integration test fix

tests/conftest.py

@@ -263,7 +263,7 @@ def tiny_config(tmp_path):
         "train_label_smoothing": 0.01,
         "warmup_iters": 1,
         "cosine_schedule_period_iters": 1,
-        "max_epochs": 15,
+        "max_epochs": 20,
         "val_check_interval": 1,
         "accelerator": "cpu",
         "precursor_mass_tol": 5,
@@ -304,7 +304,7 @@ def tiny_config(tmp_path):
         "gradient_clip_val": None,
         "gradient_clip_algorithm": None,
         "precision": "32-true",
-        "replace_isoleucine_with_leucine": False,
+        "replace_isoleucine_with_leucine": True,
         "reverse_peptides": False,
         "mskb_tokenizer": True,
         "residues": {

tests/test_integration.py

@@ -40,7 +40,7 @@ def test_train_and_run(
     ]
 
     result = run(train_args)
-    model_file = tmp_path / "train.epoch=14-step=15.ckpt"
+    model_file = tmp_path / "train.epoch=19-step=20.ckpt"
     best_model = tmp_path / "train.best.ckpt"
     assert result.exit_code == 0
     assert model_file.exists()
@@ -79,13 +79,13 @@ def test_train_and_run(
     # Verify that the spectrum predictions are correct
     # and indexed according to the peak input file type.
     psms = mztab.spectrum_match_table
-    assert psms.loc[1, "sequence"] == "LESLIEK"
+    assert psms.loc[1, "sequence"] == "LESLLEK"
     assert psms.loc[1, "spectra_ref"] == "ms_run[1]:index=0"
-    assert psms.loc[2, "sequence"] == "PEPTIDEK"
+    assert psms.loc[2, "sequence"] == "PEPTLDEK"
     assert psms.loc[2, "spectra_ref"] == "ms_run[1]:index=1"
-    assert psms.loc[3, "sequence"] == "LESLIEK"
+    assert psms.loc[3, "sequence"] == "LESLLEK"
     assert psms.loc[3, "spectra_ref"] == "ms_run[2]:scan=17"
-    assert psms.loc[4, "sequence"] == "PEPTIDEK"
+    assert psms.loc[4, "sequence"] == "PEPTLDEK"
     assert psms.loc[4, "spectra_ref"] == "ms_run[2]:scan=111"
 
     # Finally, try evaluating:
@@ -118,9 +118,9 @@ def test_train_and_run(
     # Verify that the spectrum predictions are correct
     # and indexed according to the peak input file type.
     psms = mztab.spectrum_match_table
-    assert psms.loc[1, "sequence"] == "LESLIEK"
+    assert psms.loc[1, "sequence"] == "LESLLEK"
     assert psms.loc[1, "spectra_ref"] == "ms_run[1]:index=0"
-    assert psms.loc[2, "sequence"] == "PEPTIDEK"
+    assert psms.loc[2, "sequence"] == "PEPTLDEK"
     assert psms.loc[2, "spectra_ref"] == "ms_run[1]:index=1"
 
     # Validate mztab output