# An open engine that ranks every drug pair by predicted synergy before anyone runs a trial

Source: https://onco.cc/ideas/idea-tr2-synergy-ranking-engine/  
OnCo record `idea-tr2-synergy-ranking-engine` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Use existing cell-line and organoid data to score thousands of drug pairs, publish the ranking openly, and only test the top of the list in people.

## Summary

DepMap dependency screens, the NCI ALMANAC pairwise matrix and published organoid drug-response sets contain far more combination signal than has been mined. A public model that predicts synergy and, critically, therapeutic window (tumour versus normal-cell toxicity) for each pair in each molecular context would give trialists a prioritised shortlist. Models should be scored prospectively against every new combination readout.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- Hypothesis: Combinations in the top decile of the published ranking will show randomised phase 2 success (meeting primary endpoint) at least twice as often as combinations chosen by conventional mechanistic argument.
- Rationale: The DREAM AstraZeneca-Sanger synergy challenge showed predictive signal in cell lines. NCI ALMANAC identified bortezomib plus clofarabine from a systematic screen. The failure has been that rankings are not published, not maintained and not scored against outcomes.
- Proposed test: Publish rankings for all pairs of approved oncology drugs; register predictions; score them against every randomised combination readout over three years, reporting calibration publicly.
- Maturity: preclinical-evidence
- Actor: data

## Sources

- DepMap portal: https://depmap.org/portal/
- NCI ALMANAC: https://dtp.cancer.gov/ncialmanac
- DREAM Challenges: https://dreamchallenges.org/

## Connected records

- collections: [DepMap (Cancer Dependency Map)](https://onco.cc/collections/depmap/), [DrugBank & ChEMBL](https://onco.cc/collections/drugbank-chembl/)
- ideas: [A public atlas of drug-pair responses across a thousand patient-derived organoids](https://onco.cc/ideas/idea-tr2-organoid-matrix-atlas/), [An open forecasting tournament on which combination trials will succeed](https://onco.cc/ideas/idea-tr2-combination-forecast-tournament/), [Patient-derived organoids to pick ADC payloads](https://onco.cc/ideas/idea-organoid-guided-adc/)
- technologies: [AI-driven drug & target discovery](https://onco.cc/technologies/ai-drug-design/), [CRISPR functional genomics](https://onco.cc/technologies/crispr-screens/), [Patient-derived organoids](https://onco.cc/technologies/organoids/)
- bottlenecks: [Lab models that fail to predict what happens in patients](https://onco.cc/bottlenecks/b-preclinical-models/), [Too many combinations to test](https://onco.cc/bottlenecks/b-combination-space/)

---
JSON: https://onco.cc/api/v1/entities/idea-tr2-synergy-ranking-engine.json