From ca09c0bbd41f812763996fa6e2dad1e8bd58b13d Mon Sep 17 00:00:00 2001
From: Mario Picciani <mario.picciani@tum.de>
Date: Mon, 5 Aug 2024 16:52:39 +0200
Subject: [PATCH 1/2] added new internal_to_msp function

---
 docs/reference.rst                  |  2 +-
 spectrum_fundamentals/mod_string.py | 39 ++++++++++++++++++++++++++---
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/docs/reference.rst b/docs/reference.rst
index ff7ad07..0323c01 100644
--- a/docs/reference.rst
+++ b/docs/reference.rst
@@ -1,7 +1,7 @@
 How to cite
 ===========
 
-If you want to cite spectrum_fundamentals in your work, please cite the main Oktoberfest publication following:
+If you want to cite spectrum_fundamentals in your work, please cite the main Oktoberfest publication:
 
 .. [1] Picciani M, Gabriel W, Giurcoiu VG et al. (2023),
     *Oktoberfest: Open-source spectral library generation and rescoring pipeline based on Prosit*,
diff --git a/spectrum_fundamentals/mod_string.py b/spectrum_fundamentals/mod_string.py
index 4c14f21..e3cec21 100644
--- a/spectrum_fundamentals/mod_string.py
+++ b/spectrum_fundamentals/mod_string.py
@@ -200,9 +200,7 @@ def internal_without_mods(sequences: List[str]) -> List[str]:
     return [re.sub(regex, "", seq) for seq in sequences]
 
 
-def internal_to_mod_mass(
-    sequences: List[str], custom_mods: Optional[Dict[str, Dict[str, Tuple[str, float]]]] = None
-) -> List[str]:
+def internal_to_mod_mass(sequences: List[str], custom_mods: Optional[Dict[str, float]] = None) -> List[str]:
     """
     Function to exchange the internal mod identifiers with the masses of the specific modifiction.
 
@@ -217,6 +215,41 @@ def internal_to_mod_mass(
     return [regex.sub(replacement_func, seq) for seq in sequences]
 
 
+def internal_to_msp(
+    sequences: Union[List[str], pd.Series],
+    mods: Dict[str, str],
+) -> List[Tuple[str, str]]:
+    """
+    Function to translate an internal modstring to modstring and Mods for MSP format.
+
+    :param sequences: sequences to translate
+    :param mods: dictionary mapping from internal unimod format (keys) to MSP format (values).
+    :return: a tuple for each sequence, containing (Mods, mod_string) for the MSP format
+    """
+    ret_vals = []
+    p = re.compile("|".join(mods.keys()))
+    for seq in sequences:
+        offset = 0
+        mod_list = []
+        matches = p.finditer(seq)
+        for match in matches:
+            replacement = mods[re.escape(match.group())]
+            start, end = match.span()
+            actual_start = start - offset
+            mod_list.append((actual_start, replacement))
+
+            offset += end - start - 1
+
+        mod_string = "; ".join([f"{mod[2:]}@{mod[0]}{pos}" for pos, mod in mod_list])
+        n_mods = len(mod_list)
+        if n_mods > 0:
+            mods = f"{n_mods}/{'/'.join([f'{pos},{mod}' for pos, mod in mod_list])}"
+        else:
+            mods = "0"
+        ret_vals.append((mods, mod_string))
+    return ret_vals
+
+
 def internal_to_mod_names(
     sequences: List[str],
 ) -> List[Tuple[str, str]]:

From 347979c2f22f8a208708e53c6c213e4dc071ef7b Mon Sep 17 00:00:00 2001
From: Mario Picciani <mario.picciani@tum.de>
Date: Mon, 5 Aug 2024 17:28:20 +0200
Subject: [PATCH 2/2] fixed mypy / typeguard

---
 spectrum_fundamentals/mod_string.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/spectrum_fundamentals/mod_string.py b/spectrum_fundamentals/mod_string.py
index e3cec21..2016c02 100644
--- a/spectrum_fundamentals/mod_string.py
+++ b/spectrum_fundamentals/mod_string.py
@@ -200,7 +200,9 @@ def internal_without_mods(sequences: List[str]) -> List[str]:
     return [re.sub(regex, "", seq) for seq in sequences]
 
 
-def internal_to_mod_mass(sequences: List[str], custom_mods: Optional[Dict[str, float]] = None) -> List[str]:
+def internal_to_mod_mass(
+    sequences: List[str], custom_mods: Optional[Dict[str, Dict[str, Tuple[str, float]]]] = None
+) -> List[str]:
     """
     Function to exchange the internal mod identifiers with the masses of the specific modifiction.
 
@@ -243,10 +245,10 @@ def internal_to_msp(
         mod_string = "; ".join([f"{mod[2:]}@{mod[0]}{pos}" for pos, mod in mod_list])
         n_mods = len(mod_list)
         if n_mods > 0:
-            mods = f"{n_mods}/{'/'.join([f'{pos},{mod}' for pos, mod in mod_list])}"
+            mods_field = f"{n_mods}/{'/'.join([f'{pos},{mod}' for pos, mod in mod_list])}"
         else:
-            mods = "0"
-        ret_vals.append((mods, mod_string))
+            mods_field = "0"
+        ret_vals.append((mods_field, mod_string))
     return ret_vals