Google Cloud Healthcare United States

Every Cure

Real-time Analytics

Every Cure needed to evaluate tens of millions of drug-disease combinations fast enough to find overlooked repurposing opportunities, which required a unified biomedical data foundation instead of long, batch-style research cycles.

75 million drug-disease predictions analyzed
Every Cure uses Google AI to match 4k existing drugs against 18k diseases, discovering life-saving treatments for patients faster.
Prediction pipeline accelerated from 100 days to ~17 hours

Reported impact

Business outcome

Every Cure accelerated drug-repurposing discovery, launched more active programs, and focused expert review on the strongest candidates instead of manual screening.

  • Productivity Improvement
  • Scalability
  • Speed to Market

Solution

Every Cure uses Google Cloud to address this challenge: Every Cure needed to evaluate tens of millions of drug-disease combinations fast enough to find overlooked repurposing opportunities, which required a unified biomedical data foundation instead of long, batch-style research cycles. BigQuery houses large biomedical knowledge graphs and lets the team score and query drug-disease relationships at scale, serving as the storage layer. Cloud Storage stores the platform’s biomedical data assets alongside the knowledge-graph foundation, serving as the storage layer. Gemini quantifies evidence across published research, clinical data, and molecular biology and helps triage the most promising predictions, serving as the compute layer. Google Cloud GPUs accelerate the prediction pipeline so experiments that once ran for months can complete in hours, serving as the compute layer.

Data flow

Biomedical knowledge is centralized in Cloud Storage and BigQuery, Gemini evaluates evidence across the graph to score drug-disease combinations, and GPU-backed runs generate ranked predictions that scientists review for feasibility and clinical potential.

Solution architecture

4 components · 2 layers
  1. Compute
    • Gemini quantifies evidence across published research, clinical data, and molecular biology and helps triage the most promising predictions
    • Google Cloud GPUs accelerate the prediction pipeline so experiments that once ran for months can complete in hours
  2. Storage
    • BigQuery houses large biomedical knowledge graphs and lets the team score and query drug-disease relationships at scale
    • Cloud Storage stores the platform’s biomedical data assets alongside the knowledge-graph foundation

Architecture clues

  • Cycle time dropped from 100 days for a single run to about 17 hours
  • Scientists reviewed the top 6,000 predictions from the platform in the past year
  • The platform evaluates 75 million possible drug-disease combinations

Evidence from the source

75 million drug-disease predictions analyzed
Every Cure uses Google AI to match 4k existing drugs against 18k diseases, discovering life-saving treatments for patients faster.
Every Cure’s platform relies on Google Cloud as its underlying operating system, with BigQuery and Cloud Storage to house biomedical knowledge graphs seamlessly in one place.
Gemini helps triage what comes next.
Prediction pipeline accelerated from 100 days to ~17 hours
Using Google Cloud GPUs, Every Cure has since compressed that cycle to approximately 17 hours.
Transparency Evidence & methodology 96/100 reference value · 82% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value96/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence82%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency9/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Google Cloud

    Every Cure customer story

    First-party
    https://cloud.google.com/customers/everycure
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
  2. ProPublica

    Every Cure Inc - Nonprofit Explorer

    Independent secondary
    https://projects.propublica.org/nonprofits/organizations/920240717

    The 2024 IRS filing summary for Every Cure Inc lists 'Num. employees 16'.

    Source type
    Regulatory filing index
    Supports
    • Company size

Date evidence

  • First archived Jun 30, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Jun 26, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
Not separately sourced Industry, Region. Treat these normalized attributes as lower-confidence until a dedicated source is added.