Update README and app.py to reflect stability scoring terminology

README.md

@@ -10,9 +10,9 @@ app_file: app.py
 pinned: false
 ---
 
-# Microbiome Gene Scoring Explorer
+# Microbiome Stability Scoring Explorer
 
 Upload a FASTA of genes, embed with `prokbert-mini-long` (mean pooling), score with `large-notext`, and inspect:
 - UMAP of input embeddings
 - UMAP of final embeddings
-- Logit distribution
+- Stability score distribution

app.py

@@ -542,7 +542,7 @@ def _plot_umap(vectors: np.ndarray, labels: List[str], logits: np.ndarray, title
                 mode="markers",
                 text=labels,
                 customdata=np.array(color_values).reshape(-1, 1),
-                hovertemplate="<b>%{text}</b><br>UMAP 1=%{x:.3f}<br>UMAP 2=%{y:.3f}<br>logit=%{customdata[0]:.4f}<extra></extra>",
+                hovertemplate="<b>%{text}</b><br>UMAP 1=%{x:.3f}<br>UMAP 2=%{y:.3f}<br>stability score=%{customdata[0]:.4f}<extra></extra>",
                 marker={
                     "size": 10,
                     "color": color_values,
@@ -550,7 +550,7 @@ def _plot_umap(vectors: np.ndarray, labels: List[str], logits: np.ndarray, title
                     "line": {"width": 0.6, "color": "#1d2a1f"},
                     "opacity": 0.92,
                     "showscale": True,
-                    "colorbar": {"title": "final logit"},
+                    "colorbar": {"title": "stability score"},
                 },
             )
         ]
@@ -573,9 +573,17 @@ def _display_label(record: dict) -> str:
     return record["id"]
 
 
+def _short_plot_label(label: str, max_len: int = 32) -> str:
+    short_label = _extract_taxa_name(label)
+    if len(short_label) <= max_len:
+        return short_label
+    return f"{short_label[: max_len - 1].rstrip()}…"
+
+
 def _plot_logits(logits: np.ndarray, labels: List[str]):
     order = np.argsort(logits)[::-1]
     sorted_labels = [labels[idx] for idx in order]
+    short_labels = [_short_plot_label(label) for label in sorted_labels]
     sorted_logits = [float(logits[idx]) for idx in order]
     x_positions = list(range(len(sorted_labels)))
     fig = go.Figure(
@@ -586,23 +594,23 @@ def _plot_logits(logits: np.ndarray, labels: List[str]):
                 marker={"color": "#d8832f"},
                 width=0.95,
                 customdata=np.array(sorted_labels).reshape(-1, 1),
-                hovertemplate="<b>%{customdata[0]}</b><br>logit=%{y:.4f}<extra></extra>",
+                hovertemplate="<b>%{customdata[0]}</b><br>stability score=%{y:.4f}<extra></extra>",
             )
         ]
     )
     fig.update_layout(
-        title="Ranked Microbe Logits",
-        xaxis_title="Microbe",
-        yaxis_title="Logit",
+        title="Ranked Stability Scores",
+        xaxis_title="Taxon",
+        yaxis_title="Stability Score",
         bargap=0,
         paper_bgcolor="rgba(255,255,255,0)",
         plot_bgcolor="rgba(255,255,255,0.75)",
-        margin={"l": 10, "r": 10, "t": 60, "b": 10},
+        margin={"l": 10, "r": 10, "t": 60, "b": 140},
     )
     fig.update_xaxes(
         tickmode="array",
         tickvals=x_positions,
-        ticktext=sorted_labels,
+        ticktext=short_labels,
         tickangle=-45,
     )
     return fig
@@ -759,7 +767,7 @@ with gr.Blocks(title="Microbiome Explorer", css=CSS, theme=gr.themes.Soft()) as
     gr.HTML(
         """
         <section class="hero">
-          <h1>Microbiome Gene Scoring Explorer</h1>
+          <h1>Microbiome Stability Scoring Explorer</h1>
           <p>
             Upload raw FASTA, translate a MicrobeAtlas sample into representative OTU sequences,
             or build a synthetic community by taxonomy. Every route ends in the same pipeline:
@@ -846,11 +854,11 @@ with gr.Blocks(title="Microbiome Explorer", css=CSS, theme=gr.themes.Soft()) as
         with gr.Row():
             input_umap_plot = gr.Plot(label="Input embedding UMAP")
             final_umap_plot = gr.Plot(label="Final embedding UMAP")
-        logits_plot = gr.Plot(label="Logit distribution")
+        logits_plot = gr.Plot(label="Stability score distribution")
         with gr.Accordion("Top-scoring members", open=False):
             top_table = gr.Dataframe(
-                headers=["id", "logit", "source", "taxonomy", "detail"],
-                label="Top genes by logit",
+                headers=["id", "stability_score", "source", "taxonomy", "detail"],
+                label="Top members by stability score",
                 wrap=True,
             )
         with gr.Accordion("Analyzed members", open=False):