From d9e1bf7fd9da4e0bae6579b95fd0028296b997ac Mon Sep 17 00:00:00 2001 From: Pjotr Date: Thu, 12 Nov 2026 17:15:53 +0000 Subject: compute/bnw: a Bayesian network over traits, called out to BNW's driver POST /compute/bnw learns a network over a set of variables and returns one row per candidate edge: from, to, posterior, in_structure. Inputs are published traits of a group (group + traits) or an explicit matrix (values: one entry per variable with per-sample values), which covers the case the database cannot -- a basket's columns, a handful of probe sets. BNW's knowledge stays in the gn-bnw repository. GN4 writes a variables x samples matrix, runs `bnw learn` (BNW_CMD, BNW_BIN_DIR, BNW_CACHE_DIR) and parses the reply: nothing about the three C programs, the private work directory or the type line in the input file lives here, so BNW's pipeline can change without a GN4 release. The driver's failures map onto the API's own: bad input 422, a missing driver 502 bnw_not_installed (its exit 77), a failed computation 502 bnw_failed in the driver's words. Decisions worth recording: * parameters are BNW's own defaults -- maxparents 4, k 1, tiers 3, threshold 0.5, read from its create_tiers_gom_part1.php rather than chosen here -- and the reply names the values used, because a network at 0.5 and one at 0.9 are different answers to the same question; * at most 40 variables and at least 3 samples complete across every variable. The first is the structure search's exponential in-degree; the second is BNW modelling a complete multivariate normal, so a sample missing any value is dropped -- and the note says how many survived rather than silently shrinking the panel; * its own gate, always claimed (threshold 0): there is no such thing as a small BNW run, the cost is the search, not the number of individuals; * the notes say plainly that a posterior is not a p-value and that a network is not a QTL, because that is the easiest thing to over-read. tests/bnw.rs compares the endpoint against the answer the BNW *web application* gives for its own six-trait example (the same fixture as the driver's parity check, gn-bnw/test/golden/): the five edges must match, and the notes must name the parameters and carry the caveat. It skips when the driver or its binaries are absent. Not deployed to production. --- docs/www/SKILL.md | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'docs') diff --git a/docs/www/SKILL.md b/docs/www/SKILL.md index 4bb81e4..bb8bd3e 100644 --- a/docs/www/SKILL.md +++ b/docs/www/SKILL.md @@ -152,6 +152,15 @@ header (peak, and the reference lines drawn when you asked for them). scale-free: compare `pve` with `h2`, never `vg` with `σ²_e`. A `pve` of exactly 0 or 1 is a boundary (the standard error then reads "not available"), a direction rather than a proportion. +* `/compute/bnw`: a Bayesian network over a set of traits (BNW). Give `group` + + `traits`, or `values` (one entry per variable with per-sample values). Columns + `from, to, posterior, in_structure`; one row per candidate edge, strongest + first. **A posterior is not a p-value** — it is the share of the k-best + networks containing the edge, i.e. how often the search drew that arrow in + this sample, so quote it as a structural claim and never as a threshold on a + QTL. Parameters default to BNW's own (maxparents 4, k 1, tiers 3, threshold + 0.5) and the reply names the ones used. At most 40 variables, at least 3 + samples complete across every variable. * `/compute/fitqtl`: **how big** an effect is, not just where. Give it the marker names a scan found (its peaks) and it fits R/qtl's `fitqtl` at each: columns `marker, chr, pos, lod, pct_var, additive, se, t, p`. Use it -- cgit 1.4.1