Improvement of the input arguments check

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 from Bio.PDB.PDBParser import PDBParser
-# from Bio.PDB.Polypeptide import is_aa, three_to_one
 
 from wrapper import *
 
@@ -14,11 +13,7 @@ def predict_solubility(pdb_code, chain, orig, loc, mut, model, version=None):
 		orig_list = parseList(orig, Type_aminoAcid)
 		mut_list = parseList(mut, Type_aminoAcid)
 
-		if len(loc_list) != len(mut_list):
-			if len(mut_list) == 1:
-				mut_list *= len(loc_list)
-			else:
-				raise gr.Error("Inconsistent multi-point mutant specification")
+		mut_list = check_mutList(loc_list, orig_list, mut_list)
 
 		return predict(pdb_path, chain, orig_list, loc_list, mut_list, weights=MODELS[model], rich_output=True)
 	except Exception as e:
@@ -26,7 +21,7 @@ def predict_solubility(pdb_code, chain, orig, loc, mut, model, version=None):
 
 _pdb_code = None
 _chains = None
-def get_chains(pdb_code): # 
+def get_chains(pdb_code): # display chains stored in the PDB structure
 	global _pdb_code, _chains
 	
 	if pdb_code != _pdb_code:
@@ -72,7 +67,9 @@ with gr.Blocks(
 		mut = gr.Textbox(label="Mutant residue(s)", placeholder="D[,A]", scale=0)
 
 	# with gr.Accordion("Model selection"):
-	model = gr.Radio(choices=[m.stem for m in MODELS], label="Model selection", type="index", value=MODELS[0].stem)
+	model_names = [m.stem for m in MODELS]
+	model_names[0] += " (recommended)"
+	model = gr.Radio(choices=model_names, label="Model selection", type="index", value=model_names[0])
 	
 	output = gr.HTML()
 
@@ -97,8 +94,7 @@ with gr.Blocks(
 		examples=[
 			["1EER", "48,150", "F,R", "D"],
 			["1EER", "13", "E", "K"],
-			# ["3QIB", "A,B,P,C,D", "YP7F,TP12S;YP7F;TP12S"],
-			# ["1KNE", "A,P", ';'.join([f"TP6{a}" for a in AMINO_ACID_CODES_1])]
+			# ["1z0q", "19", "F", "A"],
 		],
 		# example_labels = ["1EER F48D,R150D"],
 		inputs=[pdb_code, loc, orig, mut],
@@ -111,7 +107,7 @@ with gr.Blocks(
 	<br/>
 	
 	**Acknowledgement**. Please, use the following citation to acknowledge the use of our tool:  
-	> Velecký, J., Faldynová H., Hermosilla, P., Sandlerová, N., Dörr, M., Egersdorfová, S., Bornscheuer, U., Prokop, Z., Damborský, J., Mazurenko, S., 2025:
+	> Velecký, J., Faldynová H., Hermosilla, P., Sandlerová, N., Doerr, M., Egersdorfová, S., Bornscheuer, U., Prokop, Z., Damborský, J., Mazurenko, S., 2025:
 	> SoluProtMut: Siamese Deep Learning for Solubility Effect Prediction in Protein Mutations and Experimental Validation.
 	> *In preparation.*
 	""")

wrapper.py

@@ -53,6 +53,15 @@ def Type_PDB(pdb_code):
 		raise argparse.ArgumentTypeError(e)
 	return pdb_code, pdb_path
 
+def check_mutList(loc_list, orig_list, mut_list):
+	if len(loc_list) != len(mut_list):
+		if len(mut_list) == 1: # apply mutation to all positions
+			mut_list *= len(loc_list)
+	if len(loc_list) == len(mut_list) == len(orig_list):
+		return mut_list
+	else:
+		raise ValueError("Inconsistent multi-point mutant specification")
+
 # ----------------------------------------------END OF DATA TYPES ------------------------------------------
 
 argParser = argparse.ArgumentParser(add_help = True,
@@ -117,8 +126,12 @@ def predict(pdb_path, chain, orig, loc, mut, weights=None, version=None, rich_ou
 	from code.predictor import EnsemblePredictor # expensive import left for after the argument check
 	pred_model = EnsemblePredictor(weights=weights, version=version)
 
-	assesment, prediction = pred_model.predict_change(pdb_path, chain, orig, loc, mut)
-	assesment = {'+': 'solubilizing', 'N': 'neutral', '-': 'desolubilizing'}[assesment]
+	try:
+		assesment, prediction = pred_model.predict_change(pdb_path, chain, orig, loc, mut)
+	except KeyError as e:
+		raise ValueError("Non-existing position in the PDB: %s" % str(e))
+		
+	assesment = {'+': 'solubilizing ( > 0.5)', 'N': 'neutral (score ≈ 0.5)', '-': 'desolubilizing (score < 0.5)'}[assesment]
 	
 	print(weights)
 	
@@ -128,9 +141,9 @@ def predict(pdb_path, chain, orig, loc, mut, weights=None, version=None, rich_ou
 		BLUESH = (100, 100, 255)
 		color = tuple((o*max(0, 1-prediction*2) + b*max(0, (2*prediction)**2-1) for o, b in zip(ORANGE, BLUESH)))
 		
-		return f"Predicted solubility change: {prediction:.3f} <span style='color: rgb{color}'>({assesment})</span>"
+		return f"Predicted solubiliztation score: <span style='color: rgb{color}'>{prediction:.2f} {assesment}</span>"
 	else:
-		return "Predicted solubility change: %g (%s)" % (prediction, assesment)
+		return "Predicted solubiliztation score: %g (%s)" % (prediction, assesment)
 
 
 
@@ -144,11 +157,10 @@ if __name__ == '__main__':
 	args = argParser.parse_args()
 
 	# positional arguments parsing (argparse can't cope with nested positional arguments)
-	if len(args.loc) != len(args.mut):
-		if len(args.mut) == 1: # same target AA on all specified positions
-			args.mut = args.mut * len(args.loc)
-		else:
-			argParser.error("Inconsistent multi-point mutant specification")
+	try:
+		args.mut = check_mutList(args.loc, args.orig, args.mut)
+	except Exception as e:
+		argParser.error(str(e))
 	pdb_code, pdb_path = args.input
 	chain = args.chain