From 2060d57b0c1868c9b83ddbc9a761dcb72bedc18b Mon Sep 17 00:00:00 2001
From: MATAN NINIO <MATANN@il.ibm.com>
Date: Tue, 26 Nov 2024 15:15:57 +0200
Subject: [PATCH 1/2] double demo (dti and ppi)

---
 mammal/examples/dti_bindingdb_kd/task.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mammal/examples/dti_bindingdb_kd/task.py b/mammal/examples/dti_bindingdb_kd/task.py
index a8bc46a..f7207f6 100644
--- a/mammal/examples/dti_bindingdb_kd/task.py
+++ b/mammal/examples/dti_bindingdb_kd/task.py
@@ -126,10 +126,10 @@ def data_preprocessing(
         ground_truth_value = sample_dict.get(ground_truth_key, None)
 
         sample_dict[ENCODER_INPUTS_STR] = (
-            f"<@TOKENIZER-TYPE=AA><MASK> \
-              <@TOKENIZER-TYPE=AA@MAX-LEN={target_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_GENERAL_PROTEIN><SEQUENCE_NATURAL_START>{target_sequence}<SEQUENCE_NATURAL_END> \
-              <@TOKENIZER-TYPE=SMILES@MAX-LEN={drug_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_SMALL_MOLECULE><SEQUENCE_NATURAL_START>{drug_sequence}<SEQUENCE_NATURAL_END> \
-              <EOS>"
+            "<@TOKENIZER-TYPE=AA><MASK>"\
+                f"<@TOKENIZER-TYPE=AA@MAX-LEN={target_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_GENERAL_PROTEIN><SEQUENCE_NATURAL_START>{target_sequence}<SEQUENCE_NATURAL_END>" \
+                f"<@TOKENIZER-TYPE=SMILES@MAX-LEN={drug_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_SMALL_MOLECULE><SEQUENCE_NATURAL_START>{drug_sequence}<SEQUENCE_NATURAL_END>" \
+                "<EOS>"
         )
         tokenizer_op(
             sample_dict,

From 237801c242bd575aebad31872bea9565c042062b Mon Sep 17 00:00:00 2001
From: MATAN NINIO <MATANN@il.ibm.com>
Date: Tue, 26 Nov 2024 16:22:32 +0200
Subject: [PATCH 2/2] pre-commit fix

---
 mammal/examples/dti_bindingdb_kd/task.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mammal/examples/dti_bindingdb_kd/task.py b/mammal/examples/dti_bindingdb_kd/task.py
index f7207f6..9bea83f 100644
--- a/mammal/examples/dti_bindingdb_kd/task.py
+++ b/mammal/examples/dti_bindingdb_kd/task.py
@@ -126,10 +126,10 @@ def data_preprocessing(
         ground_truth_value = sample_dict.get(ground_truth_key, None)
 
         sample_dict[ENCODER_INPUTS_STR] = (
-            "<@TOKENIZER-TYPE=AA><MASK>"\
-                f"<@TOKENIZER-TYPE=AA@MAX-LEN={target_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_GENERAL_PROTEIN><SEQUENCE_NATURAL_START>{target_sequence}<SEQUENCE_NATURAL_END>" \
-                f"<@TOKENIZER-TYPE=SMILES@MAX-LEN={drug_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_SMALL_MOLECULE><SEQUENCE_NATURAL_START>{drug_sequence}<SEQUENCE_NATURAL_END>" \
-                "<EOS>"
+            "<@TOKENIZER-TYPE=AA><MASK>"
+            f"<@TOKENIZER-TYPE=AA@MAX-LEN={target_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_GENERAL_PROTEIN><SEQUENCE_NATURAL_START>{target_sequence}<SEQUENCE_NATURAL_END>"
+            f"<@TOKENIZER-TYPE=SMILES@MAX-LEN={drug_max_seq_length}><MOLECULAR_ENTITY><MOLECULAR_ENTITY_SMALL_MOLECULE><SEQUENCE_NATURAL_START>{drug_sequence}<SEQUENCE_NATURAL_END>"
+            "<EOS>"
         )
         tokenizer_op(
             sample_dict,