Update app.py

app.py

@@ -1,30 +1,30 @@
-# -------------------------------------------------------------------------------------------------
 #  app.py  –  Streamlit app para predição de GO:MF
-#  • ProtBERT / ProtBERT-BFD fine-tuned   (melvinalves/FineTune)
-#  • ESM-2 base                            (facebook/esm2_t33_650M_UR50D)
-# -------------------------------------------------------------------------------------------------
+#  ProtBERT / ProtBERT-BFD fine-tuned   (melvinalves/FineTune)
+#  ESM-2 base                            (facebook/esm2_t33_650M_UR50D)
+
+
 import os, re, numpy as np, torch, joblib, streamlit as st
 from huggingface_hub import login
 from transformers import AutoTokenizer, AutoModel
 from keras.models import load_model
 from goatools.obo_parser import GODag
 
-# ———————————————————  AUTENTICAÇÃO  ——————————————————— #
+# AUTENTICAÇÃO #
 login(os.environ["HF_TOKEN"])
 
-# ———————————————————  CONFIG  ——————————————————— #
+# CONFIG #
 SPACE_ID   = "melvinalves/protein_function_prediction"
 TOP_N      = 20
 THRESH     = 0.37
 CHUNK_PB   = 512
 CHUNK_ESM  = 1024
 
-# repositórios HF
+# REPOSITÓRIOS HF
 FINETUNED_PB   = ("melvinalves/FineTune", "fineTunedProtbert")
 FINETUNED_BFD  = ("melvinalves/FineTune", "fineTunedProtbertbfd")
 BASE_ESM       = "facebook/esm2_t33_650M_UR50D"
 
-# ———————————————————  HELPERS  ——————————————————— #
+# HELPERS #
 @st.cache_resource
 def download_file(path):
     """Ficheiros pequenos (≤1 GB) guardados no Space."""
@@ -76,7 +76,7 @@ def load_go_info():
 
 GO_INFO = load_go_info()
 
-# ———————————————————  CARGA MODELOS  ——————————————————— #
+# MODELOS #
 mlp_pb   = load_keras("mlp_protbert.h5")
 mlp_bfd  = load_keras("mlp_protbertbfd.h5")
 mlp_esm  = load_keras("mlp_esm2.h5")
@@ -85,7 +85,7 @@ stacking = load_keras("ensemble_stack.h5")
 mlb      = joblib.load(download_file("data/mlb_597.pkl"))
 GO       = mlb.classes_
 
-# ———————————————————  UI  ——————————————————— #
+# UI #
 st.set_page_config(page_title="Predição de Funções Moleculares de Proteínas",
                    page_icon="🧬", layout="centered")
 
@@ -111,7 +111,7 @@ st.title("Predição de Funções Moleculares de Proteínas (GO:MF)")
 fasta_input     = st.text_area("Insere uma ou mais sequências FASTA:", height=300)
 predict_clicked = st.button("Prever GO terms")
 
-# ———————————————————  UTILITÁRIOS  ——————————————————— #
+# UTILITÁRIOS #
 def parse_fasta_multiple(text):
     """Extrai [(header, seq)] de texto FASTA (bloco inicial sem '>' suportado)."""
     out = []
@@ -139,9 +139,9 @@ def clean_definition(defin: str) -> str:
 
 def go_link(go_id, name=""):
     url = f"https://www.ebi.ac.uk/QuickGO/term/{go_id}"
-    return f"[{go_id} — {name}]({url})" if name else f"[{go_id}]({url})"
+    return f"[{go_id} - {name}]({url})" if name else f"[{go_id}]({url})"
 
-# ———————————————————  MOSTRAR RESULTADOS  ——————————————————— #
+# MOSTRAR RESULTADOS #
 def mostrar(header, y_pred):
     pid      = header.split()[0]
     uniprot  = f"https://www.uniprot.org/uniprotkb/{pid}"
@@ -162,21 +162,21 @@ def mostrar(header, y_pred):
 
         col1, col2 = st.columns(2)
 
-        # --- coluna 1 : ≥ threshold
+        # coluna 1 : ≥ threshold
         with col1:
             st.markdown(f"**GO terms com prob ≥ {THRESH}**")
             hits = mlb.inverse_transform((y_pred >= THRESH).astype(int))[0]
             if hits:
                 for go_id in hits:
-                    name, defin_raw = GO_INFO.get(go_id, ("— sem nome —", ""))
+                    name, defin_raw = GO_INFO.get(go_id, ("- sem nome -", ""))
                     defin = clean_definition(defin_raw)
                     st.markdown(f"- {go_link(go_id, name)}")
                     if defin:
                         st.caption(defin)
             else:
-                st.code("— nenhum —")
+                st.code("- nenhum -")
 
-        # --- coluna 2 : Top-20
+        # coluna 2 : Top-20
         with col2:
             st.markdown(f"**Top {TOP_N} GO terms mais prováveis**")
             for rank, idx in enumerate(np.argsort(-y_pred[0])[:TOP_N], 1):
@@ -184,7 +184,7 @@ def mostrar(header, y_pred):
                 name, _ = GO_INFO.get(go_id, ("", ""))
                 st.markdown(f"{rank}. {go_link(go_id, name)} : {y_pred[0][idx]:.4f}")
 
-# ———————————————————  INFERÊNCIA  ——————————————————— #
+# INFERÊNCIA #
 if predict_clicked:
     for header, seq in parse_fasta_multiple(fasta_input):
         with st.spinner(f"A processar {header}… (pode demorar alguns minutos)"):
@@ -200,7 +200,7 @@ if predict_clicked:
 
         mostrar(header, y_ens)
 
-# ———————————————————  LISTA COMPLETA  ——————————————————— #
+# LISTA COMPLETA #
 with st.expander("Mostrar lista completa dos 597 GO terms possíveis", expanded=False):
     cols = st.columns(3)
     for i, go_id in enumerate(GO):