about summary refs log tree commit diff
path: root/src/heatmap.rs
diff options
context:
space:
mode:
authorPjotr Prins <pjotr.public01@thebird.nl>2026-11-16 17:17:11 +0000
committerPjotr Prins <pjotr.public01@thebird.nl>2026-11-16 17:17:11 +0000
commitea3dd926211e8db4a0d7d3739a606440b888e8b0 (patch)
tree31b58cd0126960e70a76e45dc2c3b7c9a1c6d0b6 /src/heatmap.rs
parent33e837e771e07936c808fb3aeb3540525691718c (diff)
downloadgenenetwork4-main.tar.gz
correlation matrix: clustered heatmap and its plot HEAD main
`"cluster": true` adds `heatmap: {order, merges, max_height}` to the matrix
reply and `POST /plot/heatmap` draws it: the r matrix in that order, the
dendrogram that produced it, and a diverging scale with blue negative and red
positive. A reader can see *why* two traits are neighbours instead of trusting
an ordering.

Clustering decisions, all recorded because an unrepeatable clustering is worse
than none:

* distance `1 - r` -- the usual choice for correlations, and it keeps
  anti-correlated traits apart, which is what a heatmap of correlations should
  show;
* **average linkage (UPGMA)** -- single linkage chains along a gradient and
  complete linkage makes one flat blob out of noisy traits; average is the
  compromise GN1's R heatmaps used too;
* **deterministic ties and leaf order** (lower index first), so two runs on one
  matrix produce the same picture and plots stay diffable;
* a matrix with a **gap is refused** rather than clustered: an unknown distance
  treated as 1 would invent a structure, and the reply's note says to drop
  those traits and ask again.

Pairing with the PCA work this is the visual half of a collection: scree plot
for how much structure there is, clustered heatmap for where it is.

Monitor, as asked: `compute-correlation-heatmap` (order must be a permutation
with n-1 merges), `plot-heatmap`, and the plot endpoints that had no check at
all -- `plot-gemma` and `plot-bnw`, each posting a real compute result back.
Plots tier is now five checks, all ok; full run 47 ok, 0 failed, 1 skipped.
Diffstat (limited to 'src/heatmap.rs')
-rw-r--r--src/heatmap.rs214
1 files changed, 214 insertions, 0 deletions
diff --git a/src/heatmap.rs b/src/heatmap.rs
new file mode 100644
index 0000000..f179980
--- /dev/null
+++ b/src/heatmap.rs
@@ -0,0 +1,214 @@
+//! Clustered ordering of a correlation matrix, for a heatmap.
+//!
+//! The matrix is symmetric, so one ordering serves both axes: cluster the
+//! traits, then draw the r matrix in that order and a neighbour is a trait that
+//! actually looks like its neighbour.
+//!
+//! Decisions, all stated because a clustering nobody can reproduce is worse
+//! than no clustering:
+//!
+//! * **Distance is `1 - r`**, so a pair at r = 1 sits at 0 and a pair at
+//!   r = -1 at 2. That is the usual choice for correlation matrices and it
+//!   keeps anti-correlated traits far apart, which is what a reader expects
+//!   from a heatmap of *correlations*.
+//! * **Average linkage (UPGMA).** Single linkage chains along a gradient and
+//!   complete linkage makes one huge flat cluster from anything with noise in
+//!   it; average is the compromise that behaves on real expression traits. It
+//!   is also what GN1's heatmaps used (R's `hclust(method="average")`).
+//! * **Deterministic ties**: when two merges have the same height the lower
+//!   index wins, and the leaf order comes out of the tree by always placing the
+//!   earlier-clustered side first. Two runs on the same matrix give the same
+//!   order, which is what makes the plot diffable.
+//!
+//! The algorithm is the textbook O(n^3) one: n is at most `MAX_PCA_TRAITS`, and
+//! clarity beats a faster distance-update scheme that has to be trusted.
+
+/// One merge in the tree, enough to draw a dendrogram.
+#[derive(Debug, Clone, serde::Serialize, utoipa::ToSchema)]
+pub struct Merge {
+    /// Cluster ids 0..n-1 are the traits themselves; n and up are merges, in
+    /// the order they appear in this list.
+    pub left: usize,
+    pub right: usize,
+    /// Distance at which the two were joined (`1 - r`, so 0 is identical).
+    pub height: f64,
+}
+
+/// The clustered order and the tree that produced it.
+#[derive(Debug, Clone, serde::Serialize, utoipa::ToSchema)]
+pub struct Clustering {
+    /// Trait indices in drawing order (row and column order both).
+    pub order: Vec<usize>,
+    pub merges: Vec<Merge>,
+    /// Largest distance seen, so a plotter can scale the dendrogram.
+    pub max_height: f64,
+}
+
+/// Average-linkage clustering of a correlation matrix.
+///
+/// Returns `None` for a matrix that is not square, is larger than the cap, or
+/// has a cell that is not a number -- a gap means the two traits' distance is
+/// unknown, and quietly treating it as 1 would invent a structure.
+pub fn cluster(r: &[Vec<Option<f64>>], cap: usize) -> Option<Clustering> {
+    let n = r.len();
+    if n < 2 || n > cap || r.iter().any(|row| row.len() != n) {
+        return None;
+    }
+    let mut distance = vec![vec![0.0; n]; n];
+    for i in 0..n {
+        for j in 0..n {
+            let value = r[i][j]?;
+            if !value.is_finite() {
+                return None;
+            }
+            distance[i][j] = 1.0 - value;
+        }
+    }
+
+    // Active clusters: members and the merge tree.
+    let mut members: Vec<Vec<usize>> = (0..n).map(|index| vec![index]).collect();
+    let mut active: Vec<bool> = vec![true; n];
+    let mut sizes: Vec<usize> = vec![1; n];
+    let mut dist = distance;
+    let mut merges: Vec<Merge> = Vec::new();
+    let mut max_height = 0.0_f64;
+
+    for _ in 1..n {
+        // Nearest pair of active clusters, lowest index pair on a tie.
+        let mut best = (f64::INFINITY, 0usize, 0usize);
+        for i in 0..dist.len() {
+            if !active[i] {
+                continue;
+            }
+            for j in (i + 1)..dist.len() {
+                if !active[j] {
+                    continue;
+                }
+                let d = dist[i][j];
+                if d < best.0 {
+                    best = (d, i, j);
+                }
+            }
+        }
+        let (height, left, right) = best;
+        if !height.is_finite() {
+            return None;
+        }
+        max_height = max_height.max(height);
+        // Ids in this array ARE the tree ids: traits are 0..n-1 and merge m is
+        // n+m, created in this order, so the pair can be recorded as it stands.
+        let new_id = dist.len();
+        merges.push(Merge { left, right, height });
+
+        // Average linkage: the new distance is the size-weighted mean.
+        let mut row = vec![0.0; new_id + 1];
+        for k in 0..new_id {
+            if !active[k] || k == left || k == right {
+                continue;
+            }
+            row[k] = (dist[left][k] * sizes[left] as f64 + dist[right][k] * sizes[right] as f64)
+                / (sizes[left] + sizes[right]) as f64;
+        }
+        // Grow the matrix to new_id + 1 rows before writing into the new row:
+        // pushing the row first is what makes dist[new_id] exist.
+        for existing in dist.iter_mut() {
+            existing.push(0.0);
+        }
+        dist.push(row.clone());
+        for k in 0..new_id {
+            dist[new_id][k] = row[k];
+            dist[k][new_id] = row[k];
+        }
+
+        active[left] = false;
+        active[right] = false;
+        active.push(true);
+        sizes.push(sizes[left] + sizes[right]);
+        members.push(Vec::new());
+        let mut merged = members[left].clone();
+        merged.extend(members[right].iter().copied());
+        members[new_id] = merged;
+    }
+
+    // Leaf order: walk the tree, earlier-clustered side first (deterministic).
+    let mut order = Vec::with_capacity(n);
+    fn walk(id: usize, n: usize, merges: &[Merge], order: &mut Vec<usize>) {
+        if id < n {
+            order.push(id);
+            return;
+        }
+        let index = id - n;
+        let merge = &merges[index];
+        walk(merge.left, n, merges, order);
+        walk(merge.right, n, merges, order);
+    }
+    walk(dist.len() - 1, n, &merges, &mut order);
+    if order.len() != n {
+        return None;
+    }
+    Some(Clustering {
+        order,
+        merges,
+        max_height,
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn matrix(values: &[&[f64]]) -> Vec<Vec<Option<f64>>> {
+        values
+            .iter()
+            .map(|row| row.iter().map(|v| Some(*v)).collect())
+            .collect()
+    }
+
+    #[test]
+    fn two_blocks_are_ordered_together() {
+        // 0 and 1 correlate strongly with each other and with nothing else;
+        // same for 2 and 3. A good ordering keeps each pair adjacent.
+        let r = matrix(&[
+            &[1.0, 0.9, 0.0, 0.1],
+            &[0.9, 1.0, 0.1, 0.0],
+            &[0.0, 0.1, 1.0, 0.85],
+            &[0.1, 0.0, 0.85, 1.0],
+        ]);
+        let clustering = cluster(&r, 300).expect("4x4");
+        let order = clustering.order;
+        let position = |trait_index: usize| order.iter().position(|x| *x == trait_index).unwrap();
+        assert_eq!(position(0).abs_diff(position(1)), 1, "0 and 1 adjacent: {order:?}");
+        assert_eq!(position(2).abs_diff(position(3)), 1, "2 and 3 adjacent: {order:?}");
+        assert_eq!(order.len(), 4);
+        assert_eq!(clustering.merges.len(), 3);
+        // The first merges are the within-block ones, so they are the closest.
+        assert!(clustering.merges[0].height < 0.2);
+        assert!(clustering.merges[2].height >= clustering.merges[0].height);
+    }
+
+    #[test]
+    fn the_order_is_reproducible() {
+        let r = matrix(&[
+            &[1.0, 0.4, -0.2],
+            &[0.4, 1.0, 0.1],
+            &[-0.2, 0.1, 1.0],
+        ]);
+        let first = cluster(&r, 300).expect("3x3");
+        let second = cluster(&r, 300).expect("3x3");
+        assert_eq!(first.order, second.order);
+        assert_eq!(first.merges.len(), second.merges.len());
+    }
+
+    #[test]
+    fn a_gap_refuses_rather_than_invents() {
+        let mut r = matrix(&[&[1.0, 0.5], &[0.5, 1.0]]);
+        r[0][1] = None;
+        assert!(cluster(&r, 300).is_none(), "a null cell is not a distance of 1");
+    }
+
+    #[test]
+    fn the_cap_is_honoured() {
+        let r = matrix(&[&[1.0, 0.5, 0.2], &[0.5, 1.0, 0.3], &[0.2, 0.3, 1.0]]);
+        assert!(cluster(&r, 2).is_none());
+    }
+}