Flapping Airplanes wants to train AI with less data and get more out of each chip. Credit: Omar:. Lopez-Rincon on Unsplash Paris-based Orakl Oncology has raised a $34M Series A co-led by Norrsken VC and Singular. It grows copies of patients’ tumours in the lab, tests drugs on them and uses AI to predict trial results.
It will expand into lung and gastric cancer. Paris-based Orakl Oncology has raised a $34M Series A to predict how cancer drugs will perform before they reach patients, European Biotechnology reported. The round was co-led by Swedish investor Norrsken VC and French firm Singular, taking total funding to $50M. Orakl was spun out of French cancer centre Gustave Roussy in 2023.
It grows small copies of patients’ tumours in the lab, called organoids, and tests drugs on them. It then combines those results with patients’ medical records to train AI that predicts how a drug will do in clinical trials. Norrsken says the system is 90% accurate. An April preprint, not yet peer-reviewed, tested the model on 23 past colorectal and pancreatic cancer trials.
Its forecasts of how long patients went without their cancer worsening were off by 0.82 months on average. It also picked the better treatment in seven of eight cases. But those tests looked back at trials that had already finished, and most involved standard chemotherapy. How the model handles newer drugs still needs to be proven.
The money will go into producing five times more lab data, expanding into lung and gastric cancers, and opening teams in the US and UK. Norrsken says 18 of the world’s 20 biggest drugmakers are in talks with Orakl, and in July it won rights to test four of Sanofi’s cancer drugs. Orakl joins a wave of Paris startups using AI in biology, including Rivercell, which raised $25M in October. Singular also led a $20M round in Paris health startup Lucis this year, while US drug-design startup Chai Discovery raised $400M in July.
Get the TNW newsletter ✕ Close Get the TNW newsletter Get the most important tech news in your inbox each week.
Leave a Reply