Skip to content

feat: add support for per-cluster centroid dataset in sequence processing #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
AStaroverov wants to merge 4 commits into from
Closed

feat: add support for per-cluster centroid dataset in sequence processing #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
75badbb
feat: add support for per-cluster centroid dataset in sequence proces…
AStaroverov Jun 11, 2026
32d5946
feat: add support for per-cluster centroid datasets in sequence proce…
AStaroverov Jun 15, 2026
8d8bc4c
feat: clarify receptor resolution logic for centroidId axis in detect…
AStaroverov Jun 15, 2026
97f7d09
Treat per-cluster centroid dataset as peptide
AStaroverov Jun 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/per-cluster-centroid-dataset.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
---
"@platforma-open/milaboratories.sequence-properties.workflow": patch
"@platforma-open/milaboratories.sequence-properties.model": patch
---

Add support for per-cluster centroid datasets (clonotype-clustering). The model accepts a 2-axis `[sampleId, centroidId]` anchor, and the workflow processes the synthetic per-cluster consensus sequence in peptide mode (the upstream "Export consensus sequences as a dataset" feature is peptide-only, so the centroid sequence column is a peptide amino-acid column).
10 changes: 10 additions & 0 deletions model/src/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,16 @@ const inputAnchorSpecs = [
axes: [{ name: "pl7.app/sampleId" }, { name: "pl7.app/vdj/scClonotypeKey" }],
annotations: { "pl7.app/isAnchor": "true" },
},
// Per-cluster centroid dataset (clonotype-clustering). A clonotype-shaped 2-axis
// dataset where the row entity is a cluster: axis[0] = sampleId (real per-sample
// abundance anchor), axis[1] = "pl7.app/clustering/centroidId" (values = real
// clusterId) carrying the synthetic per-cluster centroid sequence. The dedicated
// centroidId axis (not the producer's plain clusterId) keeps anchoring here from
// pulling its clusters table's centroid_*/reference_centroid_* columns.
{
axes: [{ name: "pl7.app/sampleId" }, { name: "pl7.app/clustering/centroidId" }],
annotations: { "pl7.app/isAnchor": "true" },
},
];

export const platforma = BlockModelV3.create(blockDataModel)
Expand Down
11 changes: 11 additions & 0 deletions workflow/src/main.tpl.tengo
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,17 @@ detectMode := func(axisSpec) {
if axisSpec.name == "pl7.app/vdj/scClonotypeKey" {
return "antibody_tcr_legacy_sc"
}
// Per-cluster centroid dataset (clonotype-clustering): a synthetic 2-axis
// [sampleId, centroidId] anchor carrying one consensus sequence per cluster. The
// "Export consensus sequences as a dataset" feature is peptide-only (the producer
// gates the export on peptide inputs), so the centroid sequence column is a peptide
// aminoacid column (pl7.app/sequence, pl7.app/feature: "peptide") and the dataset is
// processed in peptide mode — the peptideSequences matcher in prepare() picks it up.
// NOTE: if VDJ/single-cell centroid export is ever re-enabled upstream, this must
// branch on the centroid sequence column's feature instead of assuming peptide.
if axisSpec.name == "pl7.app/clustering/centroidId" {
return "peptide"
}
Comment on lines +63 to +65

@greptile-apps greptile-apps Bot Jun 15, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Receptor detection fully deferred to sequence-column domains

Unlike pl7.app/vdj/cloneId / clonotypeKey, the centroidId axis domain carries no VDJ keys (pl7.app/vdj/receptor, pl7.app/vdj/chain), so resolveReceptor will always return seen: false from the axis-level check. Receptor is then determined solely by the d["pl7.app/vdj/chain"] lookup on each sequence column inside the for s in vdjCols loop. If the centroid sequence columns happen to omit that domain key — e.g. a bulk-clustering producer that does not propagate chain metadata — receptorSeen stays false, the default "IG" is used silently, and messages.receptorNotDetected() fires at line 323. The comment says "single-cell centroids still carry the chain domain on the sequence columns", so this is likely safe in practice, but a missing chain annotation on the centroid sequence columns would silently produce IG properties for what might be a TCR dataset.

Prompt To Fix With AI 
This is a comment left during a code review.
Path: workflow/src/main.tpl.tengo
Line: 59-61

Comment:
**Receptor detection fully deferred to sequence-column domains**

Unlike `pl7.app/vdj/cloneId` / `clonotypeKey`, the `centroidId` axis domain carries no VDJ keys (`pl7.app/vdj/receptor`, `pl7.app/vdj/chain`), so `resolveReceptor` will always return `seen: false` from the axis-level check. Receptor is then determined solely by the `d["pl7.app/vdj/chain"]` lookup on each sequence column inside the `for s in vdjCols` loop. If the centroid sequence columns happen to omit that domain key — e.g. a bulk-clustering producer that does not propagate chain metadata — `receptorSeen` stays false, the default "IG" is used silently, and `messages.receptorNotDetected()` fires at line 323. The comment says "single-cell centroids still carry the chain domain on the sequence columns", so this is likely safe in practice, but a missing chain annotation on the centroid sequence columns would silently produce IG properties for what might be a TCR dataset.

How can I resolve this? If you propose a fix, please make it concise.

return ""
}

Expand Down
Loading