Settings
Watch it: Start here, end to end. The guided tab: what you have, which genes, which label, what you want to know -- then the ranked strategies and Run. Silent screen capture of the real application.
Gene list135 genes
Column the list came fromcompartment
UMAP neighbours to try15, 50
UMAP min_dist to try0.0
Cluster sizes to try20, 50
Cluster selection to tryeom, leaf
Genes per map2000
Feature setsall
Random lists for the null100
The card strategy 02 opens on: the same four bars as every strategy (better than chance, reach, two plain task metrics, each with its interval and chance), Run / Test / Details ▸, what its test does, and one real failure beside one real success.
Console
strategy 02 test: Find the map where your gene list is one cluster (UMAP + HDBSCAN) -- started
map 1 of 2: all permitted, n_neighbors 15, min_dist 0.0
map 2 of 2: all permitted, n_neighbors 50, min_dist 0.0
geneset_hunt: FAIL
strategy 02 run: Find the map where your gene list is one cluster (UMAP + HDBSCAN) -- started
map 1 of 2: all permitted, n_neighbors 15, min_dist 0.0
map 2 of 2: all permitted, n_neighbors 50, min_dist 0.0
geneset_hunt: done in 0.2s
FAIL: F1 of the hidden members against the best cluster's other genes 0.068 against 0.043 ± 0.012 under 20 random sets of the same size, same walk (bar 0.061, p 0.0952); effect +0.025, needed +0.050; 40 hidden
135 genes found (0 not found). Best of 8 configurations: all permitted, n_neighbors 15, min_dist 0.0, min cluster 20 (leaf) -- cluster 5 holds 22 of your 135 placed genes among 96 (precision 0.23, recall 0.16, F1 0.19). Random sets of the same size reach F1 0.13 ± 0.00 at their best over the same walk (search-corrected p = 0.0099). 74 genes in that cluster are not on your list.