UC San Diego Team Builds Virtual Mitochondrial Cell Predicting Drug Responses
Start here
Johannes Schöneberg's team at UC San Diego published two studies in Cell describing a virtual mitochondrial cell built from 4D imaging and AI. One study trained the deep learning model MitoSpace on 40,000 4D lattice light-sheet microscopy movies of cancer cells treated with 25 compounds, creating a resource the researchers call MitoSpace alongside a digital twin designed to predict how mitochondria respond to drugs. The work aims to let researchers simulate mitochondrial behavior in cancer cells without running every experiment at the bench. The studies were published on 2026-10-20. How broadly the digital twin's predictions generalize beyond the 25 compounds and cancer cell settings tested remains an open question.
Written by a model from the reports · updated 2 hours ago
Coverage timeline
Follow the coverage to see the different angles.
- news.bioon.comUC San Diego Cell Papers Build Virtual Mitochondrial Cell with 4D Microscopy and AI: MitoSpace and Digital Twin Predict Drug Responses
Johannes Schöneberg's team at UC San Diego published two studies in Cell. One trained the deep learning model MitoSpace on 40,000 4D lattice light-sheet microscopy movies of cancer cells treated with 25 compounds.
Coverage and heat for this story
Reports so far 1·Heat now 6·Peak heat 10 (Oct 20 00:00)·Reports, 24h +1
Two panels, same clock (pointer stays in sync): top is cumulative editorial reports — only rises; last point = All reports; slope = new reports that hour. Bottom is Live-board heatIndex — 7-day participants with a 24-hour half-life, so it can fall when talk cools.