Skip to content
No. 010Ruled outRare pediatric cancerUpdated Nov 14, 2026

Better computer ranking of medicine pairs for DIPG

Good it would do
2 / 5
Can AI help
3 / 5
How neglected
2 / 5
Can we check it
4 / 5

Why we stopped

Rejected on prior art and target validity: in-dish synergy, the label a pair ranking would learn, has not predicted benefit in animal models in this disease or pan-cancer; public combination data are essentially one cell line around two anchor drugs; and funded groups with labs already design combinations by other methods. One narrow open benchmark survives but was judged too narrow; the brain-exposure route stays under parked problem 9.

Why it's stuck

A 2020 repurposing study found only moderate agreement between computer predictions and lab results, and blamed weak brain-permeability modeling and bias in the literature it learned from. Few groups have followed up.

What we'd try

Redo the search with better permeability models and patient-derived data, then hand a ranked list to lab partners.

Source: https://www.biorxiv.org/content/10.1101/2020.06.14.150714v3.full

Think we got it wrong?

Ruled-out problems can come back. Tell us what we missed.

Members can read the full record for this problem, check its sources and comment. Open the member view →