BBS:      TELESC.NET.BR
Assunto:  AI modeling of human cells
De:       Mike Powell
Data:     Sun, 3 May 2026 09:30:46 -0500
-----------------------------------------------------------
 * Originally in: SF_Reality

'Build AI that can accurately represent the full complexity of biology': Mark 
Zuckerberg wants to cure all diseases but needs far more data to deliver a 
digital twin of human cells.  As genetic data becomes the next frontier, will
you trust him with yours?

Date:
Sat, 02 May 2026 18:20:00 +0000

Description:
Mark Zuckerberg backs $500 million push to build AI models of human cells as 
part of long-term effort to cure disease.

FULL STORY
Meta billionaire Mark Zuckerberg is backing a sweeping $500 million push to 
build massive biological datasets that could power AI models capable of 
simulating human cells. 

The effort, called the Virtual Biology Initiative , comes from Biohub, the 
nonprofit led by Zuckerberg and Priscilla Chan, M.D., and focuses on creating 
what scientists describe as predictive models of life at the cellular level. 
The project will split the funding, with $100 million going toward supporting 
global data collection and $400 million on developing tools for imaging, 
measuring, and engineering biology at unprecedented scale.

Wanted: vast amounts of biological data -- Building accurate digital
models of cells has long been discussed as a pathway toward faster drug 
discovery and improved understanding of disease. 

Scientists say the tools to begin that work now exist, but the missing 
ingredient remains vast amounts of high-quality biological data. 

To build artificial intelligence that can accurately represent the full 
complexity of biology and accelerate scientific research, we need orders of 
magnitude more data than exists today. We need new technologies to observe 
the cell, from the molecular to the tissue level, and in the context of 
health and disease," said Alex Rives, Biohub Head of Science. 

"At Biohub, were committing our resources to solve this problem. Generating 
this data will require a coordinated global effort. Were thrilled to partner 
with leading institutions and consortia who are also committed to this and to 
work with them to galvanize a larger effort to create the foundation for 
predictive models of the cell, Rives added.

Several major research organizations have agreed to participate, including 
the Allen Institute, Arc Institute, Broad Institute, and Wellcome Sanger 
Institute. 

The scale of the project reflects how quickly artificial intelligence is 
moving into biology, especially as researchers attempt to model how cells 
behave under different conditions. 

Support from Nvidia will provide the computing power needed to process the 
enormous datasets, which scientists say are essential for training AI systems 
that can simulate cellular behavior accurately.

Zuckerberg said last year that Biohub s long-term goal is to cure all human 
disease by combining advances in AI with large-scale biological research. 

Accurate digital models of cells could allow scientists to test ideas 
virtually before running expensive laboratory experiments, dramatically 
increasing the speed of discovery. 

Achieving a predictive understanding of cellular behavior will require 
coordination and data at a truly global scale. The Human Cell Atlas brings 
together a global community, data, capabilities, and expertise needed to help 
make this possibleand efforts like this, where leading partners including 
Biohub come together, have the potential to accelerate progress in ways no 
single organization and consortium could achieve alone, said Muzz Haniffa, 
co-Vice-Chair of the Human Cell Atlas Organising Committee. 

Although the scientific promise is substantial, the scale of data required 
raises big questions about governance, ownership, and trust as biological 
information becomes an increasingly valuable resource.

Link to news story:
https://www.techradar.com/pro/build-ai-that-can-accurately-represent-the-full-
complexity-of-biology-mark-zuckerberg-wants-to-cure-all-diseases-but-needs-far
-more-data-to-deliver-a-digital-twin-of-human-cells-as-genetic-data-becomes-th
e-next-frontier-will-you-trust-him-with-yours

$$
--- MultiMail/DOS
 * Origin: Capitol City Hub (1:2320/105)

-----------------------------------------------------------
[Voltar]