Clinical trial landscape

Every registered trial counted once and classified by mechanism, line of therapy, sponsor and endpoint, with readout timing from company disclosures. Every row carries its registry number

Customize this Agent

XLSXDOCX14 steps

The problem

Three registry numbers for one trial, four names for one drug

Search ClinicalTrials.gov for small cell lung cancer and more than four in five of the Phase 3 records that come back are non small cell. One drug runs under several names: pumitamig is PM8002 on one Phase 3 and BNT327 on another. Registry dates go stale: a Phase 3 last updated in October 2024 still shows primary completion in September 2026

The request

Build a small cell lung cancer trial landscape. Industry sponsored drug trials, Phase 2 onward plus Phase 1/2 with small cell cohorts, recruiting, not yet recruiting or active, and anything completed or stopped since January 1, 2025. Phase 1 small cell cohorts go on an early pipeline tab. Flag but keep EGFR transformed and large cell neuroendocrine cohorts. Search ClinicalTrials.gov, CTIS, China's CDE and jRCT, counting each trial once. Classify by mechanism, phase, sponsor and partner, geography, line and primary endpoint. Next readouts from company disclosures, sourced and dated, flagging registry conflicts. I need the workbook and two page summary, every trial cited by registry number, with changes since our July landscape, attached. Save the search for next quarter.

SCLC landscape July 2026.xlsx

How Axe works

ApprovedChanges asked

Your reviewApprove, or say what to change

Approved or changes

Landscape and summaryWorkbook, summary and verification log

Final reviewApprove the revised files

Revised landscape and summaryRevised files and verification log

Step

Deduplicate across registries

Prompt

Sent to the model at this step

Collapse the records to one row per trial. Treat two records as one trial only on hard evidence: one record lists the other's number, they share a sponsor protocol number, or sponsor, drug, arms, comparator, line of therapy and planned enrolment all match. Use the ClinicalTrials.gov number as the primary identifier where one exists, and carry the EU CT, CDE and jRCT numbers beside it. Never merge on drug name alone: the same molecule in two trials stays two rows. Then group the rows by molecule using the drug dictionary, so that PM8002, BNT327, BMS-986545 and pumitamig sit under one asset, and HS-20093, GSK5764227 and risvutatug rezetecan under another, each with its originator and licensees. List every probable match you could not confirm, with the evidence for and against, for me to decide.

Uses

Registry records
Drug dictionary

Produces

Trial table
Match log

What you get back

XLSXLandscape workbookOne row per trial, every registry number, then early pipeline, readouts and search protocol

DOCXLandscape summaryCrowding by mechanism and line, the next readouts and what changed since July

Verification logOpen items and probable duplicates first, then each row marked checked or corrected

Make it yours

Point it at your indication, change the registries or the line of therapy buckets, or add the fields your team tracks. Every step and every prompt can be edited

Customize this Agent

Opens a private copy of this Agent in your workspace, ready to adapt to your own sources

More agent examples

HEOR scientistsIndirect treatment comparisonDOCXXLSX15 steps

Pharma forecastersPatient based forecastXLSXDOCX16 steps

Product strategy teamsTarget product profileDOCXXLSX15 steps

Capital markets analystsBroker opinion of valuePPTXXLSX16 steps

Financial planning analystsBudget variance analysisXLSXDOCX13 steps