Upload folder using huggingface_hub

app.py

@@ -76,6 +76,16 @@ PMID_GROUPS = {
     for pmid, entry in META.items()
 }
 
+PMID_ERA_BINS = [
+    ("pre-2001",  0,          10_000_000),
+    ("2001–2005", 10_000_000, 15_000_000),
+    ("2006–2009", 15_000_000, 20_000_000),
+    ("2010–2013", 20_000_000, 25_000_000),
+    ("2014–2017", 25_000_000, 30_000_000),
+    ("2018–2020", 30_000_000, 35_000_000),
+    ("2021–2023", 35_000_000, 40_000_000),
+]
+
 # Column sets
 EXTRACTION_FIELDS = [
     "pmid", "enzyme_name", "organism_source", "strain", "expression_strain",
@@ -713,6 +723,19 @@ def clustering_tab():
                 ),
             ], width=2),
         ], className="mb-2 align-items-end"),
+        dbc.Row([
+            dbc.Col([
+                html.Label("Filter by publication era", className="fw-semibold small mb-1"),
+                dcc.Dropdown(
+                    id="dd-era-filter",
+                    options=[{"label": label, "value": label}
+                             for label, _, _ in PMID_ERA_BINS],
+                    placeholder="All time periods",
+                    clearable=True,
+                    style={"fontSize": "13px"},
+                ),
+            ], width=4),
+        ], className="mb-2"),
         dbc.Row([dbc.Col(html.Div(id="plot-status", className="text-danger small mb-1"))]),
         dbc.Row([
             dbc.Col(
@@ -2124,8 +2147,9 @@ def populate_cross_filter_values(cross_field, model, min_val, threshold):
     Input("cluster-group-filter", "value"),
     Input("dd-cross-field", "value"),
     Input("dd-cross-value", "value"),
+    Input("dd-era-filter", "value"),
 )
-def update_cluster_plot(model, min_val, threshold, field, plot_type, top_n, groups, cross_field, cross_value):
+def update_cluster_plot(model, min_val, threshold, field, plot_type, top_n, groups, cross_field, cross_value, era):
     empty_fig = go.Figure()
     empty_fig.update_layout(paper_bgcolor="#ffffff", plot_bgcolor="#f9fafc")
     if not all([model, min_val, threshold, field, plot_type]):
@@ -2135,6 +2159,16 @@ def update_cluster_plot(model, min_val, threshold, field, plot_type, top_n, grou
     if cdf is None:
         return empty_fig, f"Data file not found for model={model} min={min_val} t={threshold}"
 
+    # Apply era filter based on PMID as publication year proxy
+    if era:
+        era_range = {label: (lo, hi) for label, lo, hi in PMID_ERA_BINS}
+        if era in era_range:
+            lo, hi = era_range[era]
+            pmid_num = pd.to_numeric(cdf["key"], errors="coerce")
+            cdf = cdf[(pmid_num >= lo) & (pmid_num < hi)]
+        if cdf.empty:
+            return empty_fig, f"No data found for era '{era}'."
+
     # Apply cross-field filter: keep only (key, protein_index) in the selected cross-field cluster
     if cross_field and cross_value:
         keep = cdf[(cdf["field"] == cross_field) & (cdf["cluster_label"] == cross_value)][["key", "protein_index"]]
@@ -2159,6 +2193,8 @@ def update_cluster_plot(model, min_val, threshold, field, plot_type, top_n, grou
 
     n = top_n or 0
     suffix_parts = []
+    if era:
+        suffix_parts.append(era)
     if groups:
         suffix_parts.append(", ".join(groups))
     if cross_field and cross_value: