Autonomous omics
Evaluated, not asserted
di-omics / github

How each capability is evaluated

Measured,
not asserted.

Each repo is checked on two axes: whether the science holds and whether it runs unattended. Physical execution is measured with Rhodamine B, Qubit, and computer vision, never inferred from a software log.


01

Two axes

Axis 1 · Science

Does the science hold?

The physical biology and chemistry executed correctly, and the bioinformatics recovers ground truth, against a metric fixed before the run.

Rules out: passing in silico while the wet step silently failed. Physical execution is verified, never assumed.
Axis 2 · Autonomy

Does it run unattended?

Physical-AI QC in the loop, error handling that fails closed, and closed-loop feedback where the agent reads QC, corrects, and re-runs.

Rules out: a demo that only works with a human quietly saving it. The loop has to close on its own.

02

The infrastructure behind the checks

Liquid-handling QC
Verified
Rhodamine B for per-well CV%, Qubit or PicoGreen for yield. Upfront, fail-closed.
Computer-vision QC
Verified
Reads wells, pipetting, and steps from bench video. Ground-truth-validated.
Error handling
Verified
Guards, do-not-over-dry limits, one approval before purchase. Fails closed on readiness.
Robust bioinformatics
Verified
Reproducible fastq-to-result pipelines: scanpy, BJ-WGS Nextflow, versioned.
Preset statistics
Verified
Metric and threshold fixed before the run. Plant ground truth, recover, score.
Closed-loop agentic feedback
Building
Agent reads QC and CV, corrects the deck, and re-runs without a human in the path.

03

Guardrails against fooling ourselves


04

Per-capability status

Capability Science axis Autonomy axis Graded by Expert in loop
fullstack-omics
FLASH-seq scRNA + scWGS
UMI counts, low-input recovery, coverage; wet chemistry to run on deckBuilding
End to end in the PyLabRobot simulator; scWGS 10/10 testsVerified
scanpy, BJ-WGS concordance operator at deck
plr-mcp
Instruments as agent tools
Actions execute on liquid handler, reader, cycler, shakerVerified
MCP tool-call round-trip; CI green on 3.10-3.13Verified
simulator + hardware handshake agent proposes, operator confirms
omics-demos
Nine scored demos
Recovery vs. planted ground truth across nine assaysVerified
Blind run, per-assay recovery scoreVerified
recovery score, threshold preset none, automated eval
plr-minimum-effective
Minimal recipe search
Yield held at reduced reagent; wet confirmation pendingBuilding
Bayesian optimization, held-out recoveryVerified
cross-validated recovery expert sets acceptance floor
plr-clarity
(sci)TIP-seq on Hamilton STAR
Rhodamine-B validation ladder on a real deck; biovalidated tierBuilding
Plan text compiled into a runnable methodVerified
validation tier reached expert signs each tier
lab-cv
Spatial AI on bench video
Wells filled vs. empty, pipetting correctVerified
ROI motion QC + detection on protocol video, CPU-onlyVerified
ground-truth-validated frames reviewer adjudicates