Cellular & Systems Modeling
Cellular & Systems Modeling ("Virtual Cells")
Benchmarks & competitions
annual benchmark for context generalization (predict perturbation effects in held-out cell types).
Datasets enabling this
consolidated perturbation data resource.
genome-wide CRISPR screens (Replogle, Norman, etc.) at K562 and other lines.
100M cells, 50 cancer lines, 1100 drugs, the largest public perturbation atlas.
Industry players
Twitter/X feeds for real-time field developments.
companies pursuing virtual-cell-style approaches with image and transcriptomic phenotypes.
companies pursuing virtual-cell-style approaches with image and transcriptomic phenotypes.
companies pursuing virtual-cell-style approaches with image and transcriptomic phenotypes.
companies pursuing virtual-cell-style approaches with image and transcriptomic phenotypes.
Perturbation prediction
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
generative cellular world model, leading on Virtual Cell Challenge benchmarks.
proteomics-based foundation model using ODE network architecture for drug response prediction.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
various architectures predicting how a cell's transcriptome shifts under genetic or chemical perturbation.
Single-cell foundation models
have shown these models often don't dramatically outperform simpler baselines on real perturbation tasks, there's a recognized "foundation model honeymoon" reckoning happening.
transformer-based, trained on 30-100M cells.
transformer-based, trained on 30-100M cells.
transformer-based, trained on 30-100M cells.
transformer-based, trained on 30-100M cells.
transformer-based, trained on 30-100M cells.