04 · 21 proprietary layers
Layer 6 of 21 · Six shared core layers
AccessMatch Actionable alterations and targetability.
Why it's needed
Which alterations may have treatment relevance or warrant further review?
What it draws on
3 of 8 evidence domains.
What it produces
Potentially relevant alterations, evidence and review priorities.
Why it's essential
Layer 6 of 21.
1 · What it does
What AccessMatch does
AccessMatch is intended to identify which alterations have evidence connecting them to therapies, whether approved, guideline-referenced or investigational, and to prioritise them for the treating team's review.
2 · Scientific question
The question it addresses
Which alterations may have treatment relevance or warrant further review?
Intended function
Explain how findings are connected to evidence about targetability and options for evaluation.
3 · Data inputs and required context
What it draws on
- 01 Molecular & genomic
- 03 Clinical context
- 08 Evidence ecosystem
Annotated somatic alterations, the diagnosis and the current evidence base.
4 · Scientific basis
The science behind it
Scientific basis
Actionability is usually expressed with tiered evidence systems that consider the cancer type, the specific variant and the strength of evidence, which ranges from regulatory approval and guidelines to clinical trials, case reports and preclinical data. The same variant can carry very different evidence in different tumour types.
5 · Output and evidence sources
What it produces
Main output
Potentially relevant alterations, evidence and review priorities.
Output type
- Evidence-linked interpretation. Connects a finding to published or curated evidence, which has a source and a date.
6 · Why it\u2019s essential
How it powers the Twin
The main contributor to the treatment-options section of the report. It also passes biomarker context to TrialGraph for investigational options and is read alongside ResistMap and ToxCast.
Report section
Capability
ExploreReview treatment-relevant evidence, resistance-related findings and potential trial matches.
7 · Why it\u2019s needed
What it changes — for doctors, patients and researchers
Clinicians
Alterations organised by evidence strength and tumour-type match, ready for evaluation.
Doctor & Clinical TeamPatients & caregivers
A 'match' is something to discuss with the oncologist, not a prescription.
Patient & Caregiver8 · Dependencies and limitations
Limitations
- A potential match is not a treatment recommendation, an eligibility confirmation or proof of benefit.
- Approval status and access differ between countries and change over time.
- Evidence for a variant in one tumour type cannot simply be transferred to another.
9 · Review and uncertainty
How the output is handled
Output status
An AI-assisted analytical output presented as structured findings for clinician review. It becomes part of a report only after the treating oncologist has reviewed and signed it.
How uncertainty is communicated
Each association shows its evidence level, whether the tumour type matches the evidence, and the date the evidence was checked.
10 · Claim boundary
What this layer does not establish
It does not establish that a therapy will work, that it is approved for the patient's indication, or that it is appropriate for the patient.
The treating oncologist owns every decision. Every Twin report is reviewed and signed by the treating oncologist, then taken to KPCIRC's Molecular Tumour Board.
KPCIRC sign-off process