Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore the development of multimodal foundation models for molecular cell biology in this conference talk that examines how large-language model approaches can address the exponential growth of biological data from high-throughput omics technologies. Learn about the vision for creating pretrained models that integrate diverse omics datasets including genomics, transcriptomics, epigenomics, proteomics, metabolomics and spatial profiling to characterize molecular states of cells across a broad continuum. Discover how these foundation models can facilitate the creation of holistic maps of cells, genes and tissues, while enabling context-specific transfer learning for applications such as novel cell-type recognition, biomarker discovery, gene regulation inference, and in silico perturbations. Understand how this artificial intelligence-empowered paradigm promises to unravel the complexities of molecular cell biology, support experimental design, and extend our understanding of life sciences by moving beyond traditional single-modality approaches to embrace the full spectrum of biological data integration.
