Skip to main content

Data Coverage

This article describes the data Atlas CI draws on: what it covers, where it comes from, and what you can retrieve.

Written by George Larrington

Overview

Atlas CI is an AI agent that supports pharma competitive-intelligence workflows. It retrieves and analyzes pharma and life sciences data from Norstella’s curated enterprise dataset and generates ready-to-use summaries and reports.

Atlas CI is more than aggregated source data. Norstella transforms information from across the pharma landscape into structured, validated, and searchable intelligence. Across every data set, this includes:

  • Curation — selecting and organizing the sources that matter.

  • Standardization — mapping drugs, companies, trials, and indications to consistent identifiers and ontologies, so they can be searched and compared reliably.

  • Structuring — converting unstructured text into structured, queryable records.

  • Validation — checking records for accuracy and consistency.

  • Enrichment — adding derived fields and relationships, such as development stage, approval timing, and the links between drugs, trials, and companies.

Together, our team of subject-matter-experts turn raw inputs into the validated, searchable intelligence that Atlas CI works from.

Coverage scale

The data is organized into masters: Drugs, Trials, Organizations, Events and catalysts. Coverage is global, spans 20+ years of historical data, and includes local-language sources across Asia and Europe.

Coverage at a glance

Master

What’s available

Representative sources

Drugs

Drug and biologic assets with indications, development stage and status, mechanism of action, modality, and originating and developing organizations, plus key development and regulatory events.

Company pipelines, clinical trial registries, scientific literature, conferences, press releases, and regulatory and health-authority sources.

Trials

Interventional and observational studies with status, phase, key dates, sponsors, design, endpoints, enrollment, indications, interventions, sites, and investigators.

Trial registries and sponsor disclosures.

Organizations

Company profiles with pipelines, corporate hierarchy and identifiers, locations, and corporate activity such as deals, partnerships, and financings.

Company websites, regulatory and financial filings, investor materials, newswires, and news and press releases.

Events and catalysts

Dated, value-driving developments — trial readouts, regulatory decisions, approvals and designations, licensing and partnership events, and conference disclosures — each linked to the related drug, trial, or company.

Clinical trial registries, regulatory and health-authority sources, press releases, conferences, and newswires.

Drugs Coverage

What you can retrieve

Changes tracked

Representative sources

Asset identity — drug or biologic name, synonyms and codes, originator, and developing organizations.

New assets, name and code changes, and changes to the originating or developing company.

Company pipelines, press releases, regulatory filings.

Mechanism and modality — mechanism of action, molecular target, and drug type or modality.

Reclassification of mechanism, target, or modality as evidence emerges.

Scientific literature, conference materials, company disclosures.

Indications and development stage — indications under investigation and the highest development stage, by indication and region.

Stage advances and setbacks such as phase changes, approvals, and discontinuations, by indication and region.

Clinical trial registries, company pipelines, conference abstracts.

Regulatory status — approvals, label and indication changes, designations (e.g., orphan, fast track, breakthrough), and safety actions.

New approvals, label changes, new designations, withdrawals, and safety actions.

Health-authority sources.

Relationships — links from a drug to its trials, indications, developing companies, and comparable competitor assets.

New and updated relationships as trials, deals, and disclosures occur.

Derived across the underlying dataset.

Trials Coverage

What you can retrieve

Changes tracked

Representative sources

Registration and sponsorship — registry IDs, title, study type (interventional or observational), sponsor, and collaborators.

New registrations and changes to sponsor or collaborators.

Trial registries.

Design and endpoints — phase, study design, arms, primary and secondary endpoints, and eligibility and population.

Protocol amendments affecting design, endpoints, or eligibility.

Trial registries and sponsor disclosures.

Status and key dates — recruitment status and milestones such as start, primary completion, and completion dates.

Status transitions and changes to start or completion dates.

Trial registries, sponsor disclosures, press releases.

Enrollment — target enrollment and, where disclosed, actual enrollment.

Updates to target or actual enrollment.

Trial registries and sponsor disclosures.

Sites and investigators — participating sites and locations, and named investigators and contacts.

Added or removed sites and changes to investigators.

Trial registries and sponsor disclosures.

Organizations Coverage

What you can retrieve

Changes tracked

Representative sources

Profile and identifiers — legal name, aliases, corporate hierarchy (parent and subsidiaries), and standardized organization identifiers.

Name changes, restructuring, and parent or subsidiary changes.

Company websites, regulatory and financial filings.

Pipeline — the assets and indications a company is developing and their development stages.

Pipeline additions, stage changes, and discontinuations.

Company pipelines, trial registries, press releases.

Locations — headquarters and operating locations.

Relocations and changes to operating locations.

Company websites, regulatory filings.

Corporate activity — deals, partnerships, licensing, mergers and acquisitions, and financings.

New deals, partnerships, M&A, and financing events.

Press releases, newswires, regulatory and financial filings.

Events and catalysts Coverage

What you can retrieve

Changes tracked

Representative sources

Clinical and trial events — readouts, data presentations, and study milestones such as primary completion and readout dates.

New readouts and milestone updates as they are reported.

Clinical trial registries, conference materials, press releases.

Regulatory events — approvals, label and indication changes, designations (e.g., orphan, fast track, breakthrough), safety actions, and decision dates.

New decisions, designations, and safety actions as published.

Health-authority sources.

Corporate and commercial events — corporate announcements, partnerships, licensing, and product launches.

New corporate announcements.

Press releases, newswires, regulatory and financial filings.

Linkage and history — each event is dated and linked to the related drug, trial, or company, and historical events are retained.

New events captured and linked over time.

Derived across the underlying dataset.

Did this answer your question?