MUSS derives peak- and gene-level representations from DNA using a frozen pre-trained sequence encoder and integrates them through peak-peak self-attention and distance-biased peak-gene interactions, which support sequence-grounded, multi-scale representations for decoding cell-type-specific regulatory programs.
Kang-Jie Zheng, Amirhossein Vahidi, Li-Ying Jin et al.· 0 citations
CellBridge is introduced, a multi-modal contrastive learning framework pretrained on 16M cells with paired H&E and spatial profiles, for transferring molecular information into morphological representations that consistently achieves smaller prediction sets, while reducing class-wise coverage gaps.
Spatial transcriptomics maps gene expression at cellular resolution, revealing how cells organize into multicellular niches. Yet computational analyses remain dataset-specific, without a transferable representation of tissue organization that generalizes across datasets, tasks and tissues or predicts how tissues behave...
Sebastian Birk, M. V. Sanian, Amirhossein Vahidi et al.· bioRxiv· 4 citations· ⚡1
SQUINT is presented, a graph vector-quantized variational autoencoder that learns two disjoint codebooks per cell from a shared architecture that outperforms or is competitive with strong baselines on identification and achieves the most faithful cross-section integration.
Sebastian Birk, Arpit Merchant, Amirhossein Vahidi et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.