180.579996767,
@@ -136,7 +136,7 @@
         "max_mass": 185.77979635695002
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 5,
         "charge": 3,
         "mass": 186.75590433366668,
@@ -160,15 +160,15 @@
         "max_mass": 224.12287753657
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 6,
         "charge": 3,
         "mass": 229.77010200033337,
         "min_mass": 229.76550659829337,
         "max_mass": 229.77469740237336
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 4,
         "charge": 2,
         "mass": 231.10383626700002,
@@ -184,7 +184,7 @@
         "max_mass": 244.13406515565143
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 2,
         "charge": 1,
         "mass": 247.068653067,
@@ -200,7 +200,7 @@
         "max_mass": 278.1660462291604
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 5,
         "charge": 2,
         "mass": 279.63021826700003,
@@ -224,15 +224,15 @@
         "max_mass": 341.18877021093147
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 6,
         "charge": 2,
         "mass": 344.15151476700004,
         "min_mass": 344.1446317367047,
         "max_mass": 344.1583977972954
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 3,
         "charge": 1,
         "mass": 360.152717067,
@@ -248,7 +248,7 @@
         "max_mass": 442.23847016451145
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 4,
         "charge": 1,
         "mass": 461.20039606700004,
@@ -264,7 +264,7 @@
         "max_mass": 555.3247958457914
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 5,
         "charge": 1,
         "mass": 558.2531600670001,
@@ -280,7 +280,7 @@
         "max_mass": 670.3540393846513
     },
     {
-        "ion_type": "z●",
+        "ion_type": "z_r",
         "no": 6,
         "charge": 1,
         "mass": 687.2957530670001,