Deep Visual Multi-Omics: AI-powered 3D mapping reveals intra-tumor heterogeneity of colorectal cancer
Peer-Reviewed Publication
Updates every hour. Last Updated: 27-Oct-2026 01:16 ET (27-Oct-2026 05:16 GMT/UTC)
A new study in Science Bulletin presents DVSTP, a deep learning system that integrates pathology images with spatial transcriptomics and proteomics to map intra-tumor heterogeneity. DVSTP predicts molecular profiles from routine pathology slides, making spatial multi-omics more accessible. Whole–tumor 3D reconstruction reveals that SRSF6 drives immune exclusion and is associated with poor clinical outcomes.
Women with abnormal mammograms often have to wait for weeks to find out whether they have breast cancer.
Now, researchers at UC San Francisco and UC Berkeley have found a way to help reduce the wait and the worry by using AI to quickly identify those who are most likely to have the disease. By triaging these patients, the AI-guided workflow takes women with abnormal scans through the diagnostic process — from imaging to evaluation and sometimes even biopsy — in a single day.
A UC Irvine-led study analyzed 3,511 cancer patients across six UC medical centers to examine infection-related side effects to antibody-drug conjugates, or ADCs.
Researchers found some ADC therapies were linked to dangerously low infection-fighting white blood cell counts and related complications, including hospitalization.
Led by pharmacy professor Alexandre Chan, the study highlights the need for closer monitoring and supportive care as targeted cancer therapies become more widely used.