Update src/app.py

src/app.py

@@ -20,10 +20,10 @@ st.title("Bitconverter")
 # =========================
 # Encoding Schemes
 # =========================
-ENCODING_OPTIONS = ["Voyager 6-bit", "Base64 (6-bit)", "ASCII (7-bit)", "UTF-8 (8-bit)"]
+ENCODING_OPTIONS = ["6-bit LNS", "Base64 (6-bit)", "ASCII (7-bit)", "UTF-8 (8-bit)"]
 
 BITS_PER_UNIT = {
-    "Voyager 6-bit": 6,
+    "6-bit LNS": 6,
     "Base64 (6-bit)": 6,
     "ASCII (7-bit)": 7,
     "UTF-8 (8-bit)": 8,
@@ -39,7 +39,7 @@ voyager_table = {
         'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '0', '1', '2',
         '3', '4', '5', '6', '7', '8', '9', '.', ',', '(',
         ')','+', '-', '*', '/', '=', '$', '!', ':', '%',
-        '"', '#', '@', "'", '?', '&'
+        '"', '#', '@', "'", '?', '&', '(Image)'
     ])
 }
 reverse_voyager_table = {v: k for k, v in voyager_table.items()}
@@ -176,7 +176,7 @@ def encode_to_binary(text: str, scheme: str) -> tuple[list[int], list[str], list
     - display_units: the encoded representation (Base64 symbol, hex byte, ASCII code, Voyager char)
     - source_chars: the original text character each chunk maps to
     """
-    if scheme == "Voyager 6-bit":
+    if scheme == "6-bit LNS":
         bits = []
         for char in text:
             val = reverse_voyager_table.get(char.upper(), 0)
@@ -233,7 +233,7 @@ def encode_to_binary(text: str, scheme: str) -> tuple[list[int], list[str], list
 # Decoding Functions
 # =========================
 def decode_from_binary(bits: list[int], scheme: str) -> str:
-    if scheme == "Voyager 6-bit":
+    if scheme == "6-bit LNS":
         chars = []
         for i in range(0, len(bits), 6):
             chunk = bits[i:i + 6]
@@ -307,7 +307,7 @@ with tab1:
             index=0,
             key="enc_scheme",
             help=(
-                "**Voyager 6-bit** – Custom 56-character table (A-Z, 0-9, punctuation). 6 bits/char.\n\n"
+                "**6-bit LNS** – Custom 56-character table (A-Z, 0-9, punctuation). 6 bits/char.\n\n"
                 "**Base64 (6-bit)** – Standard Base64 encoding of UTF-8 bytes. 6 bits/symbol.\n\n"
                 "**ASCII (7-bit)** – Standard 7-bit ASCII. 7 bits/char.\n\n"
                 "**UTF-8 (8-bit)** – Full UTF-8 byte encoding. 8 bits/byte. Supports all Unicode."
@@ -316,7 +316,7 @@ with tab1:
 
         bits_per = BITS_PER_UNIT[encoding_scheme]
 
-        if encoding_scheme == "Voyager 6-bit":
+        if encoding_scheme == "6-bit LNS":
             supported = ''.join(voyager_table[i] for i in range(len(voyager_table)))
             st.caption(f"Supported characters ({len(voyager_table)}): `{supported}`")
 
@@ -335,7 +335,7 @@ with tab1:
             binary_concat = ''.join(map(str, binary_labels))
 
             st.markdown("### Output 1 – Binary Labels per Character")
-            st.caption(f"Encoding: **{encoding_scheme}** — {bits_per} bits per unit")
+            st.caption(f"Encoding: **{encoding_scheme}** - {bits_per} bits per unit")
 
             grouped_bits = [binary_labels[i:i + bits_per] for i in range(0, len(binary_labels), bits_per)]
             scroll_html = (
@@ -345,7 +345,7 @@ with tab1:
             for i, bits in enumerate(grouped_bits):
                 src = source_chars[i] if i < len(source_chars) else "?"
                 enc = display_units[i] if i < len(display_units) else "?"
-                if encoding_scheme == "Voyager 6-bit":
+                if encoding_scheme == "6-bit LNS":
                     scroll_html += f"<div>'{src}' → {bits}</div>"
                 else:
                     scroll_html += f"<div>'{src}' → '{enc}' → {bits}</div>"
@@ -357,7 +357,7 @@ with tab1:
                 src = source_chars[i] if i < len(source_chars) else "?"
                 enc = display_units[i] if i < len(display_units) else "?"
                 bit_str = ''.join(map(str, bits))
-                if encoding_scheme == "Voyager 6-bit":
+                if encoding_scheme == "6-bit LNS":
                     per_char_lines.append(f"'{src}' → {bit_str}")
                 else:
                     per_char_lines.append(f"'{src}' → '{enc}' → {bit_str}")
@@ -411,8 +411,8 @@ with tab1:
             ["Black & White (1-bit)", "Grayscale (4-bit)"],
             key="enc_image_type",
             help=(
-                "**Black & White (1-bit)** — Each pixel = 1 bit (0 or 1). Uses a brightness threshold.\n\n"
-                "**Grayscale (4-bit)** — Each pixel = 4 bits (0–15 levels). "
+                "**Black & White (1-bit)** - Each pixel = 1 bit (0 or 1). Uses a brightness threshold.\n\n"
+                "**Grayscale (4-bit)** - Each pixel = 4 bits (0–15 levels). "
                 "Uniform quantization in sRGB/BT.601 luma space. 0 = black, 15 = white. "
                 "Two pixels per byte, high-nibble first; rows top-to-bottom, no row padding."
             )
@@ -429,7 +429,7 @@ with tab1:
             orig_w, orig_h = img.size
             aspect = orig_h / orig_w
 
-            st.image(img, caption=f"Original (grayscale) — {orig_w}×{orig_h} px", use_container_width=True)
+            st.image(img, caption=f"Original (grayscale) - {orig_w}×{orig_h} px", use_container_width=True)
 
             st.markdown("#### ⚙️ Resolution")
             target_width = st.slider(
@@ -456,7 +456,7 @@ with tab1:
 
                 binary_matrix = (img_array < threshold).astype(int)
 
-                st.markdown("### Preview — Black & White Output")
+                st.markdown("### Preview - Black & White Output")
                 col_prev1, col_prev2 = st.columns(2)
                 with col_prev1:
                     st.image(img_resized, caption=f"Resized grayscale ({target_width}×{target_height})", use_container_width=True)
@@ -485,7 +485,7 @@ with tab1:
                     key="download_img_binary_txt"
                 )
 
-                st.markdown("### Output 2 – Binary Matrix by dimension (Samples × Positions)")
+                st.markdown("### Output 2 – Binary Matrix by dimension (Reactions × Positions)")
                 columns = [f"Position {i+1}" for i in range(target_width)]
                 df_img = pd.DataFrame(binary_matrix, columns=columns)
                 df_img.insert(0, "Sample", range(1, len(df_img) + 1))
@@ -548,7 +548,7 @@ with tab1:
                 gray4_matrix = quantize_to_4bit(img_array)
                 gray8_preview = gray4_to_gray8(gray4_matrix)
 
-                st.markdown("### Preview — 4-bit Grayscale (16 levels)")
+                st.markdown("### Preview - 4-bit Grayscale (16 levels)")
                 col_prev1, col_prev2 = st.columns(2)
                 with col_prev1:
                     st.image(img_resized, caption=f"Original resized ({target_width}×{target_height}, 256 levels)", use_container_width=True)
@@ -740,8 +740,8 @@ with tab2:
             ["Black & White (1-bit)", "Grayscale (4-bit)"],
             key="dec_image_type",
             help=(
-                "**Black & White** — Input is 0/1 binary data. Each value = 1 pixel.\n\n"
-                "**Grayscale (4-bit)** — Input is a **value matrix (0–15)**, **binary data** "
+                "**Black & White** - Input is 0/1 binary data. Each value = 1 pixel.\n\n"
+                "**Grayscale (4-bit)** - Input is a **value matrix (0–15)**, **binary data** "
                 "(every 4 bits = one pixel), or a packed **.g4 file**."
             )
         )
@@ -817,7 +817,7 @@ with tab2:
                         display_w = img_width * display_scale
                         display_h = img_height * display_scale
                         pil_display = pil_img.resize((display_w, display_h), Image.NEAREST)
-                        st.image(pil_display, caption=f"Binary image — {img_width}×{img_height} (1=black, 0=white)")
+                        st.image(pil_display, caption=f"Binary image - {img_width}×{img_height} (1=black, 0=white)")
 
                         ones = int(bits_matrix.sum())
                         st.markdown(
@@ -861,10 +861,10 @@ with tab2:
                 ["Value matrix (0–15)", "Binary (4 bits per pixel)", "Packed .g4 file"],
                 key="g4_input_format",
                 help=(
-                    "**Value matrix** — CSV/XLSX where each cell is a pixel value 0–15. "
+                    "**Value matrix** - CSV/XLSX where each cell is a pixel value 0–15. "
                     "Rows = pixel rows, columns = pixel columns.\n\n"
-                    "**Binary** — 0/1 data where every 4 consecutive bits encode one pixel (0–15).\n\n"
-                    "**Packed .g4 file** — Binary file with G4 header + packed 4bpp payload "
+                    "**Binary** - 0/1 data where every 4 consecutive bits encode one pixel (0–15).\n\n"
+                    "**Packed .g4 file** - Binary file with G4 header + packed 4bpp payload "
                     "(two pixels per byte, high-nibble first)."
                 )
             )
@@ -969,7 +969,7 @@ with tab2:
                     display_w = img_width * display_scale
                     display_h = img_height * display_scale
                     pil_display = pil_img.resize((display_w, display_h), Image.NEAREST)
-                    st.image(pil_display, caption=f"4-bit grayscale — {img_width}×{img_height} (0=black, 15=white)")
+                    st.image(pil_display, caption=f"4-bit grayscale - {img_width}×{img_height} (0=black, 15=white)")
 
                     # Stats
                     unique_vals, counts = np.unique(gray4_matrix, return_counts=True)
@@ -1014,7 +1014,7 @@ with tab3:
     st.header("📊 Data Analytics")
     st.markdown("""
     Upload your sample data file (Excel or CSV) for a quick exploratory assessment of the editing rates distribution.  
-    The file should contain samples as rows and position columns with editing values.  
+    The file should contain Reactions as rows and position columns with editing values.  
     This tab provides visualizations **before** any binary labelling.
     """)
 
@@ -1049,7 +1049,7 @@ with tab3:
                 st.error("No numeric position columns detected.")
                 st.stop()
 
-            st.info(f"Detected **{len(position_cols)}** position columns and **{len(adf)}** samples.")
+            st.info(f"Detected **{len(position_cols)}** position columns and **{len(adf)}** Reactions.")
 
             pos_data = adf[position_cols].apply(pd.to_numeric, errors="coerce").fillna(0.0)
 
@@ -1059,34 +1059,32 @@ with tab3:
                 total_edited = pos_data.sum(axis=1)
 
             st.markdown("### 1️⃣ Raw Data Distribution")
-            st.caption("Visualize editing values across all positions and samples — before any binary labelling.")
+            st.caption("Visualize editing values across all positions and Reactions - before any binary labelling.")
 
             transform_option = st.selectbox(
                 "Value transformation:",
-                ["Raw (linear)", "log1p", "log1p → log1p", "log1p → pos. norm."],
+                ["Raw (linear)", "log1p", "log1p → log1p"],
                 index=0,
                 key="transform_select",
                 help=(
-                    "**Raw** — No transformation.\n\n"
-                    "**log1p** — `log(1 + x)`. Compresses high values, spreads low range.\n\n"
-                    "**log1p → log1p** — Double log1p. Even stronger compression.\n\n"
-                    "**log1p → pos. norm.** — log1p then robust per-position normalization "
-                    "(median / IQR scaling per position column)."
+                    "**Raw** - No transformation.\n\n"
+                    "**log1p** - `log(1 + x)`. Compresses high values, spreads low range.\n\n"
+                    "**log1p → log1p** - Double log1p. Even stronger compression.\n\n"
                 )
             )
 
-            def robust_pos_normalize_log1p(data: pd.DataFrame) -> pd.DataFrame:
-                logged = np.log1p(data)
-                result = logged.copy()
-                for col in result.columns:
-                    med = result[col].median()
-                    q75, q25 = result[col].quantile(0.75), result[col].quantile(0.25)
-                    iqr = q75 - q25
-                    if iqr > 0:
-                        result[col] = (result[col] - med) / iqr
-                    else:
-                        result[col] = result[col] - med
-                return result
+            # def robust_pos_normalize_log1p(data: pd.DataFrame) -> pd.DataFrame:
+            #     logged = np.log1p(data)
+            #     result = logged.copy()
+            #     for col in result.columns:
+            #         med = result[col].median()
+            #         q75, q25 = result[col].quantile(0.75), result[col].quantile(0.25)
+            #         iqr = q75 - q25
+            #         if iqr > 0:
+            #             result[col] = (result[col] - med) / iqr
+            #         else:
+            #             result[col] = result[col] - med
+            #     return result
 
             if transform_option == "log1p":
                 transformed = np.log1p(pos_data)
@@ -1096,10 +1094,10 @@ with tab3:
                 transformed = np.log1p(np.log1p(pos_data))
                 value_label = "Editing Value (log1p → log1p)"
                 transform_tag = "log1p_log1p"
-            elif transform_option == "log1p → pos. norm.":
-                transformed = robust_pos_normalize_log1p(pos_data)
-                value_label = "Editing Value (log1p → pos. norm.)"
-                transform_tag = "log1p_posnorm"
+            # elif transform_option == "log1p → pos. norm.":
+            #     transformed = robust_pos_normalize_log1p(pos_data)
+            #     value_label = "Editing Value (log1p → pos. norm.)"
+            #     transform_tag = "log1p_posnorm"
             else:
                 transformed = pos_data
                 value_label = "Editing Value"
@@ -1110,7 +1108,7 @@ with tab3:
                 lambda x: int(re.search(r"(\d+)", str(x)).group(1)) if re.search(r"(\d+)", str(x)) else 0
             )
 
-            st.markdown("#### 📊 Histogram — All Values")
+            st.markdown("#### 📊 Histogram - All Values")
 
             n_bins = st.number_input("Number of bins:", min_value=10, max_value=300, value=80, step=10, key="hist_bins")
 
@@ -1137,7 +1135,7 @@ with tab3:
             fig2.tight_layout()
             st.pyplot(fig2)
 
-            st.markdown("#### 2️⃣ Density Scatter Plot (FACS-style)")
+            st.markdown("#### 2️⃣ Density Scatter Plot")
             st.caption("Each dot = one measurement (sample × position). Color = local point density.")
 
             x_vals = melted["Position_idx"].values.astype(float)
@@ -1162,36 +1160,12 @@ with tab3:
             cbar = fig3.colorbar(scatter, ax=ax3, label="Density")
             ax3.set_xlabel("Position")
             ax3.set_ylabel(value_label)
-            ax3.set_title(f"Density Scatter — Position vs. {value_label}")
+            ax3.set_title(f"Density Scatter - {value_label} by Position")
             ax3.set_xticks(sorted(melted["Position_idx"].unique()))
             ax3.grid(alpha=0.2)
             fig3.tight_layout()
             st.pyplot(fig3)
 
-            st.markdown("#### 3️⃣ 2D Density Heatmap")
-            st.caption("Binned heatmap of editing values by position — similar to a FACS density plot.")
-
-            y_bins = st.slider("Vertical bins:", min_value=20, max_value=150, value=60, key="heatmap_ybins")
-
-            positions_unique = sorted(melted["Position_idx"].unique())
-            n_positions = len(positions_unique)
-
-            fig4, ax4 = plt.subplots(figsize=(12, 6))
-            h = ax4.hist2d(
-                x_vals, y_vals,
-                bins=[n_positions, y_bins],
-                cmap="jet",
-                norm=mcolors.LogNorm() if melted["Value"].max() > 0 else None,
-            )
-            fig4.colorbar(h[3], ax=ax4, label="Count (log scale)")
-            ax4.set_xlabel("Position")
-            ax4.set_ylabel(value_label)
-            ax4.set_title(f"2D Density Heatmap — Position vs. {value_label}")
-            ax4.set_xticks(positions_unique)
-            ax4.grid(alpha=0.15)
-            fig4.tight_layout()
-            st.pyplot(fig4)
-
         except Exception as e:
             st.error(f"❌ Error processing file: {e}")
             import traceback
@@ -1334,7 +1308,7 @@ with tab4:
 
             if not any(c.lower() == "sample" for c in df.columns):
                 df.insert(0, "Sample", np.arange(1, len(df) + 1))
-                st.info("`Sample` column missing — automatically generated 1..N.")
+                st.info("`Sample` column missing - automatically generated 1..N.")
 
             position_cols = [c for c in df.columns if re.match(r"(?i)^position\s*\d+", c)]
             if not position_cols:
@@ -1352,7 +1326,7 @@ with tab4:
 
             if "Total edited" not in df.columns:
                 df["Total edited"] = df[position_cols].sum(axis=1).astype(int)
-                st.info("`Total edited` column missing — calculated automatically as sum of 1s per row.")
+                st.info("`Total edited` column missing - calculated automatically as sum of 1s per row.")
 
             st.markdown("#### ⚙️ Volume Calculation Settings")
             default_total_vol = st.number_input(
@@ -1365,7 +1339,7 @@ with tab4:
             if not vol_candidates:
                 df['Volume per "1"'] = default_total_vol / df["Total edited"].replace(0, np.nan)
                 df['Volume per "1"'] = df['Volume per "1"'].fillna(0)
-                st.info(f'`Volume per "1"` column missing — calculated automatically as {default_total_vol:.0f} µL (max per input well) / Total edited.')
+                st.info(f'`Volume per "1"` column missing - calculated automatically as {default_total_vol:.0f} µL (max per input well) / Total edited.')
                 volume_col = 'Volume per "1"'
             else:
                 volume_col = vol_candidates[0]
@@ -1385,7 +1359,7 @@ with tab4:
 
             st.markdown("### 👀 Preview: Suggested Uniform Layout")
             if max_wells_per_source == 0:
-                st.info("No edits detected — nothing to allocate.")
+                st.info("No edits detected - nothing to allocate.")
                 st.stop()
 
             st.write(