Makes sure that the position in the variant is accurate by relying on…

… the residue information
MachineLearningLifeScience · Oct 24, 2023 · dea47d5 · dea47d5
1 parent 30ff002
commit dea47d5
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 9 deletions.
diff --git a/examples/using_rasp/querying_rasp.py b/examples/using_rasp/querying_rasp.py
@@ -4,13 +4,7 @@
 """
 from pathlib import Path
 
-import numpy as np
-
-from poli.objective_repository.rasp.register import RaspBlackBox, RaspProblemFactory
-from poli.core.problem_setup_information import ProblemSetupInformation
-
-from poli.core.util.proteins.defaults import AMINO_ACIDS
-from poli.core.util.proteins.pdb_parsing import parse_pdb_as_residue_strings
+from poli.objective_repository.rasp.register import RaspProblemFactory
 
 
 THIS_DIR = Path(__file__).parent.resolve()

diff --git a/src/poli/core/util/proteins/rasp/rasp.py b/src/poli/core/util/proteins/rasp/rasp.py
@@ -396,8 +396,14 @@ def create_df_structure(
             for mutant_residue_string in mutant_residue_strings:
                 if mutant_residue_string == wildtype_residue_string:
                     # Then we append a mock mutation.
+                    original_residue_as_single_character = wildtype_residue_string[0]
+                    position_in_chain = res_info.iloc[0]["pos"]
+                    mutant_residue_as_single_character = wildtype_residue_string[0]
+
                     mutations_in_rasp_format.append(
-                        wildtype_residue_string[0] + f"{1}" + wildtype_residue_string[0]
+                        original_residue_as_single_character
+                        + f"{position_in_chain}"
+                        + mutant_residue_as_single_character
                     )
                     continue
 
@@ -406,8 +412,14 @@ def create_df_structure(
                 )
                 for edit_ in edits_:
                     _, i, _ = edit_
+                    original_residue_as_single_character = wildtype_residue_string[i]
+                    position_in_chain = res_info.iloc[i]["pos"]
+                    mutant_residue_as_single_character = mutant_residue_string[i]
+
                     mutations_in_rasp_format.append(
-                        wildtype_residue_string[i] + f"{i+1}" + mutant_residue_string[i]
+                        original_residue_as_single_character
+                        + f"{position_in_chain}"
+                        + mutant_residue_as_single_character
                     )
 
             # Filter df_structure to only contain the mutations in