Tools

Software you can use, and software we are still building.

Each tool is labelled with its real maturity. The Evidence Explorer, over the released Evidence Atlas, is the one you can use on real data today.

Live Over the released OmicsEdge Evidence Atlas v1.0.0

Evidence Explorer

Search 11,553 released benchmark events and 23,106 observations for HG002, HG003 and HG004 across Illumina and Oxford Nanopore, and trace every observation to its benchmark run and artifacts.

  • Search by 1-based locus, range, normalized allele, event ID or variant ID
  • Filter by sample, technology, chromosome, identity state, recorded decision, variant type and release phase
  • Structured evidence view: both observations, identity, sequencing, pipeline, benchmark run, artifacts and provenance
  • Loads one evidence shard per event; served byte-identical from the frozen release
  • Retrieval only: no scores, rankings, consensus or clinical interpretation

Research Research visualization

RNA observability visualizer

An interactive explanation of the RNA Measurement Intelligence idea. Choose a transcript type, toggle its properties and see how two workflows might observe it. Illustrative, not a predictive tool.

Transcript

Properties

IllustrativeHow transcript properties and sequencing workflow shape what can be observedTranscriptIllumina short-readNanopore direct-RNAObservationabundantE1E2E3E4E5long transcriptstrongstrongclassBOTHrareE1E2E3E4E5long transcriptno readsweakmissingclassILLUMINA_ONLYmoderateE1E2E3E4E5long transcriptisoform B shares these exonsuncertainstrongclassDIRECT_RNA_ONLYmoderateE1E2short transcriptlow mappability: sequence repeated elsewhereno readsuncertainmissingclassINDETERMINATE

Plenty of molecules and unique sequence: both workflows see it clearly.

Structure is drawn because it was tested. In the K562 study, transcript-wide measured in-vivo structure added negligible predictive value beyond the other properties shown.

Illustrative, not study data. Outcome classes use the study’s vocabulary (BOTH, ILLUMINA_ONLY, DIRECT_RNA_ONLY, NEITHER, INDETERMINATE). Real observability depends on the specific protocol, depth, quantifier and thresholds. Modelling that dependence explicitly is the research direction.
Illustrative outcomes by transcript type
TranscriptIllumina short-readNanopore direct-RNAClassWhy
Abundant, distinctstrongstrongBOTHPlenty of molecules and unique sequence: both workflows see it clearly.
RareweakmissingILLUMINA_ONLYFew molecules. Deep short-read sampling catches a little; a lower-throughput direct-RNA run may catch nothing.
Shares exons with an isoformuncertainstrongDIRECT_RNA_ONLYShort reads on shared exons cannot be assigned to one isoform. Full-length reads can tell the isoforms apart.
Short, repetitive sequenceuncertainmissingINDETERMINATESequence that reads cannot be placed uniquely, and too short to anchor long reads: neither workflow gives a clean answer.

In development In development

Variant Evidence Adjudication

A concept walkthrough of the evidence states and abstention. There is no model to try yet: protocols and feature extraction are frozen, evaluation has not happened, and nothing here is model output.

Illustrative · not model outputPaired Illumina and Oxford Nanopore evidence converging on a candidate variant, weighed, and resolved to a support state or ABSTAINIllumina readsONT readscontext: non-difficultcontext: homopolymerreads cannot be placed uniquelycontext: low mappabilitycontext: segmental duplicationcontext: outside benchmark regionscandidatevariantEvidence weighedIllumina call evidenceONT call evidenceQuality consistencyContext difficultyInterpretationBOTH_SUPPORTEDILLUMINA_SUPPORTEDONT_SUPPORTEDNEITHER_SUPPORTEDABSTAINUNASSESSABLEbenchmark labelling only

Both platforms call the same allele with strong, consistent evidence in easy sequence. The supportable interpretation is that both calls hold.

Illustrative cases showing what each state means. They are not predictions: the adjudication model has not been evaluated and no performance figures exist. Evidence levels are drawn qualitatively on purpose; the eventual system reads 42 approved features.
  • Clear agreement: BOTH_SUPPORTED. Both platforms call the same allele with strong, consistent evidence in easy sequence. The supportable interpretation is that both calls hold.
  • Illumina-only indel in a homopolymer: ILLUMINA_SUPPORTED. Short reads call a small deletion in a run of one base; long reads do not. Context matters: homopolymers are a known difficulty for some long-read chemistries.
  • ONT-only call in low mappability: ONT_SUPPORTED. Long reads span a region where short reads cannot be placed uniquely. The absence of a short-read call is weak evidence here.
  • Conflicting evidence: ABSTAIN. Both platforms call something, with different genotypes, low quality and in duplicated sequence. The honest output is: not enough evidence for an automated conclusion.
  • Benchmark cannot judge: UNASSESSABLE. The truth set cannot establish whether either call is right. This is benchmark uncertainty, not model abstention: such cases are excluded from training labels.