Skip to content
Sunday, 4 October 2026
Tenesys AI News
Subscribe

Microsoft Research launches Quine, an AI world model built for biological discovery

In short: Microsoft Research has unveiled Quine, a research system combining a multimodal 'world model' of biology with an interactive harness linking AI models, scientific literature, lab tools, and researchers. Built jointly across data types such as genomics, proteins, chemistry, RNA/cell state, and bioimaging, the model aims to predict how biological systems respond to interventions before costly lab experiments are run. Working with the Broad Institute of MIT and Harvard, Microsoft used Quine to rank thousands of compounds for their potential to shift pancreatic cancer cells between therapeutic states, and the top-ranked candidates were validated in wet-lab assays within a single weekend. Microsoft is now opening a 'Quine Fellows' program to give selected scientists early access, while cautioning that the system is experimental, research-only, and not intended for clinical use.

Source: Microsoft ResearchMicrosoftQuineOriginal article ↗

This summary was generated automatically by AI from Microsoft Research's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.

What changed?

  • 1Introduces Quine, a multimodal 'world model' of biology trained jointly across genomics, protein, chemistry, RNA/cell-state, and bioimaging data
  • 2Pairs the world model with an interactive harness connecting it to orchestration/reasoning models, scientific literature, lab tools, and researchers
  • 3Used with the Broad Institute of MIT and Harvard to prioritize thousands of compounds for pancreatic ductal adenocarcinoma (PDAC) cell-state shifts
  • 4Top-ranked compounds produced the largest intended classical-to-basal cell-state shifts in wet-lab validation, with the full process taking one weekend
  • 5Model also predicted an unexpected third cell phenotype shift, later confirmed experimentally
  • 6Launching a 'Quine Fellows' program for select researchers; broader access expected later via Microsoft Discovery
  • 7Explicitly positioned as experimental research technology, not for clinical or medical use

Why it matters

This shows how foundation-model and reasoning-model techniques originally developed for language are being adapted to accelerate scientific discovery by predicting experiment outcomes before lab work, potentially compressing research cycles from months to days in fields like drug repurposing.

Sources

  • Microsoft ResearchOfficialPrimary source
    „Introducing Quine: An AI research system designed for the complexity of biology“
    29 Sept 2026, 17:00
    Original article →
Published by source
29 Sept 2026, 17:00
Found by our system
2 Oct 2026, 19:51
Summary generated
2 Oct 2026, 22:56

This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy