Data sources
Every number, back to a public source.
The engine reads from seven backbone public registries plus ~50 live public-data connectors — no private black boxes. Each citation records the exact record and snapshot date, so any figure is public and re-verifiable.
Seven backbone registries plus ~50 live connectors behind every cited figure.
Backbone registries
The seven that carry the load
These are the public registries most of the engine's evidence comes from — named, linked, and open for you to check. Roughly fifty live public-data connectors sit behind them for the narrower questions.
Source
What it provides
What we do with it
Refresh
What it provides
Registry of public and private clinical studies worldwide — enrollment, status, sponsors, sites, and outcomes.
Site densityEnrollment benchmarksCompetitive trial landscapeWhat we do with it
Our registry of record for site density, where studies in your indication are actually running, and the competitive trial landscape.
Refresh
DailyWhat it provides
Biomedical literature index of 36M+ citations — used to ground indication baselines and standard-of-care evidence.
Indication baselinesEndpoint precedentStatistical methodsWhat we do with it
The literature backbone — it grounds indication baselines, endpoint precedent, and the evidence behind PTRS scoring.
Refresh
DailyWhat it provides
Approvals, labels, guidance, and adverse-event signals (openFDA) used to anchor regulatory-uplift and safety risk.
Regulatory upliftMolecule riskApproval precedentWhat we do with it
Anchors regulatory-uplift estimates, approval precedent, and molecule-level safety risk from labels and adverse-event signals.
Refresh
WeeklyWhat it provides
European approvals, EPARs, and scientific guidance used to model EU regulatory pathways and country benchmarks.
EU regulatory pathwayCountry benchmarksWhat we do with it
Models the European regulatory pathway and country-level benchmarks from EPARs and scientific guidance.
Refresh
WeeklyWhat it provides
Target–disease association evidence integrating genetics, pathways, and known drugs — feeds PTRS scoring.
PTRS (probability of technical & regulatory success)Target tractabilityWhat we do with it
The evidence basis for probability-of-success (PTRS) scoring and target tractability.
Refresh
QuarterlyWhat it provides
Relational, queryable database of all ClinicalTrials.gov content — the analytical backbone for site and enrollment statistics.
Site densityEnrollment velocityInvestigator historyWhat we do with it
The analytical engine behind our cohort, enrollment-velocity, and investigator-history statistics.
Refresh
DailyWhat it provides
Manually curated bioactivity database of drug-like molecules — used to characterize molecule risk and mechanism precedent.
Molecule riskMechanism precedentWhat we do with it
Characterises molecule risk and mechanism precedent from the chemistry and target side.
Refresh
Quarterly
Freshness
Refreshed on each source's own published cadence
Nothing here runs on a schedule we invented. Every citation also stamps the snapshot date it relied on, so a verdict can be reproduced against the same data later.
| Refresh cadence | Backbone sources |
|---|---|
| Daily | ClinicalTrials.gov · PubMed · AACT |
| Weekly | FDA · EMA |
| Quarterly | Open Targets · ChEMBL |
Limits
We won’t surface a number we can’t trace
Honest note on connectors
Some additional connectors — such as EudraVigilance and DrugBank — are gated or optional and remain pending licensing. We only cite sources we can lawfully read and that you can re-verify yourself; a figure we cannot trace to a public record does not appear in a verdict.
See a verdict you can actually check.
Send us a protocol — or just a molecule and an indication. We'll return a fully cited feasibility assessment you can trace, line by line, back to public data — yours to defend in a bid, take to your board or investment committee, or hand to a regulator.