Update requirements and make necessary code changes

.ipynb_checkpoints/app-checkpoint.py

@@ -39,8 +39,9 @@ from scipy.special import expit
 #from peft import get_peft_config, PeftModel, PeftConfig, inject_adapter_in_model, LoraConfig
 
 checkpoint='ThorbenF/prot_t5_xl_uniref50'
+max_length=1500
 
-model, tokenizer = load_model(checkpoint)
+model, tokenizer = load_model(checkpoint,max_length)
 
 def create_dataset(tokenizer,seqs,labels,checkpoint):
     
@@ -80,7 +81,7 @@ def predict_protein_sequence(test_one_letter_sequence):
     test_one_letter_sequence = test_one_letter_sequence.replace("O", "X").replace("B", "X").replace("U", "X").replace("Z", "X").replace("J", "X")
     
     # Add spaces between each amino acid for ProtT5 and ProstT5 models
-    if "prot_t5" in checkpoint:
+    if ("prot_t5" in checkpoint) or ("ProstT5" in checkpoint):
         test_one_letter_sequence = " ".join(test_one_letter_sequence)
     
     # Add <AA2fold> for ProstT5 model input format

.ipynb_checkpoints/model_loader-checkpoint.py

@@ -613,7 +613,7 @@ def load_esm_model_classification(checkpoint, num_labels, half_precision, full=F
     
     return model, tokenizer
 
-def load_model(checkpoint):
+def load_model(checkpoint,max_length):
     #checkpoint='ThorbenF/prot_t5_xl_uniref50'
     #best_model_path='ThorbenF/prot_t5_xl_uniref50/cpt.pth'
     full=False

app.py

@@ -39,8 +39,9 @@ from scipy.special import expit
 #from peft import get_peft_config, PeftModel, PeftConfig, inject_adapter_in_model, LoraConfig
 
 checkpoint='ThorbenF/prot_t5_xl_uniref50'
+max_length=1500
 
-model, tokenizer = load_model(checkpoint)
+model, tokenizer = load_model(checkpoint,max_length)
 
 def create_dataset(tokenizer,seqs,labels,checkpoint):
     
@@ -80,7 +81,7 @@ def predict_protein_sequence(test_one_letter_sequence):
     test_one_letter_sequence = test_one_letter_sequence.replace("O", "X").replace("B", "X").replace("U", "X").replace("Z", "X").replace("J", "X")
     
     # Add spaces between each amino acid for ProtT5 and ProstT5 models
-    if "prot_t5" in checkpoint:
+    if ("prot_t5" in checkpoint) or ("ProstT5" in checkpoint):
         test_one_letter_sequence = " ".join(test_one_letter_sequence)
     
     # Add <AA2fold> for ProstT5 model input format

model_loader.py

@@ -613,7 +613,7 @@ def load_esm_model_classification(checkpoint, num_labels, half_precision, full=F
     
     return model, tokenizer
 
-def load_model(checkpoint):
+def load_model(checkpoint,max_length):
     #checkpoint='ThorbenF/prot_t5_xl_uniref50'
     #best_model_path='ThorbenF/prot_t5_xl_uniref50/cpt.pth'
     full=False