all comments addressed

casanovo/config.yaml

@@ -46,7 +46,7 @@ devices:
 # See pyteomics.parser.expasy_rules for valid enzymes
 enzyme: "trypsin"
 # Digestion type for candidate peptide generation.
-# Full: standard digestion. Semi: Include products of semi-specific cleavage
+# full: standard digestion. semi: Include products of semi-specific cleavage
 digestion: "full"
 # Number of allowed missed cleavages when digesting protein
 missed_cleavages: 0
@@ -55,6 +55,11 @@ missed_cleavages: 0
 max_mods: 
 # Maximum peptide length to consider
 max_peptide_len: 50
+# Toggle allowed modifications on/off
+# Permanent fixed mod (don't include): C+57.021
+# Allowed variable mods: M+15.995, N+0.984, Q+0.984, 
+# Allowed N-terminal mods: +42.011, +43.006, -17.027, +43.006-17.027
+allowed_mods: "M+15.995,N+0.984,Q+0.984,+42.011,+43.006,-17.027,+43.006-17.027"
 
 
 ###

casanovo/data/db_utils.py

@@ -15,16 +15,6 @@
 PROTON = 1.00727646677
 ISOTOPE_SPACING = 1.003355
 
-var_mods = {
-    "d": ["N", "Q"],
-    "ox": ["M"],
-    "ace-": True,
-    "carb-": True,
-    "nh3x-": True,
-    "carbnh3x-": True,
-}
-fixed_mods = {"carbm": ["C"]}
-
 
 class ProteinDatabase:
     """
@@ -51,6 +41,8 @@ class ProteinDatabase:
         The precursor mass tolerance in ppm.
     isotope_error : List[int]
         Isotopes to consider when comparing predicted and observed precursor m/z's.
+    allowed_mods : List[str]
+        A list of allowed modifications to consider.
     """
 
     def __init__(
@@ -64,7 +56,11 @@ def __init__(
         max_mods: int,
         precursor_tolerance: float,
         isotope_error: List[int],
+        allowed_mods: List[str],
     ):
+        self.fixed_mods, self.var_mods = self._construct_mods_dict(
+            allowed_mods
+        )
         self.digest = self._digest_fasta(
             fasta_path,
             enzyme,
@@ -197,8 +193,8 @@ def _digest_fasta(
         for pep, prot in peptide_list:
             peptide_isoforms = parser.isoforms(
                 pep,
-                variable_mods=var_mods,
-                fixed_mods=fixed_mods,
+                variable_mods=self.var_mods,
+                fixed_mods=self.fixed_mods,
                 max_mods=max_mods,
             )
             peptide_isoforms = list(
@@ -218,6 +214,54 @@ def _digest_fasta(
         logger.info("Digestion complete. %d peptides generated.", len(pdb_df))
         return pdb_df
 
+    def _construct_mods_dict(self, allowed_mods):
+        """
+        Constructs dictionaries of fixed and variable modifications.
+
+        Parameters
+        ----------
+        allowed_mods : str
+            A comma-separated list of allowed modifications.
+
+        Returns
+        -------
+        fixed_mods : dict
+            A dictionary of fixed modifications.
+        var_mods : dict
+            A dictionary of variable modifications.
+        """
+        fixed_mods = {"carbm": ["C"]}
+        var_mods = {}
+
+        if allowed_mods is "" or None:
+            return fixed_mods, var_mods
+        for mod in allowed_mods.split(","):
+            if mod == "M+15.995":
+                if "ox" not in var_mods:
+                    var_mods["ox"] = []
+                var_mods["ox"].append("M")
+            elif mod == "N+0.984":
+                if "d" not in var_mods:
+                    var_mods["d"] = []
+                var_mods["d"].append("N")
+            elif mod == "Q+0.984":
+                if "d" not in var_mods:
+                    var_mods["d"] = []
+                var_mods["d"].append("Q")
+            elif mod == "+42.011":
+                var_mods["ace-"] = True
+            elif mod == "+43.006":
+                var_mods["carb-"] = True
+            elif mod == "-17.027":
+                var_mods["nh3x-"] = True
+            elif mod == "+43.006-17.027":
+                var_mods["carbnh3x-"] = True
+            else:
+                logger.error("Modification %s not recognized.", mod)
+                raise ValueError(f"Modification {mod} not recognized.")
+
+        return fixed_mods, var_mods
+
     @jit
     def _to_mz(precursor_mass, charge):
         """

casanovo/denovo/model_runner.py

@@ -124,6 +124,7 @@ def db_search(
             self.config.max_mods,
             self.config.precursor_mass_tol,
             self.config.isotope_error_range,
+            self.config.allowed_mods,
         )
         self.loaders.setup(stage="test", annotated=False)
         self.trainer.predict(self.model, self.loaders.db_dataloader())

tests/conftest.py

@@ -299,6 +299,10 @@ def tiny_config(tmp_path):
             "-17.027": -17.026549,
             "+43.006-17.027": 25.980265,
         },
+        "allowed_mods": (
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     }
 
     cfg_file = tmp_path / "config.yml"

tests/unit_tests/test_unit.py

@@ -287,6 +287,10 @@ def test_digest_fasta_cleave(tiny_fasta_file):
             max_mods=0,
             precursor_tolerance=20,
             isotope_error=[0],
+            allowed_mods=(
+                "M+15.995,N+0.984,Q+0.984,"
+                "+42.011,+43.006,-17.027,+43.006-17.027"
+            ),
         )
         peptide_list = list(pdb.digest["peptide"])
         assert peptide_list == expected
@@ -356,6 +360,10 @@ def test_digest_fasta_mods(tiny_fasta_file):
         max_mods=1,
         precursor_tolerance=20,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     peptide_list = list(pdb.digest["peptide"])
     peptide_list = [
@@ -389,6 +397,10 @@ def test_length_restrictions(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=20,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     peptide_list = list(pdb.digest["peptide"])
     assert peptide_list == expected_long
@@ -403,6 +415,10 @@ def test_length_restrictions(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=20,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     peptide_list = list(pdb.digest["peptide"])
     assert peptide_list == expected_short
@@ -433,6 +449,10 @@ def test_digest_fasta_enzyme(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=20,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     peptide_list = list(pdb.digest["peptide"])
     assert peptide_list == expected_argc
@@ -447,6 +467,10 @@ def test_digest_fasta_enzyme(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=20,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     peptide_list = list(pdb.digest["peptide"])
     assert peptide_list == expected_aspn
@@ -472,6 +496,10 @@ def test_get_candidates(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
     assert expected_smallwindow == candidates
@@ -486,6 +514,10 @@ def test_get_candidates(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=150000,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
     assert expected_midwindow == candidates
@@ -500,6 +532,10 @@ def test_get_candidates(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=600000,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
     assert expected_widewindow == candidates
@@ -563,6 +599,10 @@ def test_get_candidates_isotope_error(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[0],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     pdb.digest = peptide_list
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
@@ -578,6 +618,10 @@ def test_get_candidates_isotope_error(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[1],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     pdb.digest = peptide_list
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
@@ -593,6 +637,10 @@ def test_get_candidates_isotope_error(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[2],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     pdb.digest = peptide_list
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
@@ -608,6 +656,10 @@ def test_get_candidates_isotope_error(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[3],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     pdb.digest = peptide_list
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)
@@ -623,6 +675,10 @@ def test_get_candidates_isotope_error(tiny_fasta_file):
         max_mods=0,
         precursor_tolerance=10000,
         isotope_error=[0, 1, 2, 3],
+        allowed_mods=(
+            "M+15.995,N+0.984,Q+0.984,"
+            "+42.011,+43.006,-17.027,+43.006-17.027"
+        ),
     )
     pdb.digest = peptide_list
     candidates, _ = pdb.get_candidates(precursor_mz=496.2, charge=2)