← Back to all news
DeepMind Blog

Fast-tracking genetic leads to reverse cellular aging

Biologists use Co-Scientist to find novel factors that successfully rejuvenate human cells.

Related stories

arXiv Statistics ML
Sep 16

Causal Path Analysis from Perturbational and Population-Scale Single-Cell Data with Multiscale Confounding and Measurement Error

The paper presents a framework that merges single‑cell perturbation experiments with population‑scale single‑cell data to perform causal path analysis of gene regulation. It incorporates externally learned ancestral relationships to constrain network topology, re‑estimates direct edges from population data, and applies a surrogate‑variable procedure plus errors‑in‑variables correction to handle multiscale heterogeneity and measurement error. The authors provide theoretical guarantees for confounder recovery and high‑dimensional estimation, and demonstrate the method’s effectiveness through simulations and an acute myeloid leukemia case study that uncovers distinct regulatory pathways linking transcriptional regulators to blast count.

By Kwangmoon Park, Hongzhe Li
More like this →
arXiv AI
Sep 11

A Trust-Network-Based Federated Learning Framework for Multi-Center Aging Clock Prediction

The paper introduces TNFL, a trust‑network‑based federated learning framework designed for multi‑center aging clock prediction. TNFL propagates models along directed trust relations without centralized aggregation, combining an age‑aware mixture‑of‑experts model with generative replay to mitigate forgetting and drift. Experiments on multiple molecular datasets demonstrate effective aging‑clock prediction with limited local data, interpretable age‑dependent patterns, and stable performance across interaction orders, while revealing coordinated higher‑order protein subnetworks linked to aging.

By Chunxu Zhang, Bo Li, Wenliang Wang, Yang Liu, Di Jiang, Yuan Huang, Yo-ichi Nabeshima, Akinori Yamamura, Bo Yang, Qiang Yang
safety
More like this →
arXiv AI
Jun 30

Accelerating scientific discovery with Co-Scientist

arXiv:2502. 18864v2 Announce Type: replace Abstract: Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation.

By Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Petar Sirkovic, Artiom Myaskovsky, Grzegorz Glowaty, Felix Weissenberger, Alessio Orlandi, Dan Popovici, Anil Palepu, Keran Rong, Ryutaro Tanno, Khaled Saab, Fan Zhang, Jacob Blum, Andrew Carroll, Kavita Kulkarni, Nenad Tomasev, Dina Zverinski, Ivor Rendulic, Elahe Vedadi, Florian Hasler, Luka Rimanic, Marina Boia, Ivan Budiselic, Ben Feinstein, Mathias Bellaiche, Tom Sheffer, Jan Freyberg, Jeremy Ratcliff, Ottavia Bertolli, Katherine Chou, Avinatan Hassidim, Burak Gokturk, Amin Vahdat, Yuan Guan, Vikram Dhillon, Eeshit Dhaval Vaishnav, Byron Lee, Tiago R D Costa, Jos\'e R Penad\'es, Gary Peltz, Yossi Matias, James Manyika, Demis Hassabis, Yunhan Xu, Pushmeet Kohli, Annalisa Pawlosky, Alan Karthikesalingam, Vivek Natarajan
llmsagents
More like this →
arXiv Machine Learning
Sep 18

CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling

CellRFT is a reinforcement fine‑tuning framework designed to improve single‑cell perturbation modeling by directly optimizing biological evaluation metrics. It employs policy‑gradient methods to learn from non‑differentiable biological rewards and aggregates multiple rewards hierarchically. Experiments show that CellRFT enhances perturbation prediction across various pretrained models and reveals interactions between different biological criteria, suggesting new ways to shape model behavior and evaluation design.

By Jie Yan, Li Liu, Hanze Guo, Jiaxin Hu, Houxin He, Xiaoning Qi, Haoran Wang, Cong Li, Zhong-Yuan Zhang, Yong Wang
fine-tuning
More like this →