Today we're launching the Alzheimer's Translation Challenge, a global AI competition to discover new therapeutic hypotheses for Alzheimer's disease. At its core is a new 150M cell atlas of neurons, astrocytes, and microglia across different genetic backgrounds under combinatorial perturbations, with multi-modal readouts. The data will be made available through the AD workbench, Hugging Face and Prima Mente's modeling platform. The challenge is led by @PrimaMente and @AlzData in collaboration with @nvidia, @huggingface, @nebiusai, Talisman Therapeutics, @UltimaGenomics, @cellanome, @PrimeIntellect, @GoodfireAI, and @boltz_bio. In 1906, Alois Alzheimer described a new disease of the brain. After 120 years of progress, we still don't fully understand what drives this disease. We want to change that. Participants will use the dataset to build AI models, assessed through a series of evals from general benchmarks to more complex tasks. Top teams will be shortlisted, and their experimental hypotheses tested in Prima Mente's wet lab. Teams win when their hypotheses demonstrate the predicted molecular and functional effect.

Each dataset becomes a source of evals for model development and testing. These three gave us six new tasks for prima-bench, our soon-to-be-released suite of evals. These included isoform prediction, splicing change in disease, cancer detection from plasma, and chromatin accessibility from DNA sequence.

How long did this take? 5, 9 and 6 days. Against modelled one-person manual schedules that's up to 10x faster and an estimated 89% cheaper, showing how efficient and affordable well-designed AI workflows in the sciences can be. Directing AI tools with no framework around them can end up slower and pricier than doing it by hand.

Case 2: plasma cell-free RNA for cancer detection. Default pipeline settings would have discarded the microbial reads for modelling, so the agents changed them. Cancer vs healthy AUROC 0.89 (paper ~0.9), and five-cancer mean recall of 63.8% vs the published best of 60.4%.

Published biology can take weeks or months to turn into usable training data and new evals. Our Prima Daedalus agents do it up to 10× faster, and 89% lower estimated cost. They reproduce papers, beat published results, and find previously overlooked biology.

Thrilled to share that we are one of the 20 Discovery Award winners of the @longitude_prize on ALS. With this award, we gain access to the largest and most comprehensive ALS patient datasets ever assembled, supplemented by our own internal data generation efforts. By combining whole genome sequencing, multi-omic patient data, and high-throughput cellular models, we are bringing together a highly vetted ALS data corpus with a level of scale and quality that has not previously existed in one place.

At Prima Mente, we believe that combining clinically informed patient data, frontier biological models, and experimental validation can unlock biological insights and therapeutic opportunities that were previously out of reach. Paired with lab autonomy, this enables us to validate insights from models at scale and accelerate discovery toward patient impact.

Excited to share that Prima Mente is part of the founding portfolio of the @UKSovereignAI Fund. We are one of the first companies selected to receive backing and access to the UK’s leading AI supercomputers. Thank you for backing AI companies building in Britain Joséphine Kant, @KanishkaNarayan, Andrew Crawford and the entire @UKSovereignAI team.