feat(primo): clarify purpose and RNAseq boards

boards.py

@@ -32,6 +32,10 @@ from dataclasses import dataclass
 from evaluator import _norm_id
 
 METRIC_LABEL = {"auroc": "AUROC", "pearson": "Pearson"}
+MODALITY_LABEL = {
+    "bulk RNA": "Bulk RNAseq",
+    "single-cell RNA": "single-cell RNAseq",
+}
 
 MODALITY_GROUP = "Modality"
 AREA_GROUP = "Therapeutic Areas"
@@ -65,6 +69,11 @@ def metric_label(metric: str) -> str:
     return METRIC_LABEL.get(metric, metric)
 
 
+def modality_label(modality: str) -> str:
+    """Return the visitor-facing label for a stored modality identifier."""
+    return MODALITY_LABEL.get(modality, modality)
+
+
 def short_code(name: str) -> str:
     """The board's letter tag, standing in for what used to be a per-board emoji.
 
@@ -162,7 +171,7 @@ def _cohort_stats(tasks: list[dict]) -> tuple[int, int, int]:
 
 def _blurb(group: str, name: str, tasks: list[dict]) -> str:
     if group == MODALITY_GROUP:
-        return f"Every PRIMO task, scored from {name} profiles."
+        return f"Every PRIMO task, scored from {modality_label(name)} profiles."
     if group == CATEGORY_GROUP:
         return CATEGORY_BLURB.get(name, label(name))
     families = [label(c) for c in distinct(tasks, "category")]
@@ -172,7 +181,7 @@ def _blurb(group: str, name: str, tasks: list[dict]) -> str:
 def _board(group: str, name: str, modality: str, tasks: list[dict]) -> Board:
     """One card. The modality board owns the bare slug; the rest are suffixed by it."""
     n_cohorts, n_patients, n_diseases = _cohort_stats(tasks)
-    display = name if group == MODALITY_GROUP else label(name)
+    display = modality_label(name) if group == MODALITY_GROUP else label(name)
     return Board(
         slug=slugify(modality) if group == MODALITY_GROUP else slugify(name, modality),
         group=group,
@@ -226,7 +235,7 @@ class OpenBoard:
 OPEN_BOARDS: tuple[OpenBoard, ...] = (
     OpenBoard(
         MODALITY_GROUP,
-        "single-cell RNA",
+        "single-cell RNAseq",
         "Dissociated tissue, labelled at the patient level. No cohort yet.",
     ),
     OpenBoard(

render.py

@@ -35,6 +35,7 @@ from boards import (
     OpenBoard,
     in_group,
     metric_label,
+    modality_label,
     open_in_group,
 )
 from leaderboard import per_task_table, ranked_table, tasks_table, top_models
@@ -164,12 +165,11 @@ def render_boards(boards: list[Board], df: pd.DataFrame, by_id: dict[str, dict])
             '<div class="pm-body"><p class="pm-caption">The task registry is '
             "unavailable right now. Please retry in a moment.</p></div>"
         )
-    n_live = len(boards)
-    n_open = sum(len(open_in_group(boards, group)) for group in SECTIONS)
     out = [
         '<div class="pm-head"><div><h1>Boards</h1>',
-        f"<p>{n_live} live · {n_open} open. Every board is scored by the same "
-        "fixed linear probe on sample embeddings.</p></div></div>",
+        "<p>PRIMO evaluates representations of omics samples through "
+        "drug-development-related tasks. Benchmarks are organized by data "
+        "modality, therapeutic area, or task category.</p></div></div>",
         '<div class="pm-body">',
     ]
     for group in SECTIONS:
@@ -294,7 +294,7 @@ def _board_meta(board: Board) -> str:
     tail = f" · {metrics}" if metrics else ""
     return (
         f"{escape(board.blurb)} · {board.n_tasks} tasks · {board.n_cohorts} cohorts · "
-        f"{board.n_patients:,} patients · {escape(board.modality)}{tail}"
+        f"{board.n_patients:,} patients · {escape(modality_label(board.modality))}{tail}"
     )