Models (5)
Transformer-based contrastive pretraining framework that learns technology-agnostic single-cell representations by contrasting cell views instead of reconstructing gene expression.
Deep learning model predicting single-cell read counts from DNA sequence features and cell transition graphs to identify transcriptional regulators.
Generative image perturbation autoencoder that predicts cellular morphological responses to chemical and genetic perturbations using untreated cell images as input.
Compositional Perturbation Autoencoder that predicts single-cell transcriptional responses to unseen drug combinations and doses using disentangled latent representations.
Variational autoencoder that predicts single-cell perturbation responses across cell types and species using latent space vector arithmetic.