OncoSignal

Oncology intelligence, from open data

What moved in a tumour type this month, who is running it, and which targets have the genetics behind them.

OncoSignal watches ClinicalTrials.gov for phase advances and readouts, PubMed for new trial papers, Open Targets for target–disease genetic evidence, and the 2026 SITC, ESMO, ASCO, AACR and ASH abstracts, and puts them on one page per indication. Every row is live or verified and links to its source.

Case study · why a trial failed

IGF-1R antibodies in Ewing sarcoma

Ewing sarcoma (paediatric) · IGF1R · ganitumab. The randomised trial was sized to detect a hazard ratio of 0.67, about 33% fewer relapses, new cancers or deaths. It found 1.00 (95% CI 0.76 to 1.33): no difference. Built from 79 checked sources, with charts.

Read the case study
Relapse, new cancer or death: hazard ratio
Planned 0.67Result 1.00
Fewer events with the drugMore events

A five-minute explainer of the case study, with captions. Every number in it comes from the case study's checked sources. The analysis has not yet been checked line by line by a person.

Late-breaking and headline abstracts

All meetings →

Five views per indication

Indications

Paediatric abstracts and FDA target list

Paediatric abstracts across the 2026 meetings and the FDA Pediatric Relevant Molecular Target List.

Why build this

Curing All Disease, Ahead of Schedule

Essay by tp53, November 2026

The essay argues that drug development is held back less by discovery than by herding: companies crowd onto the same validated targets while coordination and institutional waiting slow everything else. AI should be aimed at genuinely new bets, with people keeping the scientific judgment.

OncoSignal is the instrument for that argument in oncology. Put the herd on one screen (who is in Ph3 on which target, and who just got there), then ask where the human genetic evidence points that the pipeline does not.

Read the essay →