calibration bug fix

CHANGELOG.md

@@ -5,6 +5,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to
 [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+# [2.1.1] - 2023-05-08
+
+### Changed
+- Calibration bug fix
+
 # [2.1.0] - 2023-05-08
 
 ### Changed

deeplc/__main__.py

@@ -171,6 +171,7 @@ def run(
         dict_cal_divider=dict_divider,
         write_library=write_library,
         use_library=use_library,
+        pygam_calibration=pygam_calibration,
         batch_num=batch_num,
         n_jobs=n_threads,
         verbose=verbose,
@@ -181,12 +182,11 @@ def run(
     # Calibrate the original model based on the new retention times
     if len(psm_list_cal) > 0:
         logger.info("Selecting best model and calibrating predictions...")
-        print(psm_list_cal)
         dlc.calibrate_preds(psm_list=psm_list_cal)
 
     # Make predictions; calibrated or uncalibrated
     logger.info("Making predictions using model: %s", dlc.model)
-    if file_cal:
+    if len(psm_list_cal) > 0:
         preds = dlc.make_preds(seq_df=df_pred, infile=file_pred, psm_list=psm_list_pred)
     else:
         preds = dlc.make_preds(seq_df=df_pred, infile=file_pred, psm_list=psm_list_pred, calibrate=False)

deeplc/_argument_parser.py

@@ -139,7 +139,7 @@ def parse_arguments(gui=False):
     calibration_group.add_argument(
         "--pygam_calibration",
         dest="pygam_calibration",
-        action="store_true",
+        default=True,
         help=(
             "use pyGAM generalized additive model as calibration method; "
             "recommended; default"
@@ -150,7 +150,8 @@ def parse_arguments(gui=False):
     calibration_group.add_argument(
         "--transfer_learning",
         dest="transfer_learning",
-        action="store_false",
+        #action="store_false",
+        default=False,
         help="use transfer learning as calibration method",
         **gooey_args["transfer_learning"]
     )

setup.py

@@ -6,7 +6,7 @@
 
 setup(
     name='deeplc',
-    version='2.1.0',
+    version='2.1.1',
     license='apache-2.0',
     description='DeepLC: Retention time prediction for (modified) peptides using Deep Learning.',
     long_description=LONG_DESCRIPTION,

tests/test_deeplc.py

@@ -27,14 +27,16 @@ def test_cli_full():
 
     command = [
         "deeplc", "--file_pred", file_path_pred, "--file_cal", file_path_cal,
-        "--file_pred_out", file_path_out
+        "--file_pred_out", file_path_out,
     ]
     subprocess.run(command, check=True)
 
     preds_df = pd.read_csv(file_path_out)
-    model_r2 = r2_score(preds_df['tr'], preds_df['predicted_tr'])
+    train_df = pd.read_csv(file_path_pred)
+    model_r2 = r2_score(train_df['tr'], preds_df['predicted retention time'])
+    logging.info(f"{len(train_df.index)}{len(preds_df.index)}")
     logging.info("DeepLC R2 score on %s: %f", file_path_pred, model_r2)
-    assert model_r2 > 0.90, f"DeepLC R2 score on {file_path_pred} below 0.95 \
+    assert model_r2 > 0.90, f"DeepLC R2 score on {file_path_pred} below 0.9 \
 (was {model_r2})"